diff --git a/tools/samtools/bam_to_sam.xml b/tools/samtools/bam_to_sam.xml index 7bf804c50c6..0fdb3acd267 100644 --- a/tools/samtools/bam_to_sam.xml +++ b/tools/samtools/bam_to_sam.xml @@ -12,7 +12,7 @@ - + diff --git a/tools/samtools/sam2interval.xml b/tools/samtools/sam2interval.xml index 82d2a10fbc2..788eac9a098 100644 --- a/tools/samtools/sam2interval.xml +++ b/tools/samtools/sam2interval.xml @@ -10,7 +10,7 @@ - + diff --git a/tools/samtools/sam_merge.xml b/tools/samtools/sam_merge.xml index 96355a93fab..75e420eaed1 100644 --- a/tools/samtools/sam_merge.xml +++ b/tools/samtools/sam_merge.xml @@ -20,7 +20,7 @@ - + - - - + + + + @@ -206,6 +226,8 @@ + + @@ -221,7 +243,7 @@ - + @@ -230,9 +252,9 @@ - - - + + + @@ -281,6 +303,8 @@ + + @@ -296,7 +320,7 @@ - + @@ -305,33 +329,77 @@ - - - - + + + + - + - + + + + + + (( + singlePaired['sPaired'] == "single" and + singlePaired['sParams']['sSettingsType'] == "full" and + singlePaired['sParams']['sMaxFile'] is True + ) or ( + singlePaired['sPaired'] == "paired" and + singlePaired['pParams']['pSettingsType'] == "full" and + singlePaired['pParams']['pMaxFile'] is True + )) + + + + singlePaired['sPaired'] == "paired" + singlePaired['pParams']['pSettingsType'] == "full" + singlePaired['pParams']['pMaxFile'] is True + + + + (( + singlePaired['sPaired'] == "single" and + singlePaired['sParams']['sSettingsType'] == "full" and + singlePaired['sParams']['sUnmappedFile'] is True + ) or ( + singlePaired['sPaired'] == "paired" and + singlePaired['pParams']['pSettingsType'] == "full" and + singlePaired['pParams']['pUnmappedFile'] is True + )) + + + + singlePaired['sPaired'] == "paired" + singlePaired['pParams']['pSettingsType'] == "full" + singlePaired['pParams']['pUnmappedFile'] is True + @@ -342,13 +410,18 @@ - + @@ -378,6 +451,8 @@ + + @@ -386,12 +461,15 @@ - + + + @@ -414,6 +492,8 @@ + + @@ -422,13 +502,14 @@ - + @@ -455,7 +536,7 @@ - + @@ -485,6 +566,12 @@ Bowtie accepts files in Sanger FASTQ format. Use the FASTQ Groomer to prepare yo ------ +**A Note on Built-in Reference Genomes** + +Some genomes have multiple variants. If only one "type" of genome is listed, it is the Full version, which means that everything that came in the original genome data download (possibly with mitochondrial and plasmid DNA added if it wasn't already included). The Full version is available for every genome. Some genomes also come in the Canonical variant, which contains only the "canonical" (well-defined) chromosomes or segments, such as chr1-chr22, chrX, chrY, and chrM for human. Other variations include gender. These will come in the canonical form only, so the general Canonical variant is actually Canonical Female and the other is Canonical Male (identical to female excluding chrX). + +------ + **Outputs** The output is in SAM format, and has the following columns:: diff --git a/tools/sr_mapping/bowtie_wrapper.py b/tools/sr_mapping/bowtie_wrapper.py index b64d2db433d..9382b874e7b 100644 --- a/tools/sr_mapping/bowtie_wrapper.py +++ b/tools/sr_mapping/bowtie_wrapper.py @@ -6,9 +6,15 @@ For use with Bowtie v. 0.12.3 usage: bowtie_wrapper.py [options] -t, --threads=t: The number of threads to run + -o, --output=o: The output file + --output_unmapped_reads=: File name for unmapped reads (single-end) + --output_unmapped_reads_l=: File name for unmapped reads (left, paired-end) + --output_unmapped_reads_r=: File name for unmapped reads (right, paired-end) + --output_suppressed_reads=: File name for suppressed reads because of max setting (single-end) + --output_suppressed_reads_l=: File name for suppressed reads because of max setting (left, paired-end) + --output_suppressed_reads_r=: File name for suppressed reads because of max setting (right, paired-end) -i, --input1=i: The (forward or single-end) reads file in Sanger FASTQ format -I, --input2=I: The reverse reads file in Sanger FASTQ format - -o, --output=o: The output file -4, --dataType=4: The type of data (SOLiD or Solexa) -2, --paired=2: Whether the data is single- or paired-end -g, --genomeSource=g: The type of reference provided @@ -69,10 +75,16 @@ def __main__(): #Parse Command Line parser = optparse.OptionParser() parser.add_option( '-t', '--threads', dest='threads', help='The number of threads to run' ) + parser.add_option( '-o', '--output', dest='output', help='The output file' ) + parser.add_option( '', '--output_unmapped_reads', dest='output_unmapped_reads', help='File name for unmapped reads (single-end)' ) + parser.add_option( '', '--output_unmapped_reads_l', dest='output_unmapped_reads_l', help='File name for unmapped reads (left, paired-end)' ) + parser.add_option( '', '--output_unmapped_reads_r', dest='output_unmapped_reads_r', help='File