Mercurial > repos > yhoogstrate > varscan_mpileup2snp_from_bam
changeset 35:3bb39a9058d9
Uploaded
| author | yhoogstrate |
|---|---|
| date | Tue, 18 Feb 2014 11:13:41 -0500 |
| parents | 7946b09020e0 |
| children | b578aaede79b |
| files | all_fasta.loc.sample tool-data/all_fasta.loc.sample tool_data_table_conf.xml.sample varscan_mpileup2snp_from_bam.xml |
| diffstat | 4 files changed, 31 insertions(+), 37 deletions(-) [+] |
line wrap: on
line diff
--- a/all_fasta.loc.sample Tue Feb 18 05:29:59 2014 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,18 +0,0 @@ -#This file lists the locations and dbkeys of all the fasta files -#under the "genome" directory (a directory that contains a directory -#for each build). The script extract_fasta.py will generate the file -#all_fasta.loc. This file has the format (white space characters are -#TAB characters): -# -#<unique_build_id> <dbkey> <display_name> <file_path> -# -#So, all_fasta.loc could look something like this: -# -#apiMel3 apiMel3 Honeybee (Apis mellifera): apiMel3 /path/to/genome/apiMel3/apiMel3.fa -#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /path/to/genome/hg19/hg19canon.fa -#hg19full hg19 Human (Homo sapiens): hg19 Full /path/to/genome/hg19/hg19full.fa -# -#Your all_fasta.loc file should contain an entry for each individual -#fasta file. So there will be multiple fasta files for each build, -#such as with hg19 above. -#
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/all_fasta.loc.sample Tue Feb 18 11:13:41 2014 -0500 @@ -0,0 +1,18 @@ +#This file lists the locations and dbkeys of all the fasta files +#under the "genome" directory (a directory that contains a directory +#for each build). The script extract_fasta.py will generate the file +#all_fasta.loc. This file has the format (white space characters are +#TAB characters): +# +#<unique_build_id> <dbkey> <display_name> <file_path> +# +#So, all_fasta.loc could look something like this: +# +#apiMel3 apiMel3 Honeybee (Apis mellifera): apiMel3 /path/to/genome/apiMel3/apiMel3.fa +#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /path/to/genome/hg19/hg19canon.fa +#hg19full hg19 Human (Homo sapiens): hg19 Full /path/to/genome/hg19/hg19full.fa +# +#Your all_fasta.loc file should contain an entry for each individual +#fasta file. So there will be multiple fasta files for each build, +#such as with hg19 above. +#
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Tue Feb 18 11:13:41 2014 -0500 @@ -0,0 +1,5 @@ +<?xml version="1.0"?> +<table name="all_fasta" comment_char="#"> + <columns>name, dbkey, display_name, value</columns> + <file path="tool-data/all_fasta.loc.sample" /> +</table> \ No newline at end of file
--- a/varscan_mpileup2snp_from_bam.xml Tue Feb 18 05:29:59 2014 -0500 +++ b/varscan_mpileup2snp_from_bam.xml Tue Feb 18 11:13:41 2014 -0500 @@ -9,21 +9,6 @@ #if $reference_genome_source.source_select == "attribute" and len({ alignment.metadata.dbkey:True for alignment in $alignments }.keys()) != 1 echo "Invalid number of dbkeys are found: ${ len({ alignment.metadata.dbkey:True for alignment in $alignments }.keys()) }, while only one should be used. Make sure that the alignments are done on the same reference genome and that 'tool-data/all_fasta.loc' is configured properly!" >&2 #else - - <!-- Development stuff - might be useful for later - #if $reference_genome_source.source_select == "indexed_filtered" - echo "USED FASTA = $reference_genome_source.reference_genome" - #else if $reference_genome_source.source_select == "indexed_all" - echo "USED FASTA = $reference_genome_source.reference_genome" - #else if $reference_genome_source.source_select == "history" - echo "USED FASTA = $reference_genome_source.reference_genome" - #else - echo "USED FASTA = ${ filter( lambda x: str( x[0] ) == str( { alignment.metadata.dbkey:True for alignment in $alignments }.keys()[0] ), $__app__.tool_data_tables[ 'all_fasta' ].get_fields() )[0][-1] }" - #end if - - ; - --> - samtools-mpileup-parallel mpileup -t $samtools_threads -f @@ -93,9 +78,9 @@ $varscan_variants #end if - $varscan_output_vcf + --output-vcf $varscan_output_vcf - > $output_table + > $snv_output #end if </command> @@ -199,11 +184,15 @@ </when> </conditional> - <param type="boolean" name="varscan_output_vcf" falsevalue=" --output-vcf 0" truevalue=" --output-vcf 1" label="VarScan: If set to 1, outputs in VCF format" /> + <param type="boolean" name="varscan_output_vcf" falsevalue="0" truevalue="1" label="VarScan: If set to 1, outputs in VCF format" /> </inputs> <outputs> - <data format="tabular" name="output_table" label="${tool.name} on ${', '.join([ str(a.hid)+': '+a.name for a in $alignments ])}" /> + <data format="tabular" name="snv_output" label="${tool.name} on ${', '.join([ str(a.hid)+': '+a.name for a in $alignments ])}"> + <change_format> + <when input="varscan_output_vcf" value="1" format="vcf" /> + </change_format> + </data> </outputs> <help>