Mercurial > repos > devteam > picard
diff picard_SamToFastq.xml @ 5:3d4f1fa26f0e draft
Uploaded
| author | devteam |
|---|---|
| date | Tue, 16 Dec 2014 19:03:21 -0500 |
| parents | 9227b8c3093b |
| children | 3a3234d7a2e8 |
line wrap: on
line diff
--- a/picard_SamToFastq.xml Fri Feb 21 12:07:49 2014 -0500 +++ b/picard_SamToFastq.xml Tue Dec 16 19:03:21 2014 -0500 @@ -1,189 +1,200 @@ -<tool id="picard_SamToFastq" name="SAM to FASTQ" version="1.56.1" force_history_refresh="True"> - <description>creates a FASTQ file</description> - <requirements><requirement type="package" version="1.56.0">picard</requirement></requirements> - <!-- Dan Blankenberg --> - <command interpreter="python">picard_SamToFastq_wrapper.py - -p ' - java -XX:DefaultMaxRAMFraction=1 -XX:+UseParallelGC - -jar "\$JAVA_JAR_PATH/SamToFastq.jar" - INPUT="${input_sam}" - VALIDATION_STRINGENCY="LENIENT" +<tool name="SamToFastq" id="picard_SamToFastq" version="1.126.0"> + <description>extract reads and qualities from SAM/BAM dataset and convert to fastq</description> + <requirements> + <requirement type="package" version="1.126.0">picard</requirement> + </requirements> + + <macros> + <import>picard_macros.xml</import> + </macros> + + <command> + + echo "BAM" > $report && ## This is necessary for output dataset detection (see output tags below) + + @java_options@ + + java -jar \$JAVA_JAR_PATH/picard.jar + SamToFastq + + INPUT="${inputFile}" + + #if str( $output_per_rg ) == "true": + OUTPUT_PER_RG=true + OUTPUT_DIR=. + #elif str( $output_per_rg ) == "false" and str( $interleave ) == "false": + FASTQ=READ1.fastq + SECOND_END_FASTQ=READ2.fastq + UNPAIRED_FASTQ=UNPAIRED_READS.fastq + #elif str( $output_per_rg ) == "false" and str( $interleave ) == "true": + FASTQ=INTERLEAVED.fastq + #end if + RE_REVERSE="${re_reverse}" + INTERLEAVE="${interleave}" INCLUDE_NON_PF_READS="${include_non_pf_reads}" - #if str( $clipping_attribute ): - CLIPPING_ATTRIBUTE="${clipping_attribute}" - #end if - #if str( $clipping_action ): - CLIPPING_ACTION="${clipping_action}" + CLIPPING_ATTRIBUTE="${clipping_attribute}" + CLIPPING_ACTION="${clipping_action}" + READ1_TRIM="${read1_trim}" + + #if int($read1_max_bases_to_write) > -1: + READ1_MAX_BASES_TO_WRITE="${read1_max_bases_to_write}" #end if - #if str( $read1_trim ): - READ1_TRIM="${read1_trim}" + + READ2_TRIM="${read2_trim}" + + #if int($read2_max_bases_to_write) > -1: + READ2_MAX_BASES_TO_WRITE="${read2_max_bases_to_write}" #end if - #if str( $read1_max_bases_to_write ): - READ1_MAX_BASES_TO_WRITE="${read1_max_bases_to_write}" - #end if + INCLUDE_NON_PRIMARY_ALIGNMENTS="${include_non_primary_alignments}" - #if str( $output_per_read_group_selector ) == 'per_sam_file': - ##OUTPUT_PER_RG=false - FASTQ="${output_fastq1}" - - #if str( $single_paired_end_type.single_paired_end_type_selector ) == 'paired': - SECOND_END_FASTQ="${output_fastq2}" - #if str( $single_paired_end_type.read2_trim ): - READ2_TRIM="${single_paired_end_type.read2_trim}" - #end if - #if str( $single_paired_end_type.read2_max_bases_to_write ): - READ2_MAX_BASES_TO_WRITE="${single_paired_end_type.read2_max_bases_to_write}" - #end if - #end if - ' - #else: - OUTPUT_PER_RG=true - #if str( $single_paired_end_type.single_paired_end_type_selector ) == 'paired': - ' - --read_group_file_2 "${output_fastq2}" - --file_id_2 "${output_fastq2.id}" - -p ' - #if str( $single_paired_end_type.read2_trim ): - READ2_TRIM="${single_paired_end_type.read2_trim}" - #end if - #if str( $single_paired_end_type.read2_max_bases_to_write ): - READ2_MAX_BASES_TO_WRITE="${single_paired_end_type.read2_max_bases_to_write}" - #end if - #end if - ' - --read_group_file_1 "${output_fastq1}" - --new_files_path "${__new_file_path__}" - --file_id_1 "${output_fastq1.id}" - #end if + + VALIDATION_STRINGENCY="${validation_stringency}" + QUIET=true + VERBOSITY=ERROR + </command> <inputs> - <param name="input_sam" type="data" format="sam,bam" label="BAM/SAM file" /> - <param name="read1_trim" type="integer" value="" optional="True" label="The number of bases to trim from the beginning of read 1." /> - <param name="read1_max_bases_to_write" type="integer" optional="True" value="" label="The maximum number of bases to write from read 1 after trimming." /> - <param name="output_per_read_group_selector" type="select" label="Output per read group"> - <option value="per_sam_file" selected="True">Per BAM/SAM file</option> - <option value="per_read_group">Per Read Group</option> - </param> - <conditional name="single_paired_end_type"> - <param name="single_paired_end_type_selector" type="select" label="Single or Paired end"> - <option value="single" selected="True">Single</option> - <option value="paired">Paired end</option> - </param> - <when value="single"> - <!