Mercurial > repos > greg > vsnp_get_snps
diff vsnp_get_snps.xml @ 9:0fe292b20b9d draft
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_get_snps commit 3b7fef2d17fec96647345e89c774d4af417d23d7"
| author | greg |
|---|---|
| date | Thu, 29 Jul 2021 13:16:03 +0000 |
| parents | 5e4595b9f63c |
| children | be5875f29ea4 |
line wrap: on
line diff
--- a/vsnp_get_snps.xml Thu Jul 29 12:50:01 2021 +0000 +++ b/vsnp_get_snps.xml Thu Jul 29 13:16:03 2021 +0000 @@ -1,4 +1,4 @@ -<tool id="vsnp_get_snps_broken" name="vSNP: get SNPs broken" version="@WRAPPER_VERSION@.0+galaxy0" profile="@PROFILE@"> +<tool id="vsnp_get_snps" name="vSNP: get SNPs" version="@WRAPPER_VERSION@.0+galaxy0" profile="@PROFILE@"> <description></description> <macros> <import>macros.xml</import> @@ -12,10 +12,6 @@ <command detect_errors="exit_code"><![CDATA[ #import re -#if str($input.metadata.dbkey) == '?': - >&2 echo "The dbkey must be set for the zero coverage VCF files with SNPs found in closely related isolate groups" && exit 1 -#end if - #set input_vcf_dir = 'input_vcf_dir' #set output_json_avg_mq_dir = 'output_json_avg_mq_dir' #set output_json_snps_dir = 'output_json_snps_dir' @@ -26,9 +22,20 @@ mkdir -p $output_json_snps_dir && mkdir -p $output_snps_dir && -#set input_identifier = re.sub('[^\s\w\-]', '_', str($input.element_identifier)) -ln -s '${input}' '$input_vcf_dir/${input_identifier}' && - +#set dbkey = '?' +#for $i in $input_vcf_collection: + #if str($dbkey) == '?': + #set dbkey = $i.metadata.dbkey + #else if str($dbkey) != $i.metadata.dbkey: + >&2 echo "The dbkeys associated with the zero coverage VCF files with SNPs found in closely related isolate groups are not unique" && +exit 1 + #end if + #set vcf_identifier = re.sub('[^\s\w\-]', '_', str($i.element_identifier)) + ln -s '${i}' '$input_vcf_dir/${vcf_identifier}' && +#end for +#if str($dbkey) == '?': + >&2 echo "The dbkey must be set for the zero coverage VCF files with SNPs found in closely related isolate groups" && exit 1 +#end if #if str($input_zc_vcf_type_cond.input_zc_vcf_type) == "single": #set zc_vcf_identifier = re.sub('[^\s\w\-]', '_', str($input_zc_vcf.element_identifier)) ln -s '${input_zc_vcf}' '$input_vcf_dir/${zc_vcf_identifier}' && @@ -45,7 +52,7 @@ ## The value of excel_fields is a nested list that looks like this. ## [['AF2122', 'Mbovis_define_filter.xlsx', '~/tool-data/vsnp/AF2122/excel/Mbovis_define_filter.xlsx', 'Excel file for AF2122'],...] #for $i in $excel_fields: - #if str($i[0]) == $input.metadata.dbkey: + #if str($i[0]) == $dbkey: #set excel_file = $i[2] #break #end if @@ -69,7 +76,7 @@ --output_summary '$output_summary' --processes \${GALAXY_SLOTS:-8} --quality_score_n_threshold $quality_score_n_threshold ---dbkey '$input.metadata.dbkey' +--dbkey '$dbkey' ]]></command> <inputs> <conditional name="input_zc_vcf_type_cond"> @@ -84,7 +91,7 @@ <param name="input_zc_vcf_collection" format="vcf" type="data_collection" collection_type="list" label="Collection of zero coverage VCF files"/> </when> </conditional> - <param name="input" format="vcf" type="data" label="Zero coverage VCF file with SNPs found in closely related isolate groups"/> + <param name="input_vcf_collection" format="vcf" type="data_collection" collection_type="list" label="Collection of zero coverage VCF files with SNPs found in closely related isolate groups"/> <param name="ac" type="integer" min="0" value="2" label="Allele count threshold" help="At least 1 position must have this value for a SNP to be added to a group"/> <param name="min_mq" type="integer" min="0" value="56" label="Map quality threshold" help="At least 1 position must have a higher MQ value for a SNP to be added to a group"/> <param name="min_quality_score" type="integer" min="0" value="150" label="Quality score threshold" help="At least 1 position must have a higher quality score for a SNP to be added to a group"/> @@ -103,6 +110,7 @@ <when value="cached"> <param name="input_excel" type="select" label="Excel file"> <options from_data_table="vsnp_excel"> + <filter type="data_meta" column="0" key="dbkey" ref="input_vcf_collection"/> <validator type="no_options" message="No built-in Excel grouping and filtering datasets are available"/> </options> </param> @@ -129,10 +137,17 @@ <data name="output_summary" format="html" label="${tool.name} on ${on_string} (summary)"/> </outputs> <tests> - <!