galaxy-commits November 2011

galaxy-commits@lists.galaxyproject.org

1 participants
121 discussions

commit/galaxy-central: dan: Remove no longer supported ROD datatypes from GATK tools (version 1.3).
by Bitbucket 21 Nov '11

21 Nov '11

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/945c7a47755f/ changeset: 945c7a47755f user: dan date: 2011-11-21 22:41:19 summary: Remove no longer supported ROD datatypes from GATK tools (version 1.3). affected #: 2 files diff -r 88afa15e556dfea22d34b0a78ffc3ebe162b64f7 -r 945c7a47755f4c468d0742ad02d43647a300565c tools/gatk/indel_realigner.xml --- a/tools/gatk/indel_realigner.xml +++ b/tools/gatk/indel_realigner.xml @@ -147,17 +147,17 @@ <option value="custom">Custom</option></param><when value="dbsnp"> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> + <param name="input_rod" type="data" format="vcf" label="ROD file" /></when><when value="snps"> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> + <param name="input_rod" type="data" format="vcf" label="ROD file" /></when><when value="indels"> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> + <param name="input_rod" type="data" format="vcf" label="ROD file" /></when><when value="custom"><param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> + <param name="input_rod" type="data" format="vcf" label="ROD file" /></when></conditional></repeat> diff -r 88afa15e556dfea22d34b0a78ffc3ebe162b64f7 -r 945c7a47755f4c468d0742ad02d43647a300565c tools/gatk/variant_recalibrator.xml --- a/tools/gatk/variant_recalibrator.xml +++ b/tools/gatk/variant_recalibrator.xml @@ -179,7 +179,7 @@ <option value="custom">Custom</option></param><when value="variant"> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant ROD file" /> + <param name="input_rod" type="data" format="vcf" label="Variant ROD file" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> @@ -198,7 +198,7 @@ </conditional></when><when value="comp"> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp" label="ROD file" /> + <param name="input_rod" type="data" format="vcf" label="ROD file" /><param name="custom_rod_name" type="text" value="Unnamed" label="ROD Name"/><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"> @@ -218,7 +218,7 @@ </conditional></when><when value="dbsnp"> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> + <param name="input_rod" type="data" format="vcf" label="ROD file" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> @@ -237,7 +237,7 @@ </conditional></when><when value="snps"> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> + <param name="input_rod" type="data" format="vcf" label="ROD file" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> @@ -256,7 +256,7 @@ </conditional></when><when value="hapmap"> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> + <param name="input_rod" type="data" format="vcf" label="ROD file" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> @@ -275,7 +275,7 @@ </conditional></when><when value="omni"> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> + <param name="input_rod" type="data" format="vcf" label="ROD file" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> @@ -294,7 +294,7 @@ </conditional></when><when value="indels"> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> + <param name="input_rod" type="data" format="vcf" label="ROD file" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> @@ -314,7 +314,7 @@ </when><when value="custom"><param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/> - <param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> + <param name="input_rod" type="data" format="vcf" label="ROD file" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: dan: Add SAMTools mpileup.
by Bitbucket 21 Nov '11

