Workflow Steps and Code Snippets
171 tagged steps and code snippets that match keyword BLAST
Novel insertion detection with 10X reads (0.3)
89 90 91 92 93 94 95 96 97 | run: if BLAST_DB != 'None': shell("mkdir -p blast") shell("{BLASTN} -task megablast -query {input.filtered_fasta} -db {BLAST_DB} -num_threads {THREADS} > blast/{wildcards.sample}.megablast") shell("{GIT_ROOT}/cleanmega blast/{wildcards.sample}.megablast blast/{wildcards.sample}.cleanmega") shell("{GIT_ROOT}/find_contaminations.py blast/{wildcards.sample}.cleanmega blast/{wildcards.sample}.contaminants") shell("python {GIT_ROOT}/remove_contaminations.py blast/{wildcards.sample}.contaminants {input.filtered_fasta} {output.filtered_fasta}") else: shell("cp {input.filtered_fasta} {output.filtered_fasta}") |
kGWASflow is a Snakemake workflow for performing k-mers-based GWAS. (v1.2.3)
68 69 | wrapper: "v1.25.0/bio/blast/blastn" |
Automated pipeline for amplicon sequence analysis
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
1583 1584 1585 1586 1587 | shell: "{config[assignTaxonomy][blast][command]} {params.reference} -query {input} -evalue {config[assignTaxonomy][blast][evalue]} " "-outfmt '6 qseqid sseqid pident qcovs evalue bitscore' -num_threads {config[assignTaxonomy][blast][jobs]} " "-max_target_seqs {config[assignTaxonomy][blast][max_target_seqs]} -perc_identity {config[assignTaxonomy][blast][identity]} " "{config[assignTaxonomy][blast][extra_params]} -out {output[0]} " |
1615 1616 1617 1618 | shell: "cat {input} | cut -f2 | sort | uniq | grep -F -w -f - {config[assignTaxonomy][blast][mapFile]} | " "awk 'NR==FNR {{h[$1] = $2; next}} {{print $1\"\\t\"$3\"\\t\"$2\" \"h[$2]}}' FS=\"\\t\" - FS=\"\\t\" {input} " " > {output}" |
1647 1648 | shell: "Scripts/stampa_merge.py {params} {config[assignTaxonomy][blast][taxo_separator]}" |
RADSeq tool with Snakemake workflow integration for analysis of RAD sequencing data. (latest)
73 74 | shell: "blastn -query {input.res} -outfmt 6 -db {params.dbname} -out {output.blast}" |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 | library("tidyverse") library("stringr") log <- file(snakemake@log[[1]], open="wt") sink(log) sink(log, type="message") blast <- snakemake@input[[1]] blast_data <- read_tsv(blast, col_names = TRUE, trim_ws = TRUE) names(blast_data) <- c('res_id','sim_id','identity', 'len_alignment', 'mismatches', 'gap_opens', 'q_start', 'q_end', 's_start', 's_end', 'evalue', 'bit_score') blast_data <- blast_data %>% mutate(res_id=as.character(res_id)) %>% separate(res_id, c("sample", "individual", "locus"), sep = "\\|", extra="merge", convert=TRUE) #%>% for(i in blast_data$locus) { if(nchar(strsplit(i, "-")[[1]][1])<5){ blast_data$locus[blast_data$locus==i] <- str_replace(blast_data$locus[blast_data$locus==i], 'LOC', 'LOC0') } } plot <- ggplot(data = blast_data, aes(y=locus, x=identity)) + geom_bar(width = 1.0, position = "dodge", stat="identity", aes(fill = identity), colour="Black") + scale_fill_gradient(low="mediumpurple3",high="green3", name = "Identity") + ggtitle("Indentity [%] of loci identified by NodeRAD vs. simulated loci") + xlab("Identity [%]") + ylab("Locus") + theme_minimal() + theme(aspect.ratio = 2.5/1.5, plot.title = element_text(hjust = 0.5), legend.position = "right", legend.key.size = unit(0.8, "cm"), axis.text.y = element_text(hjust = 0)) plot ggsave(snakemake@output[["ident"]], width = 7, height = 7) blast_data$intervals <- cut(blast_data$identity, seq(0,100,by=1)) plot <- ggplot(blast_data, aes(intervals)) + geom_histogram(stat= "count", aes(fill = ..count..)) + xlab("Identity [%]") + ylab("Counts") + scale_fill_gradient(name = "Counts")+ theme(aspect.ratio = 2.5/1.5, plot.title = element_text(hjust = 0.5), legend.position = "right") + ggtitle("Histogram of number of alleles identified by NodeRAD\nwith respect to their similarity to simulated data.") plot ggsave(snakemake@output[["ident_hist"]], width = 7, height = 7) plot <- ggplot(data = blast_data, aes(x=locus, y=bit_score, group = individual)) + geom_line(color = "gray70") + geom_point(aes(color = bit_score), size =3) + geom_point(shape = 1,size = 3, colour = "black") + scale_color_gradient(low="red", high="green", name = "Bit score") + ggtitle("Bitscores of loci identified by NodeRAD vs. simulated loci") + xlab("Locus") + ylab("Bit score") + theme_minimal() + theme(axis.text.x = element_text(color = "black", size = 7, angle = 90, hjust = 0, face = "plain"), plot.title = element_text(hjust = 0.5), legend.position = "right", legend.key.size = unit(0.4, "cm"), axis.text.y = element_text(hjust = 0)) plot ggsave(snakemake@output[["bit_scores"]], width = 7, height = 7) plot <- ggplot(data = blast_data, aes(x=locus, y=evalue, group = individual)) + geom_line(color = "gray70") + geom_point(aes(color = evalue), size =3) + geom_point(shape = 1,size = 3, colour = "black") + scale_color_gradient(low="green", high="red", name = "E-value") + ggtitle("E-Values of loci identified by NodeRAD vs. simulated loci") + xlab("Locus") + ylab("E-Value") + theme_minimal() + theme(axis.text.x = element_text(color = "black", size = 7, angle = 90, hjust = 0, face = "plain"), plot.title = element_text(hjust = 0.5), legend.position = "right", legend.key.size = unit(0.4, "cm"), axis.text.y = element_text(hjust = 0)) plot ggsave(snakemake@output[["evalues"]], width = 7, height = 7) |
Automatic identification, classification and annotation of plant lncRNAs in transcriptomic sequences
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 | import os import subprocess import sys from Bio import SeqIO import pandas as pd import numpy as np import matplotlib.pyplot as plt def data_base(x): x_n = x.rsplit('/', 1)[1] x_n = x_n.rsplit('.', 1)[0] dir_check = os.path.isfile('data/reference/data_index/' + x_n + '.nin') if dir_check is True: print('index exist') index_path = os.path.join('data/reference/data_index/', x_n) return index_path else: print('build index') index_path = os.path.join('data/reference/data_index/', x_n) command = 'makeblastdb -in {db} -dbtype nucl -parse_seqids -out {index}'. format(db=x, index=index_path) exit_code = subprocess.call(command, shell=True) return index_path def fasta(x): query = x['name'] for w in query: try: old_id = old_new[old_new['new_id'].isin([w])] print(record_dict[str(old_id['old_id'].to_list()[0])].format('fasta'), end='', file=lncrna) except KeyError: continue def alingment(x,y): path = x.rsplit('/', 1)[0] outfmt = os.path.join(path, 'blast' + '.outfmt6') aling = 'blastn -query {q} -db {dbw} -outfmt "6 qseqid sseqid pident length mismatch gapopen qstart qend sstart send evalue bitscore qlen slen" -evalue {evalue} -max_target_seqs {max_target} -perc_identity {identity} -num_threads {threads} -out {outfmt}'. format(q=x, dbw=y, evalue=evalue, max_target=max_target, identity=identity, threads =threads, outfmt=outfmt) #| sort -k1,1 -k12,12nr -k11,11n | sort -u -k1,1 --merge > {outfmt}'. format(q=x, dbw=y, outfmt=outfmt) exit_code = subprocess.call(aling, shell=True) # input data query = pd.read_csv(sys.argv[1], sep='\t', header=None) gff_tmap = sys.argv[2] data = sys.argv[3] record_dict = SeqIO.to_dict(SeqIO.parse(sys.argv[4], "fasta")) lncrna = open(sys.argv[5], 'w', encoding='utf-8') evalue = sys.argv[6] max_target = sys.argv[7] identity = sys.argv[8] threads = sys.argv[9] old_new = pd.read_csv(sys.argv[10], sep='\t') tmap = pd.read_csv(gff_tmap, sep='\t') # lncRNA classification graf query = query[query[7].str.contains("gene")] tmap = tmap[tmap['qry_gene_id'].str.contains("path1")] name_tmap = tmap['qry_gene_id'].str.rsplit('.', expand=True) tmap[['name','seq']] = name_tmap[[0,1]] #tmap = tmap[tmap['seq'].str.contains("path1")] tmap = tmap[tmap['name'].isin(query[10])] tmap= tmap.drop_duplicates(subset=['name']) tmap['group'] = np.nan tmap['group'][tmap['class_code'].isin(['x'])] = "exon antisense" tmap['group'][tmap['class_code'].isin(['i'])] = "intron" tmap['group'][tmap['class_code'].isin(['u'])] = "intergenic" tmap.dropna(subset = ["group"], inplace=True) print(tmap['group'].value_counts()) f, ax = plt.subplots(figsize=(13, 13)) tmap['group'].value_counts().plot(kind='bar') plt.xticks(size=15, rotation=30) plt.yticks(size=15) plt.ylabel('LncRNA transcripts number', size=15) plt.xlabel('LncRNA classes', size=15) plt.savefig("data/output/new_lncRNA/classes.png", dpi=500) # BLAST fasta(tmap) indx = data_base(data) alingment(sys.argv[5], indx) |
tool / biotools
BLAST
A tool that finds regions of similarity between biological sequences. The program compares nucleotide or protein sequences to sequence databases and calculates the statistical significance.
Are you the author of this tool?
Add a badge to your website
with a link to this page.
Insert the following code to your website
to add 
with a link to this page.
with a link to this page.