-- No excel file, all_isolates is False --> + <!-- + Unfortunately the test files cannot be gzipped since Galaxy changes the file names + to be something like 00-0121_WI_Cervid_99-A_vcf_gz, and the VCF Reader requires + gzipped files to have a .gz extension. The exception is + UnicodeDecodeError: 'utf-8' codec can't decode byte 0x8b in position 1: invalid start byte + --> + <!-- A single vcf input, no excel file, all_isolates is False --> <test expect_num_outputs="4"> - <param name="input" value="input_zc_vcf.vcf" ftype="vcf" dbkey="89"/> - <param name="input_zc_vcf_collection"> + <param name="input_zc_vcf_type" value="single"/> + <param name="input_zc_vcf" value="input_zc_vcf.vcf" ftype="vcf" dbkey="89"/> + <param name="input_vcf_collection"> <collection type="list"> <element name="SRR8073662_zc.vcf" value="SRR8073662_zc.vcf" dbkey="89"/> <element name="SRR1792272_zc.vcf" value="SRR1792272_zc.vcf" dbkey="89"/> @@ -143,62 +158,102 @@ <element name="all_vcf" file="all_vcf.fasta" ftype="fasta" compare="contains"/> </output_collection> <output_collection name="json_avg_mq" type="list" count="1"> - <element name="all_vcf" file="avg_mq.json" ftype="json" compare="contains"/> + <element name="all_vcf" file="json_avg_mq_all_vcf.json" ftype="json" compare="contains"/> </output_collection> <output_collection name="json_snps" type="list" count="1"> <element name="all_vcf" file="json_all_vcf.json" ftype="json" compare="contains"/> </output_collection> <output name="output_summary" file="output_summary.html" ftype="html" compare="contains"/> </test> - <!-- Excel file, all_isolates is False --> + <!-- An input collection, no excel file, all_isolates is False --> <test expect_num_outputs="4"> - <param name="input" value="02_0585_COA_TX_Fed.vcf" ftype="vcf" dbkey="89"/> + <param name="input_zc_vcf_type" value="collection"/> <param name="input_zc_vcf_collection"> <collection type="list"> - <element name="L02-19-1908_zc.vcf" value="L02-19-1908_zc.vcf" dbkey="89"/> - <element name="L03-13-2334_zc.vcf" value="L03-13-2334_zc.vcf" dbkey="89"/> - <element name="L03-16-0255_zc.vcf" value="L03-16-0255_zc.vcf" dbkey="89"/> + <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/> + <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/> + </collection> + </param> + <param name="input_vcf_collection"> + <collection type="list"> + <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/> + <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/> + <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/> + </collection> + </param> + <param name="input_excel_param" value="no"/> + <output_collection name="snps" type="list" count="1"> + <element name="all_vcf" file="all_vcf2.fasta" ftype="fasta" compare="contains"/> + </output_collection> + <output_collection name="json_avg_mq" type="list" count="1"> + <element name="all_vcf" file="json_avg_mq_all_vcf.json" ftype="json" compare="contains"/> + </output_collection> + <output_collection name="json_snps" type="list" count="1"> + <element name="all_vcf" file="json_all_vcf.json" ftype="json" compare="contains"/> + </output_collection> + <output name="output_summary" file="output_summary2.html" ftype="html" compare="contains"/> + </test> + <!