Mercurial > repos > richard-burhans > ncbi_egapx
changeset 18:83f9b1d86951 draft
planemo upload for repository https://github.com/richard-burhans/galaxytools/tree/main/tools/ncbi_egapx commit 8214876a80a4416d2614c7227b22a436489f59cf
| author | richard-burhans |
|---|---|
| date | Fri, 20 Dec 2024 21:26:46 +0000 |
| parents | e0de8669b340 |
| children | 5b24ea81a6f8 |
| files | macros.xml ncbi_egapx.xml test-data/input.yaml |
| diffstat | 3 files changed, 162 insertions(+), 65 deletions(-) [+] |
line wrap: on
line diff
--- a/macros.xml Mon Nov 18 17:24:04 2024 +0000 +++ b/macros.xml Fri Dec 20 21:26:46 2024 +0000 @@ -4,9 +4,9 @@ <container type="docker">quay.io/galaxy/egapx:@TOOL_VERSION@</container> </requirements> </xml> - <token name="@TOOL_VERSION@">0.2-alpha</token> - <token name="@VERSION_SUFFIX@">7</token> - <token name="@PROFILE@">22.05</token> + <token name="@TOOL_VERSION@">0.3.1-alpha</token> + <token name="@VERSION_SUFFIX@">0</token> + <token name="@PROFILE@">24.2</token> <xml name="edam_ontology"> <edam_operations> <edam_operation>operation_0362</edam_operation>
--- a/ncbi_egapx.xml Mon Nov 18 17:24:04 2024 +0000 +++ b/ncbi_egapx.xml Fri Dec 20 21:26:46 2024 +0000 @@ -6,8 +6,43 @@ <expand macro="edam_ontology"/> <expand macro="requirements"/> <command detect_errors="aggressive"><![CDATA[ - #if str($cond_input_style.input_style) == "fillform" + export NXF_DEBUG=3 && + echo \${PWD} && + #if $cond_input_style.input_style == "fillform" #set yamlconfig = $egapx_config + ## The EGAPx pipeline code determines that a file is gzipped if it has a '.gz' extension. + ## This code creates symlinks with the appropriate extension. + #if $cond_input_style.cond_genome_style.genome_style == "history" + #set $genome_pathname = "genome_" + re.sub('[^\w\-\s]', '_', str($genome.element_identifier)) + "." + $genome.ext + ln -s '$genome' '$genome_pathname' && + #else if $cond_input_style.cond_genome_style.genome_style == "indexed" + #set $genome_pathname = "genome_" + re.sub('[^\w\-\s]', '_', str($genome.fields.element_identifier)) + "." + $genome.fields.ext + ln -s '$genome.fields.path' '$genome_pathname' && + #end if + #if $cond_input_style.cond_rnaseq_style.rnaseq_style == "history" + #import re + mkdir -p reads && + #for $idx, $read in enumerate($cond_input_style.cond_rnaseq_style.rnaseq) + #if $read + #set $read_pathname = "reads/" + str($idx) + "_" + re.sub('[^\w\-\s]', '_', str($read.element_identifier)) + "." + $read.ext + ln -s '$read' '$read_pathname' && + #end if + #end for + #for $repeat_idx, $repeat_entry in enumerate($cond_input_style.cond_rnaseq_style.reads_lists) + #for $idx, $collection in enumerate($repeat_entry.rnaseq_single) + #set $read_pathname = "reads/" + str($repeat_idx) + str($idx) + "_" + re.sub('[^\w\-\s]', '_', str($collection.element_identifier)) + "." + $collection.ext + ln -s '$collection' '$read_pathname' && + #end for + #end for + #for $repeat_idx, $repeat_entry in enumerate($cond_input_style.cond_rnaseq_style.reads_paired_lists) + #for $idx, $collection in enumerate($repeat_entry.rnaseq_paired) + #set $read_pathname = "reads/" + str($repeat_idx) + str($idx) + "_" + $re.sub('[^\w\-\s]', '_', str($collection.forward.element_identifier)) + "." + $collection.forward.ext + ln -s '${collection.forward}' '$read_pathname' && + #set $read_pathname = "reads/" + str($repeat_idx) + str($idx) + "_" + re.sub('[^\w\-\s]', '_', str($collection.reverse.element_identifier)) + "." + $collection.reverse.ext + ln -s '${collection.reverse}' '$read_pathname' && + #end for + #end for + #end if #else #set yamlconfig = $yamlin #end if @@ -21,32 +56,56 @@ python3 /galaxy/egapx/ui/egapx.py '$yamlconfig' -e galaxy -o 'egapx_out' ]]></command> <configfiles> + <configfile name="reads_config"><![CDATA[ + #if $cond_input_style.input_style == "fillform" and $cond_input_style.cond_rnaseq_style.rnaseq_style == "history" + #import re + #for $idx, $read in enumerate($cond_input_style.cond_rnaseq_style.rnaseq) + #if $read + #set $read_pathname = "reads/" + str($idx) + re.sub('[^\w\-\s]', '_', str($read.element_identifier)) + "." + $read.ext +${idx}_${read.name} $read_pathname + #end if + #end for + #for $repeat_idx, $repeat_entry in enumerate($cond_input_style.cond_rnaseq_style.reads_lists) + #for $idx, $collection in enumerate($repeat_entry.rnaseq_single) + #set $read_pathname = "reads/" + str($repeat_idx) + str($idx) + re.sub('[^\w\-\s]', '_', str($collection.element_identifier)) + "." + $collection.ext +${repeat_idx}${idx}_${collection.name} $read_pathname + #end for + #end for + #for $repeat_idx, $repeat_entry in enumerate($cond_input_style.cond_rnaseq_style.reads_paired_lists) + #for $idx, $collection in enumerate($repeat_entry.rnaseq_paired) + #set $forward_read_pathname = "reads/" + str($repeat_idx) + str($idx) + re.sub('[^\w\-\s]', '_', str($collection.forward.element_identifier)) + "." + $collection.forward.ext + #set $reverse_read_pathname = "reads/" + str($repeat_idx) + str($idx) + re.sub('[^\w\-\s]', '_', str($collection.reverse.element_identifier)) + "." + $collection.reverse.ext +${repeat_idx}${idx}_${collection.name} $forward_read_pathname $reverse_read_pathname + #end for + #end for + #end if + ]]></configfile> <configfile name="egapx_config"><![CDATA[ -#if str($cond_input_style.input_style) == "fillform" +#if $cond_input_style.input_style == "fillform" + #import re + #if $cond_input_style.cond_genome_style.genome_style == "history" + #set genome_value = "genome_" + re.sub('[^\w\-\s]', '_', str($genome.element_identifier)) + "." + $genome.ext + #else if $cond_input_style.cond_genome_style.genome_style == "indexed" + #set genome_value = "genome_" + re.sub('[^\w\-\s]', '_', str($genome.fields.element_identifier)) + "." + $genomefields.ext + #else + #set genome_value = $uri + #end if # yaml generated by ncbi_egapx.xml - #if str($cond_input_style.cond_genome_style.genome_style) == "history" - #set genome_value = $cond_input_style.cond_genome_style.genome - #elif str($cond_input_style.cond_genome_style.genome_style) == "indexed" - #set genome_value = $cond_input_style.cond_genome_style.genome.fields.path - #else - #set genome_value = $cond_input_style.cond_genome_style.uri - #end if genome: $genome_value -taxid: $cond_input_style.taxid - #if str($cond_input_style.cond_rnaseq_style.rnaseq_style) == "history" - #set reads_values = $cond_input_style.cond_rnaseq_style.rnaseq +taxid: $taxid + #if $cond_input_style.cond_rnaseq_style.rnaseq_style == "history" +reads: $reads_config #else - #set reads_values = $cond_input_style.cond_rnaseq_style.rnaseq.split() + #set reads_values = $rnaseq.split() + #for $read in [str(rv).strip() for rv in $reads_values] + - $read + #end for #end if -reads: - #for r in [str(rv).strip() for rv in $reads_values] - - $r - #end for #if str($cond_input_style.proteins) != "None" -proteins: $cond_input_styleproteins +proteins: $cond_input_style.proteins #end if - #if str($cond_input_style.xtra) != "None" - #for row in str($cond_input_style.xtra).strip().split("\n") + #if str($cond_input_style.extra) != "None" + #for row in str($cond_input_style.extra).strip().split("\n") $row #end for #end if @@ -55,15 +114,13 @@ </configfiles> <inputs> <conditional name="cond_input_style"> - <param name="input_style" type="select" label="Fill in a tool form or use an existing yaml configuration from the current history?" - help="Use the tool form to select inputs from the history, or use a pre-prepared yaml file."> + <param name="input_style" type="select" label="Fill in a tool form or use an existing yaml configuration from the current history?" help="Use the tool form to select inputs from the history, or use a pre-prepared yaml file."> <option value="fillform" selected="True">Provide configuration details for conversion into a configuration yaml</option> <option value="history">Use a pre-prepared yaml egapx configuration</option> - </param> + </param> <when value="fillform"> <conditional name="cond_genome_style"> - <param name="genome_style" type="select" label="Reference genome source for mapping supplied RNA-seq reads" - help="Select a built in, history or remote URI for the reference genome FASTA"> + <param name="genome_style" type="select" label="Reference genome source for mapping supplied RNA-seq reads" help="Select a built in, history or remote URI for the reference genome FASTA"> <option value="history" selected="True">Use a genome FASTA file from the current history</option> <option value="indexed">Use a Galaxy server built-in genome</option> <option value="uri">Provide a remote web link URI ("https://...") pointing at the required genome reference FASTA file</option> @@ -72,8 +129,7 @@ <param