21 Nov '11

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/88afa15e556d/ changeset: 88afa15e556d user: dan date: 2011-11-21 22:30:34 summary: Add SAMTools mpileup. affected #: 8 files diff -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad -r 88afa15e556dfea22d34b0a78ffc3ebe162b64f7 datatypes_conf.xml.sample --- a/datatypes_conf.xml.sample +++ b/datatypes_conf.xml.sample @@ -159,6 +159,7 @@ <converter file="vcf_to_summary_tree_converter.xml" target_datatype="summary_tree"/><display file="igv/vcf.xml" /></datatype> + <datatype extension="bcf" type="galaxy.datatypes.binary:Binary" subclass="True"/><datatype extension="wsf" type="galaxy.datatypes.wsf:SnpFile" display_in_upload="true"/><datatype extension="velvet" type="galaxy.datatypes.assembly:Velvet" display_in_upload="false"/><datatype extension="wig" type="galaxy.datatypes.interval:Wiggle" display_in_upload="true"> diff -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad -r 88afa15e556dfea22d34b0a78ffc3ebe162b64f7 test-data/samtools/mpileup/samtools_mpileup_out_1.log --- /dev/null +++ b/test-data/samtools/mpileup/samtools_mpileup_out_1.log @@ -0,0 +1,2 @@ +[mpileup] 1 samples in 1 input files +<mpileup> Set max per-file depth to 8000 diff -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad -r 88afa15e556dfea22d34b0a78ffc3ebe162b64f7 test-data/samtools/mpileup/samtools_mpileup_out_1.pileup --- /dev/null +++ b/test-data/samtools/mpileup/samtools_mpileup_out_1.pileup @@ -0,0 +1,43 @@ +phiX174 1411 A 1 ^P. $ +phiX174 1412 G 3 .^D.^F. "$$ +phiX174 1413 C 5 ...^D.^F. """$$ +phiX174 1414 G 6 .....^F. #####$ +phiX174 1415 C 7 ......^F. %%%%%%& +phiX174 1416 C 8 .......^F. $$$$$$$$ +phiX174 1417 G 9 ........^F. "#######$ +phiX174 1418 T 10 .........^F. """""""""$ +phiX174 1419 G 10 .......... """""'&'%$ +phiX174 1420 G 10 .......... """""""""" +phiX174 1421 A 10 .......... """""""""" +phiX174 1422 T 10 .......... """""""""" +phiX174 1423 G 10 .......... """""""""# +phiX174 1424 C 10 ..A.AAAAAA %""""""""" +phiX174 1425 C 10 .......... $$$""""""" +phiX174 1426 T 10 .......... #####""""" +phiX174 1427 G 10 .......... ######"""" +phiX174 1428 A 10 .......... """""""""" +phiX174 1429 C 10 .......... ((((((&("" +phiX174 1430 C 10 .......... $$$$$$$$$" +phiX174 1431 G 10 .......... ########## +phiX174 1432 T 10 .......... """""""""" +phiX174 1433 A 10 .......... ########## +phiX174 1434 C 10 .......... ((((((&(%$ +phiX174 1435 C 10 .......... $$$$$$$$$$ +phiX174 1436 G 10 .......... ########## +phiX174 1437 A 10 .......... """""""""! +phiX174 1438 G 10 .......... """""####! +phiX174 1439 G 10 .......... """""""""! +phiX174 1440 C 10 .......... """""""""! +phiX174 1441 T 10 .......... """"""""#! +phiX174 1442 A 10 .......... $$$%%%&&%! +phiX174 1443 A 10 .-1C.-1C..-1C...... """""""""! +phiX174 1444 C 10 **.*...... &%"!"""""! +phiX174 1445 C 10 .......... &%&!%%%&%! +phiX174 1446 C 10 .......... """!"""""! +phiX174 1447 T 10 .$..$....... #"#!"""""! +phiX174 1448 A 8 .$..$..... #!#%%$$! +phiX174 1449 A 6 .$.$.... !""""! +phiX174 1450 T 4 .$... """! +phiX174 1451 G 3 .$.. #"! +phiX174 1452 A 2 .$. "! +phiX174 1453 G 1 .$ ! diff -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad -r 88afa15e556dfea22d34b0a78ffc3ebe162b64f7 test-data/samtools/mpileup/samtools_mpileup_out_2.bcf Binary file test-data/samtools/mpileup/samtools_mpileup_out_2.bcf has changed diff -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad -r 88afa15e556dfea22d34b0a78ffc3ebe162b64f7 tool_conf.xml.sample --- a/tool_conf.xml.sample +++ b/tool_conf.xml.sample @@ -371,6 +371,7 @@ <tool file="samtools/sam_to_bam.xml" /><tool file="samtools/bam_to_sam.xml" /><tool file="samtools/sam_merge.xml" /> + <tool file="samtools/samtools_mpileup.xml" /><tool file="samtools/sam_pileup.xml" /><tool file="samtools/pileup_parser.xml" /><tool file="samtools/pileup_interval.xml" /> diff -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad -r 88afa15e556dfea22d34b0a78ffc3ebe162b64f7 tool_data_table_conf.xml.sample --- a/tool_data_table_conf.xml.sample +++ b/tool_data_table_conf.xml.sample @@ -65,6 +65,11 @@ <columns>value, name, path</columns><file path="tool-data/perm_color_index.loc" /></table> +  + <table name="sam_fa_indexes" comment_char="#"> + <columns>line_type, value, path</columns> + <file path="tool-data/sam_fa_indices.loc" /> + </table><table name="picard_indexes" comment_char="#"><columns>value, dbkey, name, path</columns> diff -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad -r 88afa15e556dfea22d34b0a78ffc3ebe162b64f7 tools/samtools/samtools_mpileup.xml --- /dev/null +++ b/tools/samtools/samtools_mpileup.xml @@ -0,0 +1,213 @@ +<tool id="samtools_mpileup" name="MPileup" version="0.0.1"> + <description>SNP and indel caller</description> + <requirements> + <requirement type="package">samtools</requirement> + </requirements> + <command interpreter="python">samtools_wrapper.py + -p 'samtools mpileup' + --stdout "${output_log}" + #if $reference_source.reference_source_selector != "history": + -p '-f "${reference_source.ref_file.fields.path}"' + #else: + -d "-f" "${reference_source.ref_file}" "fa" "reference_input" + #end if + #for $i, $input_bam in enumerate( $reference_source.input_bams ): + -d " " "${input_bam.input_bam}" "${input_bam.input_bam.ext}" "bam_input_${i}" + -d "" "${input_bam.input_bam.metadata.bam_index}" "bam_index" "bam_input_${i}" ##hardcode galaxy ext type as bam_index + #end for + -p ' + #if str( $advanced_options.advanced_options_selector ) == "advanced": + ${advanced_options.skip_anomalous_read_pairs} + ${advanced_options.disable_probabilistic_realignment} + -C "${advanced_options.coefficient_for_downgrading}" + -d "${advanced_options.max_reads_per_bam}" + ${advanced_options.extended_BAQ_computation} + #if str( $advanced_options.position_list ) != 'None': + -l "${advanced_options.position_list}" + #end if + -q "${advanced_options.minimum_mapping_quality}" + -Q "${advanced_options.minimum_base_quality}" + #if str( $advanced_options.region_string ): + -r "${advanced_options.region_string}" + #end if + ${advanced_options.output_per_sample_read_depth} + ${advanced_options.output_per_sample_strand_bias_p_value} + #end if + #if str( $genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector ) == 'perform_genotype_likelihood_computation': + ##-g or -u + -g + -e "${genotype_likelihood_computation_type.gap_extension_sequencing_error_probability}" + -h "${genotype_likelihood_computation_type.coefficient_for_modeling_homopolymer_errors}" + #if str( $genotype_likelihood_computation_type.perform_indel_calling.perform_indel_calling_selector ) == 'perform_indel_calling': + -L "${genotype_likelihood_computation_type.perform_indel_calling.skip_indel_calling_above_sample_depth}" + #else: + -I + #end if + -o "${genotype_likelihood_computation_type.gap_open_sequencing_error_probability}" + #if len( $genotype_likelihood_computation_type.platform_list_repeat ): + -P "${ ",".join( [ str( platform.platform_entry ) for platform in $genotype_likelihood_computation_type.platform_list_repeat ] ) }" + #end if + #end if + > "${output_mpileup}" + ' + </command> + <inputs> + <conditional name="reference_source"> + <param name="reference_source_selector" type="select" label="Choose the source for the reference list"> + <option value="cached">Locally cached</option> + <option value="history">History</option> + </param> + <when value="cached"> + <repeat name="input_bams" title="BAM file" min="1"> + <param name="input_bam" type="data" format="bam" label="BAM file"> + <validator type="unspecified_build" /> + <validator type="dataset_metadata_in_data_table" table_name="sam_fa_indexes" metadata_name="dbkey" metadata_column="value" message="Sequences are not currently available for the specified build." /> + </param> + </repeat> + <param name="ref_file" type="select" label="Using reference genome"> + <options from_data_table="sam_fa_indexes"> +  + </options> + </param> + </when> + <when value="history"> + <repeat name="input_bams" title="BAM file" min="1"> + <param name="input_bam" type="data" format="bam" label="BAM file" > + <validator type="metadata" check="bam_index" message="Metadata missing, click the pencil icon in the history item and use the auto-detect feature to correct this issue."/> + </param> + </repeat> + <param name="ref_file" type="data" format="fasta" label="Using reference file" /> + </when> + </conditional> + + + <conditional name="genotype_likelihood_computation_type"> + <param name="genotype_likelihood_computation_type_selector" type="select" label="Genotype Likelihood Computation"> + <option value="perform_genotype_likelihood_computation">Perform genotype likelihood computation</option> + <option value="do_not_perform_genotype_likelihood_computation" selected="True">Do not perform genotype likelihood computation</option> + </param> + <when value="perform_genotype_likelihood_computation"> + <param name="gap_extension_sequencing_error_probability" type="integer" value="20" label="Phred-scaled gap extension sequencing error probability" /> + <param name="coefficient_for_modeling_homopolymer_errors" type="integer" value="100" label="Coefficient for modeling homopolymer errors." /> + <conditional name="perform_indel_calling"> + <param name="perform_indel_calling_selector" type="select" label="Perform INDEL calling"> + <option value="perform_indel_calling" selected="True">Perform INDEL calling</option> + <option value="do_not_perform_indel_calling">Do not perform INDEL calling</option> + </param> + <when value="perform_indel_calling"> + <param name="skip_indel_calling_above_sample_depth" type="integer" value="250" label="Skip INDEL calling if the average per-sample depth is above" /> + </when> + <when value="do_no_perform_indel_calling" /> + </conditional> + <param name="gap_open_sequencing_error_probability" type="integer" value="40" label="Phred-scaled gap open sequencing error probability" /> + <repeat name="platform_list_repeat" title="Platform for INDEL candidates"> + <param name="platform_entry" type="text" value="" label="Platform to use for INDEL candidates" /> + </repeat> + </when> + <when value="do_not_perform_genotype_likelihood_computation"> +  + </when> + </conditional> + <conditional name="advanced_options"> + <param name="advanced_options_selector" type="select" label="Set advanced options"> + <option value="basic" selected="True">Basic</option> + <option value="advanced">Advanced</option> + </param> + <when value="advanced"> + <param name="skip_anomalous_read_pairs" type="boolean" truevalue="-A" falsevalue="" checked="False" label="Do not skip anomalous read pairs in variant calling" /> + <param name="disable_probabilistic_realignment" type="boolean" truevalue="-B" falsevalue="" checked="False" label=" Disable probabilistic realignment for the computation of base alignment quality (BAQ)" /> + <param name="coefficient_for_downgrading" type="integer" value="0" label="Coefficient for downgrading mapping quality for reads containing excessive mismatches" /> + <param name="max_reads_per_bam" type="integer" value="250" label="Max reads per BAM" /> + <param name="extended_BAQ_computation" type="boolean" truevalue="-E" falsevalue="" checked="False" label="Extended BAQ computation" /> + <param name="position_list" type="data" format="bed" label="List of regions or sites on which to operate" optional="True" /> + <param name="minimum_mapping_quality" type="integer" value="0" label="Minimum mapping quality for an alignment to be used" /> + <param name="minimum_base_quality" type="integer" value="13" label="Minimum base quality for a base to be considered" /> + <param name="region_string" type="text" value="" label="Only generate pileup in region" /> + <param name="output_per_sample_read_depth" type="boolean" truevalue="-D" falsevalue="" checked="False" label="Output per-sample read depth" /> + <param name="output_per_sample_strand_bias_p_value" type="boolean" truevalue="-S" falsevalue="" checked="False" label="Output per-sample Phred-scaled strand bias P-value" /> + </when> + <when value="basic" /> + </conditional> + </inputs> + <outputs> + <data format="pileup" name="output_mpileup" label="${tool.name} on ${on_string}"> + <change_format> + <when input="genotype_likelihood_computation_type.genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" format="bcf" /> + </change_format> + </data> + <data format="txt" name="output_log" label="${tool.name} on ${on_string} (log)" /> + </outputs> + <tests> + <test> + <param name="reference_source_selector" value="history" /> + <param name="ref_file" value="phiX.fasta" ftype="fasta" /> + <param name="input_bam" value="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" /> + <param name="genotype_likelihood_computation_type_selector" value="do_not_perform_genotype_likelihood_computation" /> + <param name="advanced_options_selector" value="basic" /> + <output name="output_mpileup" file="samtools/mpileup/samtools_mpileup_out_1.pileup" /> + <output name="output_log" file="samtools/mpileup/samtools_mpileup_out_1.log" /> + </test> + <test> + <param name="reference_source_selector" value="history" /> + <param name="ref_file" value="phiX.fasta" ftype="fasta" /> + <param name="input_bam" value="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" /> + <param name="genotype_likelihood_computation_type_selector" value="perform_genotype_likelihood_computation" /> + <param name="gap_extension_sequencing_error_probability" value="20" /> + <param name="coefficient_for_modeling_homopolymer_errors" value="100" /> + <param name="perform_indel_calling_selector" value="perform_indel_calling" /> + <param name="skip_indel_calling_above_sample_depth" value="250" /> + <param name="gap_open_sequencing_error_probability" value="40" /> + <param name="platform_list_repeat" value="0" /> + <param name="advanced_options_selector" value="basic" /> + <output name="output_mpileup" file="samtools/mpileup/samtools_mpileup_out_2.bcf" /> + <output name="output_log" file="samtools/mpileup/samtools_mpileup_out_1.log" /> + </test> + </tests> + <help> +**What it does** + + Generate BCF or pileup for one or multiple BAM files. Alignment records are grouped by sample identifiers in @RG header lines. If sample identifiers are absent, each input file is regarded as one sample. + +------ + +**Settings**:: + + Input Options: + -6 Assume the quality is in the Illumina 1.3+ encoding. + -A Do not skip anomalous read pairs in variant calling. + -B Disable probabilistic realignment for the computation of base alignment quality (BAQ). BAQ is the Phred-scaled probability of a read base being misaligned. Applying this option greatly helps to reduce false SNPs caused by misalignments. + -b FILE List of input BAM files, one file per line [null] + -C INT Coefficient for downgrading mapping quality for reads containing excessive mismatches. Given a read with a phred-scaled probability q of being generated from the mapped position, the new mapping quality is about sqrt((INT-q)/INT)*INT. A zero value disables this functionality; if enabled, the recommended value for BWA is 50. [0] + -d INT At a position, read maximally INT reads per input BAM. [250] + -E Extended BAQ computation. This option helps sensitivity especially for MNPs, but may hurt specificity a little bit. + -f FILE The faidx-indexed reference file in the FASTA format. The file can be optionally compressed by razip. [null] + -l FILE BED or position list file containing a list of regions or sites where pileup or BCF should be generated [null] + -q INT Minimum mapping quality for an alignment to be used [0] + -Q INT Minimum base quality for a base to be considered [13] + -r STR Only generate pileup in region STR [all sites] + Output Options: + + -D Output per-sample read depth + -g Compute genotype likelihoods and output them in the binary call format (BCF). + -S Output per-sample Phred-scaled strand bias P-value + -u Similar to -g except that the output is uncompressed BCF, which is preferred for piping. + + Options for Genotype Likelihood Computation (for -g or -u): + + -e INT Phred-scaled gap extension sequencing error probability. Reducing INT leads to longer indels. [20] + -h INT Coefficient for modeling homopolymer errors. Given an l-long homopolymer run, the sequencing error of an indel of size s is modeled as INT*s/l. [100] + -I Do not perform INDEL calling + -L INT Skip INDEL calling if the average per-sample depth is above INT. [250] + -o INT Phred-scaled gap open sequencing error probability. Reducing INT leads to more indel calls. [40] + -P STR Comma dilimited list of platforms (determined by @RG-PL) from which indel candidates are obtained. It is recommended to collect indel candidates from sequencing technologies that have low indel error rate such as ILLUMINA. [all] + +------ + +**Citation** + +For the underlying tool, please cite `Li H, Handsaker B, Wysoker A, Fennell T, Ruan J, Homer N, Marth G, Abecasis G, Durbin R; 1000 Genome Project Data Processing Subgroup. The Sequence Alignment/Map format and SAMtools. Bioinformatics. 2009 Aug 15;25(16):2078-9. <http://www.ncbi.nlm.nih.gov/pubmed/19505943>`_ + +If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.* + + </help> +</tool> diff -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad -r 88afa15e556dfea22d34b0a78ffc3ebe162b64f7 tools/samtools/samtools_wrapper.py --- /dev/null +++ b/tools/samtools/samtools_wrapper.py @@ -0,0 +1,110 @@ +#!/usr/bin/env python +#Dan Blankenberg + +""" +A wrapper script for running SAMTools commands. +""" + +import sys, optparse, os, tempfile, subprocess, shutil +from string import Template + +GALAXY_EXT_TO_SAMTOOLS_EXT = { 'bam_index':'bam.bai', } #items not listed here will use the galaxy extension as-is +GALAXY_EXT_TO_SAMTOOLS_FILE_TYPE = GALAXY_EXT_TO_SAMTOOLS_EXT #for now, these are the same, but could be different if needed +DEFAULT_SAMTOOLS_PREFIX = "SAMTools_file" +CHUNK_SIZE = 2**20 #1mb + + +def cleanup_before_exit( tmp_dir ): + if tmp_dir and os.path.exists( tmp_dir ): + shutil.rmtree( tmp_dir ) + +def SAMTOOLS_filename_from_galaxy( galaxy_filename, galaxy_ext, target_dir = None, prefix = None ): + suffix = GALAXY_EXT_TO_SAMTOOLS_EXT.get( galaxy_ext, galaxy_ext ) + if prefix is None: + prefix = DEFAULT_SAMTOOLS_PREFIX + if target_dir is None: + target_dir = os.getcwd() + SAMTools_filename = os.path.join( target_dir, "%s.%s" % ( prefix, suffix ) ) + os.symlink( galaxy_filename, SAMTools_filename ) + return SAMTools_filename + +def SAMTOOLS_filetype_argument_substitution( argument, galaxy_ext ): + return argument % dict( file_type = GALAXY_EXT_TO_SAMTOOLS_FILE_TYPE.get( galaxy_ext, galaxy_ext ) ) + +def open_file_from_option( filename, mode = 'rb' ): + if filename: + return open( filename, mode = mode ) + return None + +def html_report_from_directory( html_out, dir ): + html_out.write( '<html>\n<head>\n<title>Galaxy - SAMTOOLS Output</title>\n</head>\n<body>\n<p/>\n<ul>\n' ) + for fname in sorted( os.listdir( dir ) ): + html_out.write( '<li><a href="%s">%s</a></li>\n' % ( fname, fname ) ) + html_out.write( '</ul>\n</body>\n</html>\n' ) + +def __main__(): + #Parse Command Line + parser = optparse.OptionParser() + parser.add_option( '-p', '--pass_through', dest='pass_through_options', action='append', type="string", help='These options are passed through directly to SAMTOOLS, without any modification.' ) + parser.add_option( '-d', '--dataset', dest='datasets', action='append', type="string", nargs=4, help='"-argument" "original_filename" "galaxy_filetype" "name_prefix"' ) + parser.add_option( '', '--stdout', dest='stdout', action='store', type="string", default=None, help='If specified, the output of stdout will be written to this file.' ) + parser.add_option( '', '--stderr', dest='stderr', action='store', type="string", default=None, help='If specified, the output of stderr will be written to this file.' ) + parser.add_option( '', '--html_report_from_directory', dest='html_report_from_directory', action='append', type="string", nargs=2, help='"Target HTML File" "Directory"') + (options, args) = parser.parse_args() + + tmp_dir = tempfile.mkdtemp( prefix='tmp-SAMTOOLS-' ) + + #set up stdout and stderr output options + stdout = open_file_from_option( options.stdout, mode = 'wb' ) + stderr = open_file_from_option( options.stderr, mode = 'wb' ) + #if no stderr file is specified, we'll use our own + if stderr is None: + stderr = tempfile.NamedTemporaryFile( prefix="SAMTOOLS-stderr-", dir=tmp_dir ) + + if options.pass_through_options: + cmd = ' '.join( options.pass_through_options ) + else: + cmd = '' + return_code = None + if options.datasets: + for ( dataset_arg, filename, galaxy_ext, prefix ) in options.datasets: + SAMTools_filename = SAMTOOLS_filename_from_galaxy( filename, galaxy_ext, target_dir = tmp_dir, prefix = prefix ) + if dataset_arg: + if '>' in cmd: + cmd = cmd.replace( '>', ' %s "%s" >' % ( SAMTOOLS_filetype_argument_substitution( dataset_arg, galaxy_ext ), SAMTools_filename ), 1 ) + else: + cmd = '%s %s "%s"' % ( cmd, SAMTOOLS_filetype_argument_substitution( dataset_arg, galaxy_ext ), SAMTools_filename ) + #auto index fasta files: + if galaxy_ext == 'fa': + index_cmd = 'samtools faidx %s' % ( SAMTools_filename ) + proc = subprocess.Popen( args=index_cmd, stdout=stdout, stderr=stderr, shell=True, cwd=tmp_dir ) + return_code = proc.wait() + if return_code: + break + if return_code is None or not return_code: + proc = subprocess.Popen( args=cmd, stdout=stdout, stderr=stderr, shell=True, cwd=tmp_dir ) + return_code = proc.wait() + if return_code: + stderr_target = sys.stderr + else: + if stdout: + stderr_target = stdout + else: + stderr_target = sys.stdout + stderr.flush() + stderr.seek(0) + while True: + chunk = stderr.read( CHUNK_SIZE ) + if chunk: + stderr_target.write( chunk ) + else: + break + stderr.close() + #generate html reports + if options.html_report_from_directory: + for ( html_filename, html_dir ) in options.html_report_from_directory: + html_report_from_directory( open( html_filename, 'wb' ), html_dir ) + + cleanup_before_exit( tmp_dir ) + +if __name__=="__main__": __main__() Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: dan: Remove --rodToIntervalTrackName from GATK tools; not present in version 1.3.
by Bitbucket 21 Nov '11

