Mercurial > repos > richard-burhans > ncbi_egapx
changeset 39:4f85da43b40c draft
planemo upload for repository https://github.com/richard-burhans/galaxytools/tree/main/tools/ncbi_egapx commit d96d9578e86e3a3d3569dbc2294cfb15f6678729
| author | richard-burhans |
|---|---|
| date | Mon, 30 Jun 2025 23:21:01 +0000 |
| parents | b0f07e3d6f07 |
| children | b095c69eab5b |
| files | macros.xml ncbi_egapx.xml |
| diffstat | 2 files changed, 172 insertions(+), 66 deletions(-) [+] |
line wrap: on
line diff
--- a/macros.xml Thu Jun 19 21:31:50 2025 +0000 +++ b/macros.xml Mon Jun 30 23:21:01 2025 +0000 @@ -4,8 +4,8 @@ <container type="docker">quay.io/galaxy/egapx:@TOOL_VERSION@-alpha</container> </requirements> </xml> - <token name="@TOOL_VERSION@">0.3.2</token> - <token name="@VERSION_SUFFIX@">10</token> + <token name="@TOOL_VERSION@">0.4.0</token> + <token name="@VERSION_SUFFIX@">0</token> <token name="@PROFILE@">23.0</token> <xml name="edam_ontology"> <edam_operations> @@ -39,12 +39,17 @@ </assert_contents> </output> <output_collection name="output_files" type="list"> - <element name="complete_genomic_gtf" ftype="gtf"> + <element name="annotated_genome" ftype="asn1"> <assert_contents> <has_size min="1"/> </assert_contents> </element> - <element name="complete_genomic_fna" ftype="fasta"> + <element name="annotation_data" ftype="tabular"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> + <element name="gnomon_accepted" ftype="txt"> <assert_contents> <has_size min="1"/> </assert_contents> @@ -54,7 +59,12 @@ <has_size min="1"/> </assert_contents> </element> - <element name="complete_transcripts" ftype="fasta"> + <element name="complete_genomic_fna" ftype="fasta"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> + <element name="complete_genomic_gtf" ftype="gtf"> <assert_contents> <has_size min="1"/> </assert_contents> @@ -64,17 +74,27 @@ <has_size min="1"/> </assert_contents> </element> - <element name="annotated_genome" ftype="asn1"> + <element name="complete_transcripts" ftype="fasta"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> + <element name="gnomon_contam_report" ftype="fasta"> <assert_contents> <has_size min="1"/> </assert_contents> </element> - <element name="accept_ftable_annot" ftype="txt"> + <element name="gnomon_quality_report" ftype="fasta"> <assert_contents> <has_size min="1"/> </assert_contents> </element> - <element name="annotation_data_cmt" ftype="tabular"> + <element name="gnomon_report" ftype="txt"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> + <element name="sra_metadata" ftype="binary"> <assert_contents> <has_size min="1"/> </assert_contents> @@ -89,6 +109,11 @@ <is_valid_xml/> </assert_contents> </element> + <element name="all_unannotated_val" ftype="xml"> + <assert_contents> + <is_valid_xml/> + </assert_contents> + </element> <element name="genome_val" ftype="xml"> <assert_contents> <is_valid_xml/> @@ -96,6 +121,16 @@ </element> </output_collection> <output_collection name="nextflow_stats" type="list"> + <element name="nextflow_log" ftype="txt"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> + <element name="run_params" ftype="yaml"> + <assert_contents> + <has_size min="1"/> + </assert_contents> + </element> <element name="run_report" ftype="html"> <assert_contents> <has_size min="1"/> @@ -106,21 +141,11 @@ <has_size min="1"/> </assert_contents> </element> - <element name="nextflow_log" ftype="txt"> - <assert_contents> - <has_size min="1"/> - </assert_contents> - </element> <element name="run_trace" ftype="tabular"> <assert_contents> <has_size min="1"/> </assert_contents> </element> - <element name="run_params" ftype="yaml"> - <assert_contents> - <has_size min="1"/> - </assert_contents> - </element> </output_collection> </xml> </macros>
--- a/ncbi_egapx.xml Thu Jun 19 21:31:50 2025 +0000 +++ b/ncbi_egapx.xml Mon Jun 30 23:21:01 2025 +0000 @@ -20,23 +20,47 @@ #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" + #if $cond_input_style.cond_short_reads_style.short_reads_style == "history" #import re mkdir -p reads && - #for $idx, $read in enumerate($cond_input_style.cond_rnaseq_style.rnaseq) + #for $idx, $read in enumerate($cond_input_style.cond_short_reads_style.short_reads) #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) + #for $repeat_idx, $repeat_entry in enumerate($cond_input_style.cond_short_reads_style.reads_lists) + #for $idx, $collection in enumerate($repeat_entry.short_reads_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) + #for $repeat_idx, $repeat_entry in enumerate($cond_input_style.cond_short_reads_style.reads_paired_lists) + #for $idx, $collection in enumerate($repeat_entry.short_reads_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 + #if $cond_input_style.cond_long_reads_style.long_reads_style == "history" + #import re + mkdir -p reads && + #for $idx, $read in enumerate($cond_input_style.cond_long_reads_style.long_reads) + #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_long_reads_style.reads_lists) + #for $idx, $collection in enumerate($repeat_entry.long_reads_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_long_reads_style.reads_paired_lists) + #for $idx, $collection in enumerate($repeat_entry.long_reads_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 @@ -64,23 +88,47 @@ <environment_variable name="NXF_DEBUG">3</environment_variable> </environment_variables> <configfiles> - <configfile name="reads_config"><![CDATA[#slurp - #if $cond_input_style.input_style == "fillform" and $cond_input_style.cond_rnaseq_style.rnaseq_style == "history" + <configfile name="short_reads_config"><![CDATA[#slurp + #if $cond_input_style.input_style == "fillform" and $cond_input_style.cond_short_reads_style.short_reads_style == "history" #import re - #for $idx, $read in enumerate($cond_input_style.cond_rnaseq_style.rnaseq) + #for $idx, $read in enumerate($cond_input_style.cond_short_reads_style.short_reads) #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) + #for $repeat_idx, $repeat_entry in enumerate($cond_input_style.cond_short_reads_style.reads_lists) + #for $idx, $collection in enumerate($repeat_entry.short_reads_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) + #for $repeat_idx, $repeat_entry in enumerate($cond_input_style.cond_short_reads_style.reads_paired_lists) + #for $idx, $collection in enumerate($repeat_entry.short_reads_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 + #silent pass]]></configfile> + <configfile name="long_reads_config"><![CDATA[#slurp + #if $cond_input_style.input_style == "fillform" and $cond_input_style.cond_long_reads_style.long_reads_style == "history" + #import re + #for $idx, $read in enumerate($cond_input_style.cond_long_reads_style.long_reads) + #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_long_reads_style.reads_lists) + #for $idx, $collection in enumerate($repeat_entry.long_reads_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_long_reads_style.reads_paired_lists) + #for $idx, $collection in enumerate($repeat_entry.long_reads_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 @@ -101,13 +149,22 @@ # yaml generated by ncbi_egapx.xml genome: $genome_value taxid: $taxid - #if $cond_input_style.cond_rnaseq_style.rnaseq_style == "history" -reads: $reads_config + #if $cond_input_style.cond_short_reads_style.short_reads_style == "history" +short_reads: $short_reads_config #else -reads: - #set reads_values = $rnaseq.split() - #for $read in [str(rv).strip() for rv in $reads_values] - - $read +short_reads: + #set short_reads_values = $short_reads.split() + #for $short_read in [str(rv).strip() for rv in $short_reads_values] + - $short_read + #end for + #end if + #if $cond_input_style.cond_long_reads_style.long_reads_style == "history" +long_reads: $long_reads_config + #else +long_reads: + #set long_reads_values = $long_reads.split() + #for $long_read in [str(rv).strip() for rv in $long_reads_values] + - $long_read #end for #end if #if str($cond_input_style.proteins) != "None" @@ -151,22 +208,42 @@ </when> </conditional> <param name="taxid" type="integer" min="0" value="0" label="NCBI Taxon ID" help="Used to identify the HMM model files needed"/> - <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"> - <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> + <conditional name="cond_short_reads_style"> + <param name="short_reads_style" type="select" label="short RNA-seq sequence data source" help="Select short RNA-seq input data from history or input a list of SRA identifiers or remote URI"> + <option value="history" selected="True">Select one or more short RNA-seq fastq datasets from the current history</option> + <option value="list">Type in a list of SRA identifiers and/or remote short RNA-seq FASTA URI</option> </param> <when value="history"> - <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"/> + <param name="short_reads" type="data" format="fastqsanger,fastqsanger.gz" multiple="true" optional="true" label="Select multiple short 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"/> + <param name="short_reads_single" type="data_collection" format="fastqsanger,fastqsanger.gz" collection_type="list" label="Select