Workflow Steps and Code Snippets
457 tagged steps and code snippets that match keyword QIIME2.0
Automated pipeline for amplicon sequence analysis
7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 | import os import subprocess from sys import stdin #import benchmark_utils from benchmark_utils import countFasta def complement(seq): complement = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A', 'Y':'R', 'R':'Y','S':'S','W':'W','K':'M','M':'K','N':'N','B':'V','V':'B','D':'H','H':'D'} bases = list(seq) bases = [complement[base] for base in bases] return ''.join(bases) def reverse_complement(s): return complement(s[::-1]) #from Bio.Seq import Seq primer_by_sample={} uniq_primers={} idx_fw_primer=-1 # default for qiime (col 3) idx_rv_primer=-1 # new field idx_rv_revcomp_primer=-1 isRC = False foundSample=False primer="" if snakemake.config["primers"]["remove"].lower() == "metadata": with open(snakemake.input[1]) as mappingFile: l=0 for line in mappingFile: l=l+1; columns = line.split('\t') #the header is always at row 1 and must contain these first 3 fields (qiime specs): #SampleID BarcodeSequence LinkerPrimerSequence Description if l==1 : c=0 #Find target headers for col in columns: if col == "ReversePrimer" or col == "LinkerPrimerSequenceReverse" or col == "ReverseLinkerPrimerSequence" or col == "RvLinkerPrimerSequence" or col == "ReversePrimerSequence" : idx_rv_primer=c elif col == "LinkerPrimerSequence": idx_fw_primer=c elif col == "ReverseLinkerPrimerSequenceRevCom" or col == "ReversePrimerRevCom": idx_rv_revcomp_primer=c isRC=True c=c+1 if isRC: idx_rv_primer=idx_rv_revcomp_primer elif line.startswith(snakemake.params[4]): foundSample=True if idx_rv_primer != -1: if isRC: #fw_primer=columns[idx_fw_primer] #rv_primer=columns[idx_rv_primer] primer="-g "+columns[idx_fw_primer]+"..."+columns[idx_rv_primer] else: #fw_primer=columns[idx_fw_primer] #rv_primer=reverse_complement(columns[idx_rv_primer]) primer="-g "+columns[idx_fw_primer]+"..."+reverse_complement(columns[idx_rv_primer]) else: #fw_primer=columns[idx_fw_primer] primer="-g "+columns[idx_fw_primer] if not foundSample: print("\033[91m" +"No primers found for sample:"+ snakemake.params[4]+ " \033[0m") print("\033[91mPlease make sure to have the sample included in the mapping file: "+snakemake.input[1]+" \033[0m") print("\033[91m Aborting the pipeline \033[0m") exit(1) elif snakemake.config["primers"]["remove"].lower() == "cfg": primer="-g " + snakemake.config["primers"]["fw_primer"] if snakemake.config["primers"]["rv_primer"].len() > 2 : primer=primer+"..."+reverse_complement(snakemake.config["primers"]["rv_primer"]) discard = True if "--discard-untrimmed" in snakemake.params[0]: extra=snakemake.params[0].replace("--discard-untrimmed","") else: extra=snakemake.params[0] discard = False #This file will contain the untrimmed reads for the first pass no_primer=" --untrimmed-output " + snakemake.params[2]+".tmp" if snakemake.config["primers"]["remove"].lower() == "metadata": subprocess.run( ["cutadapt "+ primer +" "+ extra+" -o "+snakemake.output[0] + ".1 "+ no_primer +" " + snakemake.input[0]+ ">"+ snakemake.params[5]],stdout=subprocess.PIPE, shell=True) else: subprocess.run( ["cutadapt "+ primer +" "+extra+" -o "+snakemake.output[0] + ".1 "+ no_primer +" " + snakemake.input[0]+ ">"+ snakemake.params[5]],stdout=subprocess.PIPE, shell=True) # primer=snakemake.config["cutadapt"]["adapters"] #comment above line because we just add the primer generation in the elif above.... initialReads=countFasta(snakemake.input[0],False) disscardedReads=countFasta(snakemake.params[2]+".tmp",False) #The "extra" var returns to the original values in the sense that if the user wants to disscard reads # this option will be present on the final cutadapt command extra=snakemake.params[0] #if we disscarded reads if disscardedReads>0: #reverse complement disscardedReads subprocess.run( ["vsearch --fastx_revcomp "+ snakemake.params[2]+".tmp --fastaout "+ snakemake.params[2]+".tmp2"],stdout=subprocess.PIPE, shell=True) if snakemake.config["primers"]["remove"].lower() == "metadata": if discard: #Run cutadapt on disscarded reads subprocess.run( ["cutadapt "+ primer +" "+ extra+" -o "+snakemake.output[0] + ".2 " + snakemake.params[2]+".tmp2"+ ">>"+ snakemake.params[5]],stdout=subprocess.PIPE, shell=True) else: print("Running second cutadapt") print("cutadapt "+ primer +" "+ extra+" -o "+snakemake.output[0] + ".2 --untrimmed-output "+ snakemake.output[0] + ".3 " + snakemake.params[2]+".tmp2"+ ">>"+ snakemake.params[5]) subprocess.run( ["cutadapt "+ primer +" "+ extra+" -o "+snakemake.output[0] + ".2 --untrimmed-output "+ snakemake.output[0] + ".3 " + snakemake.params[2]+".tmp2"+ ">>"+ snakemake.params[5]],stdout=subprocess.PIPE, shell=True) #reverse complement untrimmed disscardedReads subprocess.run( ["vsearch --fastx_revcomp "+ snakemake.output[0]+".3 --fastaout "+ snakemake.params[2]+".tmp3"],stdout=subprocess.PIPE, shell=True) else: if discard: subprocess.run( ["cutadapt "+ primer +" "+extra+" -o "+snakemake.output[0] + ".2 " + snakemake.params[2]+".tmp2 >>"+ snakemake.params[5]],stdout=subprocess.PIPE, shell=True) else: subprocess.run( ["cutadapt "+ primer +" "+extra+" -o "+snakemake.output[0] + ".2 --untrimmed-output "+ snakemake.output[0] + ".3 " + snakemake.params[2]+".tmp2 >>"+ snakemake.params[5]],stdout=subprocess.PIPE, shell=True) subprocess.run( ["vsearch --fastx_revcomp "+ snakemake.output[0]+".3 --fastaout "+ snakemake.params[2]+".tmp3"],stdout=subprocess.PIPE, shell=True) if discard: #Concatenate results subprocess.run( ["cat "+snakemake.output[0] + ".1 "+ snakemake.output[0] + ".2 > "+ snakemake.output[0]],stdout=subprocess.PIPE, shell=True) #remove intermediate files: disscarded reads first round, disscarded reads RC, accepted reads first round, accepted reads second round subprocess.run( ["rm -f "+ snakemake.params[2]+".tmp "+ snakemake.params[2]+".tmp2 "+snakemake.output[0] + ".1 "+ snakemake.output[0] + ".2"],stdout=subprocess.PIPE, shell=True) else: #Concatenate results subprocess.run( ["cat "+snakemake.output[0] + ".1 "+ snakemake.output[0] + ".2 " + snakemake.params[2] + ".tmp3 > " + snakemake.output[0]],stdout=subprocess.PIPE, shell=True) #remove intermediate files: disscarded reads first round, disscarded reads RC, accepted reads first round, accepted reads second round #subprocess.run( ["rm -f "+ snakemake.params[2]+".tmp "+ snakemake.params[2]+".tmp2 "+snakemake.output[0] + ".1 "+ snakemake.output[0] + ".2 "+ snakemake.params[2]+".tmp3"],stdout=subprocess.PIPE, shell=True) else: #no reads to evaluate just rename file print("No untrimmed output!!!!") subprocess.run( ["mv "+snakemake.output[0] + ".1 > "+ snakemake.output[0]],stdout=subprocess.PIPE, shell=True) survivingReads=countFasta(snakemake.output[0],False) prc = float((survivingReads/initialReads)*100) prc_str = "{:.2f}".format(float((survivingReads/initialReads)*100)) with open(snakemake.params[1], "w") as primers: primers.write(primer) primers.close() print("\033[91m This step removes primers \033[0m") print("\033[93m Total number of initial reads: " + str(initialReads) + " \033[0m") print("\033[93m Total number of surviving reads: " + str(survivingReads) + " = "+ prc_str + "% \033[0m") print("\033[93m You can find cutadapt's log file at: " + snakemake.params[5] +"\n \033[0m") if snakemake.config["interactive"] != "F" or prc < snakemake.config["primers"]["min_prc"]: print("\033[92m Do you want to continue?(y/n): \033[0m") user_input = stdin.readline() #READS A LINE user_input = user_input[:-1] if user_input.upper() == "N" or user_input.upper() == "NO": subprocess.run( ["rm -f "+ snakemake.output[0]],stdout=subprocess.PIPE, shell=True) exit(1) else: print("\033[93m" +" Interactive mode off \033[0m") print("\033[93m" +" Removing primers...\033[0m") if not os.path.exists(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/report_files"): os.makedirs(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/report_files") subprocess.run( ["cat "+ snakemake.output[0]+"| grep '^>' | cut -f1 -d' ' | sed 's/>// ; s/_[0-9]*$//' | sort | uniq -c | awk '{print $2\"\\t\"$1}' > " + snakemake.params[3]+".tmp1"],stdout=subprocess.PIPE, shell=True) subprocess.run( ["cat "+ snakemake.input[0]+"| grep '^>' | cut -f1 -d' ' | sed 's/>// ; s/_[0-9]*$//' | sort | uniq -c | awk '{print $2\"\\t\"$1}'| awk -F'\t' 'NR==FNR{h[$1]=$2;next} BEGIN{print \"Sample\\tReads_before_cutadapt\\tSurviving_reads\\tPrc_surviving_reads\"}{if(h[$1]){print $1\"\\t\"h[$1]\"\\t\"$2\"\\t\"($2/h[$1])*100\"%\"}else{print $1\"\\t\"$2\"\\t0\\t0%\"}}' - "+snakemake.params[3]+".tmp1 > "+ snakemake.params[3]],stdout=subprocess.PIPE, shell=True) os.remove(snakemake.params[3]+".tmp1") exit(0) |
Python
Cutadapt
QIIME2.0
VSEARCH
benchmark-utils
From
line
7
of
Scripts/remove_adapters_by_sample.py
7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 | import os import subprocess from benchmark_utils import countFasta from sys import stdin def complement(seq): complement = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A', 'Y':'R', 'R':'Y','S':'S','W':'W','K':'M','M':'K','N':'N','B':'V','V':'B','D':'H','H':'D'} bases = list(seq) bases = [complement[base] for base in bases] return ''.join(bases) def reverse_complement(s): return complement(s[::-1]) primer_by_sample={} uniq_primers={} idx_fw_primer=-1 # default for qiime (col 3) idx_rv_primer=-1 # new field idx_rv_revcomp_primer=-1 isRC = False primer_set = "" no_primer = "" extra=snakemake.params[0] log_by_sample="Sample\tInitial reads\tSurviving reads\n" if "--discard-untrimmed" in snakemake.params[0]: no_primer=" --untrimmed-output " + snakemake.params[2] extra=snakemake.params[0].replace("--discard-untrimmed","") if not os.path.exists(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/report_files"): os.makedirs(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/report_files") if snakemake.config["primers"]["remove"].lower() == "metadata": with open(snakemake.input[1]) as mappingFile: l=0 for line in mappingFile: l=l+1; columns = line.split('\t') #the header is always at row 1 and must contain these first 3 fields (qiime specs): #SampleID BarcodeSequence LinkerPrimerSequence Description if l==1 : c=0 #Find target headers for col in columns: if col == "ReversePrimer" or col == "LinkerPrimerSequenceReverse" or col == "ReverseLinkerPrimerSequence" or col == "RvLinkerPrimerSequence" or col == "ReversePrimerSequence" : idx_rv_primer=c elif col == "LinkerPrimerSequence": idx_fw_primer=c elif col == "ReverseLinkerPrimerSequenceRevCom" or col == "ReversePrimerRevCom": idx_rv_revcomp_primer=c isRC=True c=c+1 if isRC: idx_rv_primer=idx_rv_revcomp_primer elif not line.startswith("#"): if idx_rv_primer != -1: #here, we are creating a dic with sample:primer if isRC: primer_by_sample[columns[0]]=[columns[idx_fw_primer],columns[idx_rv_primer]] else: primer_by_sample[columns[0]]=[columns[idx_fw_primer],reverse_complement(columns[idx_rv_primer])] #for primer in uniq_primers: if columns[idx_fw_primer]+columns[idx_rv_primer] not in uniq_primers: if isRC: uniq_primers[columns[idx_fw_primer]+columns[idx_rv_primer]]=[columns[idx_fw_primer],columns[idx_rv_primer]] else: uniq_primers[columns[idx_fw_primer]+columns[idx_rv_primer]]=[columns[idx_fw_primer],reverse_complement(columns[idx_rv_primer])] else: primer_by_sample[columns[0]]=[columns[idx_fw_primer]] if columns[idx_fw_primer] not in uniq_primers: uniq_primers[columns[idx_fw_primer]]=[columns[idx_fw_primer]] mappingFile.close() #If we have more than one different pair of primers, we run cutadapt by sample #otherwise we run only one instance if len(uniq_primers) >1: #create tmp dir if not os.path.exists(snakemake.params[4]): os.makedirs(snakemake.params[4]) else: #it exists and most lickly we want to delete all its content. subprocess.run( ["rm -fr " + snakemake.params[4]+"*"],stdout=subprocess.PIPE, shell=True) #split the reads #If we are running this, it comes from our demultiplexing, and thus we have fasta headers like this: #><sample>_### so we remove the _### subprocess.run(["cat "+ snakemake.input[0]+ " | awk '{if($0 ~ \"^>\"){sample=$1; header=$0; gsub(\">\",\"\",sample);gsub(\"_[0-9].*\",\"\",sample);}else{print header\"\\n\"$0 >> \""+snakemake.params[4]+"\"sample\".fasta\"} }'"],stdout=subprocess.PIPE, shell=True) all_primers="" for file in os.listdir(snakemake.params[4]): #file only has the name of the file, the path is already discarded #the function os.path.splitext strip the extension sample=os.path.splitext(file)[0] no_primer="" extra="" if "--discard-untrimmed" in snakemake.params[0]: no_primer=" --untrimmed-output " + snakemake.params[4]+sample+"_untrimmed.fasta" extra=snakemake.params[0].replace("--discard-untrimmed","") tmp_out = snakemake.params[4]+sample+"_trimmed.fasta" tmp_log = snakemake.params[4]+sample+".log" if sample in primer_by_sample: if len(primer_by_sample[sample])>1: primer_set=" -g "+primer_by_sample[sample][0]+"..."+primer_by_sample[sample][1]+" " else: primer_set=" -g "+primer_by_sample[sample][0] #run cutadapt by sample subprocess.run(["echo \"Processing sample\" " + sample + "\n >> "+ snakemake.params[5]],stdout=subprocess.PIPE, shell=True) subprocess.run( ["cutadapt "+ primer_set +" "+extra+" -o "+tmp_out + " "+ no_primer +" " + snakemake.params[4]+file+ ">>"+ snakemake.params[5]],stdout=subprocess.PIPE, shell=True) #stats by sample initialReads=countFasta(snakemake.params[4]+file,False) survivingReads=countFasta(tmp_out,False) prc = "{:.2f}".format(float((survivingReads/initialReads)*100)) log_by_sample=log_by_sample+sample+"\t"+str(initialReads)+"\t"+str(survivingReads)+" ("+prc+"%)\n" all_primers=all_primers+sample+"\t"+primer_set+"\n" else: print("\033[91mNo primers found for sample:"+ sample+ " \033[0m") print("\033[91mPlease make sure to have the sample included in the mapping file: "+snakemake.input[1]+" \033[0m") print("\033[91mAborting the pipeline \033[0m") exit(1) #merge results subprocess.run( ["cat "+ snakemake.params[4]+"*_trimmed.fasta > "+ snakemake.output[0]],stdout=subprocess.PIPE, shell=True) with open(snakemake.params[1], "a") as primers: primers.write(all_primers) primers.close() #subprocess.run( ["cat "+ snakemake.params[4]+"*_untrimmed.fasta > " snakemake.params[5]],stdout=subprocess.PIPE, shell=True) else: #only run one cutadapt instance new_key = list(uniq_primers) if len(uniq_primers[new_key[0]])>1: #is PE? primer_set=" -g "+uniq_primers[new_key[0]][0]+"..."+uniq_primers[new_key[0]][1]+" " else: #is SE primer_set=" -g "+uniq_primers[new_key[0]][0] subprocess.run( ["cutadapt "+ primer_set +" "+extra+" -o "+snakemake.output[0] + " "+ no_primer +" " + snakemake.input[0]+ ">"+ snakemake.params[5]],stdout=subprocess.PIPE, shell=True) with open(snakemake.params[1], "a") as primers: primers.write(primer_set) primers.close() else: #values come at the CFG, run only once primer_set="-g " + snakemake.config["primers"]["fw_primer"] if snakemake.config["primers"]["rv_primer"].len() > 2 : primer_set=primer_set+"..."+reverse_complement(snakemake.config["primers"]["rv_primer"]) subprocess.run( ["cutadapt "+ primer_set +" "+extra+" -o "+snakemake.output[0] + " "+ no_primer +" " + snakemake.input[0]+ ">"+ snakemake.params[5]],stdout=subprocess.PIPE, shell=True) # primer_set = snakemake.config["cutadapt"]["adapters"] with open(snakemake.params[1], "w") as primers: primers.write(primer_set) primers.close() initialReads=countFasta(snakemake.input[0],False) survivingReads=countFasta(snakemake.output[0],False) prc=float((survivingReads/initialReads)*100) prc_str = "{:.2f}".format(float((survivingReads/initialReads)*100)) user_input="0" while (user_input != "1" and user_input != "2"): print("\033[91m This step removes primers \033[0m") print("\033[93m Total number of initial reads: " + str(initialReads) + " \033[0m") print("\033[93m Total number of surviving reads: " + str(survivingReads) + " = "+ prc_str + "% \033[0m") print("\033[93m You can find cutadapt's log file at: " + snakemake.params[5] +"\n \033[0m") if snakemake.config["interactive"] != "F" or prc < snakemake.config["primers"]["min_prc"]: print("\033[92m What would you like to do? \033[0m") print("\033[92m 1. Continue with the workflow. \033[0m") print("\033[92m 2. Interrupt the workflow. \033[0m") if snakemake.config["primers"]["remove"].lower() == "metadata" and len(uniq_primers)>1: print("\033[92m 3. Print results by sample. \033[0m") user_input = stdin.readline() #READS A LINE user_input = user_input[:-1] if user_input == "2": print("\033[91m Aborting workflow... \033[0m") #delete target outpu (snakemake also does it) subprocess.run( ["rm -f "+ snakemake.output[0]],stdout=subprocess.PIPE, shell=True) #delete cutadapt mp directory subprocess.run( ["rm -fr " + snakemake.params[4]],stdout=subprocess.PIPE, shell=True) #delete all the concatenated log files subprocess.run( ["rm -f " + snakemake.params[5]],stdout=subprocess.PIPE, shell=True) #delete primers file subprocess.run( ["rm -f " + snakemake.params[1]],stdout=subprocess.PIPE, shell=True) exit(1) if user_input == "3": print(log_by_sample) else: print("\033[93m" +" Interactive mode off \033[0m") print("\033[93m" +" Removing primers...\033[0m") user_input="1" # if we ran multiple cutadap tasks, now delete tmp files and logs. if snakemake.config["primers"]["remove"].lower() == "metadata" and len(uniq_primers)>1: print("\033[96mCleaning intermediate files...\033[0m") subprocess.run( ["rm -fr " + snakemake.params[4]],stdout=subprocess.PIPE, shell=True) #Summarize results subprocess.run( ["cat "+ snakemake.output[0]+"| grep '^>' | cut -f1 -d' ' | sed 's/>// ; s/_[0-9]*$//' | sort | uniq -c | awk '{print $2\"\\t\"$1}' > " + snakemake.params[3]+".tmp1"],stdout=subprocess.PIPE, shell=True) subprocess.run( ["cat "+ snakemake.input[0]+"| grep '^>' | cut -f1 -d' ' | sed 's/>// ; s/_[0-9]*$//' | sort | uniq -c | awk '{print $2\"\\t\"$1}'| awk -F'\t' 'NR==FNR{h[$1]=$2;next} BEGIN{print \"Sample\\tReads_before_cutadapt\\tSurviving_reads\\tPrc_surviving_reads\"}{if(h[$1]){print $1\"\\t\"h[$1]\"\\t\"$2\"\\t\"($2/h[$1])*100\"%\"}else{print $1\"\\t\"$2\"\\t0\\t0%\"}}' - "+snakemake.params[3]+".tmp1 > "+ snakemake.params[3]],stdout=subprocess.PIPE, shell=True) os.remove(snakemake.params[3]+".tmp1") exit(0) |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 | import os from sys import stdin import subprocess try: treads = subprocess.run( ["grep '^>' " + snakemake.input[0] + " | wc -l"],stdout=subprocess.PIPE, shell=True) totalReads = treads.stdout.decode('utf-8').strip() creads = subprocess.run( ["cat " + snakemake.input[1] + " | wc -l"],stdout=subprocess.PIPE, shell=True) chimericReads = creads.stdout.decode('utf-8').strip() prc = (float(chimericReads)/float(totalReads))*100 print("\033[91m This step can remove possible chimeric sequences \033[0m") print("\033[93m Total number of reads: " + totalReads + " \033[0m") print("\033[93m Total number of possible chimeras: " + chimericReads + " ({0:.2f}".format(prc) + "%) \033[0m") print("\033[92m Do you want to remove chimeric sequences?(y/n): \033[0m") if snakemake.config["interactive"] != "F": user_input = stdin.readline() #READS A LINE user_input = user_input[:-1] filter_log = "Total number of possible chimeras: " + chimericReads + " ({0:.2f}".format(prc) + ")%\n\n" if user_input.upper() == "Y" or user_input.upper() == "YES": subprocess.run( ["filter_fasta.py -f " + snakemake.input[0] + " -s "+ snakemake.input[1] + " -n -o " + snakemake.output[0]], stdout=subprocess.PIPE, shell=True) filter_log += "The chimeric sequences were removed with the following command:\n\n" filter_log += ":commd:`filter_fasta.py -f " + snakemake.input[0] + " -s "+ snakemake.input[1] + " -n -o " + snakemake.output[0]+"`\n\n" else: subprocess.run( ["mv " + snakemake.input[0] + " " + snakemake.output[0]], stdout=subprocess.PIPE, shell=True) filter_log += "The user didn't remove the chimeric sequences\n\n" with open(snakemake.output[1], "w") as out: out.write(filter_log) out.close() else: print("\033[93m" +" Interactive mode off \033[0m") print("\033[93m" +" Removing chimeras...\033[0m") subprocess.run( [snakemake.config["qiime"]["path"]+"filter_fasta.py -f " + snakemake.input[0] + " -s "+ snakemake.input[1] + " -n -o " + snakemake.output[0]], stdout=subprocess.PIPE, shell=True) filter_log = "Total number of possible chimeras: " + chimericReads + " ({0:.2f}".format(prc) + ")%\n\n" filter_log += "The chimeric sequences were removed with the following command:\n\n" filter_log += ":commd:`filter_fasta.py -f " + snakemake.input[0] + " -s "+ snakemake.input[1] + " -n -o " + snakemake.output[0]+"`\n\n" with open(snakemake.output[1], "w") as out: out.write("Interactive mode off. Automatic chimera removing...\n") out.write(str(filter_log)) out.close() except Exception as e: print("Problem executing script.\nMessage: " + str(e)) |