-- nothing yet --> - </when> - <when value="paired"> - <param name="read2_trim" type="integer" value="" optional="True" label="The number of bases to trim from the beginning of read 2." /> - <param name="read2_max_bases_to_write" type="integer" optional="True" value="" label="The maximum number of bases to write from read 2 after trimming." /> - </when> - </conditional> - <param name="re_reverse" type="boolean" truevalue="true" falsevalue="false" checked="True" label="Re-reverse bases and qualities of reads on negative strand"/> - <param name="include_non_pf_reads" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Include non-PF reads from the SAM file into the output FASTQ files."/> - <param name="clipping_attribute" type="text" value="" label="The attribute that stores the position at which the SAM record should be clipped" help="Leave blank for null" /> - <param name="clipping_action" type="text" value="" label="The action that should be taken with clipped reads" help="'X' means the reads and qualities should be trimmed at the clipped position; 'N' means the bases should be changed to Ns in the clipped region; and any integer means that the base qualities should be set to that value in the clipped region. Leave blank for null" /> - <param name="include_non_primary_alignments" type="boolean" truevalue="true" falsevalue="false" checked="False" label="If true, include non-primary alignments in the output." help="Support of non-primary alignments in SamToFastq is not comprehensive, so there may be exceptions if this is set to true and there are paired reads with non-primary alignments."/> - </inputs> + <param format="sam,bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/> + <param name="output_per_rg" type="boolean" checked="False" label="Do you want to output a fastq file per read group (two fastq files per read group if the group is paired)" help="OUTPUT_PER_RG; default=False"/> + <param name="re_reverse" type="boolean" checked="True" label="Re-reverse bases and qualities of reads with negative strand flag set before writing them to fastq" help="RE_REVERSE; default=True"/> + <param name="interleave" type="boolean" label="Will generate an interleaved fastq if paired, each line will have /1 or /2 to describe which end it came from" help="INTERLEAVE; default=False"/> + <param name="include_non_pf_reads" type="boolean" label="Include non-PF reads from the SAM/BAM dataset into the output FASTQ" help="INCLUDE_NON_PF_READS; PF means 'passes filtering'. Reads whose 'not passing quality controls' flag is set are non-PF reads; default=False"/> + <param name="clipping_attribute" type="text" size="4" value="null" label="The attribute that stores the position at which the SAM/BAM record should be clipped" help="CLIPPING_ATTRIBUTE; default=null"/> + <param name="clipping_action" type="text" size="10" value="null" label="The action that should be taken with clipped reads: 'X' means the reads and qualities should be trimmed at the clipped position; 'N' means the bases should be changed to Ns in the clipped region; and any integer means that the base qualities should be set to that value in the clipped region" help="CLIPPING_ACTION; default=null"/> + <param name="read1_trim" type="integer" value="0" min="0" label="The number of bases to trim from the beginning of read 1" help="READ1_TRIM; default=0"/> + <param name="read1_max_bases_to_write" type="integer" value="-1" label="The maximum number of bases to write from read 1 after trimming" help="READ1_MAX_BASES_TO_WRITE; If there are fewer than this many bases left after trimming, all will be written. If this value is null then all bases left after trimming will be written; default=null (-1)"/> + <param name="read2_trim" type="integer" value="0" min="0" label="The number of bases to trim from