Mercurial > repos > rnateam > bctools
changeset 58:bbbae1ee87e0 draft default tip
fix for flexbar with small data issue
author | rnateam |
---|---|
date | Tue, 16 Feb 2016 10:08:58 -0500 |
parents | 537657678b2b |
children | |
files | coords2clnt.xml extract_aln_ends.xml flexbar_no_split.xml flexbar_split_RR_bcs.xml flexbar_split_RYYR_bcs.xml merge_pcr_duplicates.py tool_dependencies.xml |
diffstat | 7 files changed, 45 insertions(+), 28 deletions(-) [+] |
line wrap: on
line diff
--- a/coords2clnt.xml Mon Feb 15 07:32:50 2016 -0500 +++ b/coords2clnt.xml Tue Feb 16 10:08:58 2016 -0500 @@ -1,7 +1,9 @@ <tool id="coords2clnt.py" name="Get crosslinked nucleotides" version="0.1.0"> <description>from full alignments</description> <requirements> - <requirement type="package" version="0.6.9">pybedtools</requirement> + <requirement type="package" version="2.24">bedtools</requirement> + <requirement type="package" version="0.7.4">pybedtools</requirement> + <requirement type="package" version="0.8.3">pysam</requirement> </requirements> <macros> <import>macros.xml</import>
--- a/extract_aln_ends.xml Mon Feb 15 07:32:50 2016 -0500 +++ b/extract_aln_ends.xml Tue Feb 16 10:08:58 2016 -0500 @@ -1,7 +1,8 @@ <tool id="extract_aln_ends.py" name="Extract alignment ends." version="0.2.0"> <description>from SAM or BAM.</description> <requirements> - <requirement type="package" version="0.6.9">pybedtools</requirement> + <requirement type="package" version="2.24">bedtools</requirement> + <requirement type="package" version="0.7.4">pybedtools</requirement> <requirement type="package" version="0.8.3">pysam</requirement> </requirements> <macros>
--- a/flexbar_no_split.xml Mon Feb 15 07:32:50 2016 -0500 +++ b/flexbar_no_split.xml Tue Feb 16 10:08:58 2016 -0500 @@ -16,7 +16,7 @@ <version_command>flexbar --version</version_command> - <command> + <command><![CDATA[ flexbar @@ -102,12 +102,12 @@ $cLogging.rndTags #end if - > $output; + && mv flexbar_1.fastq $output_1 + && mv flexbar_2.fastq $output_2 - mv flexbar_1.fastq $output_1; - mv flexbar_2.fastq $output_2; + && sleep 20 - </command> + ]]></command> <inputs>
--- a/flexbar_split_RR_bcs.xml Mon Feb 15 07:32:50 2016 -0500 +++ b/flexbar_split_RR_bcs.xml Tue Feb 16 10:08:58 2016 -0500 @@ -14,7 +14,7 @@ <version_command>flexbar --version</version_command> - <command> + <command><![CDATA[ flexbar @@ -49,14 +49,16 @@ --max-uncalled $maxUncalled --min-read-length $minReadLen - > $output; + > $output - mv flexbar_barcode_repA_1.fastq $output_repA_1; - mv flexbar_barcode_repA_2.fastq $output_repA_2; - mv flexbar_barcode_repB_1.fastq $output_repB_1; - mv flexbar_barcode_repB_2.fastq $output_repB_2; + && mv flexbar_barcode_repA_1.fastq $output_repA_1 + && mv flexbar_barcode_repA_2.fastq $output_repA_2 + && mv flexbar_barcode_repB_1.fastq $output_repB_1 + && mv flexbar_barcode_repB_2.fastq $output_repB_2 - </command> + && sleep 20 + + ]]></command> <inputs>