7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 | import os import subprocess from benchmark_utils import countFasta from benchmark_utils import countFastaGZ from sys import stdin import shutil def complement(seq): complement = {'A': 'T', 'C': 'G', 'G': 'C', 'T': 'A', 'Y':'R', 'R':'Y','S':'S','W':'W','K':'M','M':'K','N':'N','B':'V','V':'B','D':'H','H':'D'} bases = list(seq) bases = [complement[base] for base in bases] return ''.join(bases) def reverse_complement(s): return complement(s[::-1]) #from Bio.Seq import Seq primer_by_sample={} uniq_primers={} idx_fw_primer=-1 # default for qiime (col 3) idx_rv_primer=-1 # new field idx_rv_revcomp_primer=-1 isRC = False with open(snakemake.input[0]) as mappingFile: l=0 for line in mappingFile: l=l+1; columns = line.split('\t') #the header is always at row 1 and must contain these first 3 fields (qiime specs): #SampleID BarcodeSequence LinkerPrimerSequence Description if l==1 : c=0 #Find target headers for col in columns: if col == "ReverseLinkerPrimerSequence" or col == "RvLinkerPrimerSequence" or col == "ReversePrimer" or col == "ReversePrimerSequence" : idx_rv_primer=c elif col == "LinkerPrimerSequence": idx_fw_primer=c elif col == "ReverseLinkerPrimerSequenceRevCom" or col == "RvLinkerPrimerSequenceRevCom" or col == "ReversePrimerRevCom": idx_rv_revcomp_primer=c c=c+1 #if there is no "ReverseLinkerPrimerSequence" we look for the ReverseLinkerPrimerSequenceRevCom if idx_rv_primer == -1 and idx_rv_revcomp_primer !=1: idx_rv_primer=idx_rv_revcomp_primer isRC = True elif not line.startswith("#"): if idx_rv_primer != -1: #if the valuee is the reverse complemented now we want the 5' to 3' orientation so rev com again. if isRC: primer_by_sample[columns[0]]=[columns[idx_fw_primer],reverse_complement(columns[idx_rv_primer])] else: primer_by_sample[columns[0]]=[columns[idx_fw_primer],columns[idx_rv_primer]] elif idx_fw_primer != -1: primer_by_sample[columns[0]]=[columns[idx_fw_primer]] else: print("\033[91m ERROR: LinkerPrimerSequence not found on mapping file: "+ snakemake.input[0] +" \033[0m") exit(1) # List files fq_files = [f for f in os.listdir(snakemake.params[0]) if f.endswith("_1."+snakemake.params[2])] if not os.path.exists(snakemake.params[0]+"/reads_discarded_primer/"): os.makedirs(snakemake.params[0]+"/reads_discarded_primer/") if not os.path.exists(snakemake.params[0]+"/primer_removed/"): os.makedirs(snakemake.params[0]+"/primer_removed/") if not os.path.exists(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/report_files"): os.makedirs(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/report_files") summ_file = open(snakemake.output[0],"w") summ_file2 = open(snakemake.params[4],"w") summ_file.write("Sample\tReads_before_cutadapt\tSurviving_reads\tPrc_surviving_reads\n") summ_file2.write("Sample\tReads_before_cutadapt\tSurviving_reads\tPrc_surviving_reads\n") log_str = "Sample\tReads_before_cutadapt\tSurviving_reads\tPrc_surviving_reads\n" log_zero = "Sample\tReads_before_cutadapt\tSurviving_reads\tPrc_surviving_reads\n" has_zero_length_reads = False zero_samples = 0; to_remove = [] for fw in fq_files: sample=fw.replace("_1."+snakemake.params[2],"") fw_fq= snakemake.params[0]+"/"+fw rv=fw.replace("_1."+snakemake.params[2],"_2."+snakemake.params[2]) rv_fq= snakemake.params[0]+"/"+rv #Count reads before trimming if snakemake.params[2].endswith("gz"): reads_ori=countFastaGZ(fw_fq,True) else: reads_ori=countFasta(fw_fq,True) #no cutadapt if no reads #if reads_ori > 0: if sample in primer_by_sample: runCutAdapt=False discard_untrimmed="" extra_params=snakemake.params[1] if len(primer_by_sample[sample])>1 and reads_ori < 1: reads_after = 0 prcOK="{:.2f}".format(float((reads_after/1)*100)) to_copy=snakemake.params[0]+"/primer_removed/"+sample+"_1."+snakemake.params[2] os.symlink(fw_fq,to_copy) if snakemake.params[3] == "PE": to_copy_rv=snakemake.params[0]+"/primer_removed/"+sample+"_2."+snakemake.params[2] os.symlink(rv_fq,to_copy_rv) runCutAdapt=True elif len(primer_by_sample[sample])>1 and snakemake.params[3] == "PE" : if "--discard-untrimmed" in snakemake.params[1]: discard_untrimmed=" --untrimmed-output "+snakemake.params[0]+"/reads_discarded_primer/"+sample+"_1.fastq.gz --untrimmed-paired-output "+snakemake.params[0]+"/reads_discarded_primer/"+sample+"_2.fastq.gz" extra_params=snakemake.params[1].replace("--discard-untrimmed","") #print("cutadapt -g "+ primer_by_sample[sample][0] + " -G " + primer_by_sample[sample][1] + " " +extra_params+" -O "+ snakemake.config["primers"]["min_overlap"] +" -o "+snakemake.params[0]+"/primer_removed/"+sample+"_1.fastq.gz -p "+snakemake.params[0]+"/primer_removed/"+sample+"_2.fastq.gz "+discard_untrimmed +" "+ fw_fq + " " + rv_fq + " >> "+snakemake.params[0]+"/primer_removed/"+sample+".cutadapt.log") subprocess.run(["cutadapt -g "+ primer_by_sample[sample][0] + " -G " + primer_by_sample[sample][1]+" -m "+ snakemake.config["primers"]["min_length"] + " " +extra_params+" -O "+ snakemake.config["primers"]["min_overlap"] +" -o "+snakemake.params[0]+"/primer_removed/"+sample+"_1.fastq.gz -p "+snakemake.params[0]+"/primer_removed/"+sample+"_2.fastq.gz "+discard_untrimmed +" "+ fw_fq + " " + rv_fq + " >> "+snakemake.params[0]+"/primer_removed/"+sample+".cutadapt.log"],stdout=subprocess.PIPE, shell=True) runCutAdapt=True #subprocess.run(["grep \"(passing filters)\" "+snakemake.params[0]+"/primer_removed/"+sample+".cutadapt.log | awk '{print \""+sample+"\t\"$5\"\t\"$6}' >> "+snakemake.output[0]],stdout=subprocess.PIPE, shell=True) #subprocess.run( ["cutadapt "+ primer_set +" "+snakemake.params[0]+" -o "+snakemake.output[0] + " " + snakemake.input[0]+ ">"+ snakemake.output[1]],stdout=subprocess.PIPE, shell=True) elif len(primer_by_sample[sample])>=1 and snakemake.params[3] == "SE": if "--discard-untrimmed" in snakemake.params[0]: discard_untrimmed=" --untrimmed-output "+snakemake.params[0]+"/reads_discarded_primer/"+sample+"_1.fastq.gz" extra_params=snakemake.params[1].replace("--discard-untrimmed","") subprocess.run(["cutadapt -g "+ primer_by_sample[sample][0] +" -m "+ snakemake.config["primers"]["min_length"] +" " +extra_params+" -O "+ snakemake.config["primers"]["min_overlap"] +" -o "+snakemake.params[0]+"/primer_removed/"+sample+"_1.fastq.gz "+ discard_untrimmed + " " + fw_fq + " >> "+ snakemake.params[0]+"/primer_removed/"+sample+".cutadapt.log"],stdout=subprocess.PIPE, shell=True) #subprocess.run(["grep \"(passing filters)\" "+snakemake.params[0]+"/primer_removed/"+sample+".cutadapt.log | awk '{print \""+sample+"\t\"$5\"\t\"$6}' >> "+snakemake.output[0]],stdout=subprocess.PIPE, shell=True) runCutAdapt=True elif len(primer_by_sample[sample])==1 and snakemake.params[3] == "PE": print("\033[91m ERROR: Found forward and reverse reads, but only one primer was supplied \033[0m") print("sample: "+sample + " primer " + primer_by_sample[sample][0]) summ_file.close() summ_file2.close() exit(1) if runCutAdapt and reads_ori > 0: if snakemake.params[2].endswith("gz"): reads_ori=countFastaGZ(fw_fq,True) reads_after=countFastaGZ(snakemake.params[0]+"/primer_removed/"+sample+"_1.fastq.gz",True) else: reads_ori=countFasta(fw_fq,True) reads_after=countFasta(snakemake.params[0]+"/primer_removed/"+sample+"_1.fastq",True) prcOK="{:.2f}".format(float((reads_after/reads_ori)*100)) summ_file.write(sample+"\t"+str(reads_ori)+"\t"+str(reads_after)+"\t"+prcOK+"\n"); summ_file2.write(sample+"\t"+str(reads_ori)+"\t"+str(reads_after)+"\t"+prcOK+"\n"); log_str = log_str + sample+"\t"+str(reads_ori)+"\t"+str(reads_after)+"\t"+prcOK+"\n" if reads_after < 1: has_zero_length_reads = True log_zero = log_zero + sample+"\t"+str(reads_ori)+"\t"+str(reads_after)+"\t"+prcOK+"\n" to_remove.append(snakemake.params[0]+"/primer_removed/"+sample+"_1."+snakemake.params[2]) if snakemake.params[3] == "PE": to_remove.append(snakemake.params[0]+"/primer_removed/"+sample+"_2."+snakemake.params[2]) zero_samples = zero_samples + 1 elif runCutAdapt and reads_ori < 1: summ_file.write(sample+"\t"+str(reads_ori)+"\t"+str(reads_after)+"\t"+prcOK+"\n"); summ_file2.write(sample+"\t"+str(reads_ori)+"\t"+str(reads_after)+"\t"+prcOK+"\n"); log_str = log_str + sample+"\t"+str(reads_ori)+"\t"+str(reads_after)+"\t"+prcOK+"\n" log_zero = log_zero + sample+"\t"+str(reads_ori)+"\t"+str(reads_after)+"\t"+prcOK+"\n" zero_samples = zero_samples + 1 has_zero_length_reads = True to_remove.append(snakemake.params[0]+"/primer_removed/"+sample+"_1."+snakemake.params[2]) if snakemake.params[3] == "PE": to_remove.append(snakemake.params[0]+"/primer_removed/"+sample+"_2."+snakemake.params[2]) else: print("\033[93m WARNING: No primers found for sample: "+sample +" \033[0m") summ_file.close() summ_file2.close() exit(1) summ_file.close() summ_file2.close() user_input="0" show_menu = True if zero_samples > 0: while show_menu: print("\033[91m\n########### Primer removal validation ###########\033[0m") print("\033[91m You have " + str(zero_samples) + " samples without reads surviving filters. \033[0m") print("\033[92m LIBRARY: "+snakemake.wildcards.sample+" \033[0m") print("\033[92m cutadapt_log: "+snakemake.params[0]+"/primer_removed/"+sample+".cutadapt.log \033[0m") print("\033[93m Please select one of the following options: \033[0m") print("\033[93m 1. Print samples with 0 reads \033[0m") print("\033[93m 2. Print summary (all the samples) \033[0m") print("\033[93m 3. Remove from this analysis samples with 0 reads\033[0m") print("\033[93m and continue with the workflow. \033[0m") print("\033[93m 4. Interrupt the workflow and re-do primer removal step. \033[0m") print("\033[93m Adjust primer values in your configuration and/or mapping file \033[0m") print("\033[93m and restart the pipeline. \033[0m") print("\033[93m This action will remove:"+snakemake.params[0]+"/primer_removed \033[0m") print("\033[93m 5. Interrupt the workflow \033[0m") print("\033[93m Select an option: \033[0m") user_input = stdin.readline() #READS A LINE user_input = user_input[:-1] if user_input == "1": print(log_zero) elif user_input == "2": print(log_str) elif user_input == "3": for file in to_remove: newn = file+"_NOK" os.rename(file, newn) show_menu = False elif user_input == "4": shutil.rmtree(snakemake.params[0]+"/primer_removed") exit(1) elif user_input == "5": exit(1) exit(0) |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 | import subprocess import functools from snakemake.utils import report from benchmark_utils import readBenchmark from benchmark_utils import countTxt from seqsChart import createChart from seqsChart import createChartPrc from benchmark_utils import countFasta from benchmark_utils import make_table ################ #Function to retrive the sample names and put in the report title #@param file with the sample list, it is created during combine_filtered_samples #snakemake.wildcards.project + "/runs/" + snakemake.wildcards.run + "/samples.log" #@return the title with the samples def getSampleList(sampleFile): with open(sampleFile) as sfile: samps ="Amplicon Analysis Report for Libraries: " for l in sfile: samps+= l samps+="\n" for i in range(0,len(samps)): samps+="=" return samps; ######################### #This function reads the file cat_samples.log which have the executed command to #combine all the libraries after cleaning and demultiplexing and before taxonomy #assignation #@param catLogFile file with the command #snakemake.wildcards.project + "/runs/" + snakemake.wildcards.run + "/cat_samples.log" #@return the string ready to be concatenated into the report. def getCombinedSamplesList(catLogFile): with open(catLogFile) as sfile: command =":commd:`" i=0 for l in sfile: if i == 0: command+= l + "`\n\n" i+=1 return command; #title = getSampleList(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/samples.log") #catCommand = getCombinedSamplesList(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/cat_samples.log") title = "Amplicon Analysis Report\n===========================\n\n" ################################################################################ # Benchmark Section # # This section is to generate a pre-formatted text with the benchmark info for # # All the executed rules. # ################################################################################ #combineBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/combine_seqs_fw_rev.benchmark") dada2Benchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/dada2.benchmark") asvFilterBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/filter.benchmark") #pikRepBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/pick_reps.benchmark") #assignTaxaBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/assign_taxa.benchmark") otuTableBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/dada2.table.benchmark") convertOtuBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/dada2.biom.benchmark") #convertOtuBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/otuTable.txt.benchmark") summTaxaBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/summary/summarize_taxa.benchmark") asvNoSingletonsBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/asvTable_nosingletons.bio.benchmark") filterASVTableBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/asvTable_nosingletons.txt.benchmark") filterBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/representative_seq_set_noSingletons.benchmark") deRepBenchmark="" #if snakemake.config["derep"]["dereplicate"] == "T" and snakemake.config["pickOTU"]["m"] != "swarm" and snakemake.config["pickOTU"]["m"] != "usearch": # deRepBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/derep/derep.benchmark") if snakemake.config["alignRep"]["align"] == "T": #align_seqs.py -m {config[alignRep][m]} -i {input} -o {params.outdir} {config[alignRep][extra_params]} alignBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/aligned/align_rep_seqs.benchmark") #"filter_alignment.py -i {input} -o {params.outdir} {config[filterAlignment][extra_params]}" alignFilteredBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/aligned/filtered/align_rep_seqs.benchmark") #"make_phylogeny.py -i {input} -o {output} {config[makeTree][extra_params]}" makePhyloBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/aligned/filtered/representative_seq_set_noSingletons_aligned_pfiltered.benchmark") kronaBenchmark="" if snakemake.config["krona"]["report"].casefold() == "t" or snakemake.config["krona"]["report"].casefold() == "true": kronaBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/krona_report.benchmark") #dada2FilterBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/filter.benchmark") #dada2Benchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/dada2.benchmark") #dada2BiomBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/dada2.biom.benchmark") ################################################################################ # TOOLS VERSION SECTION # ################################################################################ #clusterOtuV = subprocess.run([snakemake.config["qiime"]["path"]+'pick_otus.py', '--version'], stdout=subprocess.PIPE) #clusterOtuVersion = "**" + clusterOtuV.stdout.decode('utf-8').replace('Version:','').strip() + "**" #pickRepV = subprocess.run([snakemake.config["qiime"]["path"]+'pick_rep_set.py', '--version'], stdout=subprocess.PIPE) #pickRepVersion = "**" + pickRepV.stdout.decode('utf-8').replace('Version:','').strip() + "**" #assignTaxaV = subprocess.run([snakemake.config["qiime"]["path"]+'parallel_assign_taxonomy_'+snakemake.config["assignTaxonomy"]["qiime"]["method"]+'.py', '--version'], stdout=subprocess.PIPE) #assignTaxaVersion = "**" + assignTaxaV.stdout.decode('utf-8').replace('Version:','').strip() + "**" #makeOTUV = subprocess.run([snakemake.config["qiime"]["path"]+'make_otu_table.py', '--version'], stdout=subprocess.PIPE) #makeOTUVersion = "**" + makeOTUV.stdout.decode('utf-8').replace('Version:','').strip() + "**" convertBiomV = subprocess.run([snakemake.config["biom"]["command"], '--version'], stdout=subprocess.PIPE) convertBiomVersion = "**" + convertBiomV.stdout.decode('utf-8').strip() + "**" dada2V = subprocess.run([snakemake.config["Rscript"]["command"],'Scripts/dada2Version.R'], stdout=subprocess.PIPE) dada2Version = "**" + dada2V.stdout.decode('utf-8').strip() + "**" summTaxaSV = subprocess.run([snakemake.config["qiime"]["path"]+'summarize_taxa.py', '--version'], stdout=subprocess.PIPE) summTaxaVersion = "**" + summTaxaSV.stdout.decode('utf-8').replace('Version:','').strip() + "**" filterOTUNoSV = subprocess.run([snakemake.config["qiime"]["path"]+'filter_otus_from_otu_table.py', '--version'], stdout=subprocess.PIPE) filterOTUNoSVersion = "**" + filterOTUNoSV.stdout.decode('utf-8').replace('Version:','').strip() + "**" filterFastaV = subprocess.run([snakemake.config["qiime"]["path"]+'filter_fasta.py', '--version'], stdout=subprocess.PIPE) filterFastaVersion = "**" + filterFastaV.stdout.decode('utf-8').replace('Version:','').strip() + "**" rscriptV = subprocess.run([snakemake.config["Rscript"]["command"], '--version'], stdout=subprocess.PIPE) rscriptVersion = "**" + filterFastaV.stdout.decode('utf-8').strip() + "**" #blastnV = subprocess.run([snakemake.config["assignTaxonomy"]["blast"]["command"], '-version'], stdout=subprocess.PIPE) #blastnVersion = "**" + blastnV.stdout.decode('utf-8').split('\n', 1)[0].replace('blastn:','').strip() + "**" #vsearchV2 = subprocess.run([snakemake.config["assignTaxonomy"]["vsearch"]["command"], '--version'], stdout=subprocess.PIPE) #vsearchVersion_tax = "**" + vsearchV2.stdout.decode('utf-8').split('\n', 1)[0].strip() + "**" #if snakemake.config["derep"]["dereplicate"] == "T" and snakemake.config["pickOTU"]["m"] != "swarm" and snakemake.config["pickOTU"]["m"] != "usearch": # vsearchV = subprocess.run([snakemake.config["derep"]["vsearch_cmd"], '--version'], stdout=subprocess.PIPE) # vsearchVersion = "**" + vsearchV.stdout.decode('utf-8').split('\n', 1)[0].strip() + "**" if snakemake.config["alignRep"]["align"] == "T": alignFastaVersion="TBD" try: alignFastaV = subprocess.run([snakemake.config["qiime"]["path"]+'align_seqs.py', '--version'], stdout=subprocess.PIPE) if "Version" in alignFastaVersion: alignFastaVersion = "**" + alignFastaV.stdout.decode('utf-8').replace('Version: ','').strip() + "**" except Exception as e: alignFastaVersion = "**Problem retriving the version**" filterAlignmentV = subprocess.run([snakemake.config["qiime"]["path"]+'filter_alignment.py', '--version'], stdout=subprocess.PIPE) filterAlignmentVersion = "**" + filterAlignmentV.stdout.decode('utf-8').replace('Version:','').strip() + "**" makePhyloV = subprocess.run([snakemake.config["qiime"]["path"]+'make_phylogeny.py', '--version'], stdout=subprocess.PIPE) makePhyloVersion = "**" + makePhyloV.stdout.decode('utf-8').replace('Version:','').strip() + "**" ################################################################################ # Compute counts section # ################################################################################ totalReads = "TBD" intTotalReads = 1; try: treads = subprocess.run( ["cat " + snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/asv/filter_summary.out | awk 'NR>1{sum=sum+$2} END{print sum}'"], stdout=subprocess.PIPE, shell=True) intTotalReads = int(treads.stdout.decode('utf-8').strip()) totalReads = "**" + str(intTotalReads) + "**" except Exception as e: totalReads = "Problem reading outputfile" filteredReads = "TBD" intFilteredReads = 1; prcFiltered=0.0 try: freads = subprocess.run( ["cat " + snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/asv/filter_summary.out | awk 'NR>1{sum=sum+$3} END{print sum}'"], stdout=subprocess.PIPE, shell=True) intFilteredReads = int(freads.stdout.decode('utf-8').strip()) filteredReads = "**" + str(intFilteredReads) + "**" prcFiltered = float(intFilteredReads/intTotalReads)*100 prcFilteredStr = "**" + "{:.2f}".format(prcFiltered) + "%**" except Exception as e: filteredReads = "Problem reading outputfile" denoisedFWReads = "TBD" intDenoisedFWReads = 1; prcDenoisedFW=0 try: dfwreads = subprocess.run( ["cat " + snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/asv/stats_dada2.txt | awk 'NR>1{sum=sum+$2} END{print sum}'"], stdout=subprocess.PIPE, shell=True) intDenoisedFWReads = int(dfwreads.stdout.decode('utf-8').strip()) denoisedFWReads = "**" + str(intDenoisedFWReads) + "**" prcDenoisedFW = float(intDenoisedFWReads/intTotalReads)*100 prcDenoisedFWStr = "**" + "{:.2f}".format(prcDenoisedFW) + "%**" prcDenoisedFWvsFiltered = (intDenoisedFWReads/intFilteredReads)*100 prcDenoisedFWStrvsFiltered = "**" + "{:.2f}".format(prcDenoisedFWvsFiltered) + "%**" except Exception as e: denoisedFWReads = "Problem reading outputfile" denoisedRVReads = "TBD" intDenoisedRVReads = 1; prcDenoisedRV=0.0 try: drvreads = subprocess.run( ["cat " + snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/asv/stats_dada2.txt | awk 'NR>1{sum=sum+$3} END{print sum}'"], stdout=subprocess.PIPE, shell=True) intDenoisedRVReads = int(drvreads.stdout.decode('utf-8').strip()) denoisedRVReads = "**" + str(intDenoisedRVReads) + "**" prcDenoisedRV = float(intDenoisedRVReads/intTotalReads)*100 prcDenoisedRVStr = "**" + "{:.2f}".format(prcDenoisedRV) + "%**" prcDenoisedRVvsFiltered = (intDenoisedRVReads/intFilteredReads)*100 prcDenoisedRVStrvsFiltered = "**" + "{:.2f}".format(prcDenoisedRVvsFiltered) + "%**" except Exception as e: denoisedRVReads = "Problem reading outputfile" mergedReads = "TBD" intmergedReads = 1; prcmerged=0.0 try: mreads = subprocess.run( ["cat " + snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/asv/stats_dada2.txt | awk 'NR>1{sum=sum+$4} END{print sum}'"], stdout=subprocess.PIPE, shell=True) intmergedReads = int(mreads.stdout.decode('utf-8').strip()) mergedReads = "**" + str(intmergedReads) + "**" prcmerged = float(intmergedReads/intTotalReads)*100 prcmergedStr = "**" + "{:.2f}".format(prcmerged) + "%**" prcmergedvsVariant = (intmergedReads/((intDenoisedFWReads+intDenoisedFWReads)/2))*100 prcmergedStrvsVariant = "**" + "{:.2f}".format(prcmergedvsFiltered) + "%**" except Exception as e: mergedReads = "Problem reading outputfile" lengthFReads = "TBD" intlengthFReads = 1; prclengthF=0.0 try: lreads = subprocess.run( ["cat " + snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/asv/stats_dada2.txt | awk 'NR>1{sum=sum+$5} END{print sum}'"], stdout=subprocess.PIPE, shell=True) intlengthFReads = int(lreads.stdout.decode('utf-8').strip()) lengthFReads = "**" + str(intlengthFReads) + "**" prclengthF = float(intlengthFReads/intTotalReads)*100 prclengthFStr = "**" + "{:.2f}".format(prclengthF) + "%**" prclengthFvsMerged = (intlengthFReads/intmergedReads)*100 prclengthFStrvsMerged = "**" + "{:.2f}".format(prclengthFvsMerged) + "%**" except Exception as e: lengthFReads = "Problem reading outputfile" chimeraReads = "TBD" intchimeraReads = 1; prcchimera=0.0 if snakemake.config["dada2_asv"]["chimeras"] == "T": try: chreads = subprocess.run( ["cat " + snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/asv/stats_dada2.txt | awk 'NR>1{sum=sum+$6} END{print sum}'"], stdout=subprocess.PIPE, shell=True) intchimeraReads = int(chreads.stdout.decode('utf-8').strip()) chimeraReads = "**" + str(intchimeraReads) + "**" prcchimera = float(intchimeraReads/intTotalReads)*100 prcchimeraStr = "**" + "{:.2f}".format(prcchimera) + "%**" prcchimeravsLength = (intchimeraReads/intlengthFReads)*100 prcchimeraStrvsLength = "**" + "{:.2f}".format(prcchimeravsLength) + "%**" except Exception as e: chimeraReads = "Problem reading outputfile" intASV = 1 totalAsvs="" intAsvs=1 try: asv_file=snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+"/asv/taxonomy_dada2/representative_seq_set_tax_assignments.txt" tasvs = subprocess.run( ["cat " + asv_file + " | wc -l"], stdout=subprocess.PIPE, shell=True) intAsvs = int(tasvs.stdout.decode('utf-8').strip()) #print("Total OTUS" + str(intOtus)) totalAsvs = "**" + str(intAsvs) + "**" except Exception as e: totalAsvs = "**Problem reading outputfile**" prcAssigned = 0.0 prcNotAssignedOtus="TBD" assignedOtus=0 notAssignedOtus=0 try: aOtus = subprocess.run( ["cat " + snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/asv/taxonomy_dada2/representative_seq_set_tax_assignments.txt | cut -f2 | grep -w NA | wc -l"], stdout=subprocess.PIPE, shell=True) notAssignedOtus = int(aOtus.stdout.decode('utf-8').strip()) #print("Not assigned OTUS" + str(notAssignedOtus)) assignedOtus = (intAsvs - notAssignedOtus) prcAssigned = float(assignedOtus/intAsvs)*100 prcAssignedAsvs = "**" + "{:.2f}".format(prcAssigned) + "%**" except Exception as e: prcAssignedAsvs = "**Problem reading outputfile**" intSingletons = 1; totalSingletons ="" try: totS = subprocess.run( ["grep -v \"^#\" " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/asvTable_noSingletons.txt" + " | wc -l"], stdout=subprocess.PIPE, shell=True) intSingletons = int(totS.stdout.decode('utf-8').strip()) #print("Total OTUS" + str(intOtus)) totalSingletons = "**" + str(intSingletons) + "**" except Exception as e: totalSingletons = "**Problem reading outputfile**" notAssignedSingleOtus = 0 assignedSingleOtus = 0 totalAssignedSingletons ="" try: sOtus = subprocess.run( ["cat " + snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/asv/taxonomy_dada2/representative_seq_set_noSingletons.fasta | grep '^>' | sed 's/>//' | grep -F -w -f - " +snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/asv/taxonomy_dada2/representative_seq_set_tax_assignments.txt | cut -f2 | grep -w NA | wc -l" ], stdout=subprocess.PIPE, shell=True) notAssignedSingleOtus = int(sOtus.stdout.decode('utf-8').strip()) #print("Not assigned OTUS" + str(notAssignedOtus)) assignedSingleOtus = (intSingletons - notAssignedSingleOtus) totalAssignedSingletons = "**" + str(assignedSingleOtus) + "%**" except Exception as e: totalAssignedSingletons = "**Problem reading outputfile**" prcSingle = 0.0 prcSingleStr="" try: prcSingle=float(assignedSingleOtus/intSingletons)*100 prcSingleStr = "**" + "{:.2f}".format(prcSingle) + "%**" except Exception as e: prcSingleStr="**Error parsing output**" #include user description on the report desc = snakemake.config["description"] txtDescription = "" if len(desc) > 0: txtDescription = "\n**User description:** "+desc+"\n" ################################################################################ # Sample distribution chart # ################################################################################ countTxt="Following the read counts: \n\n" fileData = [] headers = [] data =[] headers.append("File description") headers.append("Location") headers.append("#") headers.append("(%)") fileData.append(headers) #combined data.append("Demultiplexed reads") data.append(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/<SAMPLE>_data/demultiplexed/\*.fastq.gz") data.append(str(intTotalReads)) data.append("100%") fileData.append(data) data=[] #filtered data.append("QA filtered & trimmed reads") data.append(snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/<LIBRARY>_data/demultiplexed/filtered/\*.fastq.gz") data.append(str(intFilteredReads)) data.append("{:.2f}".format(float(prcFiltered))+"%") fileData.append(data) data=[] #fw denoised data.append("Denoised FW reads") data.append("*No intermediate file generated*") data.append(str(intDenoisedFWReads)) data.append("{:.2f}".format(prcDenoisedFW)+"%") fileData.append(data) data=[] #rv denoised data.append("Denoised RV reads") data.append("*NO intermediate file generated*") data.append(str(intDenoisedRVReads)) data.append("{:.2f}".format(prcDenoisedRV)+"%") fileData.append(data) data=[] #Merged data.append("Merged and full denoised reads") data.append("*No intermediate file generated*") data.append(str(intmergedReads)) data.append("{:.2f}".format(prcmerged)+"%") fileData.append(data) data=[] #LengthFiltered data.append("Length filtered") data.append("*No intermediate file generated*") data.append(str(intlengthFReads)) data.append("{:.2f}".format(prclengthF)+"%") fileData.append(data) data=[] if snakemake.config["dada2_asv"]["chimeras"] == "T": data.append("Chimera removed") data.append("*No intermediate file generated*") data.append(str(intchimeraReads)) data.append("{:.2f}".format(prcchimera)+"%") fileData.append(data) data=[] #asv data.append("ASV table") data.append(snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/asv/asvTable.txt") data.append(str(intAsvs)) #data.append("{:.2f}".format(float((intAsvs/intTotalReads)*100))+"%") data.append("100%") fileData.append(data) data=[] #Taxonomy data.append("Taxonomy assignation") data.append(snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/asv/taxonomy_dada2/representative_seq_set_tax_assignments.txt") data.append(str(assignedOtus)) data.append("{:.2f}".format(float((assignedOtus/intAsvs)*100))+"%") fileData.append(data) data=[] #otus no singletons data.append("ASV table (no singletons: a > " + str(snakemake.config["filterOtu"]["n"])+")") data.append(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/asvTable_noSingletons.txt") data.append(str(intSingletons)) data.append("{:.2f}".format(float((intSingletons/intAsvs)*100))+"%") fileData.append(data) data=[] #Assigned singletons data.append("Assigned no singletons") data.append(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/asvTable_noSingletons.txt") data.append(str(assignedSingleOtus)) try: data.append("{:.2f}".format(prcSingle)+"%") except Exception as e: data.append("Err") print("Error - Assigned no singletons - dividing: "+ str(assignedSingleOtus)+"/"+ str(intSingletons)) fileData.append(data) countTxt += make_table(fileData) ################################################################################ # Generate sequence amounts chart # ################################################################################ numbers=[intTotalReads]; labels=["Initial\nreads"]; prcs=[] prcs.append("100%") #if snakemake.config["derep"]["dereplicate"] == "T" and snakemake.config["pickOTU"]["m"] != "swarm" and snakemake.config["pickOTU"]["m"] != "usearch": # numbers.append(intDerep) # labels.append("Derep.") # prcs.append("{:.2f}".format(float((intDerep/intTotalReads)*100))+"%") numbers.append(intFilteredReads) labels.append("Filtered\nreads") prcs.append("{:.2f}".format(prcFiltered)+"%") #numbers.append(intDenoisedFWReads) #labels.append("Denoised\nFW reads") #prcs.append("{:.2f}".format(prcDenoisedFW)+"%") #numbers.append(intDenoisedRVReads) #labels.append("Denoised\nRV reads") #prcs.append("{:.2f}".format(prcDenoisedRV)+"%") numbers.append(intmergedReads) labels.append("Merged\nreads") prcs.append("{:.2f}".format(prcmerged)+"%") numbers.append(intlengthFReads) labels.append("Length\nfiltered") prcs.append("{:.2f}".format(prclengthF)+"%") color_index=4 if snakemake.config["dada2_asv"]["chimeras"] == "T": numbers.append(intchimeraReads) labels.append("Chimera\nremoved") prcs.append("{:.2f}".format(prcchimera)+"%") color_index=5 numbers2=[intAsvs]; labels2=["ASVs"]; prcs2=["100%"] #numbers.append(intAsvs) #labels.append("ASVs") #prcs.append("{:.2f}".format(float((intAsvs/intTotalReads)*100))+"%") numbers2.append(assignedOtus) labels2.append("Assigned\nASVs") prcs2.append("{:.2f}".format(float((assignedOtus/intAsvs)*100))+"%") numbers2.append(intSingletons) labels2.append("No\nSingletons") prcs2.append("{:.2f}".format(float((intSingletons/intAsvs)*100))+"%") numbers2.append(assignedSingleOtus) labels2.append("Assigned no\nsingletons") prcs2.append("{:.2f}".format(prcSingle)+"%") createChartPrc(numbers, tuple(labels),prcs,snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/report_files/sequence_numbers_asv.png",0) createChartPrc(numbers2, tuple(labels2),prcs2,snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/report_files/sequence_numbers_asv_2.png",color_index) ############################################################################### # Varaible sections # ################################################################################ variable_refs="" assignTaxoStr = "" if snakemake.config["ANALYSIS_TYPE"] == "ASV": assignTaxoStr =":red:`Tool:` RDP_\n\n" assignTaxoStr += ":green:`Function:` assignTaxonomy() *implementation of RDP Classifier within dada2*\n\n" assignTaxoStr += ":green:`Reference database:` " + str(snakemake.config["dada2_taxonomy"]["db"])+ "\n\n" if snakemake.config["dada2_taxonomy"]["add_sps"]["add"].casefold() == "T": assignTaxoStr += ":green:`Species information.` After assigning taxonomy, genus-species binomials were assigned with assignSpecies() function.\n\n" assignTaxoStr += ":green:`Function:` addSpecies()* wraps the assignSpecies function to assign genus-species binomials to the input sequences by exact matching against a reference fasta.*\n\n" assignTaxoStr += ":green:`Taxonomy species file:` " + str(snakemake.config["dada2_taxonomy"]["add_sps"]["db_sps"])+ "\n\n" else: assignTaxoStr += ":green:`Species information:` The *'add species'* (add_sps) option from the configuration file is set to **false**. Set it to **true** and supply a *species database* if you want to add species-level annotation to the taxonomic table.\n\n" variable_refs+=".. [RDP] Wang, Q, G. M. Garrity, J. M. Tiedje, and J. R. Cole. 2007. Naive Bayesian Classifier for Rapid Assignment of rRNA Sequences into the New Bacterial Taxonomy. Appl Environ Microbiol. 73(16):5261-7.\n\n" #Alignment report alignmentReport = "" if snakemake.config["alignRep"]["align"] == "T": alignmentReport = "\nAlign representative sequences\n-------------------------------\n\n" alignmentReport+="Align the sequences in a FASTA file to each other or to a template sequence alignment.\n\n" alignmentReport+=":red:`Tool:` [QIIME]_ - align_seqs.py\n\n" alignmentReport+=":red:`Version:` "+alignFastaVersion +"\n\n" alignmentReport+=":green:`Method:` ["+ snakemake.config["alignRep"]["m"] + "]_\n\n" alignmentReport+="**Command:**\n\n" alignmentReport+=":commd:`align_seqs.py -m "+snakemake.config["alignRep"]["m"] +" -i "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/dada2/representative_seq_set_noSingletons.fasta "+ snakemake.config["alignRep"]["extra_params"] + " -o " alignmentReport+=snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/aligned/representative_seq_set_noSingletons_aligned.fasta`\n\n" alignmentReport+="**Output files:**\n\n" alignmentReport+=":green:`- Aligned fasta file:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/aligned/representative_seq_set_noSingletons_aligned.fasta\n\n" alignmentReport+=":green:`- Log file:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/aligned/representative_seq_set_noSingletons_log.txt\n\n" alignmentReport+=alignBenchmark+"\n\n" alignmentReport+="Filter alignment\n-----------------\n\n" alignmentReport+="Removes positions which are gaps in every sequence.\n\n" alignmentReport+=":red:`Tool:` [QIIME]_ - filter_alignment.py\n\n" alignmentReport+=":red:`Version:` "+filterAlignmentVersion +"\n\n" alignmentReport+="**Command:**\n\n" alignmentReport+=":commd:`filter_alignment.py -i "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/aligned/representative_seq_set_noSingletons_aligned.fasta " +snakemake.config["filterAlignment"]["extra_params"] alignmentReport+=" -o "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/aligned/filtered/`\n\n" alignmentReport+="**Output file:**\n\n" alignmentReport+=":green:`- Aligned fasta file:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/aligned/representative_seq_set_noSingletons_aligned_pfiltered.fasta\n\n" alignmentReport+=alignFilteredBenchmark+"\n\n" alignmentReport+="Make tree\n-----------\n\n" alignmentReport+="Create phylogenetic tree (newick format).\n\n" alignmentReport+=":red:`Tool:` [QIIME]_ - make_phylogeny.py\n\n" alignmentReport+=":red:`Version:` "+makePhyloVersion +"\n\n" alignmentReport+=":green:`Method:` ["+ snakemake.config["makeTree"]["method"] + "]_\n\n" alignmentReport+="**Command:**\n\n" alignmentReport+=":commd:`make_phylogeny.py -i "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/aligned/representative_seq_set_noSingletons_aligned.fasta -o representative_seq_set_noSingletons_aligned_pfiltered.tre "+ snakemake.config["makeTree"]["extra_params"]+ " -t " + snakemake.config["makeTree"]["method"]+"`\n\n" alignmentReport+="**Output file:**\n\n" alignmentReport+=":green:`- Taxonomy tree:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/aligned/representative_seq_set_noSingletons_aligned.tre\n\n" alignmentReport+=makePhyloBenchmark+"\n\n" #KRONA REPORT kronaReport = "" if snakemake.config["krona"]["report"].casefold() == "t" or snakemake.config["krona"]["report"].casefold() == "true": kronaReport+="Krona report\n----------------\n\n" kronaReport+="Krona allows hierarchical data to be explored with zooming, multi-layered pie charts.\n\n" kronaReport+=":red:`Tool:` [Krona]_\n\n" if snakemake.config["krona"]["otu_table"].casefold() != "singletons": kronaReport+="These charts were created using the ASV table **without** singletons\n\n" else: kronaReport+="These charts were created using the ASV table **including** singletons\n\n" if snakemake.config["krona"]["samples"].strip() == "all": kronaReport+="The report was executed for all the samples.\n\n" else: kronaReport+="The report was executed for the following target samples: "+ snakemake.config["krona"]["samples"].strip() + "\n\n" if "-c" in snakemake.config["krona"]["extra_params"]: kronaReport+="The samples were combined on a single chart\n\n" else: kronaReport+="Each sample is represented on a separated chart (same html report).\n\n" kronaReport+="You can see the report at the following link:\n\n" kronaReport+=":green:`- Krona report:` kreport_\n\n" #kronaReport+=" .. _kreport: ../../runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/krona_report.html\n\n" kronaReport+=" .. _kreport: report_files/krona_report.dada2.html\n\n" kronaReport+="Or access the html file at:\n\n" kronaReport+=":green:`- Krona html file:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/taxonomy_dada2/krona_report.html\n\n" kronaReport+=kronaBenchmark+"\n\n" ############################################################################### # REFERENCES # ################################################################################ #dada2 variable_refs+= ".. [dada2] Callahan BJ, McMurdie PJ, Rosen MJ, Han AW, Johnson AJA, Holmes SP (2016). DADA2: High-resolution sample inference from Illumina amplicon data. Nature Methods, 13, 581-583. doi: 10.1038/nmeth.3869.\n\n" #ALIGNMENT if snakemake.config["alignRep"]["align"] == "T": if snakemake.config["alignRep"]["m"] == "pynast": variable_refs+= ".. [pynast] Caporaso JG, Bittinger K, Bushman FD, DeSantis TZ, Andersen GL, Knight R. 2010. PyNAST: a flexible tool for aligning sequences to a template alignment. Bioinformatics 26:266-267.\n\n" elif snakemake.config["alignRep"]["m"] == "infernal": variable_refs+= ".. [infernal] Nawrocki EP, Kolbe DL, Eddy SR. 2009. Infernal 1.0: Inference of RNA alignments. Bioinformatics 25:1335-1337.\n\n" if snakemake.config["makeTree"]["method"] == "fasttree": variable_refs+= ".. [fasttree] Price MN, Dehal PS, Arkin AP. 2010. FastTree 2-Approximately Maximum-Likelihood Trees for Large Alignments. Plos One 5(3).\n\n" elif snakemake.config["makeTree"]["method"] == "raxml": variable_refs+= "..[raxml] Stamatakis A. 2006. RAxML-VI-HPC: Maximum Likelihood-based Phylogenetic Analyses with Thousands of Taxa and Mixed Models. Bioinformatics 22(21):2688-2690.\n\n" elif snakemake.config["makeTree"]["method"] == "clearcut": variable_refs+= "..[clearcut] Evans J, Sheneman L, Foster JA. 2006. Relaxed Neighbor-Joining: A Fast Distance-Based Phylogenetic Tree Construction Method. J Mol Evol 62:785-792.\n\n" elif snakemake.config["makeTree"]["method"] == "clustalw": variable_refs+= "..[clustalw] Larkin MA, Blackshields G, Brown NP, Chenna R, McGettigan PA, McWilliam H, Valentin F, Wallace IM, Wilm A, Lopez R, Thompson JD, Gibson TJ, Higgins DG. 2007. Clustal W and Clustal X version 2.0. Bioinformatics 23:2947-2948.\n\n" ######## # EXTRA ############## errorPlots="" if snakemake.config["dada2_asv" ]["generateErrPlots"].casefold() == "t" or snakemake.config["dada2_asv" ]["generateErrPlots"].casefold() == "true": errorPlots+="**Error plots:** \n\n:green:`- FW reads error plot::` " + snakemake.wildcards.PROJECT + "/runs/"+snakemake.wildcards.run+ "/asv/fw_err.pdf\n\n" errorPlots+=":green:`- RV reads error plot::` " + snakemake.wildcards.PROJECT + "/runs/"+snakemake.wildcards.run+ "/asv/rv_err.pdf\n\n" #shorts and longs shorts = str(snakemake.config["rm_reads"]["shorts"]) longs = str(snakemake.config["rm_reads"]["longs"]) with open(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/shorts_longs.log") as trimlog: i=0 for line in trimlog: i=i+1 #tokens = line.split("\t") if i== 1: shorts = line else: longs = line trunc_fw = str(snakemake.config["dada2_filter"]["truncFW"]) trunc_rv = str(snakemake.config["dada2_filter"]["truncRV"]) with open(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/trunc_val.log") as trunclog: i=0 for line in trunclog: i=i+1 #tokens = line.split("\t") if i== 1: trunc_fw = line else: trunc_rv = line chimeras="" if snakemake.config["dada2_asv" ]["chimeras"].casefold() == "t" or snakemake.config["dada2_asv" ]["chimeras"].casefold() == "true": chimeras="Remove chimeras\n~~~~~~~~~~~~~~~~\n\n" chimeras+="Sequence variants identified as bimeric are removed, and a bimera-free collection of unique sequences is generated.