21 Nov '11

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/dccaec5a2b1e/ changeset: dccaec5a2b1e user: dan date: 2011-11-21 18:38:38 summary: Remove --rodToIntervalTrackName from GATK tools; not present in version 1.3. affected #: 9 files diff -r 3d0db17ca1fa86aaeff546c1a3cb375f15148c72 -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad tools/gatk/count_covariates.xml --- a/tools/gatk/count_covariates.xml +++ b/tools/gatk/count_covariates.xml @@ -39,9 +39,6 @@ #end if #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1 -d "--knownSites:${rod_bind_name},%(file_type)s" "${rod_binding.rod_bind_type.input_rod}" "${rod_binding.rod_bind_type.input_rod.ext}" "input_${rod_bind_name}_${rod_binding_names[$rod_bind_name]}" - #if str( $rod_binding.rod_bind_type.rodToIntervalTrackName ): - -p '--rodToIntervalTrackName "${rod_bind_name}"' - #end if #end for ##start standard gatk options @@ -186,24 +183,19 @@ </param><when value="dbsnp"><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when><when value="snps"><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when><when value="indels"><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when><when value="mask"><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when><when value="custom"><param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when></conditional></repeat> @@ -416,7 +408,6 @@ <param name="ref_file" value="phiX.fasta" ftype="fasta" /><param name="input_bam" value="gatk/gatk_indel_realigner/gatk_indel_realigner_out_1.bam" ftype="bam" /><param name="rod_bind_type_selector" value="dbsnp" /> - <param name="rodToIntervalTrackName" /><param name="input_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" /><param name="standard_covs" value="True" /><param name="covariates" value="ReadGroupCovariate,HomopolymerCovariate,MinimumNQSCovariate,PositionCovariate" /> diff -r 3d0db17ca1fa86aaeff546c1a3cb375f15148c72 -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad tools/gatk/indel_realigner.xml --- a/tools/gatk/indel_realigner.xml +++ b/tools/gatk/indel_realigner.xml @@ -31,9 +31,6 @@ #end if #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1 -d "-known:${rod_bind_name},%(file_type)s" "${rod_binding.rod_bind_type.input_rod}" "${rod_binding.rod_bind_type.input_rod.ext}" "input_${rod_bind_name}_${rod_binding_names[$rod_bind_name]}" - #if str( $rod_binding.rod_bind_type.rodToIntervalTrackName ): - -p '--rodToIntervalTrackName "${rod_bind_name}"' - #end if #end for ##start standard gatk options @@ -151,20 +148,16 @@ </param><when value="dbsnp"><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when><when value="snps"><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when><when value="indels"><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when><when value="custom"><param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when></conditional></repeat> @@ -331,7 +324,6 @@ <param name="target_intervals" value="gatk/gatk_realigner_target_creator/gatk_realigner_target_creator_out_1.gatk_interval" ftype="gatk_interval" /><param name="input_bam" value="gatk/fake_phiX_reads_1.bam" ftype="bam" /><param name="rod_bind_type_selector" value="snps" /> - <param name="rodToIntervalTrackName" /><param name="input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" /><param name="lod_threshold" value="5.0" /><param name="knowns_only" /> diff -r 3d0db17ca1fa86aaeff546c1a3cb375f15148c72 -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad tools/gatk/realigner_target_creator.xml --- a/tools/gatk/realigner_target_creator.xml +++ b/tools/gatk/realigner_target_creator.xml @@ -28,9 +28,6 @@ #end if #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1 -d "-known:${rod_bind_name},%(file_type)s" "${rod_binding.rod_bind_type.input_rod}" "${rod_binding.rod_bind_type.input_rod.ext}" "input_${rod_bind_name}_${rod_binding_names[$rod_bind_name]}" - #if str( $rod_binding.rod_bind_type.rodToIntervalTrackName ): - -p '--rodToIntervalTrackName "${rod_bind_name}"' - #end if #end for ##start standard gatk options @@ -139,20 +136,16 @@ </param><when value="dbsnp"><param name="input_rod" type="data" format="vcf" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when><when value="snps"><param name="input_rod" type="data" format="vcf" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when><when value="indels"><param name="input_rod" type="data" format="vcf" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when><when value="custom"><param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/><param name="input_rod" type="data" format="vcf" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when></conditional></repeat> @@ -306,7 +299,6 @@ <param name="ref_file" value="phiX.fasta" ftype="fasta" /><param name="input_bam" value="gatk/fake_phiX_reads_1.bam" ftype="bam" /><param name="rod_bind_type_selector" value="dbsnp" /> - <param name="rodToIntervalTrackName" /><param name="input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" /><param name="gatk_param_type_selector" value="basic" /><param name="analysis_param_type_selector" value="advanced" /> diff -r 3d0db17ca1fa86aaeff546c1a3cb375f15148c72 -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad tools/gatk/unified_genotyper.xml --- a/tools/gatk/unified_genotyper.xml +++ b/tools/gatk/unified_genotyper.xml @@ -34,9 +34,6 @@ #end if #set $rod_binding_names[$rod_bind_name] = $rod_binding_names.get( $rod_bind_name, -1 ) + 1 -d "--dbsnp:${rod_bind_name},%(file_type)s" "${rod_binding.rod_bind_type.input_rod}" "${rod_binding.rod_bind_type.input_rod.ext}" "input_${rod_bind_name}_${rod_binding_names[$rod_bind_name]}" - #if str( $rod_binding.rod_bind_type.rodToIntervalTrackName ): - -p '--rodToIntervalTrackName "${rod_bind_name}"' - #end if #end for ##start standard gatk options @@ -168,20 +165,16 @@ </param><when value="dbsnp"><param name="input_rod" type="data" format="vcf" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when><when value="snps"><param name="input_rod" type="data" format="vcf" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when><when value="indels"><param name="input_rod" type="data" format="vcf" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when><when value="custom"><param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/><param name="input_rod" type="data" format="vcf" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when></conditional></repeat> @@ -413,7 +406,6 @@ <param name="input_bam" value="gatk/gatk_table_recalibration/gatk_table_recalibration_out_1.bam" ftype="bam" /><param name="rod_bind_type_selector" value="dbsnp" /><param name="input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" /> - <param name="rodToIntervalTrackName" /><param name="standard_min_confidence_threshold_for_calling" value="0" /><param name="standard_min_confidence_threshold_for_emitting" value="4" /><param name="gatk_param_type_selector" value="basic" /> diff -r 3d0db17ca1fa86aaeff546c1a3cb375f15148c72 -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad tools/gatk/variant_annotator.xml --- a/tools/gatk/variant_annotator.xml +++ b/tools/gatk/variant_annotator.xml @@ -43,31 +43,19 @@ #for $rod_binding in $comp_rod_bind: -d "--comp:${rod_binding.comp_rod_name},%(file_type)s" "${rod_binding.comp_input_rod}" "${rod_binding.comp_input_rod.ext}" "input_comp_${rod_binding.comp_rod_name}" - #if str( $rod_binding.comp_rodToIntervalTrackName ): - -p '--rodToIntervalTrackName "${rod_binding.comp_rod_name}"' - #end if #end for #if str( $dbsnp_rod_bind_type.dbsnp_rod_bind_type_selector ) == 'set_dbsnp': -d "--dbsnp:${dbsnp_rod_bind_type.dbsnp_rod_name},%(file_type)s" "${dbsnp_rod_bind_type.dbsnp_input_rod}" "${dbsnp_rod_bind_type.dbsnp_input_rod.ext}" "input_dbsnp_${dbsnp_rod_bind_type.dbsnp_rod_name}" - #if str( $dbsnp_rod_bind_type.dbsnp_rodToIntervalTrackName ): - -p '--rodToIntervalTrackName "${dbsnp_rod_bind_type.dbsnp_rod_name}"' - #end if #end if #for $rod_binding in $resource_rod_bind: -d "--resource:${rod_binding.resource_rod_name},%(file_type)s" "${rod_binding.resource_input_rod}" "${rod_binding.resource_input_rod.ext}" "input_resource_${rod_binding.resource_rod_name}" - #if str( $rod_binding.resource_rodToIntervalTrackName ): - -p '--rodToIntervalTrackName "${rod_binding.resource_rod_name}"' - #end if #end for #if str( $snpEff_rod_bind_type.snpEff_rod_bind_type_selector ) == 'set_snpEff': -d "--snpEff:${snpEff_rod_bind_type.snpEff_rod_name},%(file_type)s" "${snpEff_rod_bind_type.snpEff_input_rod}" "${snpEff_rod_bind_type.snpEff_input_rod.ext}" "input_snpEff_${snpEff_rod_bind_type.snpEff_rod_name}" - #if str( $snpEff_rod_bind_type.snpEff_rodToIntervalTrackName ): - -p '--rodToIntervalTrackName "${snpEff_rod_bind_type.snpEff_rod_name}"' - #end if #end if #for $expression in $expressions: @@ -214,7 +202,6 @@ <repeat name="comp_rod_bind" title="Binding for reference-ordered comparison data"><param name="comp_input_rod" type="data" format="vcf" label="ROD file" /><param name="comp_rod_name" type="text" value="Unnamed" label="ROD Name"/> - <param name="comp_rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></repeat><conditional name="dbsnp_rod_bind_type"> @@ -227,7 +214,6 @@ </when><when value="set_dbsnp"><param name="dbsnp_input_rod" type="data" format="vcf" label="ROD file" /> - <param name="dbsnp_rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /><param name="dbsnp_rod_name" type="hidden" value="dbsnp" label="ROD Name"/></when></conditional> @@ -235,7 +221,6 @@ <repeat name="resource_rod_bind" title="Binding for reference-ordered resource data"><param name="resource_input_rod" type="data" format="vcf" label="ROD file" /><param name="resource_rod_name" type="text" value="Unnamed" label="ROD Name"/> - <param name="resource_rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></repeat><conditional name="snpEff_rod_bind_type"> @@ -248,7 +233,6 @@ </when><when value="set_snpEff"><param name="snpEff_input_rod" type="data" format="vcf" label="ROD file" /> - <param name="snpEff_rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /><param name="snpEff_rod_name" type="hidden" value="snpEff" label="ROD Name"/></when></conditional> @@ -403,7 +387,6 @@ <param name="annotations_type_selector" value="choose" /><param name="annotations" value="AlleleBalance,BaseQualityRankSumTest,DepthOfCoverage,HomopolymerRun,MappingQualityRankSumTest,MappingQualityZero,QualByDepth,RMSMappingQuality,SpanningDeletions,HaplotypeScore" /><param name="dbsnp_rod_bind_type_selector" value="set_dbsnp" /> - <param name="dbsnp_rodToIntervalTrackName" /><param name="dbsnp_input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" /><param name="snpEff_rod_bind_type_selector" value="exclude_snpEff" /><param name="gatk_param_type_selector" value="basic" /> diff -r 3d0db17ca1fa86aaeff546c1a3cb375f15148c72 -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad tools/gatk/variant_eval.xml --- a/tools/gatk/variant_eval.xml +++ b/tools/gatk/variant_eval.xml @@ -23,9 +23,6 @@ #for $rod_binding in $comp_rod_bind: -d "--comp:${rod_binding.comp_rod_name},%(file_type)s" "${rod_binding.comp_input_rod}" "${rod_binding.comp_input_rod.ext}" "input_comp_${rod_binding.comp_rod_name}" - #if str( $rod_binding.comp_rodToIntervalTrackName ): - -p '--rodToIntervalTrackName "${rod_binding.comp_rod_name}"' - #end if #if str( $rod_binding.comp_known_names ): -p '--known_names "${rod_binding.comp_rod_name}"' #end if @@ -33,11 +30,8 @@ #if str( $dbsnp_rod_bind_type.dbsnp_rod_bind_type_selector ) == 'set_dbsnp': -d "--dbsnp:${dbsnp_rod_bind_type.dbsnp_rod_name},%(file_type)s" "${dbsnp_rod_bind_type.dbsnp_input_rod}" "${dbsnp_rod_bind_type.dbsnp_input_rod.ext}" "input_dbsnp_${dbsnp_rod_bind_type.dbsnp_rod_name}" - #if str( $dbsnp_rod_bind_type.dbsnp_rodToIntervalTrackName ): - -p '--rodToIntervalTrackName "${dbsnp_rod_bind_type.dbsnp_rod_name}"' - #if str( $dbsnp_rod_bind_type.dbsnp_known_names ): - -p '--known_names "${dbsnp_rod_bind_type.dbsnp_rod_name}"' - #end if + #if str( $dbsnp_rod_bind_type.dbsnp_known_names ): + -p '--known_names "${dbsnp_rod_bind_type.dbsnp_rod_name}"' #end if #end if @@ -179,7 +173,6 @@ <repeat name="comp_rod_bind" title="Binding for reference-ordered comparison data"><param name="comp_input_rod" type="data" format="vcf" label="Comparison ROD file" /><param name="comp_rod_name" type="text" value="Unnamed" label="Comparison ROD Name"/> - <param name="comp_rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use Comparison ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /><param name="comp_known_names" type="boolean" truevalue="--known_names" falsevalue="" label="Use Comparison ROD as known_names" /></repeat> @@ -193,7 +186,6 @@ </when><when value="set_dbsnp"><param name="dbsnp_input_rod" type="data" format="vcf" label="dbSNP ROD file" /> - <param name="dbsnp_rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use dbSNP ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /><param name="dbsnp_rod_name" type="hidden" value="dbsnp" label="dbSNP ROD Name"/><param name="dbsnp_known_names" type="boolean" truevalue="--known_names" falsevalue="" label="Use dbSNP ROD as known_names" /></when> @@ -405,7 +397,6 @@ <param name="ref_file" value="phiX.fasta" ftype="fasta" /><param name="input_variant" value="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf" ftype="vcf" /><param name="dbsnp_rod_bind_type_selector" value="set_dbsnp" /> - <param name="dbsnp_rodToIntervalTrackName" /><param name="dbsnp_input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" /><param name="dbsnp_known_names" value="True"/><param name="comp_rod_bind" value="0" /> diff -r 3d0db17ca1fa86aaeff546c1a3cb375f15148c72 -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad tools/gatk/variant_filtration.xml --- a/tools/gatk/variant_filtration.xml +++ b/tools/gatk/variant_filtration.xml @@ -30,9 +30,6 @@ --maskExtension "${mask_rod_bind_type.mask_extension}" --maskName "${mask_rod_bind_type.mask_rod_name}" ' - #if str( $mask_rod_bind_type.mask_rodToIntervalTrackName ): - -p '--rodToIntervalTrackName "${mask_rod_bind_type.mask_rod_name}"' - #end if #end if ##start standard gatk options @@ -150,7 +147,6 @@ <param name="input_mask_rod" type="data" format="bed,gatk_dbsnp,vcf" label="Mask ROD file" /><param name="mask_rod_name" type="text" value="Mask" label="Mask Name"/><param name="mask_extension" type="integer" value="0" label="Mask Extension"/> - <param name="mask_rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use Mask ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /></when></conditional> @@ -308,7 +304,6 @@ <param name="filter_name" value="Galaxy_filter" /><param name="is_genotype_filter" /><param name="mask_rod_bind_type_selector" value="set_mask" /> - <param name="mask_rodToIntervalTrackName" /><param name="input_mask_rod" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" /><param name="mask_rod_name" value="." /><param name="mask_extension" value="0" /> diff -r 3d0db17ca1fa86aaeff546c1a3cb375f15148c72 -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad tools/gatk/variant_recalibrator.xml --- a/tools/gatk/variant_recalibrator.xml +++ b/tools/gatk/variant_recalibrator.xml @@ -38,9 +38,6 @@ #else: -d "--resource:${rod_bind_name},%(file_type)s,known=${rod_binding.rod_bind_type.rod_training_type.known},training=${rod_binding.rod_bind_type.rod_training_type.training},truth=${rod_binding.rod_bind_type.rod_training_type.truth},bad=${rod_binding.rod_bind_type.rod_training_type.bad},prior=${rod_binding.rod_bind_type.rod_training_type.prior}" "${rod_binding.rod_bind_type.input_rod}" "${rod_binding.rod_bind_type.input_rod.ext}" "input_${rod_bind_name}_${rod_binding_names[$rod_bind_name]}" #end if - #if str( $rod_binding.rod_bind_type.rodToIntervalTrackName ): - -p '--rodToIntervalTrackName "${rod_bind_name}"' - #end if #end for ##start standard gatk options @@ -183,7 +180,6 @@ </param><when value="variant"><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="Variant ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> @@ -204,7 +200,6 @@ <when value="comp"><param name="input_rod" type="data" format="vcf,gatk_dbsnp" label="ROD file" /><param name="custom_rod_name" type="text" value="Unnamed" label="ROD Name"/> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> @@ -224,7 +219,6 @@ </when><when value="dbsnp"><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> @@ -244,7 +238,6 @@ </when><when value="snps"><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> @@ -264,7 +257,6 @@ </when><when value="hapmap"><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> @@ -284,7 +276,6 @@ </when><when value="omni"><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> @@ -304,7 +295,6 @@ </when><when value="indels"><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> @@ -325,7 +315,6 @@ <when value="custom"><param name="custom_rod_name" type="text" value="Unknown" label="ROD Name"/><param name="input_rod" type="data" format="vcf,gatk_dbsnp,bed" label="ROD file" /> - <param name="rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /><conditional name="rod_training_type"><param name="rod_training_type_selector" type="select" label="Use as training/truth/known sites"><option value="is_training_truth_known">Set training/truth/known sites</option> diff -r 3d0db17ca1fa86aaeff546c1a3cb375f15148c72 -r dccaec5a2b1e41a008c63a9c08f7b21c3526fcad tools/gatk/variants_validate.xml --- a/tools/gatk/variants_validate.xml +++ b/tools/gatk/variants_validate.xml @@ -23,9 +23,6 @@ #if str( $dbsnp_rod_bind_type.dbsnp_rod_bind_type_selector ) == 'set_dbsnp': -d "--dbsnp:${dbsnp_rod_bind_type.dbsnp_rod_name},%(file_type)s" "${dbsnp_rod_bind_type.dbsnp_input_rod}" "${dbsnp_rod_bind_type.dbsnp_input_rod.ext}" "input_dbsnp_${dbsnp_rod_bind_type.dbsnp_rod_name}" - #if str( $dbsnp_rod_bind_type.dbsnp_rodToIntervalTrackName ): - -p '--rodToIntervalTrackName "${dbsnp_rod_bind_type.dbsnp_rod_name}"' - #end if #end if ##start standard gatk options @@ -117,7 +114,6 @@ </when><when value="set_dbsnp"><param name="dbsnp_input_rod" type="data" format="vcf" label="ROD file" /> - <param name="dbsnp_rodToIntervalTrackName" type="boolean" truevalue="--rodToIntervalTrackName" falsevalue="" label="Use ROD as interval List (-BTI, --rodToIntervalTrackName)" help="Only one ROD may have this option specified" /><param name="dbsnp_rod_name" type="hidden" value="dbsnp" label="ROD Name"/></when></conditional> @@ -258,7 +254,6 @@ <param name="ref_file" value="phiX.fasta" ftype="fasta" /><param name="input_variant" value="gatk/gatk_variant_annotator/gatk_variant_annotator_out_1.vcf" ftype="vcf" /><param name="dbsnp_rod_bind_type_selector" value="set_dbsnp" /> - <param name="dbsnp_rodToIntervalTrackName" /><param name="dbsnp_input_rod" value="gatk/fake_phiX_variant_locations.vcf" ftype="vcf" /><param name="warn_on_errors" value="True"/><param name="do_not_validate_filtered_records" /> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: greg: Fix for generating metadata on the repository tip.
by Bitbucket 21 Nov '11

