Workflow Steps and Code Snippets

208 tagged steps and code snippets that match keyword seqkit

In this repository, we present the code for the analysis of study of the transcription's impact on Escherichia coli chromosome. 

30
31
32
33
34
35
36
37
38
39
40
shell:
  """
  mkdir -p {params.split_dir}
  # 100 split fastqs will be created with name pattern 001.fq - 100.fq
  seqkit split2 -p {params.n_splits} \
      -w 0 \
      -f \
      -j {threads} \
      -1 {input} \
      -O {params.split_dir}
  """
SnakeMake seqkit From line 30 of rules/00_common.smk 
53
54
55
56
57
58
59
60
61
62
63
shell:
  """
  mkdir -p {params.split_dir}
  # 100 split fastqs will be created with name pattern 001.fq - 100.fq
  seqkit split2 -p {params.n_splits} \
      -w 0 \
      -f \
      -j {threads} \
      -1 {input} \
      -O {params.split_dir}
  """
SnakeMake seqkit From line 53 of rules/00_common.smk 
13
14
15
16
17
18
19
20
21
22
shell: 
    """
    seqkit sliding \
        --step 100 \
        --window 500 \
        --threads {threads} \
        {input.fasta} | \
            seqkit fx2tab --gc | \
            cut -f1,4 > {output.gc}
    """
SnakeMake seqkit From line 13 of rules/04_WT_ecoli_analysis.smk

MAGqual is a command line tool to evaluate the quality of metagenomic bins and generate recommended metadata in line with the MIMAG standards (v0.1.1-beta) 

 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
import pandas as pd
import glob
import argparse
import os
from shutil import copyfile
import seaborn as sns
import matplotlib.pyplot as plt

def qual_cluster(comp, cont):
    if (comp >90) and (cont<5):
        qual = "High Quality"
    elif (comp >= 50) and (cont <10):
        qual = "Medium Quality"
    elif (comp <50) and (cont <10):
        qual = "Low Quality"
    else:
        qual = "Failed"
    return qual

def gen_qual(comp, cont):
    if (comp - (cont*5)) >= 50:
        genome = "y"
    else:
        genome = "n"
    return genome

def bsearch(bakta_loc, cluster): 
    length = 0
    loc = str(bakta_loc + str(cluster) + '/' + str(cluster) + '.txt') #don't copy this bit change it !
    # loc = str(str(cluster) + '.txt') #don't copy this bit change it !
    for name in glob.glob(loc):
        bakta_file = name
        with open(bakta_file, 'r') as bakta_log:
            for line in bakta_log:
                if "Length:" in line:
                    length = int(line.split(":")[1])
                if "Count:" in line: 
                    count = int(line.split(":")[1])
                if "N50:" in line:
                    N50 = int(line.split(":")[1])
                if "Software:" in line: 
                    software = line.split(":")[1].strip()
                if "Database" in line:
                    db = line.split(":")[1].strip()
    bakta_v = "Bakta " + software + " DB " + db 
    row_dict = {"length" : length, "contigs" : count, "N50": N50, "bakta_v" : bakta_v}
    return pd.Series(row_dict)

parser = argparse.ArgumentParser(description='')
parser.add_argument('output', help='output directory for the organised bins', type=str)
parser.add_argument('checkm_log', help='checkm output log file (TAB SEPARATED', type=str)
parser.add_argument('bakta_loc', help='directory containing all bakta output for all clusters', type=str)
parser.add_argument('seqkit_log', help='file containing the seqkit output for all clusters', type=str)
parser.add_argument('bin_loc', help='directory containing fasta files for all clusters', type=str)
parser.add_argument('jobid', help='prefix for current jobs', type=str)

args = parser.parse_args()
output = args.output
checkm_log = args.checkm_log
bakta_loc = args.bakta_loc
seqkit_log = args.seqkit_log
bin_loc = args.bin_loc
job_id = args.jobid

comp_software = "CheckM v.1.0.13"
comp_approach = "Marker gene"

colour_dict = dict({'High Quality':'#50C5B7',
                  'Near Complete':'#9CEC5B',
                  'Medium Quality': '#F0F465',
                  'Low Quality': "#F8333C",
                  'Failed': '#646E78'})

