Mercurial > repos > iuc > medaka_variant
diff variant.xml @ 12:0f5f4a208660 draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/medaka commit 86211daa63a6f39524df8759364795b782324303"
| author | iuc |
|---|---|
| date | Fri, 17 Sep 2021 20:22:49 +0000 |
| parents | 9fb055604648 |
| children | 222669c4afb6 |
line wrap: on
line diff
--- a/variant.xml Sun Sep 12 20:35:26 2021 +0000 +++ b/variant.xml Fri Sep 17 20:22:49 2021 +0000 @@ -1,28 +1,11 @@ <?xml version="1.0"?> -<tool id="medaka_variant" name="medaka variant tool" version="@TOOL_VERSION@+galaxy0" profile="@PROFILE@"> - <description>Probability decoding</description> +<tool id="medaka_variant" name="medaka variant tool" version="@TOOL_VERSION@+galaxy1" profile="@PROFILE@"> + <description>decodes variant calls from medaka consensus output</description> <macros> <import>macros.xml</import> </macros> <expand macro="requirements"/> - <expand macro="version_command"/> - - <configfiles> - <configfile name="convert_fasta"> -import sys -infile = open(sys.argv[1], 'r') -outfile = open(sys.argv[2], 'w') -for line in infile: - if line[0] == '>': - outfile.write(line) - else: - outfile.write(line.upper()) -infile.close() -outfile.close() - </configfile> - </configfiles> - <command detect_errors="exit_code"><![CDATA[ ## initialize @REF_FASTA@ @@ -44,8 +27,6 @@ #for $current in $pool.inputs '$current' #end for - '$out_result' ## output - 2>&1 | tee '$out_log' #elif $pool.pool_mode == "No": ## run medaka variant @@ -60,16 +41,17 @@ ## required reference.fa '$pool.input' - '$out_result' ##output +#end if +#if str($output_annotated.output_annotated_select) == 'false': + '$out_variants' ##output 2>&1 | tee '$out_log' -#end if -#if $out_annotated: - ## medaka annotate errors out if the reference is lower case at a position it's annotating because it checks vs the ref base in the vcf - && python '$convert_fasta' reference.fa upper_reference.fa +#else + raw.vcf ##output of medaka variant + 2>&1 | tee '$out_log' && ln -s '$output_annotated.in_bam' in.bam && ln -s '$output_annotated.in_bam.metadata.bam_index' in.bai - && medaka tools annotate --dpsp --pad $output_annotated.pad '$out_result' upper_reference.fa in.bam tmp.vcf - && python '$__tool_directory__/convert_VCF_info_fields.py' tmp.vcf '$out_annotated' + && medaka tools annotate --dpsp --pad $output_annotated.pad raw.vcf reference.fa in.bam tmp.vcf + && python '$__tool_directory__/convert_VCF_info_fields.py' tmp.vcf '$out_variants' #end if ]]></command> <inputs> @@ -99,39 +81,38 @@ <param argument="--ambig_ref" type="boolean" truevalue="--ambig_ref" falsevalue="" label="Decode variants at ambiguous reference positions?" checked="false"/> <param argument="--gvcf" type="boolean" truevalue="--gvcf" falsevalue="" label="Output VCF records for reference loci predicted to be non-variant?" checked="false"/> <conditional name="output_annotated"> - <param name="output_annotated_select" type="select" label="Output annotated VCF?" help="Annotate allele frequency, depth of coverage, etc for each variant (requires BAM file)"> - <option value="true" selected="true">Output annotated VCF</option> - <option value="false">Don't output annotated VCF</option> + <param name="output_annotated_select" type="select" + label="Type of VCF to generate" + help="Variant INFO fields in the VCF can be extended to include allele frequency, depth of coverage, etc., but this requires a BAM dataset to calculate those values from."