\n\n" chimeras+=":green:`Function:` removeBimeraDenovo()\n\n" chimeras+=":green:`Method:` consensus\n\n" report(""" {title} .. role:: commd .. role:: red .. role:: green **CASCABEL** is designed to run amplicon sequence analysis across single or multiple read libraries. This report consists of the ASV table creation and taxonomic assignment for all the combined accepted reads of given samples or libraries, if multiple. {txtDescription} Filter and Trim --------------- Once that all the individual libraries were demultiplexed, the fastq files from all the samples for all the libraries were processed together. The filter and trimming steps were both performed with the **filterAndTrim()** function from the R package dada2, according to user parameters. :red:`Tool:` dada2_ :red:`Version:` {dada2Version} :green:`Function:` filterAndTrim() :green:`Max Expected Errors (maxEE) FW:` {snakemake.config[dada2_filter][maxEE_FW]} :green:`Max Expected Errors (maxEE) RV:` {snakemake.config[dada2_filter][maxEE_RV]} :green:`Forward read truncation:` {trunc_fw} :green:`Reverse read truncation:` {trunc_rv} **Command:** :commd:`Scripts/asvFilter.R $PWD {snakemake.config[dada2_filter][generateQAplots]} {snakemake.config[dada2_filter][truncFW]} {snakemake.config[dada2_filter][truncRV]} {snakemake.config[dada2_filter][maxEE_FW]} {snakemake.config[dada2_filter][maxEE_RV]} {snakemake.config[dada2_filter][cpus]} {snakemake.config[dada2_filter][extra_params]} {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/filter_summary.out` **Output file:** :green:`- Filtered fastq files:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/<Library>/demultiplexed/filtered/ :green:`- Summary:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/filter_summary.out :red:`Note:` To speed up downstream computation, consider tightening maxEE. If too few reads are passing the filter, consider relaxing maxEE, perhaps especially on the reverse reads. Make sure that your forward and reverse reads overlap after length truncation. {asvFilterBenchmark} Amplicon Sequence Variants ---------------------------- In order to identify ASVs, dada2 workflow require to execute several steps. Following a summary of these steps and its main parameters. :red:`Tool:` dada2_ :red:`Version:` {dada2Version} Learn errors ~~~~~~~~~~~~~~~~ The first step after filtering the reads is to learn the errors from the fastq files. :green:`Function:` learnErrors(filteredFQ) {errorPlots} ASV inference ~~~~~~~~~~~~~~~ The amplicon sequence variant identification consists of a high resolution sample inference from the amplicon data using the learned errors. :green:`Function:` dada(filteredFQ, errors, pool='{snakemake.config[dada2_asv][pool]}') Merge pairs ~~~~~~~~~~~~~~~ In this step, forward and reverse reads are paired in order to create full denoised sequences. :green:`Function:` mergePairs(dadaF, dadaR) :green:`Min overlap:` {snakemake.config[dada2_merge][minOverlap]} :green:`Max mismatch:` {snakemake.config[dada2_merge][maxMismatch]} Length filtering ~~~~~~~~~~~~~~~~~~ Sequences that are much longer or shorter than expected may be the result of non-specific priming. :green:`- Shortest length:` {shorts} :green:`- Longest length:` {longs} {chimeras} **Output files:** :green:`- Representative ASV sequences:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/representative_seq_set.fasta The total number of different ASVs is: {totalAsvs} Assign taxonomy ---------------- Given a set of sequences, assign the taxonomy of each sequence. {assignTaxoStr} The percentage of successfully assigned ASVs is: {prcAssignedAsvs} **Output file:** :green:`- ASV taxonomy assignation:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/representative_seq_set_tax_assignments.txt The previous steps were performed within a Cascabel R script according to the following command: **Command** :commd:`Scripts/asvDada2.R $PWD {snakemake.config[dada2_asv][pool]} {snakemake.config[dada2_asv][cpus]} {snakemake.config[dada2_asv][generateErrPlots]} {snakemake.config[dada2_asv][extra_params]} {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/ {snakemake.config[rm_reads][shorts]} {snakemake.config[rm_reads][longs]} {snakemake.config[rm_reads][offset]} {snakemake.config[dada2_asv][chimeras]} {snakemake.config[dada2_taxonomy][db]} {snakemake.config[dada2_taxonomy][add_sps][db_sps]} {snakemake.config[dada2_taxonomy][add_sps][add]} {snakemake.config[dada2_taxonomy][extra_params]} {snakemake.config[dada2_merge][minOverlap]} {snakemake.config[dada2_merge][maxMismatch]} {snakemake.config[dada2_taxonomy][add_sps][extra_params]}` {dada2Benchmark} Make ASV table --------------- Tabulates the number of times an ASV is found in each sample, and adds the taxonomic predictions for each ASV in the last column. **Command:** :commd:`cat {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/representative_seq_set_tax_assignments.txt | awk 'NR==FNR{{if(NR>1){{tax=$2;for(i=3;i<=NF;i++){{tax=tax";"$i}};h[$1]=tax;}}next;}} {{if(FNR==1){{print $0"\\ttaxonomy"}}else{{print $0"\\t"h[$1]}}' - {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/asv_table.txt > {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/asvTable.txt` **Output file:** :green:`- ASV table:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/asvTable.txt {otuTableBenchmark} Convert ASV table ------------------ Convert from txt to the BIOM table format. :red:`Tool:` [BIOM]_ :red:`Version:` {convertBiomVersion} **Command:** :commd:`biom convert -i {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/asvTable.txt -o {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/asvTable.biom {snakemake.config[biom][tableType]} --table type "OTU table" --to-hdf5 --process-obs-metdata taxonomy` **Output file:** :green:`- Biom format table:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/asvTable.biom {convertOtuBenchmark} Summarize Taxa --------------- Summarize information of the representation of taxonomic groups within each sample. :red:`Tool:` [QIIME]_ - summarize_taxa.py :red:`Version:` {summTaxaVersion} **Command:** :commd:`summarize_taxa.py -i {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/otuTable.biom {snakemake.config[summTaxa][extra_params]} -o {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/summary/` **Output file:** :green:`- Taxonomy summarized counts at different taxonomy levels:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/summary/otuTable_L**N**.txt Where **N** is the taxonomy level. Default configuration produces levels from 2 to 6. {summTaxaBenchmark} Filter ASV table ----------------- Filter ASVs from an ASV table based on their observed counts or identifier. :red:`Tool:` [QIIME]_ - filter_otus_from_otu_table.py :red:`Version:` {filterOTUNoSVersion} :green:`Minimum observation counts:` {snakemake.config[filterOtu][n]} **Command:** :commd:`filter_otus_from_otu_table.py -i {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/asvTable.biom -o {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/asvTable_noSingletons.biom {snakemake.config[filterOtu][extra_params]} -n {snakemake.config[filterOtu][n]}` **Output file:** :green:`- Biom table:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/otuTable_noSingletons.biom {asvNoSingletonsBenchmark} Convert Filtered ASV table --------------------------- Convert the filtered OTU table from the BIOM table format to a human readable format :red:`Tool:` [BIOM]_ :red:`Version:` {convertBiomVersion} **Command:** :commd:`biom convert -i {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_dada2/asvTable_noSingletons.biom -o {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/asvTable_noSingletons.txt {snakemake.config[biom][tableType]} {snakemake.config[biom][headerKey]} {snakemake.config[biom][extra_params]} {snakemake.config[biom][outFormat]}` **Output file:** :green:`- TSV format table:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/asv/taxonomy_dada2/asvTable_noSingletons.txt {filterASVTableBenchmark} Filter representative sequences --------------------------------- Remove sequences according to the filtered OTU biom table. :red:`Tool:` [QIIME]_ - filter_fasta.py :red:`Version:` {filterFastaVersion} **Command:** :commd:`filter_fasta.py -f {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.run}/asv/representative_seq_set.fasta -o {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.run}/asv/taxonomy_dada2/representative_seq_set_noSingletons.fasta {snakemake.config[filterFasta][extra_params]} -b {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.run}/asv/taxonomy_dada2/otuTable_noSingletons.biom` **Output file:** :green:`- Filtered fasta file:` {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.run}/asv/taxonomy_dada2/representative_seq_set_noSingletons.fasta {alignmentReport} {kronaReport} Final counts ------------- {countTxt} .. image:: report_files/sequence_numbers_asv.png .. image:: report_files/sequence_numbers_asv_2.png :red:`Note:` :green:`- Assigned ASVs percentage` is the amount of successfully assigned ASVs. :green:`- No singletons percentage` is the percentage of no singletons ASVs in reference to the complete ASV table. :green:`- Assigned No singletons` is the amount of successfully no singletons assigned ASVs. References ------------ .. [QIIME] QIIME. Caporaso JG, Kuczynski J, Stombaugh J, Bittinger K, Bushman FD, Costello EK, Fierer N, Gonzalez Pena A, Goodrich JK, Gordon JI, Huttley GA, Kelley ST, Knights D, Koenig JE, Ley RE, Lozupone CA, McDonald D, Muegge BD, Pirrung M, Reeder J, Sevinsky JR, Turnbaugh PJ, Walters WA, Widmann J, Yatsunenko T, Zaneveld J, Knight R. 2010. QIIME allows analysis of high-throughput community sequencing data. Nature Methods 7(5): 335-336. .. [Cutadapt] Cutadapt v1.15 .Marcel Martin. Cutadapt removes adapter sequences from high-throughput sequencing reads. EMBnet.Journal, 17(1):10-12, May 2011. http://dx.doi.org/10.14806/ej.17.1.200 .. [vsearch] Rognes T, Flouri T, Nichols B, Quince C, Mahé F. (2016) VSEARCH: a versatile open source tool for metagenomics. PeerJ 4:e2584. doi: 10.7717/peerj.2584 .. [Krona] Ondov BD, Bergman NH, and Phillippy AM. Interactive metagenomic visualization in a Web browser. BMC Bioinformatics. 2011 Sep 30; 12(1):385. .. [BIOM] The Biological Observation Matrix (BIOM) format or: how I learned to stop worrying and love the ome-ome. Daniel McDonald, Jose C. Clemente, Justin Kuczynski, Jai Ram Rideout, Jesse Stombaugh, Doug Wendel, Andreas Wilke, Susan Huse, John Hufnagle, Folker Meyer, Rob Knight, and J. Gregory Caporaso.GigaScience 2012, 1:7. doi:10.1186/2047-217X-1-7 {variable_refs} """, snakemake.output[0], metadata="Author: J. Engelmann & A. Abdala ") |
Python
QIIME2.0
BLAST
VSEARCH
fasttree
Swarm
benchmark-utils
From
line
1
of
Scripts/report_all_asv.py
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 | import subprocess import functools from snakemake.utils import report from benchmark_utils import readBenchmark from benchmark_utils import countTxt from seqsChart import createChart from seqsChart import createChartPrc from benchmark_utils import countFasta from benchmark_utils import make_table ################ #Function to retrive the sample names and put in the report title #@param file with the sample list, it is created during combine_filtered_samples #snakemake.wildcards.project + "/runs/" + snakemake.wildcards.run + "/samples.log" #@return the title with the samples def getSampleList(sampleFile): with open(sampleFile) as sfile: samps ="Amplicon Analysis Report for Libraries: " for l in sfile: samps+= l samps+="\n" for i in range(0,len(samps)): samps+="=" return samps; ######################### #This function reads the file cat_samples.log which have the executed command to #combine all the libraries after cleaning and demultiplexing and before taxonomy #assignation #@param catLogFile file with the command #snakemake.wildcards.project + "/runs/" + snakemake.wildcards.run + "/cat_samples.log" #@return the string ready to be concatenated into the report. def getCombinedSamplesList(catLogFile): with open(catLogFile) as sfile: command =":commd:`" i=0 for l in sfile: if i == 0: command+= l + "`\n\n" i+=1 return command; title = getSampleList(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/samples.log") catCommand = getCombinedSamplesList(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/cat_samples.log") ################################################################################ # Benchmark Section # # This section is to generate a pre-formatted text with the benchmark info for # # All the executed rules. # ################################################################################ combineBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/combine_seqs_fw_rev.benchmark") otuBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu.benchmark") pikRepBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/pick_reps.benchmark") assignTaxaBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/assign_taxa.benchmark") otuTableBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/otuTable.biom.benchmark") convertOtuBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/otuTable.txt.benchmark") summTaxaBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/summary/summarize_taxa.benchmark") otuNoSingletonsBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/otuTable_nosingletons.bio.benchmark") filterBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/representative_seq_set_noSingletons.benchmark") deRepBenchmark="" if (snakemake.config["derep"]["dereplicate"] == "T" and snakemake.config["pickOTU"]["m"] != "usearch") or snakemake.config["pickOTU"]["m"] == "swarm": deRepBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/derep/derep.benchmark") if snakemake.config["alignRep"]["align"] == "T": #align_seqs.py -m {config[alignRep][m]} -i {input} -o {params.outdir} {config[alignRep][extra_params]} alignBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/aligned/align_rep_seqs.benchmark") #"filter_alignment.py -i {input} -o {params.outdir} {config[filterAlignment][extra_params]}" alignFilteredBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/aligned/filtered/align_rep_seqs.benchmark") #"make_phylogeny.py -i {input} -o {output} {config[makeTree][extra_params]}" makePhyloBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/aligned/filtered/representative_seq_set_noSingletons_aligned_pfiltered.benchmark") kronaBenchmark="" if snakemake.config["krona"]["report"].casefold() == "t" or snakemake.config["krona"]["report"].casefold() == "true": kronaBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/krona_report.benchmark") #dada2FilterBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/filter.benchmark") #dada2Benchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/dada2.benchmark") #dada2BiomBenchmark = readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/asv/dada2.biom.benchmark") ################################################################################ # TOOLS VERSION SECTION # ################################################################################ clusterOtuV = subprocess.run([snakemake.config["qiime"]["path"]+'pick_otus.py', '--version'], stdout=subprocess.PIPE) clusterOtuVersion = "**" + clusterOtuV.stdout.decode('utf-8').replace('Version:','').strip() + "**" pickRepV = subprocess.run([snakemake.config["qiime"]["path"]+'pick_rep_set.py', '--version'], stdout=subprocess.PIPE) pickRepVersion = "**" + pickRepV.stdout.decode('utf-8').replace('Version:','').strip() + "**" assignTaxaV = subprocess.run([snakemake.config["qiime"]["path"]+'parallel_assign_taxonomy_'+snakemake.config["assignTaxonomy"]["qiime"]["method"]+'.py', '--version'], stdout=subprocess.PIPE) assignTaxaVersion = "**" + assignTaxaV.stdout.decode('utf-8').replace('Version:','').strip() + "**" makeOTUV = subprocess.run([snakemake.config["qiime"]["path"]+'make_otu_table.py', '--version'], stdout=subprocess.PIPE) makeOTUVersion = "**" + makeOTUV.stdout.decode('utf-8').replace('Version:','').strip() + "**" convertBiomV = subprocess.run([snakemake.config["biom"]["command"], '--version'], stdout=subprocess.PIPE) convertBiomVersion = "**" + convertBiomV.stdout.decode('utf-8').strip() + "**" summTaxaSV = subprocess.run([snakemake.config["qiime"]["path"]+'summarize_taxa.py', '--version'], stdout=subprocess.PIPE) summTaxaVersion = "**" + summTaxaSV.stdout.decode('utf-8').replace('Version:','').strip() + "**" filterOTUNoSV = subprocess.run([snakemake.config["qiime"]["path"]+'filter_otus_from_otu_table.py', '--version'], stdout=subprocess.PIPE) filterOTUNoSVersion = "**" + filterOTUNoSV.stdout.decode('utf-8').replace('Version:','').strip() + "**" filterFastaV = subprocess.run([snakemake.config["qiime"]["path"]+'filter_fasta.py', '--version'], stdout=subprocess.PIPE) filterFastaVersion = "**" + filterFastaV.stdout.decode('utf-8').replace('Version:','').strip() + "**" blastnV = subprocess.run([snakemake.config["assignTaxonomy"]["blast"]["command"], '-version'], stdout=subprocess.PIPE) blastnVersion = "**" + blastnV.stdout.decode('utf-8').split('\n', 1)[0].replace('blastn:','').strip() + "**" vsearchV2 = subprocess.run([snakemake.config["assignTaxonomy"]["vsearch"]["command"], '--version'], stdout=subprocess.PIPE, stderr=subprocess.STDOUT) vsearchVersion_tax = "**" + vsearchV2.stdout.decode('utf-8').split('\n', 1)[0].strip() + "**" if (snakemake.config["derep"]["dereplicate"] == "T" and snakemake.config["pickOTU"]["m"] != "usearch") or snakemake.config["pickOTU"]["m"] == "swarm": vsearchV = subprocess.run([snakemake.config["derep"]["vsearch_cmd"], '--version'], stdout=subprocess.PIPE, stderr=subprocess.STDOUT) vsearchVersion = "**" + vsearchV.stdout.decode('utf-8').split('\n', 1)[0].strip() + "**" if snakemake.config["pickOTU"]["m"] == "swarm": swarmV = subprocess.run(['swarm', '--version'], stdout=subprocess.PIPE, stderr=subprocess.STDOUT) swarmVersion = "**" + vsearchV.stdout.decode('utf-8').split('\n', 1)[0].strip() + "**" if snakemake.config["alignRep"]["align"] == "T": alignFastaVersion="TBD" try: alignFastaV = subprocess.run([snakemake.config["qiime"]["path"]+'align_seqs.py', '--version'], stdout=subprocess.PIPE) if "Version" in alignFastaVersion: alignFastaVersion = "**" + alignFastaV.stdout.decode('utf-8').replace('Version: ','').strip() + "**" except Exception as e: alignFastaVersion = "**Problem retriving the version**" filterAlignmentV = subprocess.run([snakemake.config["qiime"]["path"]+'filter_alignment.py', '--version'], stdout=subprocess.PIPE) filterAlignmentVersion = "**" + filterAlignmentV.stdout.decode('utf-8').replace('Version:','').strip() + "**" makePhyloV = subprocess.run([snakemake.config["qiime"]["path"]+'make_phylogeny.py', '--version'], stdout=subprocess.PIPE) makePhyloVersion = "**" + makePhyloV.stdout.decode('utf-8').replace('Version:','').strip() + "**" ################################################################################ # Compute counts section # ################################################################################ totalReads = "TBD" intTotalReads = 1; try: treads = subprocess.run( ["grep '^>' " + snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/seqs_fw_rev_combined.fasta | wc -l"], stdout=subprocess.PIPE, shell=True) intTotalReads = int(treads.stdout.decode('utf-8').strip()) totalReads = "**" + str(intTotalReads) + "**" except Exception as e: totalReads = "Problem reading outputfile" derep_reads = "TBD" intDerep=1 if (snakemake.config["derep"]["dereplicate"] == "T" and snakemake.config["pickOTU"]["m"] != "usearch") or snakemake.config["pickOTU"]["m"] == "swarm": try: totd = subprocess.run( ["grep \"^>\" " + snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/derep/seqs_fw_rev_combined_derep.fasta" + " | wc -l"], stdout=subprocess.PIPE, shell=True) intDerep = int(totd.stdout.decode('utf-8').strip()) derep_reads = "**" + str(intDerep) + "**" except Exception as e: derep_reads = "**Problem reading outputfile**" intOtus = 1 try: otu_file="" if (snakemake.config["derep"]["dereplicate"] == "T" and snakemake.config["pickOTU"]["m"] != "usearch") or