21 Nov '11

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/3d0db17ca1fa/ changeset: 3d0db17ca1fa user: greg date: 2011-11-21 18:09:25 summary: Fix for generating metadata on the repository tip. affected #: 1 file diff -r 058c507d05fd41694261f9f679b7cccafe295faf -r 3d0db17ca1fa86aaeff546c1a3cb375f15148c72 lib/galaxy/webapps/community/controllers/repository.py --- a/lib/galaxy/webapps/community/controllers/repository.py +++ b/lib/galaxy/webapps/community/controllers/repository.py @@ -1631,7 +1631,10 @@ for changeset in repo.changelog: current_changeset_revision = str( repo.changectx( changeset ) ) ctx = get_changectx_for_changeset( trans, repo, current_changeset_revision ) - current_metadata_dict, invalid_files = generate_metadata_for_changeset_revision( trans, id, ctx, current_changeset_revision, repo_dir ) + if current_changeset_revision == repository.tip: + current_metadata_dict, invalid_files = generate_metadata_for_repository_tip( trans, id, ctx, current_changeset_revision, repo_dir ) + else: + current_metadata_dict, invalid_files = generate_metadata_for_changeset_revision( trans, id, ctx, current_changeset_revision, repo_dir ) if current_metadata_dict: if ancestor_changeset_revision: # Compare metadata from ancestor and current. The value of comparsion will be one of: Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: greg: Subtle but critical fixes in resetting all metadata for tool shed repositories ( and some code clean up ).
by Bitbucket 21 Nov '11

21 Nov '11

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/058c507d05fd/ changeset: 058c507d05fd user: greg date: 2011-11-21 17:21:23 summary: Subtle but critical fixes in resetting all metadata for tool shed repositories ( and some code clean up ). affected #: 4 files diff -r 66038323cb438066cb76e255fd436fc245056bfd -r 058c507d05fd41694261f9f679b7cccafe295faf lib/galaxy/webapps/community/controllers/repository.py --- a/lib/galaxy/webapps/community/controllers/repository.py +++ b/lib/galaxy/webapps/community/controllers/repository.py @@ -1622,51 +1622,56 @@ if len( repo ) == 1: message, status = set_repository_metadata( trans, id, repository.tip, **kwd ) else: - # The following will be a list of changeset_revisions that have been created or updated. - # When the following loop completes, we'll delete all repository_metadata records for - # this repository that do not have a changeset_revision value in this list. + # The list of changeset_revisions refers to repository_metadata records that have been + # created or updated. When the following loop completes, we'll delete all repository_metadata + # records for this repository that do not have a changeset_revision value in this list. changeset_revisions = [] - repository_metadata_tup_for_comparison = () + ancestor_changeset_revision = None + ancestor_metadata_dict = None for changeset in repo.changelog: - ctx = repo.changectx( changeset ) - current_changeset_revision = str( ctx ) + current_changeset_revision = str( repo.changectx( changeset ) ) ctx = get_changectx_for_changeset( trans, repo, current_changeset_revision ) current_metadata_dict, invalid_files = generate_metadata_for_changeset_revision( trans, id, ctx, current_changeset_revision, repo_dir ) if current_metadata_dict: - if repository_metadata_tup_for_comparison: - ancestor_changeset_revision, ancestor_metadata_dict = repository_metadata_tup_for_comparison - comparison = self.__compare_changeset_revisions( ancestor_changeset_revision, - ancestor_metadata_dict, - current_changeset_revision, - current_metadata_dict ) - # The value of comparsion will be one of: + if ancestor_changeset_revision: + # Compare metadata from ancestor and current. The value of comparsion will be one of: # 'no metadata' - no metadata for either ancestor or current, so continue from current # 'equal' - ancestor metadata is equivalent to current metadata, so continue from current # 'subset' - ancestor metadata is a subset of current metadata, so continue from current # 'not equal and not subset' - ancestor metadata is neither equal to nor a subset of current # metadata, so persist ancestor metadata. + comparison = self.__compare_changeset_revisions( ancestor_changeset_revision, + ancestor_metadata_dict, + current_changeset_revision, + current_metadata_dict ) if comparison in [ 'no metadata', 'equal', 'subset' ]: - repository_metadata_tup_for_comparison = ( current_changeset_revision, current_metadata_dict ) + ancestor_changeset_revision = current_changeset_revision + ancestor_metadata_dict = current_metadata_dict elif comparison == 'not equal and not subset': self.__create_or_update_repository_metadata( trans, id, repository, ancestor_changeset_revision, ancestor_metadata_dict ) - # keep track of the changeset_revisions that we've persisted. + # Keep track of the changeset_revisions that we've persisted. changeset_revisions.append( ancestor_changeset_revision ) - repository_metadata_tup_for_comparison = () + ancestor_changeset_revision = None + ancestor_metadata_dict = None else: - # We're at the first change set in the change log. - repository_metadata_tup_for_comparison = ( current_changeset_revision, current_metadata_dict ) + # We're either at the first change set in the change log or we have just created or updated + # a repository_metadata record. At this point we set the ancestor changeset to the current + # changeset for comparison in the next iteration. + ancestor_changeset_revision = current_changeset_revision + ancestor_metadata_dict = current_metadata_dict if not ctx.children(): # We're at the end of the change log. self.__create_or_update_repository_metadata( trans, id, repository, current_changeset_revision, current_metadata_dict ) changeset_revisions.append( current_changeset_revision ) + ancestor_changeset_revision = None + ancestor_metadata_dict = None elif ancestor_metadata_dict: # Our current change set has no metadata, but our ancestor change set has metadata, so save it. self.__create_or_update_repository_metadata( trans, id, repository, ancestor_changeset_revision, ancestor_metadata_dict ) - # keep track of the changeset_revisions that we've persisted. + # Keep track of the changeset_revisions that we've persisted. changeset_revisions.append( ancestor_changeset_revision ) - repository_metadata_tup_for_comparison = () - ancestor_changeset_revision = current_changeset_revision - ancestor_metadata_dict = current_metadata_dict + ancestor_changeset_revision = None + ancestor_metadata_dict = None self.__clean_repository_metadata( trans, id, changeset_revisions ) if not message: message = "Repository metadata has been reset." @@ -1699,6 +1704,12 @@ def __compare_changeset_revisions( self, ancestor_changeset_revision, ancestor_metadata_dict, current_changeset_revision, current_metadata_dict ): # The metadata associated with ancestor_changeset_revision is ancestor_metadata_dict. This changeset_revision # is an ancestor of current_changeset_revision which is associated with current_metadata_dict. + # + # TODO: a new repository_metadata record will be created only when this method returns the string + # 'not equal and not subset'. However, we're currently also returning the strings 'no metadata', + # 'equal' and 'subset', depending upon how the 2 change sets compare. We'll leave things this way + # for the current time in case we discover a use for these additional result strings. + # # Get information about tools. if 'tools' in ancestor_metadata_dict: ancestor_tools = ancestor_metadata_dict[ 'tools' ] @@ -1735,7 +1746,7 @@ else: current_datatypes = [] # Handle case where no metadata exists for either changeset. - if not ( ancestor_guids or current_guids or ancestor_workflows or current_workflows or ancestor_datatypes or current_datatypes ): + if not ancestor_guids and not current_guids and not ancestor_workflows and not current_workflows and not ancestor_datatypes and not current_datatypes: return 'no metadata' workflow_comparison = self.__compare_workflows( ancestor_workflows, current_workflows ) datatype_comparison = self.__compare_datatypes( ancestor_datatypes, current_datatypes ) @@ -1758,9 +1769,13 @@ for ancestor_workflow in ancestor_workflows: # Currently the only way to differentiate workflows is by name. ancestor_workflow_name = ancestor_workflow[ 'name' ] + num_ancestor_workflow_steps = len( ancestor_workflow[ 'steps' ] ) found_in_current = False for current_workflow in current_workflows: - if current_workflow[ 'name' ] == ancestor_workflow_name: + # Assume that if the name and number of steps are euqal, + # then the workflows are the same. Of course, this may + # not be true... + if current_workflow[ 'name' ] == ancestor_workflow_name and len( current_workflow[ 'steps' ] ) == num_ancestor_workflow_steps: found_in_current = True break if not found_in_current: diff -r 66038323cb438066cb76e255fd436fc245056bfd -r 058c507d05fd41694261f9f679b7cccafe295faf lib/galaxy/webapps/community/model/mapping.py --- a/lib/galaxy/webapps/community/model/mapping.py +++ b/lib/galaxy/webapps/community/model/mapping.py @@ -194,7 +194,7 @@ categories=relation( RepositoryCategoryAssociation ), ratings=relation( RepositoryRatingAssociation, order_by=desc( RepositoryRatingAssociation.table.c.update_time ), backref="repositories" ), user=relation( User.mapper ), - downloadable_revisions=relation( RepositoryMetadata, order_by=desc( RepositoryMetadata.table.c.id ) ) ) ) + downloadable_revisions=relation( RepositoryMetadata, order_by=desc( RepositoryMetadata.table.c.update_time ) ) ) ) assign_mapper( context, RepositoryMetadata, RepositoryMetadata.table, properties=dict( repository=relation( Repository ) ) ) diff -r 66038323cb438066cb76e255fd436fc245056bfd -r 058c507d05fd41694261f9f679b7cccafe295faf templates/webapps/community/repository/common.mako --- a/templates/webapps/community/repository/common.mako +++ b/templates/webapps/community/repository/common.mako @@ -181,7 +181,7 @@ <a href="${h.url_for( controller='workflow', action='view_workflow', repository_metadata_id=repository_metadata_id, workflow_name=encode( workflow_name ), webapp=webapp )}">${workflow_name}</a></td><td> - %if 'steps' in workflow_dict: + %if steps: ${len( steps )} %else: unknown diff -r 66038323cb438066cb76e255fd436fc245056bfd -r 058c507d05fd41694261f9f679b7cccafe295faf templates/webapps/community/repository/view_changelog.mako --- a/templates/webapps/community/repository/view_changelog.mako +++ b/templates/webapps/community/repository/view_changelog.mako @@ -107,7 +107,7 @@ else: ctx_parent_str = "%s:%s" % ( ctx_parent_rev, ctx_parent ) if changeset[ 'has_metadata' ]: - has_metadata_str = 'Repository metadata is associated with this change set.' + has_metadata_str = '<table border="0" bgcolor="#D8D8D8"><tr><td>Repository metadata is associated with this change set.</td></tr></table>' else: has_metadata_str = '' %> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: dan: Update modified generic GATK 1.3 arguments.
by Bitbucket 21 Nov '11