name="genome" type="data" format="fasta" label="Select the reference genome FASTA from the current history"/> </when> <when value="indexed"> - <param name="genome" type="select" label="Select a built in reference genome or custom genome" - help="If not listed, add a custom genome or use a reference genome from the history"> + <param name="genome" type="select" label="Select a built in reference genome or custom genome" help="If not listed, add a custom genome or use a reference genome from the history"> <options from_data_table="all_fasta"> <validator message="No genomes are available " type="no_options"/> </options> @@ -83,30 +139,31 @@ <param name="uri" type="text" label="URI pointing to the reference genome FASTA file"/> </when> </conditional> - <param name="taxid" type="text" label="NCBI Taxon ID" help="Used to identify the HMM model files needed"> <validator type="regex" message="Numeric">^[0-9]+$</validator> </param> - <conditional name="cond_rnaseq_style"> - <param name="rnaseq_style" type="select" label="RNA sequence data source" - help="Select RNAseq input data from history or input a list of SRA identifiers or remote URI"> + <param name="rnaseq_style" type="select" label="RNA sequence data source" help="Select RNAseq input data from history or input a list of SRA identifiers or remote URI"> <option value="history" selected="True">Select one or more RNA-seq fastq datasets from the current history</option> <option value="list">Type in a list of SRA identifiers and/or remote RNA-seq FASTA URI</option> </param> <when value="history"> - <param name="rnaseq" type="data" format="fastqsanger,fastqsanger.gz" multiple="true" label="Select multiple RNA-seq fastqsanger inputs from the current history" - help="All selected rna-seq fastqsanger will be added to the yaml for egapx configuration"/> + <param name="rnaseq" type="data" format="fastqsanger,fastqsanger.gz" multiple="true" optional="true" label="Select multiple RNA-seq fastqsanger inputs from the current history" help="All selected rna-seq fastqsanger will be added to the yaml for egapx configuration"/> + <repeat name="reads_lists" title="Single-end reads" min="0"> + <param name="rnaseq_single" type="data_collection" format="fastqsanger,fastqsanger.gz" collection_type="list" label="Select multiple RNA-seq fastqsanger inputs from the current history" help="All selected rna-seq fastqsanger will be added to the yaml for egapx configuration"/> + </repeat> + <repeat name="reads_paired_lists" title="Paired-end reads" min="0"> + <param name="rnaseq_paired" type="data_collection" format="fastqsanger,fastqsanger.gz" collection_type="list:paired" label="Select multiple RNA-seq fastqsanger inputs from the current history" help="All selected rna-seq fastqsanger will be added to the yaml for egapx configuration"/> + </repeat> </when> <when value="list"> - <param name="rnaseq" type="text" area="true" label="List all required individual RNA-seq URI or SRA identifiers, separated by spaces or newlines" - help="Either a working URI for a RNA-seq FASTA, or a bare SRA identifier will work - can be mixed"> + <param name="rnaseq" type="text" area="true" label="List all required individual RNA-seq URI or SRA identifiers, separated by spaces or newlines" help="Either a working URI for a RNA-seq FASTA, or a bare SRA identifier will work - can be mixed"> <validator type="empty_field"/> </param> </when> </conditional> <param name="proteins" type="data" format="fasta,fasta.gz" optional="true" label="Select a protein set"/> - <param name="xtra" type="text" area="true" optional="true" label="Additional yaml to append to the egapx.yaml configuration" + <param name="extra" type="text" area="true" optional="true" label="Additional yaml to append to the egapx.yaml configuration" help="Not normally needed but useful for testing additional configuration elements"> <sanitizer invalid_char=""> <valid initial="string.printable"/> @@ -136,26 +193,74 @@ <param name="uri" value="https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/020/809/275/GCF_020809275.1_ASM2080927v1/GCF_020809275.1_ASM2080927v1_genomic.fna.gz"/> <param name="rnaseq_style" value="list"/> <param name="rnaseq" value="https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR8506572.1 https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR8506572.2 