snakemake.config["pickOTU"]["m"] == "swarm" : otu_file = snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/otu/seqs_fw_rev_combined_remapped_otus.txt" else: otu_file = snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/otu/seqs_fw_rev_combined_otus.txt" totus = subprocess.run( ["cat " + otu_file + " | wc -l"], stdout=subprocess.PIPE, shell=True) intOtus = int(totus.stdout.decode('utf-8').strip()) #print("Total OTUS" + str(intOtus)) totalOtus = "**" + str(intOtus) + "**" except Exception as e: totalOtus = "**Problem reading outputfile**" prcAssigned = 0.0 prcNotAssignedOtus="TBD" try: nohit = "'No blast hit|Unassigned'" #if snakemake.config["assignTaxonomy"]["tool"] != "blast": # nohit = "'Unassigned'" aOtus = subprocess.run( ["grep -E "+ nohit + " " + snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/representative_seq_set_tax_assignments.txt | wc -l"], stdout=subprocess.PIPE, shell=True) notAssignedOtus = int(aOtus.stdout.decode('utf-8').strip()) #print("Not assigned OTUS" + str(notAssignedOtus)) assignedOtus = (intOtus - notAssignedOtus) prcAssigned = (assignedOtus/intOtus)*100 prcAssignedOtus = "**" + "{:.2f}".format(prcAssigned) + "%**" except Exception as e: prcAssignedOtus = "**Problem reading outputfile**" intSingletons = 1; try: totS = subprocess.run( ["grep -v \"^#\" " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/otuTable_noSingletons.txt" + " | wc -l"], stdout=subprocess.PIPE, shell=True) intSingletons = int(totS.stdout.decode('utf-8').strip()) #print("Total OTUS" + str(intOtus)) totalSingletons = "**" + str(intSingletons) + "**" except Exception as e: totalSingletons = "**Problem reading outputfile**" nohit = "'No blast hit|Unassigned|None'" #if snakemake.config["assignTaxonomy"]["tool"] != "blast": # nohit = "'Unassigned'" notAssignedSingleOtus = 0 assignedSingleOtus = 0 try: sOtus = subprocess.run( ["grep -E "+ nohit + " " + snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/otuTable_noSingletons.txt | wc -l"], stdout=subprocess.PIPE, shell=True) notAssignedSingleOtus = int(sOtus.stdout.decode('utf-8').strip()) #print("Not assigned OTUS" + str(notAssignedOtus)) assignedSingleOtus = (intSingletons - notAssignedSingleOtus) except Exception as e: totalAssignedSingletons = "**Problem reading outputfile**" #include user description on the report desc = snakemake.config["description"] txtDescription = "" if len(desc) > 0: txtDescription = "\n**User description:** "+desc+"\n" ################################################################################ # Sample distribution chart # ################################################################################ countTxt="Following the read counts: \n\n" fileData = [] headers = [] data =[] headers.append("File description") headers.append("Location") headers.append("#") headers.append("(%)") fileData.append(headers) #combined data.append("Combined clean reads") data.append(snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/seqs_fw_rev_combined.fasta") data.append(str(intTotalReads)) data.append("100%") fileData.append(data) data=[] #derep if (snakemake.config["derep"]["dereplicate"] == "T" and snakemake.config["pickOTU"]["m"] != "usearch") or snakemake.config["pickOTU"]["m"] == "swarm": data.append("Dereplicated reads") data.append(snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/derep/seqs_fw_rev_combined_derep.fasta") data.append(str(intDerep)) data.append("{:.2f}".format(float((intDerep/intTotalReads)*100))+"%") fileData.append(data) data=[] #otus data.append("OTU table") data.append(otu_file) data.append(str(intOtus)) data.append("{:.2f}".format(float((intOtus/intTotalReads)*100))+"%") fileData.append(data) data=[] #Taxonomy data.append("Taxonomy assignation") data.append(snakemake.wildcards.PROJECT+ "/runs/" + snakemake.wildcards.run+ "/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/representative_seq_set_tax_assignments.txt") data.append(str(assignedOtus)) data.append("{:.2f}".format(float((assignedOtus/intOtus)*100))+"%") fileData.append(data) data=[] #otus no singletons data.append("OTU table (no singletons: a > " + str(snakemake.config["filterOtu"]["n"])+")") data.append(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/otuTable_noSingletons.txt") data.append(str(intSingletons)) data.append("{:.2f}".format(float((intSingletons/intOtus)*100))+"%") fileData.append(data) data=[] #Assigned singletons data.append("Assigned no singletons") data.append(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/otuTable_noSingletons.txt") data.append(str(assignedSingleOtus)) try: data.append("{:.2f}".format(float((assignedSingleOtus/intSingletons)*100))+"%") except Exception as e: data.append("Err") print("Error - Assigned no singletons - dividing: "+ str(assignedSingleOtus)+"/"+ str(intSingletons)) fileData.append(data) countTxt += make_table(fileData) ################################################################################ # Generate sequence amounts chart # ################################################################################ #numbers=[intTotalReads]; #labels=["Combined\nreads"]; #prcs=[] #prcs.append("100%") #Now we only create the 1st chart if we dereplicate, otherwise there is no sense to show one single bar sequence_bars="" color_index=0 if (snakemake.config["derep"]["dereplicate"] == "T" and snakemake.config["pickOTU"]["m"] != "usearch") or snakemake.config["pickOTU"]["m"] == "swarm": numbers=[intTotalReads]; labels=["Combined\nreads"]; prcs=[] prcs.append("100%") numbers.append(intDerep) labels.append("Derep.") prcs.append("{:.2f}".format(float((intDerep/intTotalReads)*100))+"%") createChartPrc(numbers, tuple(labels),prcs,snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/report_files/sequence_numbers_all.png",color_index) sequence_bars=".. image:: report_files/sequence_numbers_all.png\n\n" color_index=2 numbers2=[intOtus] labels2=["OTUs"] prcs2=["{:.2f}".format(float((intOtus/intTotalReads)*100))+"%"] numbers2.append(assignedOtus) labels2.append("Assigned\nOTUs") prcs2.append("{:.2f}".format(float((assignedOtus/intOtus)*100))+"%") numbers2.append(intSingletons) labels2.append("No\nSingletons") prcs2.append("{:.2f}".format(float((intSingletons/intOtus)*100))+"%") numbers2.append(assignedSingleOtus) labels2.append("Assigned NO\n singletons") prcs2.append("{:.2f}".format(float((assignedSingleOtus/intSingletons)*100))+"%") createChartPrc(numbers2, tuple(labels2),prcs2,snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/report_files/sequence_numbers_all_2.png",color_index) ############################################################################### # Varaible sections # ################################################################################ variable_refs="" assignTaxoStr = "" if snakemake.config["assignTaxonomy"]["tool"] == "blast": assignTaxoStr =":red:`Tool:` ["+str(snakemake.config["assignTaxonomy"]["tool"])+"]_\n\n" assignTaxoStr += ":red:`Version:` " + blastnVersion + "\n\n" variable_refs+= ".. [blast] Altschul SF, Gish W, Miller W, Myers EW, Lipman DJ. 1990. Basic local alignment search tool. J Mol Biol 215(3):403-410\n\n" ref = "" if len(str(snakemake.config["assignTaxonomy"]["blast"]["blast_db"])) > 1: assignTaxoStr += ":green:`Reference database:` "+ str(snakemake.config["assignTaxonomy"]["blast"]["blast_db"])+"\n\n" ref= "-db " + str(snakemake.config["assignTaxonomy"]["blast"]["blast_db"]) else: assignTaxoStr += ":green:`Reference fasta file:` "+ str(snakemake.config["assignTaxonomy"]["blast"]["fasta_db"])+"\n\n" ref= "-subject "+ str(snakemake.config["assignTaxonomy"]["blast"]["fasta_db"]) assignTaxoStr += ":green:`Taxonomy mapping file:` "+ str(snakemake.config["assignTaxonomy"]["blast"]["mapFile"])+"\n\n" assignTaxoStr += "**Command:**\n\n" assignTaxoStr += ":commd:`"+ str(snakemake.config["assignTaxonomy"]["blast"]["command"] )+" " +ref + "-evalue " + str(snakemake.config["assignTaxonomy"]["blast"]["evalue"]) + "-outfmt '6 qseqid sseqid pident qcovs evalue bitscore' -num_threads " + str(snakemake.config["assignTaxonomy"]["blast"]["jobs"]) + " -max_target_seqs " assignTaxoStr += str(snakemake.config["assignTaxonomy"]["blast"]["max_target_seqs"]) +" -perc_identity "+ str(snakemake.config["assignTaxonomy"]["blast"]["identity"]) + " -out representative_seq_set_tax_blastn.out`\n\n" if snakemake.config["assignTaxonomy"]["blast"]["max_target_seqs"] != 1: assignTaxoStr += "After blast assignation, **results were mapped to their LCA using stampa_merge.py** script\n\n" elif snakemake.config["assignTaxonomy"]["tool"] == "qiime": assignTaxoStr =":red:`Tool:` [QIIME]_\n\n" assignTaxoStr += ":red:`Version:` "+assignTaxaVersion assignTaxoStr += ":green:`Method:` **" + str(snakemake.config["assignTaxonomy"]["qiime"]["method"])+ "**\n\n" assignTaxoStr += "Reference database: " + str(snakemake.config["assignTaxonomy"]["qiime"]["dbFile"])+ "\n\n" assignTaxoStr += "Taxonomy mapping file: " + str(snakemake.config["assignTaxonomy"]["qiime"]["mapFile"])+ "\n\n" assignTaxoStr += "**Command:**\n\n" assignTaxoStr += ":commd:`parallel_assign_taxonomy_" + str(snakemake.config["assignTaxonomy"]["qiime"]["method"])+ ".py -i " + str(snakemake.wildcards.PROJECT)+ "/runs/" + str(snakemake.wildcards.run)+ "/otu/representative_seq_set.fasta --id_to_taxonomy_fp " + str(snakemake.config["assignTaxonomy"]["qiime"]["mapFile"])+ " --reference_seqs_fp " assignTaxoStr += str(snakemake.config["assignTaxonomy"]["qiime"]["dbFile"])+ " --jobs_to_start " + str(snakemake.config["assignTaxonomy"]["qiime"]["jobs"])+ " " + str(snakemake.config["assignTaxonomy"]["qiime"]["extra_params"])+ " " assignTaxoStr += "--output_dir " + str(snakemake.wildcards.PROJECT)+ "/runs/" + str(snakemake.wildcards.run)+ "/otu/taxonomy_" + str(snakemake.config["assignTaxonomy"]["tool"])+ "/`\n\n" elif snakemake.config["assignTaxonomy"]["tool"] == "vsearch": assignTaxoStr =":red:`Tool:` [vsearch]_\n\n" assignTaxoStr += ":red:`Version:` " + vsearchVersion_tax + "\n\n" assignTaxoStr += ":green:`Reference fasta file:` "+ str(snakemake.config["assignTaxonomy"]["vsearch"]["db_file"])+"\n\n" assignTaxoStr += ":green:`Taxonomy mapping file:` "+ str(snakemake.config["assignTaxonomy"]["vsearch"]["mapFile"])+"\n\n" assignTaxoStr += "**Command:**\n\n" assignTaxoStr += ":commd:`"+ str(snakemake.config["assignTaxonomy"]["vsearch"]["command"] )+ "--usearch_global "+ str(snakemake.wildcards.PROJECT)+ "/runs/" + str(snakemake.wildcards.run)+ "/otu/representative_seq_set.fasta --db "+ str(snakemake.config["assignTaxonomy"]["vsearch"]["db_file"]) assignTaxoStr += " --dbmask none --qmask none --rowlen 0 --id "+ str(snakemake.config["assignTaxonomy"]["vsearch"]["identity"])+" --iddef " + str(snakemake.config["assignTaxonomy"]["vsearch"]["identity_definition"])+" --userfields query+id" + str(snakemake.config["assignTaxonomy"]["vsearch"]["identity_definition"])+"+target " assignTaxoStr += " --maxaccepts "+ str(snakemake.config["assignTaxonomy"]["vsearch"]["max_target_seqs"]) + " --threads " + str(snakemake.config["assignTaxonomy"]["vsearch"]["jobs"]) + " "+ str(snakemake.config["assignTaxonomy"]["vsearch"]["extra_params"]) + " --output_no_hits --userout representative_seq_set_tax_vsearch.out`\n\n" if (snakemake.config["assignTaxonomy"]["vsearch"]["max_target_seqs"]) != 1: assignTaxoStr += "After taxonomy assignation with vsearch, top hits with the same sequence identity but different taxonomy were mapped to their last common ancestor (LCA) using the script **stampa_merge.py** from https://github.com/frederic-mahe/stampa.\n\n" #Dereplication report dereplicateReport="" if (snakemake.config["derep"]["dereplicate"] == "T" and snakemake.config["pickOTU"]["m"] != "usearch") or snakemake.config["pickOTU"]["m"] == "swarm": dereplicateReport="Dereplicate reads\n" dereplicateReport+="---------------------\n\n" dereplicateReport+="Clusterize the reads with an identity threshold of 100%.\n\n" dereplicateReport+=":red:`Tool:` [vsearch]_\n\n" dereplicateReport+=":red:`Version:` " + vsearchVersion+"\n\n" dereplicateReport+="**Command:**\n\n" dereplicateReport+=":commd:`"+str(snakemake.config["derep"]["vsearch_cmd"]) +" --derep_fulllength seqs_fw_rev_combined.fasta --output seqs_fw_rev_combined_derep.fasta --uc seqs_fw_rev_combined_derep.uc --strand " + str(snakemake.config["derep"]["strand"]) + " --fasta_width 0 --minuniquesize "+ str(snakemake.config["derep"]["min_abundance"])+"`\n\n" dereplicateReport+="**Output files:**\n\n" dereplicateReport+=":green:`- Dereplicated fasta file:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/derep/seqs_fw_rev_combined_derep.fasta\n\n" dereplicateReport+=":green:`- Cluster file:` "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/derep/seqs_fw_rev_combined_derep.uc\n\n" dereplicateReport+="Total number of dereplicated sequences is: "+str(derep_reads).strip()+"\n\n"+deRepBenchmark+"\n\n" #Cluestering report otuClusteringReport="" otuClusteringReport="Cluster OTUs\n" otuClusteringReport+="---------------------\n\n" otuClusteringReport+="Assigns similar sequences to operational taxonomic units, or OTUs, by clustering sequences based on a user-defined similarity threshold.\n\n" if (snakemake.config["pickOTU"]["m"]== "swarm"): otuClusteringReport+=":red:`Tool:` [swarm]_\n\n" otuClusteringReport+=":red:`Version:` " + swarmVersion+"\n\n" otuClusteringReport+=":green:`Distance:` " + snakemake.config["pickOTU"]["s"]+"\n\n" otuClusteringReport+="**Command:**\n\n" otuClusteringReport+=":commd:`swarm -i "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/swarm.struct -s "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/swarm.stats -d "+snakemake.config["pickOTU"]["s"]+" -z -o "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/seqs_fw_rev_combined_derep_otus.txt " otuClusteringReport+="-u "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/swarms.uc -t "+ snakemake.config["pickOTU"]["cpus"]+" " + snakemake.config["pickOTU"]["extra_params"] + " < "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/derep/seqs_fw_rev_combined_derep.fasta` \n\n" otuClusteringReport+="**Output files:**\n\n" otuClusteringReport+=":green:`- OTU List:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/seqs_fw_rev_combined_derep_otus.txt\n\n" otuClusteringReport+=":green:`- Cluster file (uc):` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/swarms.uc\n\n" otuClusteringReport+=":green:`- Swarm stats:` "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/swarm.stats\n\n" otuClusteringReport+=":green:`- Swarm structure:` "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/swarm.struct\n\n" otuClusteringReport+="The total number of different OTUS (swarms) is: " +totalOtus+"\n\n" else: otuClusteringReport+=":red:`Tool:` ["+snakemake.config["pickOTU"]["m"]+"]_\n\n" otuClusteringReport+=":red:`Version:` " + clusterOtuVersion +"\n\n" otuClusteringReport+=":green:`Method:` " + snakemake.config["pickOTU"]["m"]+"\n\n" otuClusteringReport+=":green:`Identity:` " + snakemake.config["pickOTU"]["s"]+"\n\n" otuClusteringReport+="**Command:**\n\n" otuClusteringReport+=":commd:`pick_otus.py -m "+snakemake.config["pickOTU"]["m"] + "-i "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/seqs_fw_rev_filtered.fasta -o "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/ " otuClusteringReport+="-s "+snakemake.config["pickOTU"]["s"]+" " + snakemake.config["pickOTU"]["extra_params"] + " --threads "+ snakemake.config["pickOTU"]["cpus"] + "` \n\n" otuClusteringReport+="**Output files:**\n\n" otuClusteringReport+=":green:`- OTU List:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/seqs_fw_rev_filtered_otus.txt\n\n" otuClusteringReport+=":green:`- Log file:` "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/seqs_fw_rev_filtered_otus.log\n\n" otuClusteringReport+="The total number of different OTUS is: " +totalOtus+"\n\n" #Remap report remapClusters="" if (snakemake.config["derep"]["dereplicate"] == "T" and snakemake.config["pickOTU"]["m"] != "usearch") or snakemake.config["pickOTU"]["m"] == "swarm": variable_refs+= ".. [ClusterMapper] https://github.com/AlejandroAb/ClusterMapper\n\n" remapClusters="Re-map clusters\n" remapClusters+="---------------------\n\n" remapClusters+="Compute abundance values after dereplication and OTU clustering.\n\n" remapClusters+=":red:`Tool:` Cascabel Java application: [ClusterMapper]_\n\n" remapClusters+="**Command:**\n\n" if(snakemake.config["pickOTU"]["m"] == "swarm"): remapClusters+=":commd:`java -cp Scripts/ClusterMapper/build/classes clustermapper.ClusterMapper uc2otu -uc "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/derep/seqs_fw_rev_combined_derep.uc -otu " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/seqs_fw_rev_combined_derep_otus.txt -o " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/seqs_fw_rev_combined_remapped_otus.txt`\n\n" else: remapClusters+=":commd:`java -cp Scripts/ClusterMapper/build/classes clustermapper.ClusterMapper uc2uc -uc "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/derep/seqs_fw_rev_combined_derep.uc -uc2 " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/swarms.uc --full-uc --relabel -l OTU -lidx 1 -o " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/seqs_fw_rev_combined_remapped_otus.txt`\n\n" remapClusters+="**Output files:**\n\n" remapClusters+=":green:`- Mapped abundances:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/seqs_fw_rev_combined_remapped_otus.txt\n\n" remapClusters+=":green:`- Log file:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/remap.log\n\n" #Alignment report alignmentReport = "" if snakemake.config["alignRep"]["align"] == "T": alignmentReport = "\nAlign representative sequences\n-------------------------------\n\n" alignmentReport+="Align the sequences in a FASTA file to each other or to a template sequence alignment.\n\n" alignmentReport+=":red:`Tool:` [QIIME]_ - align_seqs.py\n\n" alignmentReport+=":red:`Version:` "+alignFastaVersion +"\n\n" alignmentReport+=":green:`Method:` ["+ snakemake.config["alignRep"]["m"] + "]_\n\n" alignmentReport+="**Command:**\n\n" alignmentReport+=":commd:`align_seqs.py -m "+snakemake.config["alignRep"]["m"] +" -i "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/"+snakemake.config["assignTaxonomy"]["tool"]+"/representative_seq_set_noSingletons.fasta "+ snakemake.config["alignRep"]["extra_params"] + " -o " alignmentReport+=snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/aligned/representative_seq_set_noSingletons_aligned.fasta`\n\n" alignmentReport+="**Output files:**\n\n" alignmentReport+=":green:`- Aligned fasta file:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/aligned/representative_seq_set_noSingletons_aligned.fasta\n\n" alignmentReport+=":green:`- Log file:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/aligned/representative_seq_set_noSingletons_log.txt\n\n" alignmentReport+=alignBenchmark+"\n\n" alignmentReport+="Filter alignment\n-----------------\n\n" alignmentReport+="Removes positions which are gaps in every sequence.\n\n" alignmentReport+=":red:`Tool:` [QIIME]_ - filter_alignment.py\n\n" alignmentReport+=":red:`Version:` "+filterAlignmentVersion +"\n\n" alignmentReport+="**Command:**\n\n" alignmentReport+=":commd:`filter_alignment.py -i "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/aligned/representative_seq_set_noSingletons_aligned.fasta " +snakemake.config["filterAlignment"]["extra_params"] alignmentReport+=" -o "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/aligned/filtered/`\n\n" alignmentReport+="**Output file:**\n\n" alignmentReport+=":green:`- Aligned fasta file:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/aligned/representative_seq_set_noSingletons_aligned_pfiltered.fasta\n\n" alignmentReport+=alignFilteredBenchmark+"\n\n" alignmentReport+="Make tree\n-----------\n\n" alignmentReport+="Create phylogenetic tree (newick format).\n\n" alignmentReport+=":red:`Tool:` [QIIME]_ - make_phylogeny.py\n\n" alignmentReport+=":red:`Version:` "+makePhyloVersion +"\n\n" alignmentReport+=":green:`Method:` ["+ snakemake.config["makeTree"]["method"] + "]_\n\n" alignmentReport+="**Command:**\n\n" alignmentReport+=":commd:`make_phylogeny.py -i "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/aligned/representative_seq_set_noSingletons_aligned.fasta -o representative_seq_set_noSingletons_aligned_pfiltered.tre "+ snakemake.config["makeTree"]["extra_params"]+ " -t " + snakemake.config["makeTree"]["method"]+"`\n\n" alignmentReport+="**Output file:**\n\n" alignmentReport+=":green:`- Taxonomy tree:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/aligned/representative_seq_set_noSingletons_aligned.tre\n\n" alignmentReport+=makePhyloBenchmark+"\n\n" #KRONA REPORT kronaReport = "" if snakemake.config["krona"]["report"].casefold() == "t" or snakemake.config["krona"]["report"].casefold() == "true": kronaReport+="Krona report\n----------------\n\n" kronaReport+="Krona allows hierarchical data to be explored with zooming, multi-layered pie charts.