> + <option value="true" selected="true">Write annotated VCF with extended INFO</option> + <option value="false">Write original decoded VCF with minimal INFO field</option> </param> <when value="true"> - <param name="in_bam" type="data" format="bam" optional="false" label="BAM to annotate the VCF"/> - <param name="pad" type="integer" min="1" value="25" label="Padding width on either side of variant for realignment in medaka tools anntotate, used to calculate DPSP, DPSPS, AF, FAF, RAF, SB, DP4, and AS in the output annotated VCF"/> + <param name="in_bam" type="data" format="bam" optional="false" label="BAM to caclulate additional INFO fields from"/> + <param name="pad" type="integer" min="1" value="25" + label="Padding width on either side of variant for realignment" + help="To calculate the additional INFO fields the tool will run medaka tools anntotate, which performs local realignment of the region +- this width around each variant. All calculated new fields will depend on the width chosen, so only change this value if you know what you are doing." /> </when> <when value="false"/> </conditional> <param name="output_log_bool" type="boolean" label="Output log file?" checked="true"/> </inputs> <outputs> - <!-- standard --> - <data name="out_result" format="vcf" label="${tool.name} on ${on_string}: Result"/> - <!-- optional --> - <data name="out_annotated" format="vcf" label="${tool.name} on ${on_string}: Annotated"> - <filter>output_annotated['output_annotated_select']!='false'</filter> - </data> + <data name="out_variants" format="vcf" label="${tool.name} on ${on_string}: called variants"/> <data name="out_log" format="tabular" label="${tool.name} on ${on_string}: Log"> <filter>output_log_bool</filter> </data> </outputs> <tests> <!-- #1 default --> - <test expect_num_outputs="3"> + <test expect_num_outputs="2"> <conditional name="pool"> <param name="pool_mode" value="Yes"/> <param name="inputs" value="medaka_test.hdf,medaka_test.hdf"/> </conditional> <conditional name="reference_source"> <param name="reference_source_selector" value="history"/> - <param name="ref_file" value="ref.fasta.gz"/> + <param name="ref_file" value="ref.fasta"/> </conditional> <param name="ambig_ref" value="true"/> <conditional name="output_annotated"> @@ -139,17 +120,9 @@ <param name="in_bam" value="medaka_test.bam"/> </conditional> <param name="output_log_bool" value="true"/> - - <output name="out_result"> + <output name="out_variants"> <assert_contents> - <has_n_lines n="9"/> - <has_line line="##fileformat=VCFv4.1" /> - <has_line_matching expression="##medaka_version=[0-9]+\.[0-9]+\.[0-9]+" /> - </assert_contents> - </output> - <output name="out_annotated"> - <assert_contents> - <has_n_lines n="23"/> + <has_n_lines n="18"/> <has_line line="##fileformat=VCFv4.1" /> <has_line_matching expression="##medaka_version=[0-9]+\.[0-9]+\.[0-9]+" /> <has_line_matching expression="##convert_VCF_info_fields=[0-9]+\.[0-9]+" /> @@ -162,7 +135,7 @@ </output> </test> <!--No pooling--> - <test expect_num_outputs="3"> + <test expect_num_outputs="2"> <conditional name="pool"> <param name="pool_mode" value="No"/> <param name="input" value="medaka_test.hdf"/> @@ -177,17 +150,9 @@ <param name="in_bam" value="medaka_test.bam"/> </conditional> <param name="output_log_bool" value="true"/> - - <output name="out_result"> + <output name="out_variants"> <assert_contents> - <has_n_lines n="9"/> - <has_line line="##fileformat=VCFv4.1" /> - <has_line_matching expression="##medaka_version=[0-9]+\.[0-9]+\.[0-9]+" /> - </assert_contents> - </output> - <output name="out_annotated"> - <assert_contents> - <has_n_lines n="23"/> + <has_n_lines n="18"/> <has_line line="##fileformat=VCFv4.1" /> <has_line_matching expression="##medaka_version=[0-9]+\.[0-9]+\.[0-9]+" /> <has_line_matching expression="##convert_VCF_info_fields=[0-9]+\.[0-9]+" /> @@ -213,8 +178,7 @@ <param name="output_annotated_select" value="false"/> </conditional> <param name="output_log_bool" value="false"/> - - <output name="out_result"> + <output name="out_variants"> <assert_contents> <has_n_lines n="9"/> <has_line line="##fileformat=VCFv4.1" />