--- a/flexbar_split_RYYR_bcs.xml Mon Feb 15 07:32:50 2016 -0500 +++ b/flexbar_split_RYYR_bcs.xml Tue Feb 16 10:08:58 2016 -0500 @@ -14,7 +14,7 @@ <version_command>flexbar --version</version_command> - <command> + <command><![CDATA[ flexbar @@ -49,14 +49,16 @@ --max-uncalled $maxUncalled --min-read-length $minReadLen - > $output; + > $output - mv flexbar_barcode_repA_1.fastq $output_repA_1; - mv flexbar_barcode_repA_2.fastq $output_repA_2; - mv flexbar_barcode_repB_1.fastq $output_repB_1; - mv flexbar_barcode_repB_2.fastq $output_repB_2; + && mv flexbar_barcode_repA_1.fastq $output_repA_1 + && mv flexbar_barcode_repA_2.fastq $output_repA_2 + && mv flexbar_barcode_repB_1.fastq $output_repB_1 + && mv flexbar_barcode_repB_2.fastq $output_repB_2 - </command> + && sleep 20 + + ]]></command> <inputs>
--- a/merge_pcr_duplicates.py Mon Feb 15 07:32:50 2016 -0500 +++ b/merge_pcr_duplicates.py Tue Feb 16 10:08:58 2016 -0500 @@ -108,8 +108,15 @@ check_call(syscall2, shell=True) # join barcode library and alignments - syscall3 = "cat " + args.bclib + " | awk 'BEGIN{OFS=\"\\t\"}NR%4==1{gsub(/^@/,\"\"); id=$1}NR%4==2{bc=$1}NR%4==3{print id,bc}' | sort --compress-program=gzip -k1,1 | join -1 1 -2 4 - " + tmpdir + "/alns.csv " + " | awk 'BEGIN{OFS=\"\\t\"}$4!~/N/{print $3,$4,$5,$2,$6,$7}' | datamash --sort -g 1,2,3,4,6 count 4 | awk 'BEGIN{OFS=\"\\t\"}$4!~/N/{print $1,$2,$3,$4,$6,$5}' > " + args.outfile - # 'chrom', 'start', 'stop', 'bc', 'ndupes', 'strand' + # after join: id, bc, chr, start, stop, mapscore, strand + # after datamash: bc, chr, start, stop, strand, ndupes, idrepresentative + syscall3 = "cat " + \ + args.bclib + \ + " | awk 'BEGIN{OFS=\"\\t\"}NR%4==1{gsub(/^@/,\"\"); id=$1}NR%4==2{bc=$1}NR%4==3{print id,bc}' " + \ + " | sort --compress-program=gzip -k1,1 | join -1 1 -2 4 - " + tmpdir + "/alns.csv " + \ + " | awk 'BEGIN{OFS=\"\\t\"}$2!~/N/{print $1,$2,$3,$4,$5,$6,$7}' " + \ + " | datamash --sort -g 2,3,4,5,7 count 2 first 1 " + \ + " | awk 'BEGIN{OFS=\"\\t\"}{print $2,$3,$4,$7,$6,$5}' > " + args.outfile check_call(syscall3, shell=True) finally: logging.debug("removed tmpdir: " + tmpdir)
--- a/tool_dependencies.xml Mon Feb 15 07:32:50 2016 -0500 +++ b/tool_dependencies.xml Tue Feb 16 10:08:58 2016 -0500 @@ -6,12 +6,12 @@ <!-- <package name="biopython" version="1.65"> <repository name="package_biopython_1_65" owner="biopython"/> </package> --> - <!-- <package name="pybedtools" version="0.7.4"> - <repository name="package_python_2_7_pybedtools_0_7_4" owner="iuc"/> + <package name="pybedtools" version="0.7.4"> + <repository changeset_revision="c763d117e75a" name="package_python_2_7_pybedtools_0_7_4" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" /> + </package> + <!-- <package name="pybedtools" version="0.6.9"> + <repository name="package_python_2_7_pybedtools_0_6_9" owner="iuc"/> </package> --> - <package name="pybedtools" version="0.6.9"> - <repository changeset_revision="c4641c3a869f" name="package_python_2_7_pybedtools_0_6_9" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" /> - </package> <package name="pysam" version="0.8.3"> <repository changeset_revision="7ac80143c68d" name="package_python_2_7_pysam_0_8_3" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" /> </package> @@ -30,5 +30,8 @@ <package name="datamash" version="1.0.6"> <repository changeset_revision="df06a5e1ed6f" name="package_datamash_1_0_6" owner="agordon" toolshed="https://testtoolshed.g2.bx.psu.edu" /> </package> + <package name="bedtools" version="2.24"> + <repository changeset_revision="e6f4a7398a47" name="package_bedtools_2_24" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" /> + </package> </tool_dependency>