Mercurial > repos > greg > affy2vcf2
changeset 1:b8549f504829 draft
Uploaded
author | greg |
---|---|
date | Thu, 16 May 2019 12:42:19 -0400 |
parents | 5e9d8a4f6ac8 |
children | 9910bb2e159c |
files | .shed.yml README affy2vcf.xml all_fasta.loc.sample macros.xml tool_data_table_conf.xml.sample |
diffstat | 6 files changed, 193 insertions(+), 1 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/.shed.yml Thu May 16 12:42:19 2019 -0400 @@ -0,0 +1,11 @@ +name: affy2vcf +owner: greg +description: | + Contains a tool that converts Affymetrix genotype calls and intensity files to VCF format. +homepage_url: https://github.com/freeseek/gtc2vcf +long_description: | + Contains a tool that converts Affymetrix genotype calls and intensity files to VCF format. +remote_repository_url: https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/convert_formats/affy2vcf +type: unrestricted +categories: + - Convert Formats
--- a/README Thu May 16 10:59:34 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1 +0,0 @@ -init commit
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/affy2vcf.xml Thu May 16 12:42:19 2019 -0400 @@ -0,0 +1,132 @@ +<tool id="affy2vcf" name="Convert Affymetrix" version="@WRAPPER_VERSION@"> + <description>genotype calls and intensities to VCF</description> + <macros> + <import>macros.xml</import> + </macros> + <requirements> + <requirement type="package" version="1.9">bcftools-gtc2vcf-plugin</requirement> + </requirements> + <command detect_errors="exit_code"><![CDATA[ +@PREPARE_ENV@ +#set text_outputs_dir = 'text_outputs' +mkdir $text_outputs_dir && +bcftools +\$BCFTOOLS_PLUGINS/affy2vcf.so +#if str($reference_genome_source_cond.reference_genome_source) == "history": + --fasta-ref '$reference_genome_source_cond.history_item' +#else: + --fasta-ref '$reference_genome_source_cond.locally_cached_item.fields.path' +#end if +--annot '$annot' +--snp-posteriors '$snp_posteriors' +--summary '$summary' +--report '$report' +--calls '$calls' +--confidences '$confidences' +#if str($output_gender_estimate_cond.output_gender_estimate) == "yes" + --sex '$output_gender_estimate' +#end if +#if str($append_version) == "no": + --no-version +#end if +--output '$output' +--output-type $output_type +@THREADS@ + ]]></command> + <inputs> + <param name="annot" type="data" format="csv" label="Probeset annotation file" /> + <param name="summary" type="data" format="txt" label="Apt-probeset genotype summary file" /> + <param name="snp_posteriors" type="data" format="txt" label="Apt-probeset genotype snp-posteriors file" /> + <param name="report" type="data" format="txt" label="Apt-probeset genotype report file" /> + <param name="confidences" type="data" format="txt" label="Apt-probeset genotype confidences file" /> + <param name="calls" type="data" format="txt" label="Apt-probeset genotype calls file" /> + <conditional name="reference_genome_source_cond"> + <param name="reference_genome_source" type="select" label="Choose the source for the reference genome"> + <option value="history" selected="true">Use a reference genome from my history</option> + <option value="cached">Use a locally cached genome index</option> + </param> + <when value="history"> + <param name="history_item" type="data" format="fasta" label="Select reference genome" /> + </when> + <when value="cached"> + <param name="locally_cached_item" type="select" format="fasta" label="Fasta reference sequence"> + <options from_data_table="all_fasta"> + <column name="name" index="2"/> + <column name="value" index="0"/> + <column name="path" index="3"/> + <filter type="sort_by" column="1"/> + <validator type="no_options" message="No cached Fasta genome references are available for the build associated with the selected probeset annotation file." /> + </options> + </param> + </when> + </conditional> + <conditional name="output_gender_estimate_cond"> + <param name="output_gender_estimate" type="select" force_select="true" label="Output apt-probeset-genotype gender estimate?"> + <option value="no" selected="true">No</option> + <option value="yes">Yes</option> + </param> + <when value="no"/> + <when value="yes"/> + </conditional> + <param name="append_version" type="select" force_select="true" label="Append version and command line to the header?"