multiple short 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"/> + <param name="short_reads_paired" type="data_collection" format="fastqsanger,fastqsanger.gz" collection_type="list:paired" label="Select multiple short 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="short_reads" type="text" area="true" label="List all required individual short RNA-seq URI or SRA identifiers, separated by spaces or newlines" help="Either a working URI for a short RNA-seq FASTA, or a bare SRA identifier will work - can be mixed"> + <validator type="empty_field"/> + </param> + </when> + </conditional> + <conditional name="cond_long_reads_style"> + <param name="long_reads_style" type="select" label="long RNA-seq sequence data source" help="Select long RNA-seq input data from history or input a list of SRA identifiers or remote URI"> + <option value="history" selected="True">Select one or more long RNA-seq fastq datasets from the current history</option> + <option value="list">Type in a list of SRA identifiers and/or remote long RNA-seq FASTA URI</option> + </param> + <when value="history"> + <param name="long_reads" type="data" format="fastqsanger,fastqsanger.gz" multiple="true" optional="true" label="Select multiple long 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="long_reads_single" type="data_collection" format="fastqsanger,fastqsanger.gz" collection_type="list" label="Select multiple long 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="long_reads_paired" type="data_collection" format="fastqsanger,fastqsanger.gz" collection_type="list:paired" label="Select multiple long 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="long_reads" type="text" area="true" label="List all required individual long RNA-seq URI or SRA identifiers, separated by spaces or newlines" help="Either a working URI for a long RNA-seq FASTA, or a bare SRA identifier will work - can be mixed"> <validator type="empty_field"/> </param> </when> @@ -190,25 +267,29 @@ <outputs> <data name="complete_genomic_gff" format="gff" label="Final annotation for ${on_string}" from_work_dir="egapx_out/complete.genomic.gff"/> <collection name="output_files" type="list" label="EGAPx output for ${on_string}"> - <data name="complete_genomic_gtf" format="gtf" label="Final annotation" from_work_dir="egapx_out/complete.genomic.gtf"/> + <data name="annotated_genome" format="asn1" label="Final annotation" from_work_dir="egapx_out/annotated_genome.asn"/> + <data name="annotation_data" format="tabular" label="Annotation structured comment" from_work_dir="egapx_out/annotation_data.cmt"/> + <data name="gnomon_accepted" format="txt" label="Gnomon accepted annotation models" from_work_dir="egapx_out/annot_builder_output/accept.ftable_annot"/> + <data name="complete_cds" format="fasta" label="Annotated CDS" from_work_dir="egapx_out/complete.cds.fna"/> <data name="complete_genomic_fna" format="fasta" label="Full genome sequences" from_work_dir="egapx_out/complete.genomic.fna"/> - <data name="complete_cds" format="fasta" label="Annotated CDS" from_work_dir="egapx_out/complete.cds.fna"/> + <data name="complete_genomic_gtf" format="gtf" label="Final annotation" from_work_dir="egapx_out/complete.genomic.gtf"/> + <data name="complete_proteins" format="fasta" label="Annotated protein products" from_work_dir="egapx_out/complete.proteins.faa"/> <data name="complete_transcripts" format="fasta" label="Annotated transcripts" from_work_dir="egapx_out/complete.transcripts.fna"/> - <data name="complete_proteins" format="fasta" label="Annotated proteins" from_work_dir="egapx_out/complete.proteins.faa"/> - <data name="annotated_genome" format="asn1" label="Final annotation" from_work_dir="egapx_out/annotated_genome.asn"/> - <data name="accept_ftable_annot" format="txt" label="Accepted annotation models" from_work_dir="egapx_out/annot_builder_output/accept.ftable_annot"/> - <data name="annotation_data_cmt" format="tabular" label="Structured Comment" from_work_dir="egapx_out/annotation_data.cmt"/> + <data name="gnomon_contam_report" format="tabular" label="Gnomon contamination report" from_work_dir="egapx_out/GNOMON/contam_rpt.tsv"/> + <data name="gnomon_quality_report" format="tabular" label="Gnomon quality report" from_work_dir="egapx_out/GNOMON/new.gnomon_quality_report.txt"/> + <data name="gnomon_report" format="txt" label="Gnomon report" from_work_dir="egapx_out/GNOMON/new.gnomon_report.txt"/> + <data name="sra_metadata" format="tabular" label="SRA run metadata" from_work_dir="egapx_out/sra_metadata.dat"/> <data