name for unmapped reads (right, paired-end)' ) + parser.add_option( '', '--output_suppressed_reads', dest='output_suppressed_reads', help='File name for suppressed reads because of max setting (single-end)' ) + parser.add_option( '', '--output_suppressed_reads_l', dest='output_suppressed_reads_l', help='File name for suppressed reads because of max setting (left, paired-end)' ) + parser.add_option( '', '--output_suppressed_reads_r', dest='output_suppressed_reads_r', help='File name for suppressed reads because of max setting (right, paired-end)' ) parser.add_option( '-4', '--dataType', dest='dataType', help='The type of data (SOLiD or Solexa)' ) parser.add_option( '-i', '--input1', dest='input1', help='The (forward or single-end) reads file in Sanger FASTQ format' ) parser.add_option( '-I', '--input2', dest='input2', help='The reverse reads file in Sanger FASTQ format' ) - parser.add_option( '-o', '--output', dest='output', help='The output file' ) parser.add_option( '-2', '--paired', dest='paired', help='Whether the data is single- or paired-end' ) parser.add_option( '-g', '--genomeSource', dest='genomeSource', help='The type of reference provided' ) parser.add_option( '-r', '--ref', dest='ref', help='The reference genome to use or index' ) @@ -123,25 +135,6 @@ def __main__(): (options, args) = parser.parse_args() stdout = '' - # output version # of tool - try: - tmp = tempfile.NamedTemporaryFile().name - tmp_stdout = open( tmp, 'wb' ) - proc = subprocess.Popen( args='bowtie --version', shell=True, stdout=tmp_stdout ) - tmp_stdout.close() - returncode = proc.wait() - stdout = None - for line in open( tmp_stdout.name, 'rb' ): - if line.lower().find( 'version' ) >= 0: - stdout = line.strip() - break - if stdout: - sys.stdout.write( '%s\n' % stdout ) - else: - raise Exception - except: - sys.stdout.write( 'Could not determine Bowtie version\n' ) - # make temp directory for placement of indices and copy reference file there if necessary tmp_index_dir = tempfile.mkdtemp() # get type of data (solid or solexa) @@ -248,6 +241,8 @@ def __main__(): ref_file_name = options.ref # set up aligning and generate aligning command options # automatically set threads in both cases + tmp_suppressed_file_name = None + tmp_unmapped_file_name = None if options.suppressHeader == 'true': suppressHeader = '--sam-nohead' else: @@ -261,7 +256,7 @@ def __main__(): else: mateOrient = '' if options.params == 'preSet': - aligning_cmds = '%s %s -p %s -S %s -q %s ' % \ + aligning_cmds = '-q %s %s -p %s -S %s %s ' % \ ( maxInsert, mateOrient, options.threads, suppressHeader, colorspace ) else: try: @@ -281,6 +276,10 @@ def __main__(): trimL = '-3 %s' % options.trimL else: trimL = '' + if options.maqSoapAlign != '-1' and int( options.maqSoapAlign ) >= 0: + maqSoapAlign = '-v %s' % options.maqSoapAlign + else: + maqSoapAlign = '' if options.mismatchSeed and (options.mismatchSeed == '0' or options.mismatchSeed == '1' \ or options.mismatchSeed == '2' or options.mismatchSeed == '3'): mismatchSeed = '-n %s' % options.mismatchSeed @@ -298,10 +297,6 @@ def __main__(): rounding = '--nomaqround' else: rounding = '' - if options.maqSoapAlign != '-1' and int( options.maqSoapAlign ) >= 0: - maqSoapAlign = '-v %s' % options.maqSoapAlign - else: - maqSoapAlign = '' if options.minInsert and int( options.minInsert ) > 0: minInsert = '-I %s' % options.minInsert else: @@ -355,26 +350,50 @@ def __main__(): seed = '--seed %s' % options.seed else: seed = '' + if options.paired == 'paired': + if options.output_unmapped_reads_l and options.output_unmapped_reads_r: + tmp_unmapped_file = tempfile.NamedTemporaryFile( dir=tmp_index_dir, suffix='.fastq' ) + tmp_unmapped_file_name = tmp_unmapped_file.name + tmp_unmapped_file.close() + output_unmapped_reads = '--un %s' % tmp_unmapped_file_name + else: + output_unmapped_reads = '' + if options.output_suppressed_reads: + tmp_suppressed_file = tempfile.NamedTemporaryFile( dir=tmp_index_dir, suffix='.fastq' ) + tmp_suppressed_file_name = tmp_suppressed_file.name + tmp_suppressed_file.close() + output_suppressed_reads = '--max %s' % tmp_suppressed_file_name + else: + output_suppressed_reads = '' + else: + if options.output_unmapped_reads: + output_unmapped_reads = '--un %s' % options.output_unmapped_reads + else: + output_unmapped_reads = '' + if options.output_suppressed_reads: + output_suppressed_reads = '--max %s' % options.output_suppressed_reads + else: + output_suppressed_reads = '' + snpfrac = '' if options.snpphred and int( options.snpphred ) >= 0: snpphred = '--snpphred %s' % options.snpphred else: snpphred = '' if options.snpfrac and float( options.snpfrac ) >= 0: snpfrac = '--snpfrac %s' % options.snpfrac - else: - snpfrac = '' if options.keepends and options.keepends == 'doKeepends': keepends = '--col-keepends' else: keepends = '' - aligning_cmds = '%s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s ' \ - '%s %s %s %s %s %s %s %s %s %s %s -p %s -S %s -q' % \ - ( skip, alignLimit, trimH, trimL, mismatchSeed, mismatchQual, - seedLen, rounding, maqSoapAlign, minInsert, maxInsert, - mateOrient, maxAlignAttempt, forwardAlign, reverseAlign, - maxBacktracks, tryHard, valAlign, allValAligns, suppressAlign, - best, strata, offrate, seed, colorspace, snpphred, snpfrac, - keepends, options.threads, suppressHeader ) + aligning_cmds = '-q %s %s -p %s -S %s %s %s %s %s %s %s %s %s %s %s %s ' \ + '%s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s %s' % \ + ( maxInsert, mateOrient, options.threads, suppressHeader, + colorspace, skip, alignLimit, trimH, trimL, maqSoapAlign, + mismatchSeed, mismatchQual, seedLen, rounding, minInsert, + maxAlignAttempt, forwardAlign, reverseAlign, maxBacktracks, + tryHard, valAlign, allValAligns, suppressAlign, best, + strata, offrate, seed, snpphred, snpfrac, keepends, + output_unmapped_reads, output_suppressed_reads ) except ValueError, e: # clean up temp dir if os.path.exists( tmp_index_dir ): @@ -383,7 +402,7 @@ def __main__(): try: # have to nest try-except in try-finally to handle 2.4 try: - # prepare actual aligning commands + # prepare actual mapping commands if options.paired == 'paired': cmd2 = 'bowtie %s %s -1 %s -2 %s > %s' % ( aligning_cmds, ref_file_name, options.input1, options.input2, options.output ) else: @@ -408,9 +427,28 @@ def __main__(): tmp_stderr.close() if returncode != 0: raise Exception, stderr + # get suppressed and unmapped reads output files in place if appropriate + if options.paired == 'paired' and tmp_suppressed_file_name and \ + options.output_suppressed_reads_l and options.output_suppressed_reads_r: + try: + left = tmp_suppressed_file_name.replace( '.fastq', '_1.fastq' ) + right = tmp_suppressed_file_name.replace( '.fastq', '_1.fastq' ) + shutil.move( left, options.output_suppressed_reads_l ) + shutil.move( right, options.output_suppressed_reads_r ) + except Exception, e: + sys.stdout.write( 'Error producing the suppressed output file.\n' ) + if options.paired == 'paired' and tmp_unmapped_file_name and \ + options.output_unmapped_reads_l and options.output_unmapped_reads_r: + try: + left = tmp_unmapped_file_name.replace( '.fastq', '_1.fastq' ) + right = tmp_unmapped_file_name.replace( '.fastq', '_2.fastq' ) + shutil.move( left, options.output_unmapped_reads_l ) + shutil.move( right, options.output_unmapped_reads_r ) + except Exception, e: + sys.stdout.write( 'Error producing the unmapped output file.\n' ) # check that there are results in the output file if os.path.getsize( options.output ) == 0: - raise Exception, 'The output file is empty, there may be an error with your input file or settings.' + '\nextra: ' + str(extra) + raise Exception, 'The output file is empty, there may be an error with your input file or settings.' except Exception, e: stop_err( 'Error aligning sequence. ' + str( e ) ) finally: diff --git a/tools/sr_mapping/bowtie_wrapper.xml b/tools/sr_mapping/bowtie_wrapper.xml index 4f4deb86bd4..5be3071b1c4 100644 --- a/tools/sr_mapping/bowtie_wrapper.xml +++ b/tools/sr_mapping/bowtie_wrapper.xml @@ -3,107 +3,127 @@ - bowtie_wrapper.py - --threads="4" - --dataType="solexa" - --output=$output - --suppressHeader=$suppressHeader - --genomeSource=$refGenomeSource.genomeSource - #if $refGenomeSource.genomeSource == "history": - ##index already exists - #if $refGenomeSource.ownFile.extension.startswith( 'bowtie_' ): - ##user previously built - --ref="${refGenomeSource.ownFile.extra_files_path}/${refGenomeSource.ownFile.metadata.base_name}" - --do_not_build_index - #else: - ##build index on the fly - --ref=$refGenomeSource.ownFile - --indexSettings=$refGenomeSource.indexParams.indexSettings - #if $refGenomeSource.indexParams.indexSettings == "indexFull": - --iautoB=$refGenomeSource.indexParams.autoBehavior.autoB - #if $refGenomeSource.indexParams.autoBehavior.autoB == "set": - --ipacked=$refGenomeSource.indexParams.autoBehavior.packed - --ibmax=$refGenomeSource.indexParams.autoBehavior.bmax - --ibmaxdivn=$refGenomeSource.indexParams.autoBehavior.bmaxdivn - --idcv=$refGenomeSource.indexParams.autoBehavior.dcv + bowtie_wrapper.py + ## Hackish setting of number of threads + --threads="4" + ## Outputs + --output=$output + #if $singlePaired == "single" + #if $output_unmapped_reads_l + --output_unmapped_reads=$output_unmapped_reads_l + #end if + #if $output_suppressed_reads_l + --output_suppressed_reads=$output_suppressed_reads_l + #end if + #else + #if $output_unmapped_reads_l and $output_unmapped_reads_r + --output_unmapped_reads_l=$output_unmapped_reads_l + --output_unmapped_reads_r=$output_unmapped_reads_r + #end if + #if $output_suppressed_reads_l and $output_suppressed_reads_l + --output_suppressed_reads_l=$output_suppressed_reads_l + --output_suppressed_reads_r=$output_suppressed_reads_r + #end if + #end if + ## Inputs + --dataType="solexa" + --suppressHeader=$suppressHeader + --genomeSource=$refGenomeSource.genomeSource + #if $refGenomeSource.genomeSource == "history": + ##index already exists + #if $refGenomeSource.ownFile.extension.startswith( 'bowtie_' ): + ##user previously built + --ref="${refGenomeSource.ownFile.extra_files_path}/${refGenomeSource.ownFile.metadata.base_name}" + --do_not_build_index + #else: + ##build index on the fly + --ref=$refGenomeSource.ownFile + --indexSettings=$refGenomeSource.indexParams.indexSettings + #if $refGenomeSource.indexParams.indexSettings == "indexFull": + --iautoB=$refGenomeSource.indexParams.autoBehavior.autoB + #if $refGenomeSource.indexParams.autoBehavior.autoB == "set": + --ipacked=$refGenomeSource.indexParams.autoBehavior.packed + --ibmax=$refGenomeSource.indexParams.autoBehavior.bmax + --ibmaxdivn=$refGenomeSource.indexParams.autoBehavior.bmaxdivn + --idcv=$refGenomeSource.indexParams.autoBehavior.dcv + #end if + --inodc=$refGenomeSource.indexParams.nodc + --inoref=$refGenomeSource.indexParams.noref + --ioffrate=$refGenomeSource.indexParams.offrate + --iftab=$refGenomeSource.indexParams.ftab + --intoa=$refGenomeSource.indexParams.ntoa + --iendian=$refGenomeSource.indexParams.endian + --iseed=$refGenomeSource.indexParams.seed + --icutoff=$refGenomeSource.indexParams.cutoff #end if - --inodc=$refGenomeSource.indexParams.nodc - --inoref=$refGenomeSource.indexParams.noref - --ioffrate=$refGenomeSource.indexParams.offrate - --iftab=$refGenomeSource.indexParams.ftab - --intoa=$refGenomeSource.indexParams.ntoa - --iendian=$refGenomeSource.indexParams.endian - --iseed=$refGenomeSource.indexParams.seed - --icutoff=$refGenomeSource.indexParams.cutoff + #end if + #else + ##use pre-built index + --ref="${ filter( lambda x: str( x[0] ) == str( $refGenomeSource.index ), $__app__.tool_data_tables[ 'bowtie_indexes' ].get_fields() )[0][-1] }" + #end if + --paired=$singlePaired.sPaired + #if $singlePaired.sPaired == "single": + --input1=$singlePaired.sInput1 + --params=$singlePaired.sParams.sSettingsType + #if $singlePaired.sParams.sSettingsType == "full": + --skip=$singlePaired.sParams.sSkip + --alignLimit=$singlePaired.sParams.sAlignLimit + --trimH=$singlePaired.sParams.sTrimH + --trimL=$singlePaired.sParams.sTrimL + --mismatchSeed=$singlePaired.sParams.sMismatchSeed + --mismatchQual=$singlePaired.sParams.sMismatchQual + --seedLen=$singlePaired.sParams.sSeedLen + --rounding=$singlePaired.sParams.sRounding + --maqSoapAlign=$singlePaired.sParams.sMaqSoapAlign + --tryHard=$singlePaired.sParams.sTryHard + --valAlign=$singlePaired.sParams.sValAlign + --allValAligns=$singlePaired.sParams.sAllValAligns + --suppressAlign=$singlePaired.sParams.sSuppressAlign + --best=$singlePaired.sParams.sBestOption.sBest + #if $singlePaired.sParams.sBestOption.sBest == "doBest": + --maxBacktracks=$singlePaired.sParams.sBestOption.sdMaxBacktracks + --strata=$singlePaired.sParams.sBestOption.sdStrata + #else: + --maxBacktracks=$singlePaired.sParams.sBestOption.snMaxBacktracks + #end if + --offrate=$singlePaired.sParams.sOffrate + --seed=$singlePaired.sParams.sSeed + #end if + #else: + --input1=$singlePaired.pInput1 + --input2=$singlePaired.pInput2 + --maxInsert=$singlePaired.pMaxInsert + --mateOrient=$singlePaired.pMateOrient + --params=$singlePaired.pParams.pSettingsType + #if $singlePaired.pParams.pSettingsType == "full": + --skip=$singlePaired.pParams.pSkip + --alignLimit=$singlePaired.pParams.pAlignLimit + --trimH=$singlePaired.pParams.pTrimH + --trimL=$singlePaired.pParams.pTrimL + --mismatchSeed=$singlePaired.pParams.pMismatchSeed + --mismatchQual=$singlePaired.pParams.pMismatchQual + --seedLen=$singlePaired.pParams.pSeedLen + --rounding=$singlePaired.pParams.pRounding + --maqSoapAlign=$singlePaired.pParams.pMaqSoapAlign + --minInsert=$singlePaired.pParams.pMinInsert + --maxAlignAttempt=$singlePaired.pParams.pMaxAlignAttempt + --forwardAlign=$singlePaired.pParams.pForwardAlign + --reverseAlign=$singlePaired.pParams.pReverseAlign + --tryHard=$singlePaired.pParams.pTryHard + --valAlign=$singlePaired.pParams.pValAlign + --allValAligns=$singlePaired.pParams.pAllValAligns + --suppressAlign=$singlePaired.pParams.pSuppressAlign + --best=$singlePaired.pParams.pBestOption.pBest + #if $singlePaired.pParams.pBestOption.pBest == "doBest": + --maxBacktracks=$singlePaired.pParams.pBestOption.pdMaxBacktracks + --strata=$singlePaired.pParams.pBestOption.pdStrata + #else: + --maxBacktracks=$singlePaired.pParams.pBestOption.pnMaxBacktracks + #end if + --offrate=$singlePaired.pParams.pOffrate + --seed=$singlePaired.pParams.pSeed #end if #end if - #else - ##use pre-built index - --ref="${ filter( lambda x: str( x[0] ) == str( $refGenomeSource.index ), $__app__.tool_data_tables[ 'bowtie_indexes' ].get_fields() )[0][-1] }" - #end if - --paired=$singlePaired.sPaired - #if $singlePaired.sPaired == "single": - --input1=$singlePaired.sInput1 - --params=$singlePaired.sParams.sSettingsType - #if $singlePaired.sParams.sSettingsType == "full": - --skip=$singlePaired.sParams.sSkip - --alignLimit=$singlePaired.sParams.sAlignLimit - --trimH=$singlePaired.sParams.sTrimH - --trimL=$singlePaired.sParams.sTrimL - --mismatchSeed=$singlePaired.sParams.sMismatchSeed - --mismatchQual=$singlePaired.sParams.sMismatchQual - --seedLen=$singlePaired.sParams.sSeedLen - --rounding=$singlePaired.sParams.sRounding - --maqSoapAlign=$singlePaired.sParams.sMaqSoapAlign - --tryHard=$singlePaired.sParams.sTryHard - --valAlign=$singlePaired.sParams.sValAlign - --allValAligns=$singlePaired.sParams.sAllValAligns - --suppressAlign=$singlePaired.sParams.sSuppressAlign - --best=$singlePaired.sParams.sBestOption.sBest - #if $singlePaired.sParams.sBestOption.sBest == "doBest": - --maxBacktracks=$singlePaired.sParams.sBestOption.sdMaxBacktracks - --strata=$singlePaired.sParams.sBestOption.sdStrata - #else: - --maxBacktracks=$singlePaired.sParams.sBestOption.snMaxBacktracks - #end if - --offrate=$singlePaired.sParams.sOffrate - --seed=$singlePaired.sParams.sSeed - #end if - #else: - --input1=$singlePaired.pInput1 - --input2=$singlePaired.pInput2 - --maxInsert=$singlePaired.pMaxInsert - --mateOrient=$singlePaired.pMateOrient - --params=$singlePaired.pParams.pSettingsType - #if $singlePaired.pParams.pSettingsType == "full": - --skip=$singlePaired.pParams.pSkip - --alignLimit=$singlePaired.pParams.pAlignLimit - --trimH=$singlePaired.pParams.pTrimH - --trimL=$singlePaired.pParams.pTrimL - --mismatchSeed=$singlePaired.pParams.pMismatchSeed - --mismatchQual=$singlePaired.pParams.pMismatchQual - --seedLen=$singlePaired.pParams.pSeedLen - --rounding=$singlePaired.pParams.pRounding - --maqSoapAlign=$singlePaired.pParams.pMaqSoapAlign - --minInsert=$singlePaired.pParams.pMinInsert - --maxAlignAttempt=$singlePaired.pParams.pMaxAlignAttempt - --forwardAlign=$singlePaired.pParams.pForwardAlign - --reverseAlign=$singlePaired.pParams.pReverseAlign - --tryHard=$singlePaired.pParams.pTryHard - --valAlign=$singlePaired.pParams.pValAlign - --allValAligns=$singlePaired.pParams.pAllValAligns - --suppressAlign=$singlePaired.pParams.pSuppressAlign - --best=$singlePaired.pParams.pBestOption.pBest - #if $singlePaired.pParams.pBestOption.pBest == "doBest": - --maxBacktracks=$singlePaired.pParams.pBestOption.pdMaxBacktracks - --strata=$singlePaired.pParams.pBestOption.pdStrata - #else: - --maxBacktracks=$singlePaired.pParams.pBestOption.pnMaxBacktracks - #end if - --offrate=$singlePaired.pParams.pOffrate - --seed=$singlePaired.pParams.pSeed - #end if - #end if @@ -201,6 +221,8 @@ + + @@ -270,6 +292,8 @@ + + @@ -292,56 +316,106 @@ - + - + - + + + + + + (( + singlePaired['sPaired'] == "single" and + singlePaired['sParams']['sSettingsType'] == "full" and + singlePaired['sParams']['sMaxFile'] is True + ) or ( + singlePaired['sPaired'] == "paired" and + singlePaired['pParams']['pSettingsType'] == "full" and + singlePaired['pParams']['pMaxFile'] is True + )) + + + + singlePaired['sPaired'] == "paired" + singlePaired['pParams']['pSettingsType'] == "full" + singlePaired['pParams']['pMaxFile'] is True + + + + (( + singlePaired['sPaired'] == "single" and + singlePaired['sParams']['sSettingsType'] == "full" and + singlePaired['sParams']['sUnmappedFile'] is True + ) or ( + singlePaired['sPaired'] == "paired" and + singlePaired['pParams']['pSettingsType'] == "full" and + singlePaired['pParams']['pUnmappedFile'] is True + )) + + + + singlePaired['sPaired'] == "paired" + singlePaired['pParams']['pSettingsType'] == "full" + singlePaired['pParams']['pUnmappedFile'] is True + - + + - + - + - + @@ -360,23 +434,29 @@ + + - + + + - + + @@ -393,23 +473,26 @@ + + - + - + @@ -424,12 +507,12 @@ - + - + - + @@ -457,6 +540,12 @@ Bowtie accepts files in Sanger FASTQ format. Use the FASTQ Groomer to prepare yo ------ +**A Note on Built-in Reference Genomes** + +Some genomes have multiple variants. If only one "type" of genome