21 Nov '11

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/66038323cb43/ changeset: 66038323cb43 user: dan date: 2011-11-21 15:50:37 summary: Update modified generic GATK 1.3 arguments. affected #: 13 files diff -r fd76a44745351d69f8abbccc14fec833e83b469a -r 66038323cb438066cb76e255fd436fc245056bfd tools/gatk/count_covariates.xml --- a/tools/gatk/count_covariates.xml +++ b/tools/gatk/count_covariates.xml @@ -46,9 +46,13 @@ ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $sample_metadata in $gatk_param_type.sample_metadata: - -p '--sample_metadata "${sample_metadata.sample_metadata_file}"' + #for $pedigree in $gatk_param_type.pedigree: + -p '--pedigree "${pedigree.pedigree_file}"' #end for + #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: + -p '--pedigreeString "${pedigree_string.pedigree_string}"' + #end for + -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' #for $read_filter in $gatk_param_type.read_filter: -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" ###raise Exception( str( dir( $read_filter ) ) ) @@ -67,7 +71,7 @@ -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" #end for - -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"' + -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": @@ -213,9 +217,16 @@ </when><when value="advanced"> - <repeat name="sample_metadata" title="Sample Metadata"> - <param name="sample_metadata_file" type="data" format="txt" label="Sample file in JSON format" /> + <repeat name="pedigree" title="Pedigree file"> + <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples" /></repeat> + <repeat name="pedigree_string_repeat" title="Pedigree string"> + <param name="pedigree_string" type="text" value="" label="Pedigree string for samples" /> + </repeat> + <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information"> + <option value="STRICT" selected="True">STRICT</option> + <option value="SILENT">SILENT</option> + </param><repeat name="read_filter" title="Read Filter"><conditional name="read_filter_type"><param name="read_filter_type_selector" type="select" label="Read Filter Type"> @@ -237,7 +248,7 @@ <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list" label="Genomic intervals" /></repeat> - <param name="BTI_merge_rule" type="select" label="BTI merge rule"> + <param name="interval_set_rule" type="select" label="Interval set rule"><option value="UNION" selected="True">UNION</option><option value="INTERSECTION">INTERSECTION</option></param> diff -r fd76a44745351d69f8abbccc14fec833e83b469a -r 66038323cb438066cb76e255fd436fc245056bfd tools/gatk/depth_of_coverage.xml --- a/tools/gatk/depth_of_coverage.xml +++ b/tools/gatk/depth_of_coverage.xml @@ -37,9 +37,13 @@ ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $sample_metadata in $gatk_param_type.sample_metadata: - -p '--sample_metadata "${sample_metadata.sample_metadata_file}"' + #for $pedigree in $gatk_param_type.pedigree: + -p '--pedigree "${pedigree.pedigree_file}"' #end for + #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: + -p '--pedigreeString "${pedigree_string.pedigree_string}"' + #end for + -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' #for $read_filter in $gatk_param_type.read_filter: -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" ###raise Exception( str( dir( $read_filter ) ) ) @@ -58,7 +62,7 @@ -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" #end for - -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"' + -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": @@ -229,9 +233,16 @@ </when><when value="advanced"> - <repeat name="sample_metadata" title="Sample Metadata"> - <param name="sample_metadata_file" type="data" format="txt" label="Sample file in JSON format" /> + <repeat name="pedigree" title="Pedigree file"> + <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples" /></repeat> + <repeat name="pedigree_string_repeat" title="Pedigree string"> + <param name="pedigree_string" type="text" value="" label="Pedigree string for samples" /> + </repeat> + <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information"> + <option value="STRICT" selected="True">STRICT</option> + <option value="SILENT">SILENT</option> + </param><repeat name="read_filter" title="Read Filter"><conditional name="read_filter_type"><param name="read_filter_type_selector" type="select" label="Read Filter Type"> @@ -253,7 +264,7 @@ <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list" label="Genomic intervals" /></repeat> - <param name="BTI_merge_rule" type="select" label="BTI merge rule"> + <param name="interval_set_rule" type="select" label="Interval set rule"><option value="UNION" selected="True">UNION</option><option value="INTERSECTION">INTERSECTION</option></param> diff -r fd76a44745351d69f8abbccc14fec833e83b469a -r 66038323cb438066cb76e255fd436fc245056bfd tools/gatk/indel_realigner.xml --- a/tools/gatk/indel_realigner.xml +++ b/tools/gatk/indel_realigner.xml @@ -38,9 +38,13 @@ ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $sample_metadata in $gatk_param_type.sample_metadata: - -p '--sample_metadata "${sample_metadata.sample_metadata_file}"' + #for $pedigree in $gatk_param_type.pedigree: + -p '--pedigree "${pedigree.pedigree_file}"' #end for + #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: + -p '--pedigreeString "${pedigree_string.pedigree_string}"' + #end for + -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' #for $read_filter in $gatk_param_type.read_filter: -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" ###raise Exception( str( dir( $read_filter ) ) ) @@ -59,7 +63,7 @@ -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" #end for - -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"' + -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": @@ -176,9 +180,16 @@ </when><when value="advanced"> - <repeat name="sample_metadata" title="Sample Metadata"> - <param name="sample_metadata_file" type="data" format="txt" label="Sample file in JSON format" /> + <repeat name="pedigree" title="Pedigree file"> + <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples" /></repeat> + <repeat name="pedigree_string_repeat" title="Pedigree string"> + <param name="pedigree_string" type="text" value="" label="Pedigree string for samples" /> + </repeat> + <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information"> + <option value="STRICT" selected="True">STRICT</option> + <option value="SILENT">SILENT</option> + </param><repeat name="read_filter" title="Read Filter"><conditional name="read_filter_type"><param name="read_filter_type_selector" type="select" label="Read Filter Type"> @@ -200,7 +211,7 @@ <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list" label="Genomic intervals" /></repeat> - <param name="BTI_merge_rule" type="select" label="BTI merge rule"> + <param name="interval_set_rule" type="select" label="Interval set rule"><option value="UNION" selected="True">UNION</option><option value="INTERSECTION">INTERSECTION</option></param> diff -r fd76a44745351d69f8abbccc14fec833e83b469a -r 66038323cb438066cb76e255fd436fc245056bfd tools/gatk/realigner_target_creator.xml --- a/tools/gatk/realigner_target_creator.xml +++ b/tools/gatk/realigner_target_creator.xml @@ -35,9 +35,13 @@ ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $sample_metadata in $gatk_param_type.sample_metadata: - -p '--sample_metadata "${sample_metadata.sample_metadata_file}"' + #for $pedigree in $gatk_param_type.pedigree: + -p '--pedigree "${pedigree.pedigree_file}"' #end for + #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: + -p '--pedigreeString "${pedigree_string.pedigree_string}"' + #end for + -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' #for $read_filter in $gatk_param_type.read_filter: -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" ###raise Exception( str( dir( $read_filter ) ) ) @@ -56,7 +60,7 @@ -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" #end for - -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"' + -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": @@ -162,9 +166,16 @@ </when><when value="advanced"> - <repeat name="sample_metadata" title="Sample Metadata"> - <param name="sample_metadata_file" type="data" format="txt" label="Sample file in JSON format" /> + <repeat name="pedigree" title="Pedigree file"> + <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples" /></repeat> + <repeat name="pedigree_string_repeat" title="Pedigree string"> + <param name="pedigree_string" type="text" value="" label="Pedigree string for samples" /> + </repeat> + <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information"> + <option value="STRICT" selected="True">STRICT</option> + <option value="SILENT">SILENT</option> + </param><repeat name="read_filter" title="Read Filter"><conditional name="read_filter_type"><param name="read_filter_type_selector" type="select" label="Read Filter Type"> @@ -186,7 +197,7 @@ <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list" label="Genomic intervals" /></repeat> - <param name="BTI_merge_rule" type="select" label="BTI merge rule"> + <param name="interval_set_rule" type="select" label="Interval set rule"><option value="UNION" selected="True">UNION</option><option value="INTERSECTION">INTERSECTION</option></param> diff -r fd76a44745351d69f8abbccc14fec833e83b469a -r 66038323cb438066cb76e255fd436fc245056bfd tools/gatk/table_recalibration.xml --- a/tools/gatk/table_recalibration.xml +++ b/tools/gatk/table_recalibration.xml @@ -23,9 +23,13 @@ ' ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $sample_metadata in $gatk_param_type.sample_metadata: - -p '--sample_metadata "${sample_metadata.sample_metadata_file}"' + #for $pedigree in $gatk_param_type.pedigree: + -p '--pedigree "${pedigree.pedigree_file}"' #end for + #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: + -p '--pedigreeString "${pedigree_string.pedigree_string}"' + #end for + -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' #for $read_filter in $gatk_param_type.read_filter: -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" ###raise Exception( str( dir( $read_filter ) ) ) @@ -44,7 +48,7 @@ -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" #end for - -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"' + -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": @@ -144,9 +148,16 @@ </when><when value="advanced"> - <repeat name="sample_metadata" title="Sample Metadata"> - <param name="sample_metadata_file" type="data" format="txt" label="Sample file in JSON format" /> + <repeat name="pedigree" title="Pedigree file"> + <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples" /></repeat> + <repeat name="pedigree_string_repeat" title="Pedigree string"> + <param name="pedigree_string" type="text" value="" label="Pedigree string for samples" /> + </repeat> + <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information"> + <option value="STRICT" selected="True">STRICT</option> + <option value="SILENT">SILENT</option> + </param><repeat name="read_filter" title="Read Filter"><conditional name="read_filter_type"><param name="read_filter_type_selector" type="select" label="Read Filter Type"> @@ -168,7 +179,7 @@ <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list" label="Genomic intervals" /></repeat> - <param name="BTI_merge_rule" type="select" label="BTI merge rule"> + <param name="interval_set_rule" type="select" label="Interval set rule"><option value="UNION" selected="True">UNION</option><option value="INTERSECTION">INTERSECTION</option></param> diff -r fd76a44745351d69f8abbccc14fec833e83b469a -r 66038323cb438066cb76e255fd436fc245056bfd tools/gatk/unified_genotyper.xml --- a/tools/gatk/unified_genotyper.xml +++ b/tools/gatk/unified_genotyper.xml @@ -41,9 +41,13 @@ ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $sample_metadata in $gatk_param_type.sample_metadata: - -p '--sample_metadata "${sample_metadata.sample_metadata_file}"' + #for $pedigree in $gatk_param_type.pedigree: + -p '--pedigree "${pedigree.pedigree_file}"' #end for + #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: + -p '--pedigreeString "${pedigree_string.pedigree_string}"' + #end for + -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' #for $read_filter in $gatk_param_type.read_filter: -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" ###raise Exception( str( dir( $read_filter ) ) ) @@ -62,7 +66,7 @@ -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" #end for - -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"' + -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": @@ -201,9 +205,16 @@ </when><when value="advanced"> - <repeat name="sample_metadata" title="Sample Metadata"> - <param name="sample_metadata_file" type="data" format="txt" label="Sample file in JSON format" /> + <repeat name="pedigree" title="Pedigree file"> + <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples" /></repeat> + <repeat name="pedigree_string_repeat" title="Pedigree string"> + <param name="pedigree_string" type="text" value="" label="Pedigree string for samples" /> + </repeat> + <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information"> + <option value="STRICT" selected="True">STRICT</option> + <option value="SILENT">SILENT</option> + </param><repeat name="read_filter" title="Read Filter"><conditional name="read_filter_type"><param name="read_filter_type_selector" type="select" label="Read Filter Type"> @@ -225,7 +236,7 @@ <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list" label="Genomic intervals" /></repeat> - <param name="BTI_merge_rule" type="select" label="BTI merge rule"> + <param name="interval_set_rule" type="select" label="Interval set rule"><option value="UNION" selected="True">UNION</option><option value="INTERSECTION">INTERSECTION</option></param> diff -r fd76a44745351d69f8abbccc14fec833e83b469a -r 66038323cb438066cb76e255fd436fc245056bfd tools/gatk/variant_annotator.xml --- a/tools/gatk/variant_annotator.xml +++ b/tools/gatk/variant_annotator.xml @@ -76,9 +76,13 @@ ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $sample_metadata in $gatk_param_type.sample_metadata: - -p '--sample_metadata "${sample_metadata.sample_metadata_file}"' + #for $pedigree in $gatk_param_type.pedigree: + -p '--pedigree "${pedigree.pedigree_file}"' #end for + #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: + -p '--pedigreeString "${pedigree_string.pedigree_string}"' + #end for + -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' #for $read_filter in $gatk_param_type.read_filter: -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" ###raise Exception( str( dir( $read_filter ) ) ) @@ -97,7 +101,7 @@ -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" #end for - -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"' + -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": @@ -262,9 +266,16 @@ </when><when value="advanced"> - <repeat name="sample_metadata" title="Sample Metadata"> - <param name="sample_metadata_file" type="data" format="txt" label="Sample file in JSON format" /> + <repeat name="pedigree" title="Pedigree file"> + <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples" /></repeat> + <repeat name="pedigree_string_repeat" title="Pedigree string"> + <param name="pedigree_string" type="text" value="" label="Pedigree string for samples" /> + </repeat> + <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information"> + <option value="STRICT" selected="True">STRICT</option> + <option value="SILENT">SILENT</option> + </param><repeat name="read_filter" title="Read Filter"><conditional name="read_filter_type"><param name="read_filter_type_selector" type="select" label="Read Filter Type"> @@ -286,7 +297,7 @@ <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list" label="Genomic intervals" /></repeat> - <param name="BTI_merge_rule" type="select" label="BTI merge rule"> + <param name="interval_set_rule" type="select" label="Interval set rule"><option value="UNION" selected="True">UNION</option><option value="INTERSECTION">INTERSECTION</option></param> diff -r fd76a44745351d69f8abbccc14fec833e83b469a -r 66038323cb438066cb76e255fd436fc245056bfd tools/gatk/variant_apply_recalibration.xml --- a/tools/gatk/variant_apply_recalibration.xml +++ b/tools/gatk/variant_apply_recalibration.xml @@ -24,9 +24,13 @@ ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $sample_metadata in $gatk_param_type.sample_metadata: - -p '--sample_metadata "${sample_metadata.sample_metadata_file}"' + #for $pedigree in $gatk_param_type.pedigree: + -p '--pedigree "${pedigree.pedigree_file}"' #end for + #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: + -p '--pedigreeString "${pedigree_string.pedigree_string}"' + #end for + -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' #for $read_filter in $gatk_param_type.read_filter: -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" ###raise Exception( str( dir( $read_filter ) ) ) @@ -45,7 +49,7 @@ -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" #end for - -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"' + -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": @@ -126,9 +130,16 @@ </when><when value="advanced"> - <repeat name="sample_metadata" title="Sample Metadata"> - <param name="sample_metadata_file" type="data" format="txt" label="Sample file in JSON format" /> + <repeat name="pedigree" title="Pedigree file"> + <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples" /></repeat> + <repeat name="pedigree_string_repeat" title="Pedigree string"> + <param name="pedigree_string" type="text" value="" label="Pedigree string for samples" /> + </repeat> + <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information"> + <option value="STRICT" selected="True">STRICT</option> + <option value="SILENT">SILENT</option> + </param><repeat name="read_filter" title="Read Filter"><conditional name="read_filter_type"><param name="read_filter_type_selector" type="select" label="Read Filter Type"> @@ -150,7 +161,7 @@ <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list" label="Genomic intervals" /></repeat> - <param name="BTI_merge_rule" type="select" label="BTI merge rule"> + <param name="interval_set_rule" type="select" label="Interval set rule"><option value="UNION" selected="True">UNION</option><option value="INTERSECTION">INTERSECTION</option></param> diff -r fd76a44745351d69f8abbccc14fec833e83b469a -r 66038323cb438066cb76e255fd436fc245056bfd tools/gatk/variant_combine.xml --- a/tools/gatk/variant_combine.xml +++ b/tools/gatk/variant_combine.xml @@ -30,9 +30,13 @@ ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $sample_metadata in $gatk_param_type.sample_metadata: - -p '--sample_metadata "${sample_metadata.sample_metadata_file}"' + #for $pedigree in $gatk_param_type.pedigree: + -p '--pedigree "${pedigree.pedigree_file}"' #end for + #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: + -p '--pedigreeString "${pedigree_string.pedigree_string}"' + #end for + -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' #for $read_filter in $gatk_param_type.read_filter: -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" ###raise Exception( str( dir( $read_filter ) ) ) @@ -51,7 +55,7 @@ -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" #end for - -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"' + -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": @@ -146,9 +150,16 @@ </when><when value="advanced"> - <repeat name="sample_metadata" title="Sample Metadata"> - <param name="sample_metadata_file" type="data" format="txt" label="Sample file in JSON format" /> + <repeat name="pedigree" title="Pedigree file"> + <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples" /></repeat> + <repeat name="pedigree_string_repeat" title="Pedigree string"> + <param name="pedigree_string" type="text" value="" label="Pedigree string for samples" /> + </repeat> + <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information"> + <option value="STRICT" selected="True">STRICT</option> + <option value="SILENT">SILENT</option> + </param><repeat name="read_filter" title="Read Filter"><conditional name="read_filter_type"><param name="read_filter_type_selector" type="select" label="Read Filter Type"> @@ -170,7 +181,7 @@ <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list" label="Genomic intervals" /></repeat> - <param name="BTI_merge_rule" type="select" label="BTI merge rule"> + <param name="interval_set_rule" type="select" label="Interval set rule"><option value="UNION" selected="True">UNION</option><option value="INTERSECTION">INTERSECTION</option></param> diff -r fd76a44745351d69f8abbccc14fec833e83b469a -r 66038323cb438066cb76e255fd436fc245056bfd tools/gatk/variant_eval.xml --- a/tools/gatk/variant_eval.xml +++ b/tools/gatk/variant_eval.xml @@ -43,9 +43,13 @@ ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $sample_metadata in $gatk_param_type.sample_metadata: - -p '--sample_metadata "${sample_metadata.sample_metadata_file}"' + #for $pedigree in $gatk_param_type.pedigree: + -p '--pedigree "${pedigree.pedigree_file}"' #end for + #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: + -p '--pedigreeString "${pedigree_string.pedigree_string}"' + #end for + -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' #for $read_filter in $gatk_param_type.read_filter: -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" ###raise Exception( str( dir( $read_filter ) ) ) @@ -64,7 +68,7 @@ -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" #end for - -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"' + -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": @@ -204,9 +208,16 @@ </when><when value="advanced"> - <repeat name="sample_metadata" title="Sample Metadata"> - <param name="sample_metadata_file" type="data" format="txt" label="Sample file in JSON format" /> + <repeat name="pedigree" title="Pedigree file"> + <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples" /></repeat> + <repeat name="pedigree_string_repeat" title="Pedigree string"> + <param name="pedigree_string" type="text" value="" label="Pedigree string for samples" /> + </repeat> + <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information"> + <option value="STRICT" selected="True">STRICT</option> + <option value="SILENT">SILENT</option> + </param><repeat name="read_filter" title="Read Filter"><conditional name="read_filter_type"><param name="read_filter_type_selector" type="select" label="Read Filter Type"> @@ -228,7 +239,7 @@ <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list" label="Genomic intervals" /></repeat> - <param name="BTI_merge_rule" type="select" label="BTI merge rule"> + <param name="interval_set_rule" type="select" label="Interval set rule"><option value="UNION" selected="True">UNION</option><option value="INTERSECTION">INTERSECTION</option></param> diff -r fd76a44745351d69f8abbccc14fec833e83b469a -r 66038323cb438066cb76e255fd436fc245056bfd tools/gatk/variant_filtration.xml --- a/tools/gatk/variant_filtration.xml +++ b/tools/gatk/variant_filtration.xml @@ -37,9 +37,13 @@ ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $sample_metadata in $gatk_param_type.sample_metadata: - -p '--sample_metadata "${sample_metadata.sample_metadata_file}"' + #for $pedigree in $gatk_param_type.pedigree: + -p '--pedigree "${pedigree.pedigree_file}"' #end for + #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: + -p '--pedigreeString "${pedigree_string.pedigree_string}"' + #end for + -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' #for $read_filter in $gatk_param_type.read_filter: -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" ###raise Exception( str( dir( $read_filter ) ) ) @@ -58,7 +62,7 @@ -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" #end for - -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"' + -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": @@ -160,9 +164,16 @@ </when><when value="advanced"> - <repeat name="sample_metadata" title="Sample Metadata"> - <param name="sample_metadata_file" type="data" format="txt" label="Sample file in JSON format" /> + <repeat name="pedigree" title="Pedigree file"> + <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples" /></repeat> + <repeat name="pedigree_string_repeat" title="Pedigree string"> + <param name="pedigree_string" type="text" value="" label="Pedigree string for samples" /> + </repeat> + <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information"> + <option value="STRICT" selected="True">STRICT</option> + <option value="SILENT">SILENT</option> + </param><repeat name="read_filter" title="Read Filter"><conditional name="read_filter_type"><param name="read_filter_type_selector" type="select" label="Read Filter Type"> @@ -184,7 +195,7 @@ <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list" label="Genomic intervals" /></repeat> - <param name="BTI_merge_rule" type="select" label="BTI merge rule"> + <param name="interval_set_rule" type="select" label="Interval set rule"><option value="UNION" selected="True">UNION</option><option value="INTERSECTION">INTERSECTION</option></param> diff -r fd76a44745351d69f8abbccc14fec833e83b469a -r 66038323cb438066cb76e255fd436fc245056bfd tools/gatk/variant_recalibrator.xml --- a/tools/gatk/variant_recalibrator.xml +++ b/tools/gatk/variant_recalibrator.xml @@ -45,9 +45,13 @@ ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $sample_metadata in $gatk_param_type.sample_metadata: - -p '--sample_metadata "${sample_metadata.sample_metadata_file}"' + #for $pedigree in $gatk_param_type.pedigree: + -p '--pedigree "${pedigree.pedigree_file}"' #end for + #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: + -p '--pedigreeString "${pedigree_string.pedigree_string}"' + #end for + -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' #for $read_filter in $gatk_param_type.read_filter: -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" ###raise Exception( str( dir( $read_filter ) ) ) @@ -66,7 +70,7 @@ -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" #end for - -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"' + -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": @@ -390,9 +394,16 @@ </when><when value="advanced"> - <repeat name="sample_metadata" title="Sample Metadata"> - <param name="sample_metadata_file" type="data" format="txt" label="Sample file in JSON format" /> + <repeat name="pedigree" title="Pedigree file"> + <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples" /></repeat> + <repeat name="pedigree_string_repeat" title="Pedigree string"> + <param name="pedigree_string" type="text" value="" label="Pedigree string for samples" /> + </repeat> + <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information"> + <option value="STRICT" selected="True">STRICT</option> + <option value="SILENT">SILENT</option> + </param><repeat name="read_filter" title="Read Filter"><conditional name="read_filter_type"><param name="read_filter_type_selector" type="select" label="Read Filter Type"> @@ -414,7 +425,7 @@ <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list" label="Genomic intervals" /></repeat> - <param name="BTI_merge_rule" type="select" label="BTI merge rule"> + <param name="interval_set_rule" type="select" label="Interval set rule"><option value="UNION" selected="True">UNION</option><option value="INTERSECTION">INTERSECTION</option></param> diff -r fd76a44745351d69f8abbccc14fec833e83b469a -r 66038323cb438066cb76e255fd436fc245056bfd tools/gatk/variants_validate.xml --- a/tools/gatk/variants_validate.xml +++ b/tools/gatk/variants_validate.xml @@ -30,9 +30,13 @@ ##start standard gatk options #if $gatk_param_type.gatk_param_type_selector == "advanced": - #for $sample_metadata in $gatk_param_type.sample_metadata: - -p '--sample_metadata "${sample_metadata.sample_metadata_file}"' + #for $pedigree in $gatk_param_type.pedigree: + -p '--pedigree "${pedigree.pedigree_file}"' #end for + #for $pedigree_string in $gatk_param_type.pedigree_string_repeat: + -p '--pedigreeString "${pedigree_string.pedigree_string}"' + #end for + -p '--pedigreeValidationType "${gatk_param_type.pedigree_validation_type}"' #for $read_filter in $gatk_param_type.read_filter: -p '--read_filter "${read_filter.read_filter_type.read_filter_type_selector}" ###raise Exception( str( dir( $read_filter ) ) ) @@ -51,7 +55,7 @@ -d "--excludeIntervals" "${input_intervals.input_exclude_intervals}" "${input_intervals.input_exclude_intervals.ext}" "input_exlude_intervals_${interval_count}" #end for - -p '--BTI_merge_rule "${gatk_param_type.BTI_merge_rule}"' + -p '--interval_set_rule "${gatk_param_type.interval_set_rule}"' -p '--downsampling_type "${gatk_param_type.downsampling_type.downsampling_type_selector}"' #if str( $gatk_param_type.downsampling_type.downsampling_type_selector ) != "NONE": @@ -130,9 +134,16 @@ </when><when value="advanced"> - <repeat name="sample_metadata" title="Sample Metadata"> - <param name="sample_metadata_file" type="data" format="txt" label="Sample file in JSON format" /> + <repeat name="pedigree" title="Pedigree file"> + <param name="pedigree_file" type="data" format="txt" label="Pedigree files for samples" /></repeat> + <repeat name="pedigree_string_repeat" title="Pedigree string"> + <param name="pedigree_string" type="text" value="" label="Pedigree string for samples" /> + </repeat> + <param name="pedigree_validation_type" type="select" label="How strict should we be in validating the pedigree information"> + <option value="STRICT" selected="True">STRICT</option> + <option value="SILENT">SILENT</option> + </param><repeat name="read_filter" title="Read Filter"><conditional name="read_filter_type"><param name="read_filter_type_selector" type="select" label="Read Filter Type"> @@ -154,7 +165,7 @@ <param name="input_exclude_intervals" type="data" format="bed,gatk_interval,picard_interval_list" label="Genomic intervals" /></repeat> - <param name="BTI_merge_rule" type="select" label="BTI merge rule"> + <param name="interval_set_rule" type="select" label="Interval set rule"><option value="UNION" selected="True">UNION</option><option value="INTERSECTION">INTERSECTION</option></param> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: dan: Add picard_FastqToSam.xml and picard_SamToFastq.xml to tool_conf.xml.main.
by Bitbucket 21 Nov '11