the beginning of read 2" help="READ2_TRIM; default=0"/> + <param name="read2_max_bases_to_write" type="integer" value="-1" label="The maximum number of bases to write from read 2 after trimming" help="READ2_MAX_BASES_TO_WRITE; If there are fewer than this many bases left after trimming, all will be written. If this value is null then all bases left after trimming will be written; default=null (-1)"/> + <param name="include_non_primary_alignments" type="boolean" label="If true, include non-primary alignments in the output" help="INCLUDE_NON_PRIMARY_ALIGNMENTS; Support of non-primary alignments in SamToFastq is not comprehensive, so there may be exceptions if this is set to true and there are paired reads with non-primary alignments; default=False"/> + + <expand macro="VS" /> + + </inputs> + <outputs> - <data format="fastqsanger" name="output_fastq1" label="${tool.name} on ${on_string}: FASTQ 1" /> - <data format="fastqsanger" name="output_fastq2" label="${tool.name} on ${on_string}: FASTQ 2" > - <filter>single_paired_end_type['single_paired_end_type_selector'] == 'paired'</filter> + <!-- here dataset discovery is based on fact that if OUTPUT_PER_RG=true this tool automatically adds .fastq extension to emitted files --> + <data format="txt" name="report" label="SamToFastq run" hidden="true"> + <discover_datasets pattern="(?P<designation>.+)\.fastq" ext="fastqsanger" visible="true"/> </data> </outputs> + <tests> - <test> - <param name="input_sam" value="bfast_out1.sam" ftype="sam" /> - <param name="output_per_read_group_selector" value="per_sam_file" /> - <param name="single_paired_end_type_selector" value="single" /> - <param name="read1_trim" value="" /> - <param name="read1_max_bases_to_write" value="" /> - <param name="re_reverse" value="True" /> - <param name="include_non_pf_reads" value="False" /> - <param name="clipping_action" value="" /> - <param name="clipping_attribute" value="" /> - <param name="include_non_primary_alignments" value="False" /> - <output name="output_fastq1" file="random_phiX_1.fastqsanger"/> - </test> - <test> - <param name="input_sam" value="bwa_wrapper_out3.sam" ftype="sam" /> - <param name="output_per_read_group_selector" value="per_sam_file" /> - <param name="single_paired_end_type_selector" value="paired" /> - <param name="read1_trim" value="" /> - <param name="read1_max_bases_to_write" value="" /> - <param name="read2_trim" value="" /> - <param name="read2_max_bases_to_write" value="" /> - <param name="re_reverse" value="True" /> - <param name="include_non_pf_reads" value="False" /> - <param name="clipping_action" value="" /> - <param name="clipping_attribute" value="" /> - <param name="include_non_primary_alignments" value="False" /> - <output name="output_fastq1" file="bwa_wrapper_in2.fastqsanger" lines_diff="64"/> <!-- 16 unaligned fastq blocks not present in original sam file --> - <output name="output_fastq2" file="bwa_wrapper_in3.fastqsanger" lines_diff="64"/> <!-- 16 unaligned fastq blocks not present in original sam file --> - </test> - <test> - <param name="input_sam" value="bwa_wrapper_out3.sam" ftype="sam" /> - <param name="output_per_read_group_selector" value="per_read_group" /> - <param name="single_paired_end_type_selector" value="paired" /> - <param name="read1_trim" value="" /> - <param name="read1_max_bases_to_write" value="" /> - <param name="read2_trim" value="" /> - <param name="read2_max_bases_to_write" value="" /> - <param name="re_reverse" value="True" /> - <param name="include_non_pf_reads" value="False" /> - <param name="clipping_action" value="" /> - <param name="clipping_attribute" value="" /> - <param name="include_non_primary_alignments" value="False" /> - <output name="output_fastq1" file="bwa_wrapper_in2.fastqsanger" lines_diff="64"/> <!-- 16 unaligned fastq blocks not present in original sam file --> - <output name="output_fastq2" file="bwa_wrapper_in3.fastqsanger" lines_diff="64"/> <!