is listed, it is the Full version, which means that everything that came in the original genome data download (possibly with mitochondrial and plasmid DNA added if it wasn't already included). The Full version is available for every genome. Some genomes also come in the Canonical variant, which contains only the "canonical" (well-defined) chromosomes or segments, such as chr1-chr22, chrX, chrY, and chrM for human. Other variations include gender. These will come in the canonical form only, so the general Canonical variant is actually Canonical Female and the other is Canonical Male (identical to female excluding chrX). + +------ + **Outputs** The output is in SAM format, and has the following columns:: @@ -510,92 +599,95 @@ This is an exhaustive list of Bowtie options: For indexing (bowtie-build):: - -a No auto behavior. Disable the default behavior where bowtie automatically - selects values for --bmax/--bmaxdivn/--dcv/--packed parameters according - to the memory available. [off] - --packed Packing. Use a packed representation for DNA strings. [auto] - --bmax INT Suffix maximum. The maximum number of suffixes allowed in a block. [auto] - --bmaxdivn INT Suffix maximum fraction. The maximum number of suffixes allowed in a block - expressed as a fraction of the length of the reference. [4] - --dcv INT Difference-cover sample. Use INT as the period for the difference-cover - sample. [1024] - --nodc INT No difference-cover sample. Disable the difference-cover sample. [off] - -r No reference indexes. Do not build the NAME.3.ebwt and NAME.4.ebwt portions - of the index. Used only for paired-end alignment. [off] - -o Offrate. How many Burrows-Wheeler rows get marked by the indexer. The - indexer will mark every 2^INT rows. The marked rows correspond to rows on - the genome. [5] - -t INT Ftab. The lookup table used to calculate an initial Burrows-Wheeler range - with respect to the first INT characters of the query. Ftab is 4^INT+1 - bytes. [10] - --ntoa N conversion. Convert Ns to As before building the index. Otherwise, Ns are - simply excluded from the index and Bowtie will not find alignments that - overlap them. [off] - --big Endianness. Endianness to use when serializing integers to the index file. [off] - --little Endianness. [--little] - --seed INT Random seed. Use INT as the seed for the pseudo-random number generator. [off] - --cutoff INT Cutoff. Index only the first INT bases of the reference sequences (cumulative - across sequences) and ignore the rest. [off] + -a No auto behavior. Disable the default behavior where bowtie automatically + selects values for --bmax/--bmaxdivn/--dcv/--packed parameters according + to the memory available. [off] + --packed Packing. Use a packed representation for DNA strings. [auto] + --bmax INT Suffix maximum. The maximum number of suffixes allowed in a block. [auto] + --bmaxdivn INT Suffix maximum fraction. The maximum number of suffixes allowed in a block + expressed as a fraction of the length of the reference. [4] + --dcv INT Difference-cover sample. Use INT as the period for the difference-cover + sample. [1024] + --nodc INT No difference-cover sample. Disable the difference-cover sample. [off] + -r No reference indexes. Do not build the NAME.3.ebwt and NAME.4.ebwt portions + of the index. Used only for paired-end alignment. [off] + -o Offrate. How many Burrows-Wheeler rows get marked by the indexer. The + indexer will mark every 2^INT rows. The marked rows correspond to rows on + the genome. [5] + -t INT Ftab. The lookup table used to calculate an initial Burrows-Wheeler range + with respect to the first INT characters of the query. Ftab is 4^INT+1 + bytes. [10] + --ntoa N conversion. Convert Ns to As before building the index. Otherwise, Ns are + simply excluded from the index and Bowtie will not find alignments that + overlap them. [off] + --big Endianness. Endianness to use when serializing integers to the index file. [off] + --little Endianness. [--little] + --seed INT Random seed. Use INT as the seed for the pseudo-random number generator. [off] + --cutoff INT Cutoff. Index only the first INT bases of the reference sequences (cumulative + across sequences) and ignore the rest. [off] For aligning (bowtie):: - -s INT Skip. Do not align the first INT reads or pairs in the input. [off] - -u INT Align limit. Only align the first INT reads/pairs from the input. [no limit] - -5 INT High-quality trim. Trim INT bases from the high-quality (left) end of each - read before alignment. [0] - -3 INT Low-quality trim. Trim INT bases from the low-quality (right) end of each - read before alignment. [0] - -n INT Mismatch seed. Maximum number of