# =============================================================================
# CHECKM PARSE
# =============================================================================
checkm_df = pd.read_csv(checkm_log, sep = "\t")
checkm_df['Quality'] = checkm_df.apply(lambda x: qual_cluster(x['Completeness'], x['Contamination']), axis=1)
checkm_df[['Size_bp', 'No_contigs', 'N50_length', '16S_Software']] = checkm_df.apply(lambda x: bsearch(bakta_loc, x["Bin Id"]), axis = 1)

checkm_df = checkm_df.set_index("Bin Id")

high_clusters = checkm_df[checkm_df['Quality'].str.contains("High Quality")].index.values.tolist()
med_qual_clusters = checkm_df[checkm_df['Quality'].str.contains("Medium Quality")].index.values.tolist()
low_qual_clusters = checkm_df[checkm_df['Quality'].str.contains("Low Quality")].index.values.tolist()
NA = checkm_df[checkm_df['Quality'].str.contains("Failed")].index.values.tolist()
all_clusters = high_clusters + med_qual_clusters + low_qual_clusters + NA

checkm_df = checkm_df.drop(checkm_df.columns[[1, 2, 3, 4, 5, 6, 7, 8, 9]], axis=1)

# =============================================================================
# SEQKIT PARSE
# =============================================================================
seqkit_df = pd.read_csv(seqkit_log, sep = "\t")
seqkit_df = seqkit_df[["file", "max_len"]]
seqkit_df["file"] = seqkit_df["file"].str.replace('.fasta','', regex=True)
seqkit_df["file"] = seqkit_df["file"].str.split("/").str[-1]
seqkit_df.set_index("file", inplace=True)
seqkit_df.rename(columns={"max_len":"Max_contig_length"}, inplace = True)
checkm_df = pd.merge(checkm_df, seqkit_df, left_index=True, right_index=True, how="left")

# =============================================================================
# BAKTA PARSE
# =============================================================================

high_qual_clusters= []
near_comp_clusters = []
r16s_comp_clusters = []
trna_num = {}
for cluster in all_clusters:
    loc = str(bakta_loc + cluster + '/' + cluster + '.tsv') #change this too 
    # loc = str(str(cluster) + '.tsv') #don't copy this bit change it !
    for name in glob.glob(loc):
        bakta_file = name
        with open(bakta_file, 'r') as bakta_in:
            trna_set = set()
            rna_set = set()
            rrna_16S = "N"
            for line in bakta_in:
                if "tRNA-Ala" in line:
                    trna_set.add("tRNA-Ala")
                if "tRNA-Arg" in line:
                    trna_set.add("tRNA-Arg")
                if "tRNA-Asn" in line:
                    trna_set.add("tRNA-Asn")
                if "tRNA-Asp" in line:
                    trna_set.add("tRNA-Asp")
                if "tRNA-Cys" in line:
                    trna_set.add("tRNA-Cys")
                if "tRNA-Gln" in line:
                    trna_set.add("tRNA-Gln")
                if "tRNA-Glu" in line:
                    trna_set.add("tRNA-Glu")
                if "tRNA-Gly" in line:
                    trna_set.add("tRNA-Gly")
                if "tRNA-His" in line:
                    trna_set.add("tRNA-His")
                if "tRNA-Ile" in line:
                    trna_set.add("tRNA-Ile")
                if "tRNA-Leu" in line:
                    trna_set.add("tRNA-Leu")
                if "tRNA-Lys" in line:
                    trna_set.add("tRNA-Lys")
                if "tRNA-Met" in line:
                    trna_set.add("tRNA-Met")
                if "tRNA-Phe" in line:
                    trna_set.add("tRNA-Phe")
                if "tRNA-Pro" in line:
                    trna_set.add("tRNA-Pro")
                if "tRNA-Ser" in line:
                    trna_set.add("tRNA-Ser")
                if "tRNA-Thr" in line:
                    trna_set.add("tRNA-Thr")
                if "tRNA-Trp" in line:
                    trna_set.add("tRNA-Trp")
                if "tRNA-Tyr" in line:
                    trna_set.add("tRNA-Tyr")
                if "tRNA-Val" in line:
                    trna_set.add("tRNA-Val")
                if ("5S ribosomal RNA" in line) and ("partial" not in line):
                    rna_set.add('5S')
                if ("16S ribosomal RNA" in line) and ("partial" not in line):
                    rna_set.add('16S')
                    rrna_16S = "Y"
                if ("23S ribosomal RNA" in line) and ("partial" not in line):
                    rna_set.add('23s')
        if rrna_16S == "Y":
            r16s_comp_clusters.append(cluster)
        if cluster in high_clusters:
            if (len(trna_set) >= 18) and (len(rna_set) == 3):
                high_qual_clusters.append(cluster)
            else:
                near_comp_clusters.append(cluster) # adds high qual that fail trna/rna
        trna_num.update({cluster : len(trna_set)})