-- An input collection, an excel file, all_isolates is False --> + <test expect_num_outputs="4"> + <param name="input_zc_vcf_type" value="collection"/> + <param name="input_zc_vcf_collection"> + <collection type="list"> + <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/> + <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/> + </collection> + </param> + <param name="input_vcf_collection"> + <collection type="list"> + <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/> + <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/> + <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/> </collection> </param> <param name="input_excel_param" value="yes"/> <param name="input_excel" value="89"/> <output_collection name="snps" type="list" count="1"> - <element name="Mbovis-TB" file="Mbovis-TB.fasta" ftype="fasta" compare="contains"/> + <element name="Mbovis-17" file="Mbovis-17_snps.fasta" ftype="fasta" compare="contains"/> </output_collection> <output_collection name="json_avg_mq" type="list" count="1"> - <element name="Mbovis-TB" file="avg_mq.json" ftype="json" compare="contains"/> + <element name="Mbovis-17" file="Mbovis-17_avg_mq_json.json" ftype="json" compare="contains"/> </output_collection> <output_collection name="json_snps" type="list" count="1"> - <element name="Mbovis-TB" file="Mbovis-TB_json.json" ftype="json" compare="contains"/> + <element name="Mbovis-17" file="Mbovis-17_snps_json.json" ftype="json" compare="contains"/> </output_collection> - <output name="output_summary" file="output_summary.html" ftype="html" compare="contains"/> + <output name="output_summary" file="output_summary3.html" ftype="html" compare="contains"/> </test> - <!-- Excel file, all_isolates is True --> + <!-- An input collection, an excel file, all_isolates is True --> <test expect_num_outputs="4"> - <param name="input" value="02_0585_COA_TX_Fed.vcf" ftype="vcf" dbkey="89"/> + <param name="input_zc_vcf_type" value="collection"/> <param name="input_zc_vcf_collection"> <collection type="list"> - <element name="L02-19-1908_zc.vcf" value="L02-19-1908_zc.vcf" dbkey="89"/> - <element name="L03-13-2334_zc.vcf" value="L03-13-2334_zc.vcf" dbkey="89"/> - <element name="L03-16-0255_zc.vcf" value="L03-16-0255_zc.vcf" dbkey="89"/> + <element name="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" value="BCG_Pasteur_Unknown_FR_SRR8886989.vcf" dbkey="89"/> + <element name="BCG_Tokyo_Unknown_JP_DRR029468.vcf" value="BCG_Tokyo_Unknown_JP_DRR029468.vcf" dbkey="89"/> + </collection> + </param> + <param name="input_vcf_collection"> + <collection type="list"> + <element name="01_1787_FL_Zoo_Jaguar.vcf" value="01_1787_FL_Zoo_Jaguar.vcf" dbkey="89"/> + <element name="02_5877_MEX_TX_Fed.vcf" value="02_5877_MEX_TX_Fed.vcf" dbkey="89"/> + <element name="02_0585_COA_TX_Fed.vcf" value="02_0585_COA_TX_Fed.vcf" dbkey="89"/> </collection> </param> <param name="input_excel_param" value="yes"/> <param name="input_excel" value="89"/> <param name="all_isolates" value="--all_isolates"/> <output_collection name="snps" type="list" count="2"> - <element name="Mbovis-TB" file="Mbovis-TB.fasta" ftype="fasta" compare="contains"/> - <element name="all_vcf" file="all_vcf3.fasta" ftype="fasta" compare="contains"/> + <element name="Mbovis-17" file="Mbovis-17_snps.fasta" ftype="fasta" compare="contains"/> + <element name="all_vcf" file="all_vcf2.fasta" ftype="fasta" compare="contains"/> </output_collection> <output_collection name="json_avg_mq" type="list" count="2"> - <element name="Mbovis-TB" file="avg_mq.json" ftype="json" compare="contains"/> - <element name="all_vcf" file="avg_mq.json" ftype="json" compare="contains"/> + <element name="Mbovis-17" file="Mbovis-17_avg_mq_json.json" ftype="json" compare="contains"/> + <element name="all_vcf" file="Mbovis-17_avg_mq_json.json" ftype="json" compare="contains"/> </output_collection> <output_collection name="json_snps" type="list" count="2"> - <element name="Mbovis-TB" file="Mbovis-TB_json.json" ftype="json" compare="contains"/> - <element name="all_vcf" file="all_vcf_snps_json.json" ftype="json" compare="contains"/> + <element name="Mbovis-17" file="Mbovis-17_snps_json.json" ftype="json" compare="contains"/> + <element name="all_vcf" file="Mbovis-17_snps_json.json" ftype="json" compare="contains"/> </output_collection> - <output name="output_summary" file="output_summary.html" ftype="html" compare="contains"/> + <output name="output_summary" file="output_summary4.html" ftype="html" compare="contains"/> </test> </tests> <help>