Merge pull request #67 from nf-core/nf-core-interproscan

Use nf-core interproscan instead of local version

Author: vagkaratzas

.github/workflows/nf-test.yml

@@ -51,7 +51,6 @@ jobs:
           NFT_VER: ${{ env.NFT_VER }}
         with:
           max_shards: 7
-          tags: CI
 
       - name: debug
         run: |
@@ -101,7 +100,6 @@ jobs:
           profile: ${{ matrix.profile }}
           shard: ${{ matrix.shard }}
           total_shards: ${{ env.TOTAL_SHARDS }}
-          tags: CI
 
       - name: Report test status
         if: ${{ always() }}

.prettierignore

@@ -16,4 +16,3 @@ modules/nf-core/
 subworkflows/nf-core/
 **/Makefile
 Makefile
-modules/local/interproscan/tests/fixtures/interproscan_db/data

CHANGELOG.md

@@ -9,6 +9,8 @@ Initial release of nf-core/proteinannotator, created with the [nf-core](https://
 
 ### `Added`
 
+- [#68](https://github.com/nf-core/proteinannotator/pull/68) - Using the `ARIA2` and `UNTAR` nf-core modules to download and decompress the InterProScan database. (by @vagkaratzas)
+- [#67](https://github.com/nf-core/proteinannotator/pull/67) - Swapped to the updated, non-buggy, nf-core version of `INTERPROSCAN`. (by @vagkaratzas)
 - [#65](https://github.com/nf-core/proteinannotator/pull/65) - Converted the pipeline schematic to nf-core metromap. (by @vagkaratzas)
 - [#62](https://github.com/nf-core/proteinannotator/pull/62) - Added the option to download and use the latest FunFam HMM library (or use path to an existing one) for domain annotation. (by @vagkaratzas)
 - [#61](https://github.com/nf-core/proteinannotator/pull/61) - Added nf-core modules `ARIA2` and `HMMER_HMMSEARCH` to download latest Pfam HMM library (or use path to existing one) and match domains to input sequences. (by @vagkaratzas)
@@ -20,7 +22,7 @@ Initial release of nf-core/proteinannotator, created with the [nf-core](https://
 - [#47](https://github.com/nf-core/proteinannotator/pull/47) - Update metromap with more tools added from [May 2025 Hackathon](https://nf-co.re/events/2025/hackathon-boston)
 - [#42](https://github.com/nf-core/proteinannotator/pull/42) - Updated to `nf-test` on GitHub Actions and in the `PULL_REQUEST_TEMPLATE.md`
 - [#13](https://github.com/nf-core/proteinannotator/pull/13) - Add nf-core seqkit/stats module
-- [#9](https://github.com/nf-core/proteinannotator/pull/9) - Add [InterProScan](https://interproscan-docs.readthedocs.io/) module
+- [#9](https://github.com/nf-core/proteinannotator/pull/9) - Added [InterProScan](https://interproscan-docs.readthedocs.io/) module - local version
 
 ### `Fixed`
 

CITATIONS.md

@@ -24,20 +24,12 @@
 
 - [InterProScan](https://academic.oup.com/bioinformatics/article/17/9/847/206564)
 
-> Zdobnov, Evgeni M., and Rolf Apweiler. “InterProScan – an Integration Platform for the Signature-Recognition Methods in InterPro.” Bioinformatics 17, no. 9 (September 1, 2001): 847–48. https://doi.org/10.1093/bioinformatics/17.9.847.
+> Jones P, Binns D, Chang HY, Fraser M, Li W, McAnulla C, McWilliam H, Maslen J, Mitchell A, Nuka G, Pesseat S, Quinn, A. F, Sangrador-Vegas A, Scheremetjew M, Yong S-Y, Lopez R, Hunter S. InterProScan 5: genome-scale protein function classification. Bioinformatics. 2014 May 1;30(9):1236-40. doi: 10.1093/bioinformatics/btu031. PubMed PMID: 24451626; PubMed Central PMCID: PMC3998142.
 
 - [s4pred](https://pubmed.ncbi.nlm.nih.gov/34213528/)
 
 > Moffat L, Jones DT. Increasing the accuracy of single sequence prediction methods using a deep semi-supervised learning framework. Bioinformatics. 2021 Nov 1;37(21):3744-51. doi: 10.1093/bioinformatics/btab491. PubMed PMID: 34213528; PubMed Central PMCID: PMC8570780.
 