\n\n" kronaReport+=":red:`Tool:` [Krona]_\n\n" if snakemake.config["krona"]["otu_table"].casefold() != "singletons": kronaReport+="These charts were created using the OTU table **without** singletons\n\n" else: kronaReport+="These charts were created using the OTU table **including** singletons\n\n" if snakemake.config["krona"]["samples"].strip() == "all": kronaReport+="The report was executed for all the samples.\n\n" else: kronaReport+="The report was executed for the following target samples: "+ snakemake.config["krona"]["samples"].strip() + "\n\n" if "-c" in snakemake.config["krona"]["extra_params"]: kronaReport+="The samples were combined on a single chart\n\n" else: kronaReport+="Each sample is represented on a separated chart (same html report).\n\n" kronaReport+="You can see the report at the following link:\n\n" kronaReport+=":green:`- Krona report:` kreport_\n\n" #kronaReport+=" .. _kreport: ../../runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/krona_report.html\n\n" kronaReport+=" .. _kreport: report_files/krona_report."+snakemake.config["assignTaxonomy"]["tool"]+".html\n\n" kronaReport+="Or access the html file at:\n\n" kronaReport+=":green:`- Krona html file:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/otu/taxonomy_"+snakemake.config["assignTaxonomy"]["tool"]+"/krona_report.html\n\n" kronaReport+=kronaBenchmark+"\n\n" ############################################################################### # REFERENCES # ################################################################################ #CLUSTER OTUS if snakemake.config["pickOTU"]["m"] == "uclust": variable_refs+= ".. [uclust] Edgar RC. 2010. Search and clustering orders of magnitude faster than BLAST. Bioinformatics 26(19):2460-2461.\n\n" elif snakemake.config["pickOTU"]["m"] == "usearch61": variable_refs+= ".. [usearch61] Edgar RC. 2010. Search and clustering orders of magnitude faster than BLAST. Bioinformatics 26(19):2460-2461.\n\n" elif snakemake.config["pickOTU"]["m"] == "mothur": variable_refs+= ".. [mothur] Schloss PD, Wescott SL, Ryabin T, Hall JR, Hartmann M, Hollister EB, Lesniewski RA, Oakley BB, Parks DH, Robinson CJ, Sahl JW, Stres B, Thallinger GG, Van Horn DJ, Weber CF. 2009. Introducing mothur: Open-source, platform-independent, community-supported software for describing and comparing microbial communities. Appl Environ Microbiol 75(23):7537-7541.\n\n" elif snakemake.config["pickOTU"]["m"] == "blast": variable_refs+= ".. [blast] Altschul SF, Gish W, Miller W, Myers EW, Lipman DJ. 1990. Basic local alignment search tool. J Mol Biol 215(3):403-410\n\n" elif snakemake.config["pickOTU"]["m"] == "swarm": variable_refs+= ".. [swarm] Mahé F, Rognes T, Quince C, de Vargas C, Dunthorn M. (2014) Swarm: robust and fast clustering method for amplicon-based studies. PeerJ 2:e593 doi: 10.7717/peerj.593\n\n" elif snakemake.config["pickOTU"]["m"] == "cdhit": variable_refs+= ".. [cdhit] Cd-hit: Limin Fu, Beifang Niu, Zhengwei Zhu, Sitao Wu and Weizhong Li, CD-HIT: accelerated for clustering the next generation sequencing data. Bioinformatics, (2012), 28 (23): 3150-3152. doi: 10.1093/bioinformatics/bts565.\n\n" #ALIGNMENT if snakemake.config["alignRep"]["m"] == "pynast": variable_refs+= ".. [pynast] Caporaso JG, Bittinger K, Bushman FD, DeSantis TZ, Andersen GL, Knight R. 2010. PyNAST: a flexible tool for aligning sequences to a template alignment. Bioinformatics 26:266-267.\n\n" elif snakemake.config["alignRep"]["m"] == "infernal": variable_refs+= ".. [infernal] Nawrocki EP, Kolbe DL, Eddy SR. 2009. Infernal 1.0: Inference of RNA alignments. Bioinformatics 25:1335-1337.\n\n" if snakemake.config["makeTree"]["method"] == "fasttree": variable_refs+= ".. [fasttree] Price MN, Dehal PS, Arkin AP. 2010. FastTree 2-Approximately Maximum-Likelihood Trees for Large Alignments. Plos One 5(3).\n\n" elif snakemake.config["makeTree"]["method"] == "raxml": variable_refs+= "..[raxml] Stamatakis A. 2006. RAxML-VI-HPC: Maximum Likelihood-based Phylogenetic Analyses with Thousands of Taxa and Mixed Models. Bioinformatics 22(21):2688-2690.\n\n" elif snakemake.config["makeTree"]["method"] == "clearcut": variable_refs+= "..[clearcut] Evans J, Sheneman L, Foster JA. 2006. Relaxed Neighbor-Joining: A Fast Distance-Based Phylogenetic Tree Construction Method. J Mol Evol 62:785-792.\n\n" elif snakemake.config["makeTree"]["method"] == "clustalw": variable_refs+= "..[clustalw] Larkin MA, Blackshields G, Brown NP, Chenna R, McGettigan PA, McWilliam H, Valentin F, Wallace IM, Wilm A, Lopez R, Thompson JD, Gibson TJ, Higgins DG. 2007. Clustal W and Clustal X version 2.0. Bioinformatics 23:2947-2948.\n\n" report(""" {title} .. role:: commd .. role:: red .. role:: green **CASCABEL** is designed to run amplicon sequence analysis across single or multiple read libraries. This report consists of the OTU creation and taxonomic assignment for all the combined accepted reads of given samples or libraries, if multiple. {txtDescription} Combine Reads --------------- Merge all the reads of the individual libraries into one single file. **Command:** {catCommand} **Output file:** :green:`- Merged reads:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/seqs_fw_rev_filtered.fasta The total number of reads is: {totalReads} {combineBenchmark} {dereplicateReport} {otuClusteringReport} {remapClusters} {otuBenchmark} Pick representatives ----------------------- Pick a single representative sequence for each OTU. :red:`Tool:` [QIIME]_ - pick_rep_set.py :red:`Version:` {pickRepVersion} :green:`Method:` {snakemake.config[pickRep][m]} **Command:** :commd:`pick_rep_set.py -m {snakemake.config[pickRep][m]} -i {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/seqs_fw_rev_filtered_otus.txt -f {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.run}/seqs_fw_rev_filtered.fasta -o {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.run}/otu/representative_seq_set.fasta {snakemake.config[pickRep][extra_params]} --log_fp {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.run}/otu/representative_seq_set.log` **Output file:** :green:`- Fasta file with representative sequences:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/representative_seq_set.fasta {pikRepBenchmark} Assign taxonomy ---------------- Given a set of sequences, assign the taxonomy of each sequence. {assignTaxoStr} The percentage of successfully assigned OTUs is: {prcAssignedOtus} **Output file:** :green:`- OTU taxonomy assignation:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/representative_seq_set_tax_assignments.txt {assignTaxaBenchmark} Make OTU table --------------- Tabulates the number of times an OTU is found in each sample, and adds the taxonomic predictions for each OTU in the last column. :red:`Tool:` [QIIME]_ - make_otu_table.py :red:`Version:` {makeOTUVersion} **Command:** :commd:`make_otu_table.py -i {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/seqs_fw_rev_filtered_otus.txt -t {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/representative_seq_set_tax_assignments.txt {snakemake.config[makeOtu][extra_params]} -o {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/otuTable.biom` **Output file:** :green:`- Biom format table:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/otuTable.biom {otuTableBenchmark} Convert OTU table ------------------ Convert from the BIOM table format to a human readable format. :red:`Tool:` [BIOM]_ :red:`Version:` {convertBiomVersion} **Command:** :commd:`biom convert -i {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/otuTable.biom -o {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/otuTable.txt {snakemake.config[biom][tableType]} {snakemake.config[biom][headerKey]} {snakemake.config[biom][extra_params]} {snakemake.config[biom][outFormat]}` **Output file:** :green:`- TSV format table:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/otuTable.txt {convertOtuBenchmark} Summarize Taxa --------------- Summarize information of the representation of taxonomic groups within each sample. :red:`Tool:` [QIIME]_ - summarize_taxa.py :red:`Version:` {summTaxaVersion} **Command:** :commd:`summarize_taxa.py -i {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/otuTable.biom {snakemake.config[summTaxa][extra_params]} -o {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/summary/` **Output file:** :green:`- Taxonomy summarized counts at different taxonomy levels:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/summary/otuTable_L**N**.txt Where **N** is the taxonomy level. Default configuration produces levels from 2 to 6. {summTaxaBenchmark} Filter OTU table ----------------- Filter OTUs from an OTU table based on their observed counts or identifier. :red:`Tool:` [QIIME]_ - filter_otus_from_otu_table.py :red:`Version:` {filterOTUNoSVersion} :green:`Minimum observation counts:` {snakemake.config[filterOtu][n]} **Command:** :commd:`filter_otus_from_otu_table.py -i {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/otuTable.biom -o {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/otuTable_noSingletons.biom {snakemake.config[filterOtu][extra_params]} -n {snakemake.config[filterOtu][n]}` **Output file:** :green:`- Biom table:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/otuTable_noSingletons.biom {otuNoSingletonsBenchmark} Convert Filtered OTU table --------------------------- Convert the filtered OTU table from the BIOM table format to a human readable format :red:`Tool:` [BIOM]_ :red:`Version:` {convertBiomVersion} **Command:** :commd:`biom convert -i {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/otuTable_noSingletons.biom -o {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/otuTable_noSingletons.txt {snakemake.config[biom][tableType]} {snakemake.config[biom][headerKey]} {snakemake.config[biom][extra_params]} {snakemake.config[biom][outFormat]}` **Output file:** :green:`- TSV format table:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/otuTable_noSingletons.txt {otuNoSingletonsBenchmark} Filter representative sequences --------------------------------- Remove sequences according to the filtered OTU biom table. :red:`Tool:` [QIIME]_ - filter_fasta.py :red:`Version:` {filterFastaVersion} **Command:** :commd:`filter_fasta.py -f {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.run}/otu/representative_seq_set.fasta -o {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/representative_seq_set_noSingletons.fasta {snakemake.config[filterFasta][extra_params]} -b {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.run}/otu/otuTable_noSingletons.biom` **Output file:** :green:`- Filtered fasta file:` {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.run}/otu/taxonomy_{snakemake.config[assignTaxonomy][tool]}/representative_seq_set_noSingletons.fasta {filterBenchmark} {alignmentReport} {kronaReport} Final counts ------------- {countTxt} {sequence_bars} .. image:: report_files/sequence_numbers_all_2.png :red:`Note:` :green:`- Assigned OTUs percentage` is the amount of successfully assigned OTUs. :green:`- No singletons percentage` is the percentage of no singletons OTUs in reference to the complete OTU table. :green:`- Assigned No singletons` is the amount of successfully no singletons assigned OTUs. References ------------ .. [QIIME] QIIME. Caporaso JG, Kuczynski J, Stombaugh J, Bittinger K, Bushman FD, Costello EK, Fierer N, Gonzalez Pena A, Goodrich JK, Gordon JI, Huttley GA, Kelley ST, Knights D, Koenig JE, Ley RE, Lozupone CA, McDonald D, Muegge BD, Pirrung M, Reeder J, Sevinsky JR, Turnbaugh PJ, Walters WA, Widmann J, Yatsunenko T, Zaneveld J, Knight R. 2010. QIIME allows analysis of high-throughput community sequencing data. Nature Methods 7(5): 335-336. .. [Cutadapt] Cutadapt v1.15 .Marcel Martin. Cutadapt removes adapter sequences from high-throughput sequencing reads. EMBnet.Journal, 17(1):10-12, May 2011. http://dx.doi.org/10.14806/ej.17.1.200 .. [vsearch] Rognes T, Flouri T, Nichols B, Quince C, Mahé F. (2016) VSEARCH: a versatile open source tool for metagenomics. PeerJ 4:e2584. doi: 10.7717/peerj.2584 .. [Krona] Ondov BD, Bergman NH, and Phillippy AM. Interactive metagenomic visualization in a Web browser. BMC Bioinformatics. 2011 Sep 30; 12(1):385. .. [BIOM] The Biological Observation Matrix (BIOM) format or: how I learned to stop worrying and love the ome-ome. Daniel McDonald, Jose C. Clemente, Justin Kuczynski, Jai Ram Rideout, Jesse Stombaugh, Doug Wendel, Andreas Wilke, Susan Huse, John Hufnagle, Folker Meyer, Rob Knight, and J. Gregory Caporaso.GigaScience 2012, 1:7. doi:10.1186/2047-217X-1-7 {variable_refs} """, snakemake.output[0], metadata="Author: J. Engelmann & A. Abdala ") |
Python
QIIME2.0
BLAST
VSEARCH
mothur
fasttree
Swarm
benchmark-utils
From
line
1
of
Scripts/report_all_v2.py
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 | import subprocess from snakemake.utils import report import benchmark_utils from benchmark_utils import countTxt from benchmark_utils import readBenchmark from benchmark_utils import countFasta from benchmark_utils import countFastaGZ from benchmark_utils import readSampleDist from benchmark_utils import make_table from countData import parseCounts from seqsChart import createChart #Parse the total number of counts #countTxt = parseCounts(snakemake.input.counts) ################################################################################ # TOOLS VERSION SECTION # ################################################################################ #--fastq fqv = subprocess.run([snakemake.config["fastQC"]["command"], '--version'], stdout=subprocess.PIPE) fqVersion = "**" + fqv.stdout.decode('utf-8').strip() + "**" if snakemake.config["demultiplexing"]["demultiplex"] != "F": #--qiime extract_barcodes ebv = subprocess.run([snakemake.config["qiime"]["path"]+'extract_barcodes.py', '--version'], stdout=subprocess.PIPE) ebVersion = ebv.stdout.decode('utf-8') ebVersion = "**" + ebVersion[ebVersion.find(":")+1:].strip() + "**" #--qiime split_libraries spVersion = "**TBD**" spv = subprocess.run([snakemake.config["qiime"]["path"]+'split_libraries_fastq.py', '--version'], stdout=subprocess.PIPE) spVersion = spv.stdout.decode('utf-8') if "Version" in spVersion: spVersion = "**" + spVersion[spVersion.find(":")+1:].strip() + "**" else: ebVersion = "**NA**" SPvERSION = "**NA**" vsearchVersion = "**TBD**" vsearchV = subprocess.run(['vsearch', '--version'], stdout=subprocess.PIPE, stderr=subprocess.STDOUT) vsearchVersion = "**" + vsearchV.stdout.decode('utf-8').split('\n', 1)[0].strip() + "**" #--qiime identify_chimeric_seqs icVersion = "**TBD**" icv = subprocess.run([snakemake.config["qiime"]["path"]+'identify_chimeric_seqs.py', '--version'], stdout=subprocess.PIPE) icVersion = icv.stdout.decode('utf-8') if "Version" in icVersion: icVersion = "**" + icVersion[icVersion.find(":")+1:].strip() + "**" #--pear try: pearv = subprocess.run( [snakemake.config["pear"]["command"]+" -h | grep 'PEAR v'"], stdout=subprocess.PIPE, shell=True) pearversion = "**" + pearv.stdout.decode('utf-8').strip() + "**" except Exception as e: pearversion = "Problem reading version" #--cutadapt cutVersion = "**TBD**" if snakemake.config["primers"]["remove"].casefold() == "metadata" or snakemake.config["primers"]["remove"].casefold() == "cfg" or snakemake.config["primers"]["remove"].lower() != "f": cutv = subprocess.run(['cutadapt', '--version'], stdout=subprocess.PIPE) cutVersion = "**cutadapt v" + cutv.stdout.decode('utf-8').strip() + "**" #cutVersion = "cutadapt v TBD" ################################################################################ # Chimera check # ################################################################################ removeChimeras = False if snakemake.config["chimera"]["search"] == "T": ################################################################################ # Read log file from remove_chimera.py # # After search for chimera, user have the option to remove them or not. If the # # user decides to remove the chimera, the executed command is stored on the log# # file, otherwise it stores a message indicating the user decision. # ################################################################################ chimera_log = "" try: with open(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/chimera/chimera.log") as chimlog: for line in chimlog: chimera_log += line chimlog.close() except FileNotFoundError: chiemra_log = "No Log for identify_chimeric_seqs.py" if "The chimeric sequences were removed" in chimera_log: removeChimeras = True ################################################################################ # Benchmark Section # # This section is to generate a pre-formatted text with the benchmark info for # # All the executed rules. # ################################################################################ fqBench = readBenchmark(snakemake.wildcards.PROJECT+"/samples/"+snakemake.wildcards.sample+"/qc/fq.benchmark") pearBench =readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/peared/pear.benchmark") if snakemake.config["demultiplexing"]["demultiplex"] != "F": barBench =readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/barcodes.benchmark") splitLibsBench =readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/splitLibs.benchmark") #splitLibsRCBench =readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibsRC/splitLibs.benchmark") # combineBench =readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/combine_seqs_fw_rev.benchmark") else: combineBench=pearBench #THIS IS ONLY FOR TESTING REMOVE!!! rmShorLongBench =readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/filter.benchmark") demultiplexFQBench="" if snakemake.config["demultiplexing"]["demultiplex"] == "T" and snakemake.config["demultiplexing"]["create_fastq_files"] == "T": demultiplexFQBench =readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/demultiplex_fq.benchmark") ################################################################################ # Compute Counts # ################################################################################ if snakemake.config["gzip_input"] == "F": rawCounts = countFasta(snakemake.wildcards.PROJECT+"/samples/"+snakemake.wildcards.sample+"/rawdata/fw.fastq", True); else: rawCounts = countFastaGZ(snakemake.wildcards.PROJECT+"/samples/"+snakemake.wildcards.sample+"/rawdata/fw.fastq.gz", True); #rawCountsStr= '{0:g}'.format(float(rawCounts)) rawCountsStr= str(int(rawCounts)) #-peared pearedCounts = 0 if snakemake.config["UNPAIRED_DATA_PIPELINE"] != "T": pearedCounts = countFasta(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/peared/seqs.assembled.fastq", True); else: pearedCounts = countFasta(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/peared/seqs.assembled.UNPAIRED.fastq", True); #pearedCountsStr='{0:g}'.format(float(pearedCounts)) pearedCountsStr=str(int(pearedCounts)) prcPeared = "{:.2f}".format(float((pearedCounts/rawCounts)*100)) #-dumultiplex if snakemake.config["demultiplexing"]["demultiplex"] != "F": #starting to test this and snakemake.config["demultiplexing"]["bc_mismatch"]>0: #in the past we had two files fw and reverse nos everything is on one file #fwAssignedCounts = countFasta(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/seqs.assigned.fna", False) #barcodes.fastq_corrected_toRC #rvAssignedCounts = countFasta(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibsRC/seqs.assigned.fna", False) #prcFwAssigned = "{:.2f}".format(float((fwAssignedCounts/pearedCounts)*100)) #prcRvAssigned = "{:.2f}".format(float((rvAssignedCounts/pearedCounts)*100)) #totalAssigned = fwAssignedCounts + rvAssignedCounts #prcPearedAssigned = "{:.2f}".format(float((totalAssigned/pearedCounts)*100)) #prcRawAssigned = "{:.2f}".format(float((totalAssigned/rawCounts)*100)) #New implementation totalAssigned = countFasta(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/seqs.assigned.fna", False) rvAssignedCounts = countTxt(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/barcodes.fastq_corrected_toRC") fwAssignedCounts = totalAssigned - rvAssignedCounts prcFwAssigned = "{:.2f}".format(float((fwAssignedCounts/pearedCounts)*100)) prcRvAssigned = "{:.2f}".format(float((rvAssignedCounts/pearedCounts)*100)) prcPearedAssigned = "{:.2f}".format(float((totalAssigned/pearedCounts)*100)) prcRawAssigned = "{:.2f}".format(float((totalAssigned/rawCounts)*100)) else: totalAssigned = pearedCounts prcPearedAssigned = "{:.2f}".format(float((totalAssigned/pearedCounts)*100)) prcRawAssigned = "{:.2f}".format(float((totalAssigned/rawCounts)*100)) #--cutadapt cutSequences = False if snakemake.config["primers"]["remove"].casefold() == "metadata" or snakemake.config["primers"]["remove"].casefold() == "cfg": sequenceNoAdapters = countFasta(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted_no_adapters.fna", False) if (totalAssigned - sequenceNoAdapters) > 0: cutSequences = True prcCut = "{:.2f}".format(float((sequenceNoAdapters/totalAssigned)*100)) prcCutRaw = "{:.2f}".format(float((sequenceNoAdapters/rawCounts)*100)) if removeChimeras: sequenceNoChimeras = countFasta(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_filtered_nc.fasta", False) prcChim = "{:.2f}".format(float((sequenceNoChimeras/totalAssigned)*100)) prcChimRaw = "{:.2f}".format(float((sequenceNoChimeras/rawCounts)*100)) if cutSequences: prcChimCut = "{:.2f}".format(float((sequenceNoChimeras/sequenceNoAdapters)*100)) #out="{PROJECT}/runs/{run}/{sample}_data/" trimmedCounts = countFasta(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_filtered.fasta", False) prcTrimmedSplit ="{:.2f}".format(float((trimmedCounts/totalAssigned)*100)) prcTrimmedRaw= "{:.2f}".format(float((trimmedCounts/rawCounts)*100)) if cutSequences: prcTrimmedCut="{:.2f}".format(float((trimmedCounts/sequenceNoAdapters)*100)) #if removeChimeras: # prcTrimmedChimera="{:.2f}".format(float((trimmedCounts/sequenceNoChimeras)*100)) try: samplesLib = subprocess.run( ["cat " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_filtered.dist.txt | wc -l"], stdout=subprocess.PIPE, shell=True) samplesLibInt = int(samplesLib.stdout.decode('utf-8').strip()) except Exception as e: totalReads = "Problem reading outputfile" ################################################################################ # Generate sequence amounts chart # ################################################################################ numbers=[rawCounts,pearedCounts]; labels=["Raw", "Assembled"]; if snakemake.config["demultiplexing"]["demultiplex"] == "T": numbers.append(totalAssigned) labels.append("Demultiplexed") if snakemake.config["primers"]["remove"].casefold() == "metadata" or snakemake.config["primers"]["remove"].casefold() == "cfg": numbers.append(sequenceNoAdapters) labels.append("Cutadapt") numbers.append(trimmedCounts) labels.append("Length filtering") if snakemake.config["chimera"]["search"] == "T" and removeChimeras: numbers.append(sequenceNoChimeras) labels.append("No Chimera") createChart(numbers, tuple(labels),snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/report_files/sequence_numbers."