mismatches permitted in the seed (defined - with seed length option). Can be 0, 1, 2, or 3. [2] - -e INT Mismatch quality. Maximum permitted total of quality values at mismatched - read positions. Bowtie rounds quality values to the nearest 10 and saturates - at 30. [70] - -l INT Seed length. The number of bases on the high-quality end of the read to - which the -n ceiling applies. Must be at least 5. [28] - --nomaqround Suppress MAQ rounding. Values are internally rounded to the nearest 10 and - saturate at 30. This options turns off that rounding. [off] - -v INT MAQ- or SOAP-like alignment policy. This option turns off the default - MAQ-like alignment policy in favor of a SOAP-like one. End-to-end alignments - with at most INT mismatches. [off] - -I INT Minimum insert. The minimum insert size for valid paired-end alignments. - Does checking on untrimmed reads if -5 or -3 is used. [0] - -X INT Maximum insert. The maximum insert size for valid paired-end alignments. - Does checking on untrimmed reads if -5 or -3 is used. [250] - --fr Mate orientation. The upstream/downstream mate orientations for a valid - paired-end alignment against the forward reference strand. [--fr] - --rf Mate orientation. [off] - --ff Mate orientation. [off] - --pairtries INT Maximum alignment attempts for paired-end data. [100] - --nofw No forward aligning. Choosing this option means that Bowtie will not attempt - to align against the forward reference strand. [off] - --norc No reverse-complement aligning. Setting this will mean that Bowtie will not - attempt to align against the reverse-complement reference strand. [off] - --maxbts INT Maximum backtracks. The maximum number of backtracks permitted when aligning - a read in -n 2 or -n 3 mode. [125 without --best] [800 with --best] - -y Try hard. Try as hard as possible to find valid alignments when they exist, - including paired-end alignments. [off] - --chunkmbs INT Thread memory. The number of megabytes of memory a given thread is given to - store path descriptors in --best mode. [32] - -k INT Valid alignments. The number of valid alignments per read or pair. [off] - -a All valid alignments. Choosing this means that all valid alignments per read - or pair will be reported. [off] - -m INT Suppress alignments. Suppress all alignments for a particular read or pair - if more than INT reportable alignments exist for it. [no limit] - --best Best mode. Make Bowtie guarantee that reported singleton alignments are - "best" in terms of stratum (the number of mismatches) and quality values at - mismatched position. [off] - --strata Best strata. When running in best mode, report alignments that fall into the - best stratum if there are ones falling into more than one. [off] - -o INT Offrate override. Override the offrate of the index with INT. Some row - markings are discarded when index read into memory. INT must be greater than - the value used to build the index (default: 5). [off] - --seed INT Random seed. Use INT as the seed for the pseudo-random number generator. [off] - --snpphred INT Use INT as the SNP penalty for decoding colorspace alignments. True ratio of - SNPs per base in the subject genome. [see --snpfrac] - --snpfrac DEC Use DEC as the estimated ratio of SNPs per base when decoding colorspace - alignments. [0.001] - --col-keepends Keep the extreme-end nucleotides and qualities when decoding colorspace - alignments. [off] + -s INT Skip. Do not align the first INT reads or pairs in the input. [off] + -u INT Align limit. Only align the first INT reads/pairs from the input. [no limit] + -5 INT High-quality trim. Trim INT bases from the high-quality (left) end of each + read before alignment. [0] + -3 INT Low-quality trim. Trim INT bases from the low-quality (right) end of each + read before alignment. [0] + -n INT Mismatch seed. Maximum number of mismatches permitted in the seed (defined + with seed length option). Can be 0, 1, 2, or 3. [2] + -e INT Mismatch quality. Maximum permitted total of quality values at mismatched + read positions. Bowtie rounds quality values to the nearest 10 and saturates + at 30. [70] + -l INT Seed length. The number of bases on the high-quality end of the read to + which the -n ceiling applies. Must be at least 5. [28] + --nomaqround Suppress MAQ rounding. Values are internally rounded to the nearest 10 and + saturate at 30. This options turns off that rounding. [off] + -v INT MAQ- or SOAP-like alignment policy. This option turns off the default + MAQ-like alignment policy in favor of a SOAP-like one. End-to-end alignments + with at most INT mismatches. [off] + -I INT Minimum insert. The minimum insert size for valid paired-end