21 Nov '11

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/fd76a4474535/ changeset: fd76a4474535 user: dan date: 2011-11-21 14:52:13 summary: Add picard_FastqToSam.xml and picard_SamToFastq.xml to tool_conf.xml.main. affected #: 3 files diff -r 830ea4877c7b05d1b58c3771be9adb481639d83b -r fd76a44745351d69f8abbccc14fec833e83b469a tool_conf.xml.main --- a/tool_conf.xml.main +++ b/tool_conf.xml.main @@ -406,6 +406,9 @@ <tool file="ngs_rna/filter_transcripts_via_tracking.xml" /></section><section name="NGS: Picard (beta)" id="picard_beta"> + <label text="Conversion" id="picard_conversion"/> + <tool file="picard/picard_FastqToSam.xml" /> + <tool file="picard/picard_SamToFastq.xml" /><label text="QC/Metrics for sam/bam" id="qcsambam"/><tool file="picard/picard_BamIndexStats.xml" /><tool file="picard/rgPicardASMetrics.xml" /> diff -r 830ea4877c7b05d1b58c3771be9adb481639d83b -r fd76a44745351d69f8abbccc14fec833e83b469a tools/picard/picard_FastqToSam.xml --- a/tools/picard/picard_FastqToSam.xml +++ b/tools/picard/picard_FastqToSam.xml @@ -1,6 +1,7 @@ <tool id="picard_FastqToSam" name="FASTQ to BAM" version="1.56.0"><description>creates an unaligned BAM file</description> - <requirements><requirement type="package">picard</requirement></requirements> + <requirements><requirement type="package" version="1.56.0">picard</requirement></requirements> + <command>java -XX:DefaultMaxRAMFraction=1 -XX:+UseParallelGC -jar "${GALAXY_DATA_INDEX_DIR}/shared/jars/picard/FastqToSam.jar" FASTQ="${input_fastq1}" diff -r 830ea4877c7b05d1b58c3771be9adb481639d83b -r fd76a44745351d69f8abbccc14fec833e83b469a tools/picard/picard_SamToFastq.xml --- a/tools/picard/picard_SamToFastq.xml +++ b/tools/picard/picard_SamToFastq.xml @@ -1,6 +1,7 @@ <tool id="picard_SamToFastq" name="SAM to FASTQ" version="1.56.0"><description>creates a FASTQ file</description> - <requirements><requirement type="package">picard</requirement></requirements> + <requirements><requirement type="package" version="1.56.0">picard</requirement></requirements> + <command>java -XX:DefaultMaxRAMFraction=1 -XX:+UseParallelGC -jar "${GALAXY_DATA_INDEX_DIR}/shared/jars/picard/SamToFastq.jar" INPUT="${input_sam}" Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: jgoecks: Fix Tile variable name so that it connotes what it actually stores.
by Bitbucket 19 Nov '11