+snakemake.wildcards.sample+".png") ################################################################################ # Chimera check # ################################################################################ variable_refs="" if snakemake.config["chimera"]["search"] == "T" and snakemake.config["chimera"]["method"] == "usearch61": variable_refs+= ".. [usearch61] Edgar RC. 2010. Search and clustering orders of magnitude faster than BLAST. Bioinformatics 26(19):2460-2461.\n\n" else: variable_refs+= ".. [uchime] Edgar RC, Haas BJ, Clemente JC, Quince C, Knight R (2011) UCHIME improves sensitivity and speed of chimera detection. Bioinformatics, 27 (16): 2194-2200. doi:10.1093/bioinformatics/btr381. \n\n" quimeraStr = "" if snakemake.config["chimera"]["search"] == "T": quimeraStr="Identify Chimera\n-------------------\n\n" quimeraStr+="Identify possible chimeric sequences (sequences generated due to the PCR amplification of multiple templates or parent sequences).\n\n" if snakemake.config["chimera"]["method"] == "usearch61": quimeraStr += ":red:`Tool:` [QIIME]_ - identify_chimeric_seqs.py\n\n" quimeraStr += ":red:`Version:` "+ icVersion +"\n\n" quimeraStr += ":red:`Method:` [usearch61]_ \n\n" else: quimeraStr += ":red:`Tool:` [Vsearch]_ - vsearch\n\n" quimeraStr += ":red:`Version:` "+ vsearchVersion +"\n\n" quimeraStr += ":red:`Method:` "+ str(snakemake.config["chimera"]["method"]) +" - uses [uchime]_ \n\n" quimeraStr += "**Command:**\n\n" if snakemake.config["chimera"]["method"] == "usearch61": quimeraStr+=":commd:`identify_chimeric_seqs.py -m "+ str(snakemake.config["chimera"]["method"])+" -i "+ str(snakemake.wildcards.PROJECT)+"/runs/"+str(snakemake.wildcards.run)+"/"+str(snakemake.wildcards.sample)+"_data/seqs_fw_rev_accepted.fna "+str(snakemake.config["chimera"]["extra_params"]) quimeraStr+=" -o "+ str(snakemake.wildcards.PROJECT)+"/runs/"+str(snakemake.wildcards.run)+"/"+str(snakemake.wildcards.sample)+"_data/chimera/` \n\n" else: quimeraStr+=":commd:`vsearch --"+ str(snakemake.config["chimera"]["method"])+" "+ str(snakemake.wildcards.PROJECT)+"/runs/"+str(snakemake.wildcards.run)+"/"+str(snakemake.wildcards.sample)+"_data/seqs_fw_rev_accepted.fna --threads "+ str(snakemake.config["chimera"]["threads"]) +" " +str(snakemake.config["chimera"]["extra_params"]) quimeraStr+=" --uchimeout "+ str(snakemake.wildcards.PROJECT)+"/runs/"+str(snakemake.wildcards.run)+"/"+str(snakemake.wildcards.sample)+"_data/chimera/chimeras.summary.txt` \n\n" quimeraStr+="**Output files:**\n\n" if snakemake.config["chimera"]["method"] == "usearch61": quimeraStr+=":green:`- File with the possible chimeric sequences:` "+str(snakemake.wildcards.PROJECT)+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/chimera/chimeras.txt\n\n" else: quimeraStr+=":green:`- File with the possible chimeric sequences:` "+str(snakemake.wildcards.PROJECT)+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/chimera/chimeras.summary.txt\n\n" identifyChimeraBench=readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/chimera/chimera.benchmark") quimeraStr+=identifyChimeraBench quimeraStr+=chimera_log if removeChimeras: quimeraStr+=":red:`Reads after remove chimeric sequences:` "+ str(sequenceNoChimeras)+"\n\n" quimeraStr+=":red:`Percentage of reads vs raw reads:` "+ str(prcChimRaw) + "%\n\n" quimeraStr+=":red:`Percentage of reads vs demultiplexed reads:` "+ str(prcChim) + "%\n\n" if cutSequences: quimeraStr+=":red:`Percentage of reads vs cutadapt:` "+ str(prcChimRaw) + "%\n\n" ################################################################################ # Peared FastQC # ################################################################################ fastQCPearStr = "" if snakemake.config["fastQCPear"] == "T": fastQCPearStr = "Peared FastQC Analysis\n------------------------\n\n" # title fastQCPearStr += "Check the quality of the reads after assembly.\n\n" fastQCPearStr += ":red:`Tool:` [FastQC]_\n\n" fastQCPearStr += ":red:`Version:` "+ fqVersion +"\n\n" fastQCPearStr += "**Command:**\n\n" fastQCPearStr += ":commd:`fastqc "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/peared/seqs.assembled.fastq --extract -o "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/peared/qc`\n\n" fastQCPearStr += "**Output files:**\n\n:green:`- FastQC report:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/peared/qc/seqs.assembled_fastqc.html FQ_Report_ \n\n" fastQCPearStr += ".. _FQ_Report: peared/qc/seqs.assembled_fastqc.html \n\n" fastQCPearStrBench =readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/peared/qc/fq.benchmark") fastQCPearStr += fastQCPearStrBench ################################################################################ # Extract Barcode # ################################################################################ extractBCStr = "" if snakemake.config["demultiplexing"]["demultiplex"] != "F": extractBCStr ="Extract barcodes\n-----------------\n\n" extractBCStr +="Extract the barcodes used to identify individual samples.\n\n" extractBCStr +=":red:`Tool:` [QIIME]_ - extract_barcodes.py\n\n" extractBCStr +=":red:`Version:` "+ebVersion+"\n\n" extractBCStr +="**Command:**\n\n" extractBCStr +=":commd:`extract_barcodes.py -f "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/peared/seqs.assembled.fastq -c "+str(snakemake.config["ext_bc"]["c"])+ " " + str(snakemake.config["ext_bc"]["bc_length"])+ " " + snakemake.config["ext_bc"]["extra_params"] + " -o "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/`\n\n" extractBCStr +="**Output files:**\n\n" extractBCStr +=":green:`- Fastq file with barcodes:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/barcodes.fastq\n\n" extractBCStr +=":green:`- Fastq file with the reads:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/reads.fastq\n\n" extractBCStr +=barBench ################################################################################ # CORRECT Barcodes # ################################################################################ correctBCStr = "" bcFile="barcodes.fastq" if snakemake.config["demultiplexing"]["demultiplex"] != "F": # and snakemake.config["demultiplexing"]["bc_mismatch"]: correctBCStr = "Correct Barcodes\n--------------------\n" correctBCStr += "Try to correct the barcode from unassigned reads and place reads in correct orientetion.\n\n" correctBCStr += "Maximum number of mismatches **" + str(snakemake.config["demultiplexing"]["bc_mismatch"]) + "**.\n\n" correctBCStr +=":red:`Tool:` Cascabel Java application\n\n" correctBCStr +="**Command:**\n\n" correctBCStr += ":commd:`java -jar Scripts/BarcodeCorrector.jar -b "+snakemake.wildcards.PROJECT+"/metadata/sampleList_mergedBarcodes_"+snakemake.wildcards.sample+".txt -fb "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/barcodes.fastq -fr "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/reads.fastq -m " + str(snakemake.config["demultiplexing"]["bc_mismatch"]) + " -o " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/barcodes.fastq_corrected -or " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/reads.fastq_corrected -rc -x " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/sample_matrix.txt > " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/demux.log`\n\n" correctBCStr += "**Output files:**\n\n:green:`- Barcode corrected file:` "+snakemake.wildcards.PROJECT+ "/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/barcodes.fastq_corrected\n\n" correctBCStr += ":green:`- Reads corrected file:` "+snakemake.wildcards.PROJECT+ "/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/reads.fastq_corrected\n\n" correctBCStr += ":green:`- Error correction summary:` "+snakemake.wildcards.PROJECT+ "/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/demux.log\n\n" correctBarBench =readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/barcodes_corrected.benchmark") correctBCStr += correctBarBench bcFile="barcodes.fastq_corrected" splitStr = "" if snakemake.config["demultiplexing"]["demultiplex"] != "F": splitStr+="Demultiplexing\n" splitStr+="----------------\n" splitStr+="For library splitting, also known as demultiplexing, Cascabel performs several steps to assign fragments in the original as well as reverse orientation to the correct sample.\n\n" splitStr+="Split samples from Fastq file\n" splitStr+="~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n" splitStr+=":red:`Tool:` [QIIME]_ - split_libraries_fastq.py\n\n" splitStr+=":red:`version:` "+ spVersion+"\n\n" splitStr+="**Command:**\n\n" splitStr+=":commd:`split_libraries_fastq.py -m "+snakemake.wildcards.PROJECT+"/metadata/sampleList_mergedBarcodes_"+snakemake.wildcards.sample+".txt -i "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/reads.fastq -o "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs -b "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/"+bcFile+" -q "+str(snakemake.config["split"]["q"])+" -r "+str(snakemake.config["split"]["r"])+" --retain_unassigned_reads "+str(snakemake.config["split"]["extra_params"])+" --barcode_type "+str(snakemake.config["split"]["barcode_type"])+"`\n\n" splitStr+=splitLibsBench splitStr+="Retain assigned reads\n" splitStr+="~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n" splitStr+="**Command:**\n\n" splitStr+=":commd:`cat "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/seqs.fna | grep -P -A1 \"(?!>Unass)^>\" | sed '/^--$/d' > "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/seqs.assigned.fna`\n\n" splitStr+="Create file with only unassigned reads\n" splitStr+="~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n" splitStr+="**Command:**\n\n" splitStr+=":commd:`cat "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/seqs.fna | grep \"^>Unassigned\" | sed 's/>Unassigned_[0-9]* /@/g' | sed 's/ .*//' | grep -F -w -A3 -f - "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/peared/seqs.assembled.fastq | sed '/^--$/d' >"+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/unassigned.fastq`\n\n" # splitStr+="Reverse complement unassigned reads\n" # splitStr+="~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n" # splitStr+=":red:`Tool:` [Vsearch]_\n\n" # splitStr+=":red:`version:` "+vsearchVersion+"\n\n" # splitStr+="**Command:**\n\n" # splitStr+=":commd:`vsearch --fastx_revcomp "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/unassigned.fastq --fastqout "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/unassigned.reversed.fastq`\n\n" # splitStr+="Barcode extraction for reverse complemented, unassigned reads\n" # splitStr+="~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n" # splitStr +=":red:`Tool:` [QIIME]_ - extract_barcodes.py\n\n" # splitStr +=":red:`Version:` "+ebVersion+"\n\n" # splitStr+="**Command:**\n\n" # splitStr +=":commd:`extract_barcodes.py -f "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/unassigned.reversed.fastq -c "+str(snakemake.config["ext_bc"]["c"])+" "+str(snakemake.config["ext_bc"]["bc_length"])+" "+snakemake.config["ext_bc"]["extra_params"]+" -o "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes_unassigned/`\n\n" # if snakemake.config["bc_mismatch"]: # splitStr += "Correct reverse complemented barcodes \n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" # splitStr += "Maximum number of mismatches **" + str(snakemake.config["bc_mismatch"]) + "**.\n\n" # splitStr +=":red:`Tool:` Cascabel Java application\n\n" # splitStr +="**Command:**\n\n" # splitStr += ":commd:`java -cp Scripts/BarcodeCorrector/build/classes/ barcodecorrector.BarcodeCorrector -b "+snakemake.wildcards.PROJECT+"/metadata/sampleList_mergedBarcodes_"+snakemake.wildcards.sample+".txt -f "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes_unassigned/barcodes.fastq_corrected -m " + str(snakemake.config["bc_mismatch"]) + "`\n\n" # splitStr += "**Output file:**\n\n:green:`- Barcode corrected file:` "+snakemake.wildcards.PROJECT+ "/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes/barcodes.fastq_corrected\n\n" # splitStrBench =readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes_unassigned/barcodes_corrected.benchmark") # splitStr += splitStrBench+"\n\n" # splitStr +="Split reverse complemented reads\n" # splitStr+="~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n\n" # splitStr +=":red:`Tool:` [QIIME]_ - extract_barcodes.py\n\n" # splitStr +=":red:`Version:` "+ebVersion+"\n\n" # splitStr+="**Command:**\n\n" # splitStr +=":commd:`split_libraries_fastq.py -m "+snakemake.wildcards.PROJECT+"/metadata/sampleList_mergedBarcodes_"+snakemake.wildcards.sample+".txt -i "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/barcodes_unassigned/reads.fastq -o "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibsRC -b "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+str(snakemake.wildcards.sample)+"_data/barcodes_unassigned/"+bcFile+" -q "+str(snakemake.config["split"]["q"])+" -r "+str(snakemake.config["split"]["r"])+" "+str(snakemake.config["split"]["extra_params"])+" --barcode_type "+str(snakemake.config["split"]["barcode_type"])+"`\n\n" # splitStr +=splitLibsBench+"\n\n" splitStr +="**Output files:**\n\n" # # splitStr +=":green:`- FW reads fasta file with new header:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/seqs.assigned.fna\n\n" splitStr +=":green:`- Text histogram with the length of the fw reads:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/histograms.txt\n\n" splitStr +=":green:`- Log file for the fw reads:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/split_library_log.txt\n\n" # # splitStr +=":green:`- RV reads fasta file with new header:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibsRC/seqs.assigned.fna\n\n" # splitStr +=":green:`- Text histogram with the length of the rv reads:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibsRC/histograms.txt\n\n" # splitStr +=":green:`- Log file for the rv reads:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibsRC/split_library_log.txt\n\n" # splitStr +=":green:`- Fasta file with unassigned reads:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibsRC/seqs.unassigned.fna\n\n" splitStr +=":red:`Number of reads assigned on FW:` "+str(fwAssignedCounts)+" = "+str(prcFwAssigned)+"% of the peared reads\n\n" splitStr +=":red:`Number of reads assigned on RVC:` "+str(rvAssignedCounts)+" = "+str(prcRvAssigned)+"% of the peared reads\n\n" ################################################################################ # Single FastQ creation # ################################################################################ demultiplexFQ = "" if snakemake.config["demultiplexing"]["demultiplex"] == "T" and snakemake.config["demultiplexing"]["create_fastq_files"] == "T": demultiplexFQ = "Generate single sample fastq files\n------------------------------------------\n\n" # title demultiplexFQ += "Create single fastq files per samples (based on the raw data without applying any filtering).\n\n" demultiplexFQ +=":red:`Tool:` Cascabel Java program\n\n" demultiplexFQ += "**Command:**\n\n" demultiplexFQ += ":commd:`"+snakemake.config["java"]["command"] + " -cp Scripts DemultiplexQiime --txt -a rv -b "+ str(snakemake.config["demultiplexing"]["bc_mismatch"]) + " -d "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/seqs.assigned.ori.txt -o "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/ " ext=".gz" if snakemake.config["gzip_input"].casefold() == "f": ext="" demultiplexFQ += "-r1 "+snakemake.wildcards.PROJECT+"/samples/"+snakemake.wildcards.sample+"/rawdata/fw.fastq"+ext+" -r2 "+snakemake.wildcards.PROJECT+"/samples/"+snakemake.wildcards.sample+"/rawdata/fw.fastq"+ext+"`\n\n" if snakemake.config["demultiplexing"]["remove_bc"]: demultiplexFQ +=":red:`Barcodes removed:` "+ str(snakemake.config["demultiplexing"]["remove_bc"]) + " first bases\n\n" #Now only for ASV workflow # if snakemake.config["primers"]["remove"].lower() == "cfg": # demultiplexFQ +=":red:`Primers removed:` **FW** " + snakemake.config["primers"]["fw_primer"] + " **RV** " +snakemake.config["primers"]["rv_primer"]+"\n\n" # elif snakemake.config["primers"]["remove"].lower() == "metadata": # demultiplexFQ +=":red:`Removed primers` were obtained from the metadata file.