name="feature_counts" format="xml" label="Feature counts" from_work_dir="egapx_out/stats/feature_counts.xml"/> <data name="feature_stats" format="xml" label="Feature stats" from_work_dir="egapx_out/stats/feature_stats.xml"/> - <data name="all_unannotated_val" format="xml" label="" from_work_dir="egapx_out/validated/all_unannotated.val"/> - <data name="genome_val" format="xml" label="" from_work_dir="egapx_out/validated/genome.val"/> + <data name="all_unannotated_val" format="xml" label="all_unannotated" from_work_dir="egapx_out/validated/all_unannotated.val"/> + <data name="genome_val" format="xml" label="all_unannotated" from_work_dir="egapx_out/validated/genome.val"/> </collection> <collection name="nextflow_stats" type="list" label="EGAPx nextflow stats for ${on_string}"> - <data name="run_report" format="html" label="Nextflow execution report" from_work_dir="egapx_out/run.report.html"/> - <data name="run_timeline" format="html" label="Nextflow execution timeline" from_work_dir="egapx_out/run.timeline.html"/> - <data name="nextflow_log" format="txt" label="Nextflow execution log" from_work_dir="egapx_out/nextflow.log"/> - <data name="run_trace" format="tabular" label="Nextflow trace file" from_work_dir="egapx_out/run.trace.txt"/> - <data name="run_params" format="yaml" label="Nextflow run parameters" from_work_dir="egapx_out/run_params.yaml"/> + <data name="nextflow_log" format="txt" label="Nextflow execution log" from_work_dir="egapx_out/nextflow/nextflow.log"/> + <data name="run_params" format="yaml" label="Nextflow run parameters" from_work_dir="egapx_out/nextflow/run_params.yaml"/> + <data name="run_report" format="html" label="Nextflow execution report" from_work_dir="egapx_out/nextflow/run.report.html"/> + <data name="run_timeline" format="html" label="Nextflow execution timeline" from_work_dir="egapx_out/nextflow/run.timeline.html"/> + <data name="run_trace" format="tabular" label="Nextflow trace file" from_work_dir="egapx_out/nextflow/run.trace.txt"/> </collection> <collection name="star_alignments" type="list" label="EGAPx STAR alignments for ${on_string}"> <discover_datasets pattern="(?:.+/)?bam\.[0-9A-Za-z]{10}/(?P<designation>.+)\.bam" format="bam" directory="egapx_out" recurse="true" match_relative_path="true"/> @@ -224,9 +305,9 @@ <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"/> </conditional> <param name="taxid" value="6954"/> - <conditional name="cond_rnaseq_style"> - <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.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"/> + <conditional name="cond_short_reads_style"> + <param name="short_reads_style" value="list"/> + <param name="short_reads" value="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"/> </conditional> </conditional> <section name="developer"> @@ -292,7 +373,7 @@ genome: https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/020/809/275/GCF_020809275.1_ASM2080927v1/GCF_020809275.1_ASM2080927v1_genomic.fna.gz taxid: 6954 - reads: + short_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 @@ -304,7 +385,7 @@ :: genome: https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/030/936/135/GCF_030936135.1_bGavSte3.hap2/GCF_030936135.1_bGavSte3.hap2_genomic.fna.gz - reads: txid37040[Organism] AND biomol_transcript[properties] NOT SRS024887[Accession] + short_reads: txid37040[Organism] AND biomol_transcript[properties] NOT SRS024887[Accession] taxid: 37040 input_C_longicornis.yaml @@ -312,7 +393,7 @@ :: genome: https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/029//603/195/GCF_029603195.1_ASM2960319v2/GCF_029603195.1_ASM2960319v2_genomic.fna.gz - reads: txid2530218[Organism] AND biomol_transcript[properties] NOT SRS024887[Accession] + short_reads: txid2530218[Organism] AND biomol_transcript[properties] NOT SRS024887[Accession] taxid: 2530218 Purpose @@ -348,7 +429,7 @@ :: - reads: + short_reads: - SRR8506572 - SRR9005248 @@ -357,7 +438,7 @@ :: - reads: 'txid6954[Organism] AND biomol_transcript[properties] NOT SRS024887[Accession] AND (SRR8506572[Accession] OR SRR9005248[Accession] )' + short_reads: 'txid6954[Organism] AND biomol_transcript[properties] NOT SRS024887[Accession] AND (SRR8506572[Accession] OR SRR9005248[Accession] )' **Note:** Both the above examples will have more RNA-seq data than the `input_D_farinae_small.yaml` example. To make sure the entrez query does not produce a large number of SRA runs, please run it first at the [NCBI SRA page](https://www.ncbi.nlm.nih.gov/sra). If there are too many SRA runs, then select a few of them and list it in the input yaml.