Mercurial > repos > galaxytrakr > aws_sra
changeset 30:73ee30eb273a draft
planemo upload for repository https://github.com/CFSAN-Biostatistics/galaxytrakr-tools commit d0c08749588099d40db3c23bfd554800ac307a30
| author | galaxytrakr |
|---|---|
| date | Tue, 24 Mar 2026 03:09:41 +0000 |
| parents | 569a598c7e68 |
| children | 90ae4d437133 |
| files | aws_sra.xml |
| diffstat | 1 files changed, 117 insertions(+), 75 deletions(-) [+] |
line wrap: on
line diff
--- a/aws_sra.xml Tue Mar 24 01:43:32 2026 +0000 +++ b/aws_sra.xml Tue Mar 24 03:09:41 2026 +0000 @@ -1,91 +1,145 @@ -<tool id="aws_sra" name="NCBI SRA AWS Fetch" version="0.4.0+gt_0.8" profile="23.0"> +<tool id="aws_sra" name="NCBI SRA AWS Fetch" version="0.4.0+gt_0.50" profile="22.01"> <description>Fetches one or more SRA runs from AWS S3 and converts them to FASTQ</description> <requirements> + <requirement type="package" version="3.1.1">sra-tools</requirement> + <requirement type="package" version="2.8">pigz</requirement> <requirement type="package" version="2.34.8">awscli</requirement> - <requirement type="package" version="3.2.1">sra-tools</requirement> - <requirement type="package" version="2.8">pigz</requirement> </requirements> <version_command>fasterq-dump --version</version_command> - <command detect_errors="aggressive"><![CDATA[ - ## Create a clean list of accessions from the user input - echo "$accession" | sed 's/,/\n/g; s/ \+/\n/g' | grep . > accessions.txt && - - ## Loop over each clean accession - for acc in $(cat accessions.txt); - do - echo "Processing accession: $acc" && - - ## 1. Create unique directories for this accession - mkdir -p sra_cache_${acc} fastq_out_${acc} && - - ## 2. Download the file from S3 using aws s3 cp - aws s3 cp --no-sign-request "s3://sra-pub-run-odp/sra/${acc}/${acc}" ./sra_cache_${acc}/ && - - ## 3. Convert with fasterq-dump - fasterq-dump --outdir ./fastq_out_${acc} --temp . --threads \${GALAXY_SLOTS:-4} --split-files ./sra_cache_${acc}/${acc} && - - ## 4. Compress with pigz - pigz -p \${GALAXY_SLOTS:-4} ./fastq_out_${acc}/*.fastq && - - ## 5. Move outputs for collection discovery - #if str($layout) == 'paired' - mv ./fastq_out_${acc}/${acc}_1.fastq.gz '$output_r1.files_path/${acc}_1.fastq.gz' && - mv ./fastq_out_${acc}/${acc}_2.fastq.gz '$output_r2.files_path/${acc}_2.fastq.gz' - #else - mv ./fastq_out_${acc}/${acc}.fastq.gz '$output_r1.files_path/${acc}.fastq.gz' - #end if && - - ## 6. Clean up - rm -rf sra_cache_${acc} fastq_out_${acc} - done + <command detect_errors="exit_code"><![CDATA[ + #if $input.input_select == "accession_number": + echo '${input.accession}' | sed -r 's/(\,|\;|__cn__)/\n/g' > accessions && + #else: + grep '^[[:space:]]*[ESD]RR[0-9]\{1,\}[[:space:]]*$' '${input.file_list}' > accessions && + #end if + mkdir -p output && + mkdir -p outputOther && + for acc in \$(cat ./accessions); + do ( + echo "Processing accession: \$acc" && + mkdir -p sra_cache_\${acc} && + aws s3 cp --no-sign-request "s3://sra-pub-run-odp/sra/\${acc}/\${acc}" ./sra_cache_\${acc}/\${acc} && + fasterq-dump -e \${GALAXY_SLOTS:-4} -t . --split-3 ./sra_cache_\${acc}/\${acc} && + rm -rf sra_cache_\${acc} && + count="\$(ls \${acc}*.fastq 2>/dev/null | wc -l)" && + echo "Found \$count fastq file(s) for \$acc" && + data=(\$(ls \${acc}*.fastq 2>/dev/null)) && + if [ "\$count" -eq 1 ]; then + pigz -cqp \${GALAXY_SLOTS:-4} "\${data[0]}" > output/"\${acc}".fastqsanger.gz && + rm "\${data[0]}"; + elif [ -e "\${acc}".fastq ]; then + pigz -cqp \${GALAXY_SLOTS:-4} "\${acc}".fastq > outputOther/"\${acc}"__single.fastqsanger.gz && + pigz -cqp \${GALAXY_SLOTS:-4} "\${acc}"_1.fastq > output/"\${acc}"_1.fastqsanger.gz && + pigz -cqp \${GALAXY_SLOTS:-4} "\${acc}"_2.fastq > output/"\${acc}"_2.fastqsanger.gz && + rm "\${acc}"*.fastq; + elif [ "\$count" -eq 2 ]; then + pigz -cqp \${GALAXY_SLOTS:-4} "\${acc}"_1.fastq > output/"\${acc}"_1.fastqsanger.gz && + pigz -cqp \${GALAXY_SLOTS:-4} "\${acc}"_2.fastq > output/"\${acc}"_2.fastqsanger.gz && + rm "\${acc}"*.fastq; + else + for file in \${data[*]}; do + pigz -cqp \${GALAXY_SLOTS:-4} "\$file" > outputOther/"\$file"sanger.gz && + rm "\$file"; + done; + fi + ); done; + echo "Done with all accessions." ]]></command> <inputs> - <param name="accession" type="text" label="SRA Accession(s)" help="Provide one or more accession numbers (separated by commas, spaces, or newlines)."/> - <param name="layout" type="select" label="Read layout" help="This setting is applied to all accessions."> - <option value="paired" selected="true">Paired-end (R1 + R2)</option> - <option value="single">Single-end</option> - </param> + <conditional name="input"> + <param name="input_select" type="select" label="Select input type"> + <option value="accession_number">SRA Accession number(s)</option> + <option value="file_list">File containing accession list</option> + </param> + <when value="accession_number"> + <param name="accession" type="text" label="SRA Accession(s)" + help="One or more SRA run accessions (SRR, ERR, or DRR), separated by commas or spaces."