alignments. + Does checking on untrimmed reads if -5 or -3 is used. [0] + -X INT Maximum insert. The maximum insert size for valid paired-end alignments. + Does checking on untrimmed reads if -5 or -3 is used. [250] + --fr Mate orientation. The upstream/downstream mate orientations for a valid + paired-end alignment against the forward reference strand. [--fr] + --rf Mate orientation. [off] + --ff Mate orientation. [off] + --pairtries INT Maximum alignment attempts for paired-end data. [100] + --nofw No forward aligning. Choosing this option means that Bowtie will not attempt + to align against the forward reference strand. [off] + --norc No reverse-complement aligning. Setting this will mean that Bowtie will not + attempt to align against the reverse-complement reference strand. [off] + --un FILENAME Write all reads that could not be aligned to file [off] + --max FILENAME Write all reads with a number of valid alignments exceeding the limit + set with the -m option to file [off] + --maxbts INT Maximum backtracks. The maximum number of backtracks permitted when aligning + a read in -n 2 or -n 3 mode. [125 without --best] [800 with --best] + -y Try hard. Try as hard as possible to find valid alignments when they exist, + including paired-end alignments. [off] + --chunkmbs INT Thread memory. The number of megabytes of memory a given thread is given to + store path descriptors in --best mode. [32] + -k INT Valid alignments. The number of valid alignments per read or pair. [off] + -a All valid alignments. Choosing this means that all valid alignments per read + or pair will be reported. [off] + -m INT Suppress alignments. Suppress all alignments for a particular read or pair + if more than INT reportable alignments exist for it. [no limit] + --best Best mode. Make Bowtie guarantee that reported singleton alignments are + "best" in terms of stratum (the number of mismatches) and quality values at + mismatched position. [off] + --strata Best strata. When running in best mode, report alignments that fall into the + best stratum if there are ones falling into more than one. [off] + -o INT Offrate override. Override the offrate of the index with INT. Some row + markings are discarded when index read into memory. INT must be greater than + the value used to build the index (default: 5). [off] + --seed INT Random seed. Use INT as the seed for the pseudo-random number generator. [off] + --snpphred INT Use INT as the SNP penalty for decoding colorspace alignments. True ratio of + SNPs per base in the subject genome. [see --snpfrac] + --snpfrac DEC Use DEC as the estimated ratio of SNPs per base when decoding colorspace + alignments. [0.001] + --col-keepends Keep the extreme-end nucleotides and qualities when decoding colorspace + alignments. [off] diff --git a/tools/sr_mapping/bwa_wrapper.xml b/tools/sr_mapping/bwa_wrapper.xml index e51d3210ebb..f30d11d09f9 100644 --- a/tools/sr_mapping/bwa_wrapper.xml +++ b/tools/sr_mapping/bwa_wrapper.xml @@ -100,7 +100,7 @@ - + @@ -226,6 +226,12 @@ BWA accepts files in Sanger FASTQ format. Use the FASTQ Groomer to prepare your ------ +**A Note on Built-in Reference Genomes** + +Some genomes have multiple variants. If only one "type" of genome is listed, it is the Full version, which means that everything that came in the original genome data download (possibly with mitochondrial and plasmid DNA added if it wasn't already included). The Full version is available for every genome. Some genomes also come in the Canonical variant, which contains only the "canonical" (well-defined) chromosomes or segments, such as chr1-chr22, chrX, chrY, and chrM for human. Other variations include gender. These will come in the canonical form only, so the general Canonical variant is actually Canonical Female and the other is Canonical Male (identical to female excluding chrX). + +------ + **Outputs** The output is in SAM format, and has the following columns:: diff --git a/tools/sr_mapping/lastz_paired_reads_wrapper.xml b/tools/sr_mapping/lastz_paired_reads_wrapper.xml index 0d6a431e385..e8f1ca1dc5e 100644 --- a/tools/sr_mapping/lastz_paired_reads_wrapper.xml +++ b/tools/sr_mapping/lastz_paired_reads_wrapper.xml @@ -47,7 +47,7 @@ - + lastz diff --git a/tools/sr_mapping/lastz_wrapper.xml b/tools/sr_mapping/lastz_wrapper.xml index 8c51e0f517d..0fc13212772 100644 --- a/tools/sr_mapping/lastz_wrapper.xml +++ b/tools/sr_mapping/lastz_wrapper.xml @@ -129,7 +129,7 @@ - + diff --git a/tools/sr_mapping/srma_wrapper.xml b/tools/sr_mapping/srma_wrapper.xml index 2738b3fca7c..02c348f0d35 100644 --- a/tools/sr_mapping/srma_wrapper.xml +++ b/tools/sr_mapping/srma_wrapper.xml @@ -61,7 +61,7 @@ - +