# =============================================================================
# Add these new qualities to the checkm dataframe        
# =============================================================================

checkm_df.loc[checkm_df.index.isin(near_comp_clusters), "Quality"] = "Near Complete"

checkm_df.loc[checkm_df.index.isin(r16s_comp_clusters), "16S_Recovered"] = "Y"
checkm_df["16S_Recovered"] = checkm_df["16S_Recovered"].fillna("N")

# Sort out legend order
label_order = ["High Quality", "Near Complete", "Medium Quality", "Low Quality", "Failed"]
labels_all = checkm_df["Quality"].unique().tolist()

for item in label_order:
    if item not in labels_all:
        label_order.remove(item)

labels_list = label_order

# =============================================================================
# Basic plot
# =============================================================================

checkm_df["Purity"] = 100 - checkm_df["Contamination"]
plt.figure(figsize=(15, 10))
ax = sns.scatterplot(data = checkm_df, x="Completeness", y="Purity",
                hue='Quality', size = 'Size_bp', sizes=(20, 800), alpha = 0.6, 
                palette=colour_dict, hue_order= labels_list)
sns.move_legend(ax, "upper left", bbox_to_anchor=(1, 1))

plt.xlabel('Completeness (%)', size = 24)
plt.ylabel('Purity (%)', size = 24)
plt.xlim(0)
plt.legend(prop={'size': 20})
plt.tight_layout()
plt.tick_params(labelsize=18)

plt.savefig(job_id + '_mag_qual.png')
# =============================================================================
# COPYING FILES INTO QUAL DIRECTORIES
# =============================================================================

location = bin_loc
new_loc = output + "/" + job_id + "/"
os.makedirs(new_loc + "high_qual", exist_ok=True)
os.makedirs(new_loc + "near_comp", exist_ok=True)
os.makedirs(new_loc + "med_qual", exist_ok=True)
os.makedirs(new_loc + "low_qual", exist_ok=True)
os.makedirs(new_loc + "failed", exist_ok=True)

for high in high_qual_clusters:
    file = location + high + ".fasta"
    copyfile(file, new_loc +"high_qual/"+high+".fasta")

for nc in near_comp_clusters:
    file = location + nc + ".fasta"
    copyfile(file, new_loc +"near_comp/"+nc+".fasta")

for med in med_qual_clusters:
    file = location + med + ".fasta"
    copyfile(file, new_loc+"med_qual/"+med+".fasta")

for low in low_qual_clusters:
    file = location + low + ".fasta"
    copyfile(file, new_loc+"low_qual/"+low+".fasta")

for NA_bin in NA:
    file = location + NA_bin + ".fasta"
    copyfile(file, new_loc+"failed/"+NA_bin+".fasta")

# =============================================================================
# OUTPUT CREATED HERE
# =============================================================================

magqual_df = checkm_df[["Quality", "Completeness", "Contamination", "16S_Recovered", "16S_Software", "Size_bp", "No_contigs", "N50_length", "Max_contig_length"]].copy()
magqual_df["tRNA_Extracted"] = pd.Series(trna_num)
magqual_df["tRNA_Software"] = magqual_df["16S_Software"]
magqual_df["Completeness_Approach"] = comp_approach
magqual_df["Completeness_Software"] = comp_software

magqual_df = magqual_df.reindex(columns=["Quality", "Completeness", "Contamination", "Completeness_Software","Completeness_Approach", "16S_Recovered", "16S_Software", "tRNA_Extracted", "tRNA_Software", "Size_bp", "No_contigs", "N50_length", "Max_contig_length"])

magqual_df.to_csv("analysis/" + job_id + "_mag_qual_statistics.csv")

print("-" * 12)
print(" NUMBER MAGs")
print("-" * 12)
print("High Quality:", len(high_qual_clusters))
print("Near Complete:", len(near_comp_clusters))
print("Med Quality:", len(med_qual_clusters))
print("Low Quality:", len(low_qual_clusters))
print("Failed:", len(NA), "\n")
print("-" * 12)
print(" MAG IDs")
print("-" * 12)
print("High Quality: " , ", ".join([str(x) for x in high_qual_clusters]))
print("Near Complete: ", ", ".join([str(x) for x in near_comp_clusters]))
print("Med Quality: ", ", ".join([str(x) for x in med_qual_clusters]))
print("Low Quality: ", ", ".join([str(x) for x in low_qual_clusters]))
print("Failed: ", ", ".join([str(x) for x in NA]))
Python Pandas matplotlib seaborn seqkit CheckM Bakta From line 11 of python/qual_parse.py 
128
129
130
131
shell:
    """
    seqkit stats -aT {input.clusters} > {output.tsv}
    """
SnakeMake seqkit From line 128 of workflow/Snakefile