-- 16 unaligned fastq blocks not present in original sam file --> - </test> + <test> + <param name="inputFile" value="picard_SamToFastq.bam" ftype="bam"/> + <param name="output_per_rg" value="false"/> + <param name="re_reverse" value="true"/> + <param name="interleave" value="true"/> + <param name="include_non_pf_reads" value="false"/> + <param name="clipping_attribute" value="null" /> + <param name="clipping_action" value="null" /> + <param name="read1_trim" value="0" /> + <param name="read1_max_bases_to_write" value="-1"/> + <param name="read2_trim" value="0" /> + <param name="read2_max_bases_to_write" value="-1"/> + <param name="include_non_primary_alignments" value="false"/> + <output name="report"> + <assert_contents> + <has_line line="BAM" /> + </assert_contents> + <discovered_dataset designation="INTERLEAVED" file="picard_SamToFastq_test1.fq" ftype="fastqsanger"/> + </output> + </test> </tests> + + <stdio> + <exit_code range="1:" level="fatal"/> + </stdio> + <help> -**What it does** - -Picard: SamToFastq converts SAM files to FASTQ files. -Extracts read sequences and qualities from the input SAM/BAM file and writes them into the output file in Sanger fastq format. In the RC mode (default is True), if the read is aligned and the alignment is to the reverse strand on the genome, the read's sequence from input SAM file will be reverse-complemented prior to writing it to fastq in order restore correctly the original read sequence as it was generated by the sequencer. +**Purpose** ------- - -Please cite the website "http://picard.sourceforge.net". +Extracts read sequences and qualities from the input SAM/BAM dataset and outputs them in Sanger fastq format. In the RE_REVERSE=True mode (default behavior), if the read is aligned and the alignment is to the reverse strand on the genome, the read's sequence from input SAM.BAM dataset will be reverse-complemented prior to writing it to fastq in order restore correctly the original read sequence as it was generated by the sequencer. ------- +----- +.. class:: warningmark -**Input formats** +**DANGER: Multiple Outputs** -FastqToSam accepts SAM input files, see http://samtools.sourceforge.net for more details. +Generating per readgroup fastq (setting **OUTPUT_PER_RG** to True) may produce very large numbers of outputs. Know what you are doing! ------- +@dataset_collections@ -**Outputs** +@description@ -The output is in FASTQ format. If using Paired end data, 2 fastq files are created. - -------- - -**FastqToSam settings** - -This is list of SamToFastq options:: + FASTQ=File + F=File Output fastq file (single-end fastq or, if paired, first end of the pair fastq). + Required. Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG) + + SECOND_END_FASTQ=File + F2=File Output fastq file (if paired, second end of the pair fastq). Default value: null. + Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG) + + UNPAIRED_FASTQ=File + FU=File Output fastq file for unpaired reads; may only be provided in paired-fastq mode Default + value: null. Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG) + + OUTPUT_PER_RG=Boolean + OPRG=Boolean Output a fastq file per read group (two fastq files per read group if the group is + paired). Default value: false. Possible values: {true, false} Cannot be used in + conjuction with option(s) SECOND_END_FASTQ (F2) UNPAIRED_FASTQ (FU) FASTQ (F) + + OUTPUT_DIR=File + ODIR=File Directory in which to output the fastq file(s). Used only when OUTPUT_PER_RG is true. + Default value: null. + + RE_REVERSE=Boolean + RC=Boolean Re-reverse bases and qualities of reads with negative strand flag set before writing them + to fastq Default value: true. Possible values: {true, false} + + INTERLEAVE=Boolean + INTER=Boolean Will generate an interleaved fastq if paired, each line will have /1 or /2 to describe + which end it came from Default value: false. Possible values: {true, false} + + INCLUDE_NON_PF_READS=Boolean + NON_PF=Boolean Include non-PF reads from the SAM file into the output FASTQ files. PF means 'passes + filtering'. Reads whose 'not passing quality controls' flag is set are non-PF reads. + Default value: false. Possible values: {true, false} - INPUT=File Input SAM/BAM file to extract reads from Required. - FASTQ=File Output fastq file (single-end fastq or, if paired, first end of the pair fastq). Required. Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG) - SECOND_END_FASTQ=File Output fastq file (if paired, second end of the pair fastq). Default value: null. Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG) - OUTPUT_PER_RG=Boolean Output a fastq file per read group (two fastq files per read group if the group is paired). Default value: false. This option can be set to 'null' to clear the default value. Possible values: {true, false} Cannot be used in conjuction with option(s) SECOND_END_FASTQ (F2) FASTQ (F) - OUTPUT_DIR=File Directory in which to output the fastq file(s). Used only when OUTPUT_PER_RG is true. Default value: null. - RE_REVERSE=Boolean Re-reverse bases and qualities of reads with negative strand flag set before writing them to fastq Default value: true. This option can be set to 'null' to clear the default value. Possible values: {true, false} - INCLUDE_NON_PF_READS=Boolean Include non-PF reads from the SAM file into the output FASTQ files. Default value: false. This option can be set to 'null' to clear the default value. Possible values: {true, false} - CLIPPING_ATTRIBUTE=String The attribute that stores the position at which the SAM record should be clipped Default value: null. - CLIPPING_ACTION=String The action that should be taken with clipped reads: 'X' means the reads and qualities should be trimmed at the clipped position; 'N' means the bases should be changed to Ns in the clipped region; and any integer means that the base qualities should be set to that value in the clipped region. Default value: null. - READ1_TRIM=Integer The number of bases to trim from the beginning of read 1. Default value: 0. This option can be set to 'null' to clear the default value. - READ1_MAX_BASES_TO_WRITE=Integer The maximum number of bases to write from read 1 after trimming. If there are fewer than this many bases left after trimming, all will be written. If this value is null then all bases left after trimming will be written. Default value: null. - READ2_TRIM=Integer The number of bases to trim from the beginning of read 2. Default value: 0. This option can be set to 'null' to clear the default value. - READ2_MAX_BASES_TO_WRITE=Integer The maximum number of bases to write from read 2 after trimming. If there are fewer than this many bases left after trimming, all will be written. If this value is null then all bases left after trimming will be written. Default value: null. - INCLUDE_NON_PRIMARY_ALIGNMENTS=Boolean If true, include non-primary alignments in the output. Support of non-primary alignments in SamToFastq is not comprehensive, so there may be exceptions if this is set to true and there are paired reads with non-primary alignments. Default value: false. This option can be set to 'null' to clear the default value. Possible values: {true, false} - + CLIPPING_ATTRIBUTE=String + CLIP_ATTR=String The attribute that stores the position at which the SAM record should be clipped Default + value: null. + + CLIPPING_ACTION=String + CLIP_ACT=String The action that should be taken with clipped reads: 'X' means the reads and qualities + should be trimmed at the clipped position; 'N' means the bases should be changed to Ns in + the clipped region; and any integer means that the base qualities should be set to that + value in the clipped region. Default value: null. + + READ1_TRIM=Integer + R1_TRIM=Integer The number of bases to trim from the beginning of read 1. Default value: 0. + + READ1_MAX_BASES_TO_WRITE=Integer + R1_MAX_BASES=Integer The maximum number of bases to write from read 1 after trimming. If there are fewer than + this many bases left after trimming, all will be written. If this value is null then all + bases left after trimming will be written. Default value: null. + + READ2_TRIM=Integer + R2_TRIM=Integer The number of bases to trim from the beginning of read 2. Default value: 0. + + READ2_MAX_BASES_TO_WRITE=Integer + R2_MAX_BASES=Integer The maximum number of bases to write from read 2 after trimming. If there are fewer than + this many bases left after trimming, all will be written. If this value is null then all + bases left after trimming will be written. Default value: null. + + INCLUDE_NON_PRIMARY_ALIGNMENTS=Boolean + If true, include non-primary alignments in the output. Support of non-primary alignments + in SamToFastq is not comprehensive, so there may be exceptions if this is set to true and + there are paired reads with non-primary alignments. Default value: false. + Possible values: {true, false} + +@more_info@ </help> </tool> + +