diff --git a/docker/estimate/Dockerfile b/docker/estimate/Dockerfile deleted file mode 100644 index eb4a7a057..000000000 --- a/docker/estimate/Dockerfile +++ /dev/null @@ -1,5 +0,0 @@ -FROM ghcr.io/r-hub/r-minimal/r-minimal:4.4.2 - -RUN apk upgrade --no-cache - -RUN R -e 'install.packages("estimate", repos="http://r-forge.r-project.org", dependencies=TRUE)' diff --git a/docker/estimate/package.json b/docker/estimate/package.json deleted file mode 100644 index cd5a502fe..000000000 --- a/docker/estimate/package.json +++ /dev/null @@ -1,4 +0,0 @@ -{ - "name": "estimate", - "version": "2.0.0" -} \ No newline at end of file diff --git a/tools/CHANGELOG.md b/tools/CHANGELOG.md index a46bab992..c57ce6972 100644 --- a/tools/CHANGELOG.md +++ b/tools/CHANGELOG.md @@ -10,6 +10,10 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/). - Bumped `fastp` memory requirements [#284](https://github.com/stjudecloud/workflows/pull/284) +### Removed + +- Removed the long deprecated and unused `estimate.wdl` tool [#292](https://github.com/stjudecloud/workflows/pull/292) + ## 2025 December ### Changed diff --git a/tools/estimate.wdl b/tools/estimate.wdl deleted file mode 100644 index 341eb9b40..000000000 --- a/tools/estimate.wdl +++ /dev/null @@ -1,59 +0,0 @@ -## [Homepage](https://bioinformatics.mdanderson.org/estimate/) - -version 1.1 - -task run_estimate { - meta { - description: "Given a gene expression file, run the ESTIMATE software package" - warning: "**[DEPRECATED]**" - outputs: { - estimate_file: "The results file of the ESTIMATE software package" - } - deprecated: true - } - - parameter_meta { - #@ except: DescriptionLength - gene_expression_file: "A 2 column headered TSV file with 'Gene name' in the first column and gene expression values (as floats) in the second column. Can be generated with the `calc_tpm` task." - outfile_name: "Name of the ESTIMATE output file" - memory_gb: "RAM to allocate for task, specified in GB" - disk_size_gb: "Disk space to allocate for task, specified in GB" - max_retries: "Number of times to retry in case of failure" - } - - input { - File gene_expression_file - String outfile_name = ( - basename(gene_expression_file, ".TPM.txt") + ".ESTIMATE.gct" - ) - Int memory_gb = 4 - Int disk_size_gb = 10 - Int max_retries = 1 - } - - #@ except: LineWidth, ShellCheck - command <<< - cp "~{gene_expression_file}" gene_expression.txt - Rscript - <>> - - output { - File estimate_file = "~{outfile_name}" - } - - runtime { - memory: "~{memory_gb} GB" - disks: "~{disk_size_gb} GB" - container: "ghcr.io/stjudecloud/estimate:2.0.0" - maxRetries: max_retries - } -} diff --git a/workflows/rnaseq/CHANGELOG.md b/workflows/rnaseq/CHANGELOG.md index 8bdbc8a96..3031abe92 100644 --- a/workflows/rnaseq/CHANGELOG.md +++ b/workflows/rnaseq/CHANGELOG.md @@ -4,6 +4,12 @@ All notable changes to this project will be documented in this file. The format is based on [Keep a Changelog](http://keepachangelog.com/). +## 2026 January + +### Removed + +- Removed the long deprecated and unused `ESTIMATE.wdl` tool [#292](https://github.com/stjudecloud/workflows/pull/292) + ## 2025 July ### Added diff --git a/workflows/rnaseq/ESTIMATE.wdl b/workflows/rnaseq/ESTIMATE.wdl deleted file mode 100644 index e8e8a7b01..000000000 --- a/workflows/rnaseq/ESTIMATE.wdl +++ /dev/null @@ -1,43 +0,0 @@ -#@ except: DescriptionLength - -version 1.1 - -import "../../tools/estimate.wdl" -import "../../tools/htseq.wdl" - -workflow estimate { - meta { - name: "ESTIMATE" - description: "Runs the ESTIMATE software package on a feature counts file" - warning: "**[DEPRECATED]**" - external_help: "https://bioinformatics.mdanderson.org/estimate/" - outputs: { - tpm: "Transcripts Per Million file", - estimate_result: "Final output of ESTIMATE", - } - deprecated: true - } - - parameter_meta { - counts_file: "A two column headerless TSV file with gene names in the first column and counts (as integers) in the second column. Entries starting with '__' will be discarded. Can be generated with `htseq.wdl`." - gene_lengths_file: "A two column headered TSV file with gene names (matching those in the `counts` file) in the first column and feature lengths (as integers) in the second column. Can be generated with `calc-gene-lengths.wdl`." - } - - input { - File counts_file - File gene_lengths_file - } - - call htseq.calc_tpm { input: - counts = counts_file, - feature_lengths = gene_lengths_file, - } - call estimate.run_estimate { input: - gene_expression_file = calc_tpm.tpm_file, - } - - output { - File tpm = calc_tpm.tpm_file - File estimate_result = run_estimate.estimate_file - } -}