Snakemake based analysis pipeline to identify m6As from eCLIP data 

22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
shell:
    """
    name="{params.name}"; \
    name="${{name^}}"; \
    ram="$(({params.ram}*1000000000))"; \
    curl -s --list-only {params.url_fasta}/ | if grep -q "primary_assembly"; then wget -P {output} {params.url_fasta}/${{name}}.{params.assembly_fasta}.dna.primary_assembly.fa.gz; else wget -P {output} {params.url_fasta}/${{name}}.{params.assembly_fasta}.dna.toplevel.fa.gz; fi; \
    wget -P {output} {params.url_gtf}/${{name}}.{params.assembly_gtf}.gtf.gz; \
    gzip -dr {output}; \
    echo "$(date +%b' '%d' '%H:%M:%S) Indexing genome (takes a while)..."; \
    STAR --runThreadN {threads_max} --limitGenomeGenerateRAM ${{ram}} --runMode genomeGenerate --genomeSAsparseD 2 --genomeFastaFiles {output}/*.fa --sjdbGTFfile {output}/*.gtf --genomeDir {output}/index > {log} && \
    echo "$(date +%b' '%d' '%H:%M:%S) Annotating genome (takes a while)..." && \
    seqkit split {output}/*.fa -i --by-id-prefix "" --id-regexp "([^\s]+)" -O {output}/chroms --quiet && \
    awk -F'"' -v OFS='"' '{{for(i=2; i<=NF; i+=2) gsub(";", "-", $i)}} 1' {output}/${{name}}.{params.assembly_gtf}.gtf | gtf2bed --attribute-key=gene_name - > {output}/${{name}}.{params.assembly_gtf}.geneNames.bed && \
    gtfToGenePred -genePredExt {output}/${{name}}.{params.assembly_gtf}.gtf {output}/${{name}}.{params.assembly_gtf}.genePred && \
    perl workflow/scripts/metaPlotR/make_annot_bed.pl --genomeDir {output}/chroms/ --genePred {output}/${{name}}.{params.assembly_gtf}.genePred > {output}/${{name}}.{params.assembly_gtf}.annotated.bed && \
    echo "$(date +%b' '%d' '%H:%M:%S) Sorting annotation..." && \
    sort -k1,1 -k2,2n {output}/${{name}}.{params.assembly_gtf}.annotated.bed > {output}/${{name}}.{params.assembly_gtf}.annotated.sorted.bed && \
    rm {output}/${{name}}.{params.assembly_gtf}.annotated.bed && \
    echo "$(date +%b' '%d' '%H:%M:%S) Calculating size of transcript regions (i.e. 5'UTR, CDS and 3'UTR)..." && \
    perl workflow/scripts/metaPlotR/size_of_cds_utrs.pl --annot {output}/${{name}}.{params.assembly_gtf}.annotated.sorted.bed > {output}/${{name}}.{params.assembly_gtf}.region_sizes.txt
    """
SnakeMake STAR seqkit GFFutils gtftogenepred From line 22 of workflow/Snakefile 
58
59
60
61
62
63
64
65
66
67
shell:
    """
    mkdir -p {output} && \
    rna_seq="{params.rna_seq}"; \
    rna_seq=`echo -e ">seq\n${{rna_seq}}" | seqkit subseq -r 1:7 | seqkit seq -s -t RNA --rna2dna --quiet`; \
    rna_seq_rc=`echo -e ">seq\n${{rna_seq}}" | seqkit seq -p -r -s -t DNA --quiet`; \
    echo -e "TRUSEQ_I5\t{params.truseq_read2}\nTRUSEQ_I7\t{params.truseq_read1}\n{params.rna_name}\t${{rna_seq}}\n{params.rna_name}_RC\t${{rna_seq_rc}}" > config/adapterList.txt && \
    fastqc --quiet -t {threads} -a config/adapterList.txt -o {output} {input.read2} && \
    mv {output}/*.zip {output}/{params.sample_name}_pre_fastqc.zip
    """
SnakeMake FastQC seqkit subSeq From line 58 of workflow/Snakefile 
107
108
109
110
111
112
113
114
shell:
    """
    rna_seq="{params.rna_seq}"; \
    rna_seq_rc=`echo -e ">seq\n${{rna_seq}}" | seqkit seq -p -r -s -t RNA --rna2dna --quiet`; \
    randomer_size="{params.randomer_size}"; \
    randomer_size=`echo "{{"${{randomer_size}}"}}"`; \
    cutadapt {params.args} -j {threads} -a "ssDNA=${{rna_seq_rc}};min_overlap=5...N${{randomer_size}}{params.truseq_read1};min_overlap=15" -A ssRNA={params.rna_seq} -A TruSeq={params.truseq_read2} -o {output.read1} -p {output.read2} {input} > {log}