-<!-- - [MMseqs2](https://www.nature.com/articles/nbt.3988)
-
-> Zdobnov, Evgeni M., and Rolf Apweiler. “InterProScan – an Integration Platform for the Signature-Recognition Methods in InterPro.” Bioinformatics 17, no. 9 (September 1, 2001): 847–48. https://doi.org/10.1093/bioinformatics/17.9.847.
-
-- [mTM-align](https://academic.oup.com/bioinformatics/article/34/10/1719/4769500)
-
-> Dong, Runze, Zhenling Peng, Yang Zhang, and Jianyi Yang. “mTM-Align: An Algorithm for Fast and Accurate Multiple Protein Structure Alignment.” Bioinformatics 34, no. 10 (May 15, 2018): 1719–25. https://doi.org/10.1093/bioinformatics/btx828. -->
-
 - [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
 
 > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.

conf/modules.config

@@ -110,6 +110,35 @@ process {
         ]
     }
 
+    withName: 'NFCORE_PROTEINANNOTATOR:PROTEINANNOTATOR:FUNCTIONAL_ANNOTATION:ARIA2' {
+        publishDir = [
+            path: { "${params.outdir}/downloaded_dbs/" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: 'NFCORE_PROTEINANNOTATOR:PROTEINANNOTATOR:FUNCTIONAL_ANNOTATION:UNTAR' {
+        publishDir = [
+            path: { "${params.outdir}/downloaded_dbs/" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+        ]
+    }
+
+    withName: 'NFCORE_PROTEINANNOTATOR:PROTEINANNOTATOR:FUNCTIONAL_ANNOTATION:INTERPROSCAN' {
+        publishDir = [
+            path: { "${params.outdir}/functional_annotation/interproscan/${meta.id}/" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+        ]
+        ext.args = [
+            "--applications ${params.interproscan_applications}",
+            params.interproscan_enableprecalc ? '' : '--disable-precalc'
+        ].join(' ').trim()
+        cpus = 1 // bugs with more
+    }
+
     withName: 'NFCORE_PROTEINANNOTATOR:PROTEINANNOTATOR:S4PRED_RUNMODEL' {
         ext.prefix = { params.s4pred_outfmt }
         ext.args   = { "--outfmt ${params.s4pred_outfmt}" }

conf/test.config

@@ -23,10 +23,11 @@ params {
     config_profile_description = 'Minimal test dataset to check pipeline function'
 
     // Input data
-    input = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
+    input = params.pipelines_testdata_base_path + 'proteinannotator/samplesheet/samplesheet.csv'
     // Domain annotation
     pfam_latest_link   = params.pipelines_testdata_base_path + 'proteinannotator/testdata/pfam/Pfam-A_test.hmm.gz'
     funfam_latest_link = params.pipelines_testdata_base_path + 'proteinannotator/testdata/funfam/funfam-hmm3-v4_3_0_test.lib.gz'
     // Functional annotation
-    skip_interproscan = true
+    interproscan_db_url       = params.pipelines_testdata_base_path + 'proteinannotator/testdata/interproscan/interproscan_test.tar.gz'
+    interproscan_applications = 'Hamap,TIGRFAM,sfld'
 }

conf/test_full.config

@@ -15,8 +15,11 @@ params {
     config_profile_description = 'Full test dataset to check pipeline function'
 
     // Input data for full size test
-    input = params.pipelines_testdata_base_path + 'proteinannotator/samplesheet/snap25-isoforms.csv'
+    input = params.pipelines_testdata_base_path + 'proteinannotator/testdata/samplesheet.csv'
     // Domain annotation
     pfam_latest_link   = params.pipelines_testdata_base_path + 'proteinannotator/testdata/pfam/Pfam-A_test.hmm.gz'
     funfam_latest_link = params.pipelines_testdata_base_path + 'proteinannotator/testdata/funfam/funfam-hmm3-v4_3_0_test.lib.gz'
+    // Functional annotation
+    interproscan_db_url       = params.pipelines_testdata_base_path + 'proteinannotator/testdata/interproscan_test.tar.gz'
+    interproscan_applications = 'Hamap,TIGRFAM,sfld'
 }