19 Nov '11

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/830ea4877c7b/ changeset: 830ea4877c7b user: jgoecks date: 2011-11-20 00:15:24 summary: Fix Tile variable name so that it connotes what it actually stores. affected #: 1 file diff -r dfdd405b4115c1cf06bf7f362854088478560922 -r 830ea4877c7b05d1b58c3771be9adb481639d83b static/scripts/trackster.js --- a/static/scripts/trackster.js +++ b/static/scripts/trackster.js @@ -2301,7 +2301,7 @@ this.high = (index + 1) * DENSITY * resolution; this.resolution = resolution; // Wrap element in div for background. - this.canvas = $("<div class='track-tile'/>").append(canvas); + this.html_elt = $("<div class='track-tile'/>").append(canvas); this.data = data; this.stale = false; }; @@ -2324,13 +2324,13 @@ this.message = message; this.feature_mapper = feature_mapper; - // Add message + action icons to tile's "canvas" TODO: rename canvas to element/html or something similar. + // Add message + action icons to tile's html. if (this.message) { var - canvas = this.canvas.children()[0], + canvas = this.html_elt.children()[0], message_div = $("<div/>").addClass("tile-message").text(this.message). // -1 to account for border. - css({'height': ERROR_PADDING-1, 'width': canvas.width}).prependTo(this.canvas), + css({'height': ERROR_PADDING-1, 'width': canvas.width}).prependTo(this.html_elt), more_down_icon = $("<a href='javascript:void(0);'/>").addClass("icon more-down").appendTo(message_div), more_across_icon = $("<a href='javascript:void(0);'/>").addClass("icon more-across").appendTo(message_div); @@ -2371,7 +2371,7 @@ // Only show popups in Pack mode. if (tile.mode !== "Pack") { return; } - $(this.canvas).hover( function() { + $(this.html_elt).hover( function() { this.hovered = true; $(this).mousemove(); }, function() { @@ -2435,14 +2435,14 @@ } // Attach popup to canvas's parent. - popup.appendTo($(tile.canvas).parent()); + popup.appendTo($(tile.html_elt).parent()); // Offsets are within canvas, but popup must be positioned relative to parent element. // parseInt strips "px" from left, top measurements. +7 so that mouse pointer does not // overlap popup. var - popupX = offsetX + parseInt( tile.canvas.css("left") ) - popup.width() / 2, - popupY = offsetY + parseInt( tile.canvas.css("top") ) + 7; + popupX = offsetX + parseInt( tile.html_elt.css("left") ) - popup.width() / 2, + popupY = offsetY + parseInt( tile.html_elt.css("top") ) + 7; popup.css("left", popupX + "px").css("top", popupY + "px") } else if (!e.isPropagationStopped()) { @@ -2959,7 +2959,7 @@ tile = tiles[tile_index]; if (!tile.message) { // Need to align with other tile(s) that have message(s). - tile.canvas.css("padding-top", ERROR_PADDING); + tile.html_elt.css("padding-top", ERROR_PADDING); } } } @@ -3031,7 +3031,7 @@ show_tile: function(tile, parent_element, w_scale) { var track = this, - tile_element = tile.canvas; + tile_element = tile.html_elt; // // Show/move tile element. @@ -3456,8 +3456,8 @@ for (var i = 0; i < tiles.length; i++) { var tile = tiles[i]; if (tile.max_val !== global_max) { - tile.canvas.remove(); - track.draw_helper(true, width, tile.index, tile.resolution, tile.canvas.parent(), w_scale, [], { max: global_max }); + tile.html_elt.remove(); + track.draw_helper(true, width, tile.index, tile.resolution, tile.html_elt.parent(), w_scale, [], { max: global_max }); } } } Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: jgoecks: Fix GFFDataProvider bugs introduced in 9b7d5c1c0be6.
by Bitbucket 19 Nov '11

19 Nov '11

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/dfdd405b4115/ changeset: dfdd405b4115 user: jgoecks date: 2011-11-19 21:28:16 summary: Fix GFFDataProvider bugs introduced in 9b7d5c1c0be6. affected #: 1 file diff -r 4c6f1004071d5055c9bf2d0b35f5bfe077b79e1e -r dfdd405b4115c1cf06bf7f362854088478560922 lib/galaxy/visualization/tracks/data_providers.py --- a/lib/galaxy/visualization/tracks/data_providers.py +++ b/lib/galaxy/visualization/tracks/data_providers.py @@ -99,7 +99,7 @@ pass - def get_data( self, chrom, start, end, start_val=0, max_vals=None, **kwargs ): + def get_data( self, chrom, start, end, start_val=0, max_vals=sys.maxint, **kwargs ): """ Returns data in region defined by chrom, start, and end. start_val and max_vals are used to denote the data to return: start_val is the first element to @@ -914,7 +914,15 @@ """ start, end = int( start ), int( end ) source = open( self.original_dataset.file_name ) - return GFFReaderWrapper( source, fix_strand=True ) + + def features_in_region_iter(): + for feature in GFFReaderWrapper( source, fix_strand=True ): + # Only provide features that are in region. + feature_start, feature_end = convert_gff_coords_to_bed( [ feature.start, feature.end ] ) + if feature.chrom != chrom or feature_start < start or feature_end > end: + continue + yield feature + return features_in_region_iter() def process_data( self, iterator, start_val=0, max_vals=None, **kwargs ): """ @@ -931,9 +939,6 @@ message = ERROR_MAX_VALS % ( max_vals, "reads" ) break - feature_start, feature_end = convert_gff_coords_to_bed( [ feature.start, feature.end ] ) - if feature.chrom != chrom or feature_start < start or feature_end > end: - continue payload = package_gff_feature( feature ) payload.insert( 0, offset ) results.append( payload ) Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: greg: Add the ability to reset all metadata (for every change set) in a tool shed repository (currently restricted to an admin), and add a fix for checking security when making changes to tool shed repository information on the Manage repsoitory page.
by Bitbucket 18 Nov '11