> + <validator type="empty_field" message="At least one SRA accession is required."/> + <sanitizer> + <valid initial="string.printable"> + <remove value="'"/> + </valid> + <mapping initial="none"> + <add source="'" target="'"'"'"/> + </mapping> + </sanitizer> + </param> + </when> + <when value="file_list"> + <param name="file_list" type="data" format="txt,tabular" label="Accession list file" + help="A text file with one SRA accession (SRR, ERR, or DRR) per line."/> + </when> + </conditional> </inputs> <outputs> - <collection name="output_r1" type="list" label="FASTQ Reads (R1) for ${accession}"> - <discover_datasets pattern="(?P<designation>.+)_1\.fastq\.gz" format="fastqsanger.gz" /> + <collection name="list_paired" type="list:paired" label="Paired-end FASTQ (aws_sra)"> + <discover_datasets + pattern="(?P<identifier_0>[^_]+)_(?P<identifier_1>[12])\.fastqsanger\.gz" + directory="output" + ext="fastqsanger.gz"/> </collection> - <collection name="output_r2" type="list" label="FASTQ Reads (R2) for ${accession}"> - <discover_datasets pattern="(?P<designation>.+)_2\.fastq\.gz" format="fastqsanger.gz" /> - <filter>layout == 'paired'</filter> + <collection name="output_single" type="list" label="Single-end FASTQ (aws_sra)"> + <discover_datasets + pattern="(?P<designation>.+)\.fastqsanger\.gz" + directory="output" + ext="fastqsanger.gz"/> + </collection> + <collection name="output_other" type="list" label="Other FASTQ (aws_sra)"> + <discover_datasets + pattern="(?P<designation>.+)\.fastqsanger\.gz" + directory="outputOther" + format="fastqsanger.gz"/> </collection> </outputs> <tests> - <test expect_num_outputs="2"> - <param name="accession" value="SRR13333333"/> - <param name="layout" value="paired"/> - <output_collection name="output_r1" type="list" count="1"> - <element name="SRR13333333_1" ftype="fastqsanger.gz"> - <assert_contents> - <has_text text="@SRR13333333"/> - </assert_contents> - </element> - </output_collection> - <output_collection name="output_r2" type="list" count="1"> - <element name="SRR13333333_2" ftype="fastqsanger.gz"> - <assert_contents> - <has_text text="@SRR13333333"/> - </assert_contents> + <test expect_num_outputs="3"> + <conditional name="input"> + <param name="input_select" value="accession_number"/> + <param name="accession" value="SRR13333333"/> + </conditional> + <output_collection name="list_paired" type="list:paired" count="1"> + <element name="SRR13333333"> + <element name="forward" ftype="fastqsanger.gz"> + <assert_contents> + <has_text text="@SRR13333333"/> + </assert_contents> + </element> + <element name="reverse" ftype="fastqsanger.gz"> + <assert_contents> + <has_text text="@SRR13333333"/> + </assert_contents> + </element> </element> </output_collection> </test> + </tests> <help><![CDATA[ **NCBI SRA AWS Fetch** -Fetches one or more SRA runs from the public `sra-pub-run-odp` S3 bucket and converts them to gzip-compressed FASTQ using `fasterq-dump`. This tool uses `aws s3 cp` for direct downloads within the AWS environment. +Fetches one or more SRA runs from the public ``sra-pub-run-odp`` S3 bucket and converts them to +gzip-compressed FASTQ using ``fasterq-dump``. Downloads use ``aws s3 cp`` with no credentials +required (public bucket). + +**Inputs** + +- **SRA Accession number(s)**: Type one or more accessions (SRR, ERR, or DRR) directly, comma- or space-separated. +- **File containing accession list**: A text file with one accession per line. This option is connectable as a workflow input. + +**Outputs** + +Three collections are always created (some may be empty depending on the data): + +- **Paired-end FASTQ**: A nested ``list:paired`` collection — each accession contains a forward/reverse pair. +- **Single-end FASTQ**: A flat list for reads confirmed single-end by ``--split-3``. +- **Other FASTQ**: Reads that could not be cleanly classified. ]]></help> <citations> @@ -93,22 +147,10 @@ @misc{ncbi_sra_aws, title = {{NCBI} {SRA} on {AWS} Open Data}, author = {{National Center for Biotechnology Information}}, - howpublished = {\\url{https://registry.opendata.aws/ncbi-sra/}}, + howpublished = {\url{https://registry.opendata.aws/ncbi-sra/}}, note = {Accessed via AWS S3 without credentials} } </citation> - <citation type="bibtex"> -@article{sra_toolkit, - title = {The {NCBI} {SRA} and portable data in biology}, - author = {Leinonen, Rasko and Sugawara, Hideaki and Shumway, Martin and - {International Nucleotide Sequence Database Collaboration}}, - journal = {Nucleic Acids Research}, - volume = {39}, - number = {suppl\\\_1}, - pages = {D19--D21}, - year = {2011}, - doi = {10.1093/nar/gkq1019} -} - </citation> + <citation type="doi">10.1093/nar/gkq1019</citation> </citations> </tool>