> + <option value="no" selected="true">No</option> + <option value="yes">Yes</option> + </param> + <param name="output_type" type="select" force_select="true" label="Select format for output"> + <option value="v" selected="true">Uncompressed VCF</option> + <option value="z">Compressed VCF</option> + <option value="u" selected="true">Uncompressed BCF</option> + <option value="b">Compressed BCF</option> + </param> + </inputs> + <outputs> + <expand macro="vcf_output"/> + <data name="output_gender_estimate" format="txt" label="${tool.name} (gender estimate) on ${on_string}"> + <filter>output_gender_estimate_cond['output_gender_estimate'] == "yes"</filter> + </data> + </outputs> + <tests> + <test> + <param name="reference_genome_source" value="history"/> + <param name="history_item" value="GCF_000222465.1_Adig_1.1_genomic.fna" ftype="fasta"/> + <param name="annot" value="Axion_Acropsnp_coral_Annotation_r1.csv" ftype="csv"/> + <param name="summary" value="AxiomGT1.summary.txt" ftype="txt"/> + <param name="snp_posteriors" value="AxiomGT1.snp-posteriors.txt" ftype="txt"/> + <param name="report" value="AxiomGT1.report.txt" ftype="txt"/> + <param name="confidences" value="AxiomGT1.confidences.txt" ftype="txt"/> + <param name="calls" value="AxiomGT1.calls.txt" ftype="txt"/> + <output name="output" value="output.vcf" ftype="vcf"/> + </test> + </tests> + <help> +This tool converts Affymetrix genotype calls and intensity files to VCF format. + +----- + +**Required options** + + * **Probeset annotation file** - probeset annotation file produced by the sequencing run. + * **Apt-probeset genotype summary file** - apt-probeset genotype summary file produced by the sequencing run. + * **Apt-probeset genotype snp-posteriors file** - apt-probeset genotype snp-posteriors file produced by the sequencing run. + * **Apt-probeset genotype report file** - apt-probeset genotype report file produced by the sequencing run. + * **Apt-probeset genotype confidences file** - apt-probeset genotype confidences file produced by the sequencing run. + * **Apt-probeset genotype calls file** - apt-probeset genotype calls file produced by the sequencing run. + * **Choose the source for the reference genome** - select a reference genome from your history or one installed into your local Galaxy environment by a data manager tool. + +**Other options** + + * **Output apt-probeset-genotype gender estimate** - output apt-probeset-genotype gender estimate into an additional dataset. + * **Append version and command line to the header** - append version and command line to the header of the output VCF dataset. + * **Select format for output** - select one of uncompressed/compressed VCF/BCF. + </help> + <citations> + <expand macro="citation1"/> + <citation type="bibtex"> + @misc{None, + journal = {None}, + author = {Genovese, Giulio}, + title = {None}, + year = {None}, + url = {https://github.com/freeseek/gtc2vcf},} + </citation> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/all_fasta.loc.sample Thu May 16 12:42:19 2019 -0400 @@ -0,0 +1,18 @@ +#This file lists the locations and dbkeys of all the fasta files +#under the "genome" directory (a directory that contains a directory +#for each build). The script extract_fasta.py will generate the file +#all_fasta.loc. This file has the format (white space characters are +#TAB characters): +# +#<unique_build_id> <dbkey> <display_name> <file_path> +# +#So, all_fasta.loc could look something like this: +# +#apiMel3 apiMel3 Honeybee (Apis mellifera): apiMel3 /path/to/genome/apiMel3/apiMel3.fa +#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /path/to/genome/hg19/hg19canon.fa +#hg19full hg19 Human (Homo sapiens): hg19 Full /path/to/genome/hg19/hg19full.fa +# +#Your all_fasta.loc file should contain an entry for each individual +#fasta file. So there will be multiple fasta files for each build, +#such as with hg19 above. +#
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Thu May 16 12:42:19 2019 -0400 @@ -0,0 +1,25 @@ +<macros> + <token name="@WRAPPER_VERSION@">1.9</token> + <xml name="citation1"> + <citation type="doi">10.1093/bioinformatics/btp352</citation> + </xml> + <token name="@PREPARE_ENV@"> +<![CDATA[ +export BCFTOOLS_PLUGINS=\$(dirname `which bcftools`)/../libexec/bcftools; +]]> + </token> + <token name="@THREADS@"> + --threads \${GALAXY_SLOTS:-4} + </token> + <xml name="vcf_output"> + <data name="output" format="vcf"> + <change_format> + <when input="output_type" value="b" format="bcf" /> + <when input="output_type" value="u" format="bcf" /> + <when input="output_type" value="z" format="vcf_bgzip" /> + <when input="output_type" value="v" format="vcf" /> + </change_format> + </data> + </xml> +</macros> +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Thu May 16 12:42:19 2019 -0400 @@ -0,0 +1,7 @@ +<tables> + <!-- Locations of all fasta files under genome directory --> + <table name="all_fasta" comment_char="#" allow_duplicate_entries="False"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/all_fasta.loc" /> + </table> +</tables>