18 Nov '11

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/4c6f1004071d/ changeset: 4c6f1004071d user: greg date: 2011-11-18 22:44:10 summary: Add the ability to reset all metadata (for every change set) in a tool shed repository (currently restricted to an admin), and add a fix for checking security when making changes to tool shed repository information on the Manage repsoitory page. affected #: 4 files diff -r 07df6866125adb6f3723aec8303e9300338e4cdc -r 4c6f1004071d5055c9bf2d0b35f5bfe077b79e1e lib/galaxy/webapps/community/controllers/common.py --- a/lib/galaxy/webapps/community/controllers/common.py +++ b/lib/galaxy/webapps/community/controllers/common.py @@ -343,6 +343,127 @@ mimetype=mimetype ) ) metadata_dict[ 'datatypes' ] = datatypes return metadata_dict +def generate_metadata_for_repository_tip( trans, id, ctx, changeset_revision, repo_dir ): + # Browse the repository tip files on disk to generate metadata. This is faster than + # the generate_metadata_for_changeset_revision() method below because fctx.data() does + # not have to be written to disk to load tools. also, since changeset_revision is the + # repository tip, we handle things like .loc.sample files here. + metadata_dict = {} + invalid_files = [] + sample_files = [] + datatypes_config = None + # Find datatypes_conf.xml if it exists. + for root, dirs, files in os.walk( repo_dir ): + if root.find( '.hg' ) < 0: + for name in files: + if name == 'datatypes_conf.xml': + datatypes_config = os.path.abspath( os.path.join( root, name ) ) + break + if datatypes_config: + metadata_dict = generate_datatypes_metadata( trans, id, changeset_revision, datatypes_config, metadata_dict ) + # Find all special .sample files. + for root, dirs, files in os.walk( repo_dir ): + if root.find( '.hg' ) < 0: + for name in files: + if name.endswith( '.sample' ): + sample_files.append( os.path.abspath( os.path.join( root, name ) ) ) + # Find all tool configs and exported workflows. + for root, dirs, files in os.walk( repo_dir ): + if root.find( '.hg' ) < 0 and root.find( 'hgrc' ) < 0: + if '.hg' in dirs: + dirs.remove( '.hg' ) + for name in files: + # Find all tool configs. + if name != 'datatypes_conf.xml' and name.endswith( '.xml' ): + full_path = os.path.abspath( os.path.join( root, name ) ) + try: + tool = load_tool( trans, full_path ) + valid = True + except Exception, e: + valid = False + invalid_files.append( ( name, str( e ) ) ) + if valid and tool is not None: + can_set_metadata, invalid_files = check_tool_input_params( trans, name, tool, sample_files, invalid_files ) + if can_set_metadata: + # Update the list of metadata dictionaries for tools in metadata_dict. + tool_config = os.path.join( root, name ) + metadata_dict = generate_tool_metadata( trans, id, changeset_revision, tool_config, tool, metadata_dict ) + # Find all exported workflows + elif name.endswith( '.ga' ): + try: + full_path = os.path.abspath( os.path.join( root, name ) ) + # Convert workflow data from json + fp = open( full_path, 'rb' ) + workflow_text = fp.read() + fp.close() + exported_workflow_dict = from_json_string( workflow_text ) + if 'a_galaxy_workflow' in exported_workflow_dict and exported_workflow_dict[ 'a_galaxy_workflow' ] == 'true': + # Update the list of metadata dictionaries for workflows in metadata_dict. + metadata_dict = generate_workflow_metadata( trans, id, changeset_revision, exported_workflow_dict, metadata_dict ) + except Exception, e: + invalid_files.append( ( name, str( e ) ) ) + return metadata_dict, invalid_files +def generate_metadata_for_changeset_revision( trans, id, ctx, changeset_revision, repo_dir ): + # Browse repository files within a change set to generate metadata. + metadata_dict = {} + invalid_files = [] + sample_files = [] + datatypes_config = None + # Find datatypes_conf.xml if it exists. + for filename in ctx: + if filename == 'datatypes_conf.xml': + fctx = ctx[ filename ] + datatypes_config = fctx.data() + break + if datatypes_config: + metadata_dict = generate_datatypes_metadata( trans, id, changeset_revision, datatypes_config, metadata_dict ) + # Get all tool config file names from the hgweb url, something like: + # /repos/test/convert_chars1/file/e58dcf0026c7/convert_characters.xml + for filename in ctx: + # Find all tool configs. + if filename != 'datatypes_conf.xml' and filename.endswith( '.xml' ): + fctx = ctx[ filename ] + # Write the contents of the old tool config to a temporary file. + # TODO: figure out how to enhance the load_tool method so that a + # temporary disk file is not necessary in order to pass the tool + # config. + fh = tempfile.NamedTemporaryFile( 'w' ) + tmp_filename = fh.name + fh.close() + fh = open( tmp_filename, 'w' ) + fh.write( fctx.data() ) + fh.close() + try: + tool = load_tool( trans, tmp_filename ) + valid = True + except Exception, e: + invalid_files.append( ( filename, str( e ) ) ) + valid = False + if valid and tool is not None: + # Update the list of metadata dictionaries for tools in metadata_dict. Note that filename + # here is the relative path to the config file within the change set context, something + # like filtering.xml, but when the change set was the repository tip, the value was + # something like database/community_files/000/repo_1/filtering.xml. This shouldn't break + # anything, but may result in a bit of confusion when maintaining the code / data over time. + # IMPORTANT NOTE: Here we are assuming that since the current change set is not the repository + # tip, we do not have to handle any .loc.sample files since they would have been handled previously. + metadata_dict = generate_tool_metadata( trans, id, changeset_revision, filename, tool, metadata_dict ) + try: + os.unlink( tmp_filename ) + except: + pass + # Find all exported workflows. + elif filename.endswith( '.ga' ): + try: + fctx = ctx[ filename ] + workflow_text = fctx.data() + exported_workflow_dict = from_json_string( workflow_text ) + if 'a_galaxy_workflow' in exported_workflow_dict and exported_workflow_dict[ 'a_galaxy_workflow' ] == 'true': + # Update the list of metadata dictionaries for workflows in metadata_dict. + metadata_dict = generate_workflow_metadata( trans, id, changeset_revision, exported_workflow_dict, metadata_dict ) + except Exception, e: + invalid_files.append( ( name, str( e ) ) ) + return metadata_dict, invalid_files def set_repository_metadata( trans, id, changeset_revision, **kwd ): """Set repository metadata""" message = '' @@ -350,102 +471,12 @@ repository = get_repository( trans, id ) repo_dir = repository.repo_path repo = hg.repository( get_configured_ui(), repo_dir ) - invalid_files = [] - sample_files = [] - datatypes_config = None ctx = get_changectx_for_changeset( trans, repo, changeset_revision ) if ctx is not None: - metadata_dict = {} if changeset_revision == repository.tip: - # Find datatypes_conf.xml if it exists. - for root, dirs, files in os.walk( repo_dir ): - if root.find( '.hg' ) < 0: - for name in files: - if name == 'datatypes_conf.xml': - datatypes_config = os.path.abspath( os.path.join( root, name ) ) - break - if datatypes_config: - metadata_dict = generate_datatypes_metadata( trans, id, changeset_revision, datatypes_config, metadata_dict ) - # Find all special .sample files. - for root, dirs, files in os.walk( repo_dir ): - if root.find( '.hg' ) < 0: - for name in files: - if name.endswith( '.sample' ): - sample_files.append( os.path.abspath( os.path.join( root, name ) ) ) - # Find all tool configs and exported workflows. - for root, dirs, files in os.walk( repo_dir ): - if root.find( '.hg' ) < 0 and root.find( 'hgrc' ) < 0: - if '.hg' in dirs: - dirs.remove( '.hg' ) - for name in files: - # Find all tool configs. - if name != 'datatypes_conf.xml' and name.endswith( '.xml' ): - full_path = os.path.abspath( os.path.join( root, name ) ) - try: - tool = load_tool( trans, full_path ) - valid = True - except Exception, e: - valid = False - invalid_files.append( ( name, str( e ) ) ) - if valid and tool is not None: - can_set_metadata, invalid_files = check_tool_input_params( trans, name, tool, sample_files, invalid_files ) - if can_set_metadata: - # Update the list of metadata dictionaries for tools in metadata_dict. - tool_config = os.path.join( root, name ) - metadata_dict = generate_tool_metadata( trans, id, changeset_revision, tool_config, tool, metadata_dict ) - # Find all exported workflows - elif name.endswith( '.ga' ): - try: - full_path = os.path.abspath( os.path.join( root, name ) ) - # Convert workflow data from json - fp = open( full_path, 'rb' ) - workflow_text = fp.read() - fp.close() - exported_workflow_dict = from_json_string( workflow_text ) - if exported_workflow_dict[ 'a_galaxy_workflow' ] == 'true': - # Update the list of metadata dictionaries for workflows in metadata_dict. - metadata_dict = generate_workflow_metadata( trans, id, changeset_revision, exported_workflow_dict, metadata_dict ) - except Exception, e: - invalid_files.append( ( name, str( e ) ) ) + metadata_dict, invalid_files = generate_metadata_for_repository_tip( trans, id, ctx, changeset_revision, repo_dir ) else: - # Find all special .sample files first. - for filename in ctx: - if filename.endswith( '.sample' ): - sample_files.append( os.path.abspath( filename ) ) - # Get all tool config file names from the hgweb url, something like: - # /repos/test/convert_chars1/file/e58dcf0026c7/convert_characters.xml - for filename in ctx: - # Find all tool configs - we do not have to update metadata for workflows or datatypes in anything - # but repository tips (handled above) since at the time this code was written, no workflows or - # dataytpes_conf.xml files exist in tool shed repositories, so they can only be added in future tips. - if filename.endswith( '.xml' ): - fctx = ctx[ filename ] - # Write the contents of the old tool config to a temporary file. - fh = tempfile.NamedTemporaryFile( 'w' ) - tmp_filename = fh.name - fh.close() - fh = open( tmp_filename, 'w' ) - fh.write( fctx.data() ) - fh.close() - try: - tool = load_tool( trans, tmp_filename ) - valid = True - except Exception, e: - invalid_files.append( ( filename, str( e ) ) ) - valid = False - if valid and tool is not None: - can_set_metadata, invalid_files = check_tool_input_params( trans, filename, tool, sample_files, invalid_files ) - if can_set_metadata: - # Update the list of metadata dictionaries for tools in metadata_dict. Note that filename - # here is the relative path to the config file within the change set context, something - # like filtering.xml, but when the change set was the repository tip, the value was - # something like database/community_files/000/repo_1/filtering.xml. This shouldn't break - # anything, but may result in a bit of confusion when maintaining the code / data over time. - metadata_dict = generate_tool_metadata( trans, id, changeset_revision, filename, tool, metadata_dict ) - try: - os.unlink( tmp_filename ) - except: - pass + metadata_dict, invalid_files = generate_metadata_for_changeset_revision( trans, id, ctx, changeset_revision, repo_dir ) if metadata_dict: if changeset_revision == repository.tip: if new_tool_metadata_required( trans, id, metadata_dict ) or new_workflow_metadata_required( trans, id, metadata_dict ): @@ -467,8 +498,8 @@ trans.sa_session.add( repository_metadata ) trans.sa_session.flush() else: - message = "Revision '%s' includes no tools or exported workflows for which metadata can be defined " % str( changeset_revision ) - message += "so this revision cannot be automatically installed into a local Galaxy instance." + message = "Revision '%s' includes no tools, datatypes or exported workflows for which metadata can " % str( changeset_revision ) + message += "be defined so this revision cannot be automatically installed into a local Galaxy instance." status = "error" else: # change_set is None diff -r 07df6866125adb6f3723aec8303e9300338e4cdc -r 4c6f1004071d5055c9bf2d0b35f5bfe077b79e1e lib/galaxy/webapps/community/controllers/repository.py --- a/lib/galaxy/webapps/community/controllers/repository.py +++ b/lib/galaxy/webapps/community/controllers/repository.py @@ -1311,15 +1311,14 @@ if params.get( 'edit_repository_button', False ): flush_needed = False # TODO: add a can_manage in the security agent. - if user != repository.user or not trans.user_is_admin(): + if not ( user.email == repository.user.email or trans.user_is_admin() ): message = "You are not the owner of this repository, so you cannot manage it." - status = error return trans.response.send_redirect( web.url_for( controller='repository', action='view_repository', id=id, webapp='community', message=message, - status=status ) ) + status='error' ) ) if description != repository.description: repository.description = description flush_needed = True @@ -1447,6 +1446,10 @@ changesets = [] for changeset in repo.changelog: ctx = repo.changectx( changeset ) + if get_repository_metadata_by_changeset_revision( trans, id, str( ctx ) ): + has_metadata = True + else: + has_metadata = False t, tz = ctx.date() date = datetime( *time.gmtime( float( t ) - tz )[:6] ) display_date = date.strftime( "%Y-%m-%d" ) @@ -1457,7 +1460,8 @@ 'description' : ctx.description(), 'files' : ctx.files(), 'user' : ctx.user(), - 'parent' : ctx.parents()[0] } + 'parent' : ctx.parents()[0], + 'has_metadata' : has_metadata } # Make sure we'll view latest changeset first. changesets.insert( 0, change_dict ) is_malicious = change_set_is_malicious( trans, id, repository.tip ) @@ -1608,6 +1612,190 @@ message=message, status=status ) ) @web.expose + def reset_all_metadata( self, trans, id, **kwd ): + params = util.Params( kwd ) + message = util.restore_text( params.get( 'message', '' ) ) + status = params.get( 'status', 'done' ) + repository = get_repository( trans, id ) + repo_dir = repository.repo_path + repo = hg.repository( get_configured_ui(), repo_dir ) + if len( repo ) == 1: + message, status = set_repository_metadata( trans, id, repository.tip, **kwd ) + else: + # The following will be a list of changeset_revisions that have been created or updated. + # When the following loop completes, we'll delete all repository_metadata records for + # this repository that do not have a changeset_revision value in this list. + changeset_revisions = [] + repository_metadata_tup_for_comparison = () + for changeset in repo.changelog: + ctx = repo.changectx( changeset ) + current_changeset_revision = str( ctx ) + ctx = get_changectx_for_changeset( trans, repo, current_changeset_revision ) + current_metadata_dict, invalid_files = generate_metadata_for_changeset_revision( trans, id, ctx, current_changeset_revision, repo_dir ) + if current_metadata_dict: + if repository_metadata_tup_for_comparison: + ancestor_changeset_revision, ancestor_metadata_dict = repository_metadata_tup_for_comparison + comparison = self.__compare_changeset_revisions( ancestor_changeset_revision, + ancestor_metadata_dict, + current_changeset_revision, + current_metadata_dict ) + # The value of comparsion will be one of: + # 'no metadata' - no metadata for either ancestor or current, so continue from current + # 'equal' - ancestor metadata is equivalent to current metadata, so continue from current + # 'subset' - ancestor metadata is a subset of current metadata, so continue from current + # 'not equal and not subset' - ancestor metadata is neither equal to nor a subset of current + # metadata, so persist ancestor metadata. + if comparison in [ 'no metadata', 'equal', 'subset' ]: + repository_metadata_tup_for_comparison = ( current_changeset_revision, current_metadata_dict ) + elif comparison == 'not equal and not subset': + self.__create_or_update_repository_metadata( trans, id, repository, ancestor_changeset_revision, ancestor_metadata_dict ) + # keep track of the changeset_revisions that we've persisted. + changeset_revisions.append( ancestor_changeset_revision ) + repository_metadata_tup_for_comparison = () + else: + # We're at the first change set in the change log. + repository_metadata_tup_for_comparison = ( current_changeset_revision, current_metadata_dict ) + if not ctx.children(): + # We're at the end of the change log. + self.__create_or_update_repository_metadata( trans, id, repository, current_changeset_revision, current_metadata_dict ) + changeset_revisions.append( current_changeset_revision ) + elif ancestor_metadata_dict: + # Our current change set has no metadata, but our ancestor change set has metadata, so save it. + self.__create_or_update_repository_metadata( trans, id, repository, ancestor_changeset_revision, ancestor_metadata_dict ) + # keep track of the changeset_revisions that we've persisted. + changeset_revisions.append( ancestor_changeset_revision ) + repository_metadata_tup_for_comparison = () + ancestor_changeset_revision = current_changeset_revision + ancestor_metadata_dict = current_metadata_dict + self.__clean_repository_metadata( trans, id, changeset_revisions ) + if not message: + message = "Repository metadata has been reset." + status = 'done' + return trans.response.send_redirect( web.url_for( controller='repository', + action='manage_repository', + id=id, + message=message, + status=status ) ) + def __clean_repository_metadata( self, trans, id, changeset_revisions ): + # Delete all repository_metadata reecords associated with the repository + # that have a changeset_revision that is not in changeset_revisions. + for repository_metadata in trans.sa_session.query( trans.model.RepositoryMetadata ) \ + .filter( trans.model.RepositoryMetadata.table.c.repository_id == trans.security.decode_id( id ) ): + if repository_metadata.changeset_revision not in changeset_revisions: + trans.sa_session.delete( repository_metadata ) + trans.sa_session.flush() + def __create_or_update_repository_metadata( self, trans, id, repository, changeset_revision, metadata_dict ): + repository_metadata = get_repository_metadata_by_changeset_revision( trans, id, changeset_revision ) + if repository_metadata: + # Update RepositoryMetadata.metadata. + repository_metadata.metadata = metadata_dict + trans.sa_session.add( repository_metadata ) + trans.sa_session.flush() + else: + # Create a new repository_metadata table row. + repository_metadata = trans.model.RepositoryMetadata( repository.id, changeset_revision, metadata_dict ) + trans.sa_session.add( repository_metadata ) + trans.sa_session.flush() + def __compare_changeset_revisions( self, ancestor_changeset_revision, ancestor_metadata_dict, current_changeset_revision, current_metadata_dict ): + # The metadata associated with ancestor_changeset_revision is ancestor_metadata_dict. This changeset_revision + # is an ancestor of current_changeset_revision which is associated with current_metadata_dict. + # Get information about tools. + if 'tools' in ancestor_metadata_dict: + ancestor_tools = ancestor_metadata_dict[ 'tools' ] + else: + ancestor_tools = [] + if 'tools' in current_metadata_dict: + current_tools = current_metadata_dict[ 'tools' ] + else: + current_tools = [] + ancestor_guids = [] + for tool_dict in ancestor_tools: + ancestor_guids.append( tool_dict[ 'guid' ] ) + ancestor_guids.sort() + current_guids = [] + for tool_dict in current_tools: + current_guids.append( tool_dict[ 'guid' ] ) + current_guids.sort() + # Get information about workflows. + if 'workflows' in ancestor_metadata_dict: + ancestor_workflows = ancestor_metadata_dict[ 'workflows' ] + else: + ancestor_workflows = [] + if 'workflows' in current_metadata_dict: + current_workflows = current_metadata_dict[ 'workflows' ] + else: + current_workflows = [] + # Get information about datatypes. + if 'datatypes' in ancestor_metadata_dict: + ancestor_datatypes = ancestor_metadata_dict[ 'datatypes' ] + else: + ancestor_datatypes = [] + if 'datatypes' in current_metadata_dict: + current_datatypes = current_metadata_dict[ 'datatypes' ] + else: + current_datatypes = [] + # Handle case where no metadata exists for either changeset. + if not ( ancestor_guids or current_guids or ancestor_workflows or current_workflows or ancestor_datatypes or current_datatypes ): + return 'no metadata' + workflow_comparison = self.__compare_workflows( ancestor_workflows, current_workflows ) + datatype_comparison = self.__compare_datatypes( ancestor_datatypes, current_datatypes ) + # Handle case where all metadata is the same. + if ancestor_guids == current_guids and workflow_comparison == 'equal' and datatype_comparison == 'equal': + return 'equal' + if workflow_comparison == 'subset' and datatype_comparison == 'subset': + is_subset = True + for guid in ancestor_guids: + if guid not in current_guids: + is_subset = False + break + if is_subset: + return 'subset' + return 'not equal and not subset' + def __compare_workflows( self, ancestor_workflows, current_workflows ): + # Determine if ancestor_workflows is the same as current_workflows + # or if ancestor_workflows is a subset of current_workflows. + if len( ancestor_workflows ) <= len( current_workflows ): + for ancestor_workflow in ancestor_workflows: + # Currently the only way to differentiate workflows is by name. + ancestor_workflow_name = ancestor_workflow[ 'name' ] + found_in_current = False + for current_workflow in current_workflows: + if current_workflow[ 'name' ] == ancestor_workflow_name: + found_in_current = True + break + if not found_in_current: + return 'not equal and not subset' + if len( ancestor_workflows ) == len( current_workflows ): + return 'equal' + else: + return 'subset' + return 'not equal and not subset' + def __compare_datatypes( self, ancestor_datatypes, current_datatypes ): + # Determine if ancestor_datatypes is the same as current_datatypes + # or if ancestor_datatypes is a subset of current_datatypes. Each + # datatype dict looks something like: + # {"dtype": "galaxy.datatypes.images:Image", "extension": "pdf", "mimetype": "application/pdf"} + if len( ancestor_datatypes ) <= len( current_datatypes ): + for ancestor_datatype in ancestor_datatypes: + # Currently the only way to differentiate datatypes is by name. + ancestor_datatype_dtype = ancestor_datatype[ 'dtype' ] + ancestor_datatype_extension = ancestor_datatype[ 'extension' ] + ancestor_datatype_mimetype = ancestor_datatype[ 'mimetype' ] + found_in_current = False + for current_datatype in current_datatypes: + if current_datatype[ 'dtype' ] == ancestor_datatype_dtype and \ + current_datatype[ 'extension' ] == ancestor_datatype_extension and \ + current_datatype[ 'mimetype' ] == ancestor_datatype_mimetype: + found_in_current = True + break + if not found_in_current: + return 'not equal and not subset' + if len( ancestor_datatypes ) == len( current_datatypes ): + return 'equal' + else: + return 'subset' + return 'not equal and not subset' + @web.expose def display_tool( self, trans, repository_id, tool_config, changeset_revision, **kwd ): params = util.Params( kwd ) message = util.restore_text( params.get( 'message', '' ) ) diff -r 07df6866125adb6f3723aec8303e9300338e4cdc -r 4c6f1004071d5055c9bf2d0b35f5bfe077b79e1e templates/webapps/community/repository/manage_repository.mako --- a/templates/webapps/community/repository/manage_repository.mako +++ b/templates/webapps/community/repository/manage_repository.mako @@ -20,6 +20,7 @@ else: browse_label = 'Browse repository tip files' can_set_malicious = metadata and can_set_metadata and is_admin and changeset_revision == repository.tip + can_reset_all_metadata = is_admin and len( repo ) > 0 %><%! @@ -88,6 +89,9 @@ %if can_contact_owner: <a class="action-button" href="${h.url_for( controller='repository', action='contact_owner', id=trans.security.encode_id( repository.id ), webapp='community' )}">Contact repository owner</a> %endif + %if can_reset_all_metadata: + <a class="action-button" href="${h.url_for( controller='repository', action='reset_all_metadata', id=trans.security.encode_id( repository.id ), webapp='community' )}">Reset all repository metadata</a> + %endif %if can_download: <a class="action-button" href="${h.url_for( controller='repository', action='download', repository_id=trans.app.security.encode_id( repository.id ), changeset_revision=changeset_revision, file_type='gz' )}">Download as a .tar.gz file</a><a class="action-button" href="${h.url_for( controller='repository', action='download', repository_id=trans.app.security.encode_id( repository.id ), changeset_revision=changeset_revision, file_type='bz2' )}">Download as a .tar.bz2 file</a> diff -r 07df6866125adb6f3723aec8303e9300338e4cdc -r 4c6f1004071d5055c9bf2d0b35f5bfe077b79e1e templates/webapps/community/repository/view_changelog.mako --- a/templates/webapps/community/repository/view_changelog.mako +++ b/templates/webapps/community/repository/view_changelog.mako @@ -106,6 +106,10 @@ ctx_parent_str = 'None' else: ctx_parent_str = "%s:%s" % ( ctx_parent_rev, ctx_parent ) + if changeset[ 'has_metadata' ]: + has_metadata_str = 'Repository metadata is associated with this change set.' + else: + has_metadata_str = '' %><% display_date = changeset[ 'display_date' ] %> %if test_date != display_date: @@ -113,6 +117,11 @@ %endif <tr><td> + %if is_admin and has_metadata_str: + <div class="form-row"> + ${has_metadata_str} + </div> + %endif <div class="form-row"><label>Description:</label><a href="${h.url_for( controller='repository', action='view_changeset', id=trans.security.encode_id( repository.id ), ctx_str=ctx_str )}">${changeset[ 'description' ]}</a> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

← Newer
1
2
3
4
5
6
7
...
13
Older →

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

galaxy-commits November 2011