https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR9005248.1 https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR9005248.2"/> - <param name="xtra" value="hmm: https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/gnomon/hmm_parameters/6956.params tasks: star_wnode: star_wnode: -cpus-per-worker 4"/> - <output name="output"><assert_contents><has_size min="1"/></assert_contents></output> + <param name="extra" value="hmm: https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/gnomon/hmm_parameters/6956.params tasks: star_wnode: star_wnode: -cpus-per-worker 4"/> + <output name="output"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </output> <output_collection name="nextflow_stats" type="list"> - <element name="nf_log"><assert_contents><has_size min="1"/></assert_contents></element> - <element name="nf_report"><assert_contents><has_size min="1"/></assert_contents></element> - <element name="nf_trace"><assert_contents><has_size min="1"/></assert_contents></element> - <element name="nf_timeline"><assert_contents><has_size min="1"/></assert_contents></element> - <element name="nf_params"><assert_contents><has_size min="1"/></assert_contents></element> + <element name="nf_log"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> + <element name="nf_report"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> + <element name="nf_trace"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> + <element name="nf_timeline"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> + <element name="nf_params"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> </output_collection> </test> <test expect_test_failure="true"> <param name="input_style" value="history"/> <param name="yamlin" value="input.yaml"/> - <output name="output"><assert_contents><has_size min="1"/></assert_contents></output> + <output name="output"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </output> <output_collection name="nextflow_stats" type="list"> - <element name="nf_log"><assert_contents><has_size min="1"/></assert_contents></element> - <element name="nf_report"><assert_contents><has_size min="1"/></assert_contents></element> - <element name="nf_trace"><assert_contents><has_size min="1"/></assert_contents></element> - <element name="nf_timeline"><assert_contents><has_size min="1"/></assert_contents></element> - <element name="nf_params"><assert_contents><has_size min="1"/></assert_contents></element> + <element name="nf_log"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> + <element name="nf_report"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> + <element name="nf_trace"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> + <element name="nf_timeline"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> + <element name="nf_params"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> </output_collection> </test> </tests>
--- a/test-data/input.yaml Mon Nov 18 17:24:04 2024 +0000 +++ b/test-data/input.yaml Fri Dec 20 21:26:46 2024 +0000 @@ -1,15 +1,7 @@ -# This is a very minimal example of EGAPx, it fits into 4 CPU cores and 6GB of memory. -# To be able to do this, we culled the input files and some stages of execution. -# To limit the requirements you also need to use -e docker_minimal - -genome: https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/020/809/275/GCF_020809275.1_ASM2080927v1/GCF_020809275.1_ASM2080927v1_genomic.fna.gz +genome: https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/020/809/275/GCA_020809275.1_ASM2080927v1/GCA_020809275.1_ASM2080927v1_genomic.fna.gz taxid: 6954 reads: - - https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR8506572.1 - - https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR8506572.2 - - https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR9005248.1 - - https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR9005248.2 -hmm: https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/gnomon/hmm_parameters/6956.params -tasks: - star_wnode: - star_wnode: -cpus-per-worker 4 + - https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR8506572_1.gz + - https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR8506572_2.gz + - https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR9005248_1.gz + - https://ftp.ncbi.nlm.nih.gov/genomes/TOOLS/EGAP/sample_data/Dermatophagoides_farinae_small/SRR9005248_2.gz