    """
SnakeMake Cutadapt seqkit From line 107 of workflow/Snakefile 
187
188
189
190
191
192
193
194
195
196
shell:
    """
    java -cp workflow/scripts/meclip/target/meCLIP.jar com.github.ajlabuc.meclip.MpileupParser {input.mpileup} {params.prefix} C T 0.025 0.5 2 0 && \
    seqkit subseq --quiet --bed results/mpileup/IP/{params.prefix}_motifList_positive.bed resources/*.fa > results/mpileup/IP/motifList_positive.fa && \
    seqkit subseq --quiet --bed results/mpileup/IP/{params.prefix}_motifList_negative.bed resources/*.fa > results/mpileup/IP/motifList_negative.fa && \
    java -cp workflow/scripts/meclip/target/meCLIP.jar com.github.ajlabuc.meclip.MotifFrequencyCalculator results/mpileup/IP/motifList_positive.fa results/mpileup/IP/{params.prefix}_MpileupParser_positive.xls [AG]AC && \
    java -cp workflow/scripts/meclip/target/meCLIP.jar com.github.ajlabuc.meclip.MotifFrequencyCalculator results/mpileup/IP/motifList_negative.fa results/mpileup/IP/{params.prefix}_MpileupParser_negative.xls GT[TC] && \
    cat <(echo -e "Chr \tM6A \tRef \tFreq \tMutationCount \tReadCount \tMotifStart \tMotifEnd \tMotif") results/mpileup/IP/{params.prefix}_MpileupParser_positive_motifFrequency.xls results/mpileup/IP/{params.prefix}_MpileupParser_negative_motifFrequency.xls > {output.xls} && \
    awk '{{if ($9!="No") print $0}}' {output.xls} > {output.xls}.temp && mv {output.xls}.temp {output.xls}
    """
SnakeMake seqkit subSeq From line 187 of workflow/Snakefile 
253
254
255
256
257
258
259
260
shell:
    """
    rna_seq="{params.rna_seq}"; \
    rna_seq_rc=`echo -e ">seq\n${{rna_seq}}" | seqkit seq -p -r -s -t RNA --rna2dna --quiet`; \
    randomer_size="{params.randomer_size}"; \
    randomer_size=`echo "{{"${{randomer_size}}"}}"`; \
    cutadapt {params.args} -j {threads} -a "ssDNA=${{rna_seq_rc}};min_overlap=5...N${{randomer_size}}{params.truseq_read1};min_overlap=15" -A ssRNA={params.rna_seq} -A TruSeq={params.truseq_read2} -o {output.read1} -p {output.read2} {input} > {log}
    """
SnakeMake Cutadapt seqkit From line 253 of workflow/Snakefile
tool / biotools

seqkit

seqkit

FASTA and FASTQ are basic and ubiquitous formats for storing nucleotide and protein sequences. Common manipulations of FASTA/Q file include converting, searching, filtering, deduplication, splitting, shuffling, and sampling. Existing tools only implement some of these manipulations, and not particularly efficiently, and some are only available for certain operating systems. Furthermore, the complicated installation process of required packages and running environments can render these programs less user friendly. SeqKit demonstrates competitive performance in execution time and memory usage compared to similar tools. The efficiency and usability of SeqKit enable researchers to rapidly accomplish common FASTA/Q file manipulations.

biotools seqkit
URL https://bioinf.shenwei.me/seqkit/
doi 10.1371/journal.pone.0163962
edam operation_0372
edam operation_3192
edam operation_0371
edam operation_0233
edam data_3494
edam format_1929
edam format_1930
topic: Sequence analysis
operation: Sequence conversion
signature: seqkit
input:data: DNA sequence
input:format: FASTQ
74 208 0 0
Are you the author of this tool? with a link to this page.
Insert the following code to your website to add tag icon with a link to this page.
    HTML Markdown