\n\n" demultiplexFQ += "**The demultiplexed fastq files are located at:**\n\n:green:`- Demultiplexed directory:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/\n\n" demultiplexFQ += ":green:`- Summary file:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/summary.txt\n\n" demultiplexFQ += demultiplexFQBench # also this only for the ASV workflow # if (snakemake.config["primers"]["remove"].lower() == "cfg" or snakemake.config["primers"]["remove"].lower() == "metadata"): # demultiplexFQ += "**Remove primers:**\n\nFollowing, primers were removed from the fastq files\n\n" # demultiplexFQ +=":red:`Tool:` [Cutadapt]_\n\n" # demultiplexFQ += ":red:`Version:` "+cutVersion+"\n\n" # demultiplexFQ += "**Command:**\n\n" # if snakemake.config["primers"]["remove"].lower() == "cfg": # if snakemake.config["LIBRARY_LAYOUT"].casefold()=="pe": # demultiplexFQ += ":commd:`cutadapt -g "+ snakemake.config["primers"]["fw_primer"] + " -G " + snakemake.config["primers"]["rv_primer"] + " " +snakemake.config["primers"]["extra_params"]+" -O "+ snakemake.config["primers"]["min_overlap"] +" -m " +snakemake.config["primers"]["min_length"]+ " -o "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/primer_removed/SAMPLE_1.fastq.gz -p "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/primer_removed/SAMPLE_2.fastq.gz "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/SAMPLE_1.fq.gz "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/SAMPLE_2.fq.gz >> "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/primer_removed/"+snakemake.wildcards.sample+".cutadapt.log`\n\n" # else: # demultiplexFQ += ":commd:`cutadapt -g "+ snakemake.config["primers"]["fw_primer"] + " " +snakemake.config["primers"]["extra_params"]+" -O "+ snakemake.config["primers"]["min_overlap"] +" -m " +snakemake.config["primers"]["min_length"]+ " -o "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/primer_removed/SAMPLE_1.fastq.gz "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/SAMPLE_1.fq.gz >> "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/primer_removed/"+snakemake.wildcards.sample+".cutadapt.log`\n\n" # demultiplexFQ += "The above command ran once for each single sample fastq file(s) using the mentioned primers\n\n" # else: #is from metadata # if snakemake.config["LIBRARY_LAYOUT"].casefold()=="pe": # demultiplexFQ += ":commd:`cutadapt -g sample_FW_primer -G sample_RV_primer " +snakemake.config["primers"]["extra_params"]+" -O "+ snakemake.config["primers"]["min_overlap"] +" -m " +snakemake.config["primers"]["min_length"]+ " -o "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/primer_removed/SAMPLE_1.fastq.gz -p "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/primer_removed/SAMPLE_2.fastq.gz "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/SAMPLE_1.fq.gz "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/SAMPLE_2.fq.gz >> "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/primer_removed/"+snakemake.wildcards.sample+".cutadapt.log`\n\n" # elif snakemake.config["LIBRARY_LAYOUT"].casefold()=="se": # demultiplexFQ += ":commd:`cutadapt -g sample_FW_primer "+ " " +snakemake.config["primers"]["extra_params"]+" -O "+ snakemake.config["primers"]["min_overlap"] +" -m " +snakemake.config["primers"]["min_length"]+ " -o "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/primer_removed/SAMPLE_1.fastq.gz "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/SAMPLE_1.fq.gz >> "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/primer_removed/"+snakemake.wildcards.sample+".cutadapt.log`\n\n" # demultiplexFQ += "The above command ran once for each single sample fastq file(s) and primers were obtained from the mapping file accordingly to its sample\n\n" # demultiplexFQ += ":green:`- Reads without primers:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/primer_removed\n\n" # if "--discard-untrimmed" in snakemake.config["primers"]["extra_params"]: # demultiplexFQ += ":green:`- Discarded reads (no primer):` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/demultiplexed/reads_discarded_primer\n\n" # else: # demultiplexFQ += ":red:`- Given the options, reads without primers where not removed!`\n\n" # demultiplexFQ += ":green:`- Primer removal results by sample:` primers_removal_\n\n" # demultiplexFQ +=" .. _primers_removal: report_files/cutadapt."+snakemake.wildcards.sample+".fastq_summary.tsv\n\n" ################################################################################ # Combine FW and Reverse reads # ################################################################################ combineFR = "" #if snakemake.config["demultiplexing"]["demultiplex"] != "F": # combineFR = "Combine reads\n---------------------------------\n\n" # title # combineFR += "Concatenate forward and reverse reads.\n\n" # combineFR += "**Command:**\n\n" # combineFR += ":commd:`cat "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibs/seqs.assigned.fna "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/splitLibsRC/seqs.assigned.fna > "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted.fna`\n\n" # combineFR +="**Output files:**\n\n" # combineFR +=":green:`- Fasta file with combined reads:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted.fna\n\n" # combineFR +=":red:`- Total number of acepted reads:` " +str(totalAssigned)+ " = "+ str(prcPearedAssigned)+ "% of the peared reads or "+str(prcRawAssigned)+"% of the raw reads.\n\n" # combineFR += combineBench ################################################################################ # Cut adapters # ################################################################################ cutAdaptStr = "" if snakemake.config["primers"]["remove"].casefold() == "metadata" or snakemake.config["primers"]["remove"].casefold() == "cfg": cutAdaptStr = "Remove sequence primers\n------------------------\n\n" # title cutAdaptStr +="Remove the adapters / primers from the reads.\n\n" cutAdaptStr +=":red:`Tool:` [Cutadapt]_\n\n" cutAdaptStr += ":red:`Version:` "+cutVersion+"\n\n" cutAdaptStr += "**Command:**\n\n" primer_lines=0 if snakemake.config["primers"]["remove"].lower() == "cfg": #cutAdaptStr += ":commd:`cutadapt "+ str(snakemake.config["cutadapt"]["adapters"])+" " + str(snakemake.config["cutadapt"]["extra_params"]) + " -o " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted_no_adapters.fna\n\n" #cutAdaptStr += snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted.fna > " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted_no_adapters.log`\n\n" cutAdaptStr += ":commd:`cutadapt -g "+ str(snakemake.config["primers"]["fw_primer"])+"..."+str(snakemake.config["primers"]["rv_primer"])+" "+ str(snakemake.config["primers"]["extra_params"]) + " -o " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted_no_adapters.fna "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted.fna > " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted_no_adapters.log`\n\n" elif snakemake.config["primers"]["remove"].lower() == "metadata": primers="" try: #with open(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/primers.txt") as pfile: with open(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/report_files/primers."+snakemake.wildcards.sample+".txt") as pfile: primers=pfile.read() #primer_lines=len(pfile.readlines()) primer_lines=len(primers.split("\n")) if primer_lines > 1: if snakemake.config["LIBRARY_LAYOUT"].casefold()=="pe": primers="-g sample_FW_primer...sampleRV_primer" else: primers="-g sample_FW_primer" except FileNotFoundError: primers="-ERROR reading primer file-" #cutAdaptStr += ":commd:`cutadapt "+primers +" " + str(snakemake.config["cutadapt"]["extra_params"]) + " -o " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted_no_adapters.fna\n\n" #cutAdaptStr += snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted.fna > " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted_no_adapters.log`\n\n" cutAdaptStr += ":commd:`cutadapt "+primers +" " + str(snakemake.config["primers"]["extra_params"]) + " -o " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted_no_adapters.fna "+ snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted.fna > " + snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted_no_adapters.log`\n\n" #cutAdaptStr += "*PRIMERS: primer sequences were obtained from the metadata file\n\n" if primer_lines > 1: cutAdaptStr += ":green:`- Primers used by sample:` primers_sample_\n\n" cutAdaptStr += ".. _primers_sample: report_files/primers."+snakemake.wildcards.sample+".txt\n\n" cutAdaptStr += "**Output files:**\n\n:green:`- Reads without adapters:` "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted_no_adapters.fna\n\n" if cutSequences: cutAdaptStr += ":red:`Total number of reads after cutadapt:` "+ str(sequenceNoAdapters) + " = " + str(prcCut) + "% of the assigned reads or "+ str(prcCutRaw)+"% of the total reads\n\n" #cutAdaptStr+=":\n\n" cutAdaptStr+=":green:`- Primer removal results by sample:` primers_OTU_\n\n" cutAdaptStr+=" .. _primers_OTU: report_files/cutadapt."+snakemake.wildcards.sample+".summary.tsv\n\n" cutAdaptBench =readBenchmark(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/cutadapt.benchmark") cutAdaptStr += cutAdaptBench+"\n\n" ################################################################################ # Counts for too long too shorts # ################################################################################ #trimmedStr = ":red:`Total number of reads after trimming:` "+str(trimmedCounts)+ "="+ str(prcTrimmedSplit)+"% of the demultiplexed reads or " + str(prcTrimmedRaw) + "% of the raw reads\n\n" trimmedStr = ":red:`Total number of reads after length filtering:` "+str(trimmedCounts)+ "\n\n" trimmedStr += ":red:`Percentage of reads vs raw reads:` "+str(prcTrimmedRaw)+"%\n\n" trimmedStr+=":red:`Percentage of reads vs demultiplexed reads:` " + str(prcTrimmedSplit) + "%\n\n" if cutSequences: trimmedStr+=":red:`Percentage of reads after cutadapt:` "+ str(prcTrimmedCut) + "%\n" #if removeChimeras: # trimmedStr+=":red:`Percentage of reads after remove chimeras vs trimmed reads:` "+ str(prcTrimmedChimera) + "%\n" #bcValidationBench =readBenchmark(snakemake.wildcards.PROJECT+"/metadata/bc_validation/"+snakemake.wildcards.sample+"/validation.benchmark") ################################################################################ # Remove too short and too long reads # # This rule creates a temporary file with the short and long values choosed # # by the user in order to remove the reads. The file filter.log contains the # # minimun expected length for the reads followed by the maximun length tab # # separated (shorts <TAB> longs) # ################################################################################ shorts = str(snakemake.config["rm_reads"]["shorts"]) longs = str(snakemake.config["rm_reads"]["longs"]) with open(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/filter.log") as trimlog: for line in trimlog: tokens = line.split("\t") if len(tokens)>2: shorts = tokens[1] longs = tokens[2] ################################################################################ # FInal Counts # ################################################################################ countTxt="Following you can see the final read counts: \n\n" fileData = [] headers = [] data =[] headers.append("File description") headers.append("Location") headers.append("Number of reads") headers.append("Prc(%) vs raw") fileData.append(headers) #raw data.append("Raw reads") data.append(snakemake.wildcards.PROJECT+"/samples/"+snakemake.wildcards.sample+"/rawdata/\*.fq") data.append(str(rawCounts)) data.append("{:.2f}".format(float((rawCounts/rawCounts)*100))+"%") fileData.append(data) data=[] #pear data.append("Assembled reads") data.append(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/peared/seqs.assembled.fastq") data.append(str(pearedCounts)) data.append("{:.2f}".format(float((pearedCounts/rawCounts)*100))+"%") fileData.append(data) data=[] #splitted if snakemake.config["demultiplexing"]["demultiplex"] == "T": data.append("Demultiplexed reads") data.append(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted.fna") data.append(str(totalAssigned)) data.append("{:.2f}".format(float((totalAssigned/rawCounts)*100))+"%") fileData.append(data) data=[] #adapters if snakemake.config["primers"]["remove"].casefold() == "metadata" or snakemake.config["primers"]["remove"].casefold() == "cfg": data.append("Adapter removed") data.append(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_accepted_no_adapters.fna") data.append(str(sequenceNoAdapters)) data.append("{:.2f}".format(float((sequenceNoAdapters/rawCounts)*100))+"%") fileData.append(data) data=[] #length filtered data.append("Length filtered") data.append(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_filtered.fasta") data.append(str(trimmedCounts)) data.append("{:.2f}".format(float((trimmedCounts/rawCounts)*100))+"%") fileData.append(data) data=[] #chimera if snakemake.config["chimera"]["search"] == "T" and removeChimeras: data.append("Non chimeric reads") data.append(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_filtered_nc.fasta") data.append(str(sequenceNoChimeras)) data.append("{:.2f}".format(float((sequenceNoChimeras/rawCounts)*100))+"%") fileData.append(data) data=[] countTxt += make_table(fileData) ################################################################################ # Sample distribution chart # ################################################################################ sampleDistChart = "" if snakemake.config["demultiplexing"]["demultiplex"] == "T": dist_table = readSampleDist(snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_filtered.dist.txt",trimmedCounts,samplesLibInt) sampleDistChart = "Sample distribution\n--------------------------------------\n\n" # title sampleDistChart += dist_table + "\n\n" sampleDistChart += ".. image:: report_files/seqs_fw_rev_filtered."+snakemake.wildcards.sample+".dist.png\n\n" sampleDistChart +="The previous chart shows the number of clean reads per sample. The bars are sorted from left to right, according to the metadata input file.\n\n" sampleDistChart +="**To see more details about the number of reads per sample in this library, please refer to the file:** "+snakemake.wildcards.PROJECT+"/runs/"+snakemake.wildcards.run+"/"+snakemake.wildcards.sample+"_data/seqs_fw_rev_filtered.dist.txt\n\n" ################################################################################ # User description section # ################################################################################ desc = snakemake.config["description"] txtDescription = "" if len(desc) > 0: txtDescription = "\n**User description:** "+desc+"\n" ################################################################################ # controls warning section # ################################################################################ """ We want to include a small section to warn the user about the use of controls. This could be the case if they are demultiplexing a complete library. """ ctrlWarning ="" if snakemake.config["demultiplexing"]["demultiplex"] == "T": ctrlWarning="\n:warn:`Note: Library demultiplexing has been carried out, if you have controls among your samples, please be aware that Cascabel won't perform any special operation with them. They are treated as any other sample within this workflow. Please make sure to analyze your controls with other tools, and correct your sample counts for potential contamination.`\n" ################################################################################ # Report # ################################################################################ report(""" Amplicon Analysis Report for Library: {snakemake.wildcards.sample} ===================================================================== .. role:: commd .. role:: red .. role:: green .. role:: warn **CASCABEL** is designed to run amplicon sequence analysis across single or multiple read libraries. The objective of this pipeline is to create different output files which allow the user to explore data in a simple and meaningful way, as well as facilitate downstream analysis, based on the generated output files. Another aim of **CASCABEL** is also to encourage the documentation process, by creating this report in order to assure data analysis reproducibility. {txtDescription} {ctrlWarning} Following you can see all the steps that were taken in order to get the final results of the pipeline. Raw Data --------- The raw data for this library can be found at: :green:`- FW raw reads:` {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.sample}/rawdata/fw.fastq :green:`- RV raw reads:` {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.sample}/rawdata/rv.fastq :red:`Number of total reads:` {rawCountsStr} Quality Control ------------------ Evaluate quality on raw reads. :red:`Tool:` [FastQC]_ :red:`Version:` {fqVersion} **Command:** :commd:`fastqc {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.sample}/rawdata/fw.fastq {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.sample}/rawdata/rv.fastq --extract -o {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.sample}/qc/` You can follow the links below, in order to see the complete FastQC report: :green:`- FastQC for sample {snakemake.wildcards.sample}_1:` FQ1_ .. _FQ1: ../../../samples/{snakemake.wildcards.sample}/qc/fw_fastqc.html :green:`- FastQC for sample {snakemake.wildcards.sample}_2:` FQ2_ .. _FQ2: ../../../samples/{snakemake.wildcards.sample}/qc/rv_fastqc.html {fqBench} Read pairing ---------------- Align paired end reads and merge them into one single sequence in case they overlap. :red:`Tool:` [PEAR]_ :red:`version:` {pearversion} **Command:** :commd:`pear -f {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.sample}/rawdata/fw.fastq -r {snakemake.wildcards.PROJECT}/samples/{snakemake.wildcards.sample}/rawdata/rv.fastq -t {snakemake.config[pear][t]} -v {snakemake.config[pear][v]} -j {snakemake.config[pear][j]} -p {snakemake.config[pear][p]} -o {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/{snakemake.wildcards.sample}_data/peared/seqs > {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/{snakemake.wildcards.sample}_data/peared/seqs.assembled.fastq` **Output files:** :green:`- Merged reads:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/{snakemake.wildcards.sample}_data/peared/seqs.assembled.fastq :green:`- Log file:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/{snakemake.wildcards.sample}_data/peared/pear.log :red:`Number of peared reads:` {pearedCountsStr} = {prcPeared}% {pearBench} {fastQCPearStr} {extractBCStr} {correctBCStr} {splitStr} {demultiplexFQ} {combineFR} {cutAdaptStr} Remove too long and too short reads ------------------------------------ Remove very short and long reads, with lengths more than some standard deviation below or above the mean to be short or long respectively :green:`- Minimun length expected (shorts):` {shorts} :green:`- Maximun length expected (longs):` {longs} **Command:** :commd:`awk '!/^>/ {{ next }} {{ getline seq }} length(seq) > shorts && length(seq) < longs {{ print $0 \"\\n\" seq }}' {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/{snakemake.wildcards.sample}_data/seqs_fw_rev_accepted.fna > {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/{snakemake.wildcards.sample}_data/seqs_fw_rev_filtered.fasta` **Sequence distribution before remove reads** .. image:: report_files/seqs_dist_hist.{snakemake.wildcards.sample}.png :height: 400px :width: 400px :align: center **Output file:** :green:`- Fasta file with correct sequence length:` {snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/{snakemake.wildcards.sample}_data/seqs_fw_rev_filtered.fasta {trimmedStr} {rmShorLongBench} {quimeraStr} {sampleDistChart} Final counts ------------- {countTxt} .. image:: report_files/sequence_numbers.{snakemake.wildcards.sample}.png OTU report --------------------------- Cascabel report on downstream analyses in combination with multiple libraries (if supplied), can be found at the following link: otu_report_ ({snakemake.wildcards.PROJECT}/runs/{snakemake.wildcards.run}/otu_report_{snakemake.config[assignTaxonomy][tool]}.html) .. _otu_report: otu_report_{snakemake.config[assignTaxonomy][tool]}.html References ------------------ .. [FastQC] FastQC v0.11.3. Andrews S. (2010). FastQC: a quality control tool for high throughput sequence data .. [PEAR] PEAR: a fast and accurate Illumina Paired-End reAd mergeR. Zhang et al (2014) Bioinformatics 30(5): 614-620 | doi:10.1093/bioinformatics/btt593 .. [QIIME] QIIME. Caporaso JG, Kuczynski J, Stombaugh J, Bittinger K, Bushman FD, Costello EK, Fierer N, Gonzalez Pena A, Goodrich JK, Gordon JI, Huttley GA, Kelley ST, Knights D, Koenig JE, Ley RE, Lozupone CA, McDonald D, Muegge BD, Pirrung M, Reeder J, Sevinsky JR, Turnbaugh PJ, Walters WA, Widmann J, Yatsunenko T, Zaneveld J, Knight R. 2010. QIIME allows analysis of high-throughput community sequencing data. Nature Methods 7(5): 335-336. .. [Cutadapt] Cutadapt v1.15 .Marcel Martin. Cutadapt removes adapter sequences from high-throughput sequencing reads. EMBnet.Journal, 17(1):10-12, May 2011. http://dx.doi.org/10.14806/ej.17.1.200 .. [Vsearch] Rognes T, Flouri T, Nichols B, Quince C, Mahé F. (2016) VSEARCH: a versatile open source tool for metagenomics. PeerJ 4:e2584. doi: 10.7717/peerj.2584 {variable_refs} """, snakemake.output[0], metadata="Author: J. Engelmann & A. Abdala ") |
294 295 | shell: "{config[qiime][path]}validate_mapping_file.py -o {params} -m {input.mapp}" |
341 342 343 | shell: "{config[qiime][path]}extract_barcodes.py -f {input.assembly} -c {config[ext_bc][c]} " "{config[ext_bc][bc_length]} {config[ext_bc][extra_params]} -o {params}" |
357 358 359 | shell: "{config[qiime][path]}extract_barcodes.py -f {input.assembly} -c {config[ext_bc][c]} " "{config[ext_bc][bc_length]} {config[ext_bc][extra_params]} -o {params}" |
tool / biotools
QIIME2.0
QIIME 2™ is a next-generation microbiome bioinformatics platform that is extensible, free, open source, and community developed.