Merge pull request #61 from nf-core/add-hmmsearch

Add hmmsearch

Author: vagkaratzas

CHANGELOG.md

@@ -9,6 +9,7 @@ Initial release of nf-core/proteinannotator, created with the [nf-core](https://
 
 ### `Added`
 
+- [#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)
 - [#60](https://github.com/nf-core/proteinannotator/pull/60) - Added nf-core module `S4PRED_RUNMODEL` for secondary structure prediction (i.e., α-helix, a β-strand or a coil). (by @vagkaratzas)
 - [#59](https://github.com/nf-core/proteinannotator/pull/59) - Added nf-core qc and pre-processing subworkflow for amino acid sequences `FAA_SEQFU_SEQKIT`. (by @vagkaratzas)
 - [#57](https://github.com/nf-core/proteinannotator/pull/57) - nf-core tools template update to 3.5.1. (by @vagkaratzas)

CITATIONS.md

@@ -18,6 +18,10 @@
 
 > Shen W, Sipos B, Zhao L. SeqKit2: A Swiss army knife for sequence and alignment processing. iMeta. 2024 Apr 5:e191. doi: 10.1002/imt2.191. PubMed PMID: 38898985; PubMed Central PMCID: PMC11183193.
 
+- [hmmer](https://pubmed.ncbi.nlm.nih.gov/29905871/)
+
+> Eddy SR. Accelerated profile HMM searches. PLoS computational biology. 2011 Oct 20;7(10):e1002195. doi: 10.1371/journal.pcbi.1002195. PubMed PMID: 22039361; PubMed Central PMCID: PMC3197634.
+
 - [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.

conf/modules.config

@@ -74,6 +74,24 @@ process {
         ]
     }
 
+    withName: 'NFCORE_PROTEINANNOTATOR:PROTEINANNOTATOR:DOMAIN_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:DOMAIN_ANNOTATION:HMMER_HMMSEARCH' {
+        ext.args   = { "-E ${params.hmmsearch_evalue_cutoff}" }
+        publishDir = [
+            path: { "${params.outdir}/domain_annotation/pfam/" },
+            mode: params.publish_dir_mode,
+            pattern: "*.domtbl.gz",
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: 'NFCORE_PROTEINANNOTATOR:PROTEINANNOTATOR:S4PRED_RUNMODEL' {
         ext.prefix = { params.s4pred_outfmt }
         ext.args   = { "--outfmt ${params.s4pred_outfmt}" }

conf/test.config

@@ -23,10 +23,9 @@ params {
     config_profile_description = 'Minimal test dataset to check pipeline function'
 
     // Input data
-    // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
-    // TODO nf-core: Give any required params for the test so that command line flags are not needed
-    // From: https://github.com/nf-core/proteinfold/blob/1.1.1/conf/test.config
-    // Example: https://github.com/nf-core/test-datasets/blob/proteinfold/testdata/samplesheet/v1.2/samplesheet.csv
     input = params.pipelines_testdata_base_path + 'proteinfold/testdata/samplesheet/v1.2/samplesheet.csv'
+    // Domain annotation
+    pfam_latest_link = params.pipelines_testdata_base_path + 'proteinannotator/testdata/pfam/Pfam-A_test.hmm.gz'
+    // Functional annotation
     skip_interproscan = true
 }

conf/test_full.config

@@ -15,7 +15,7 @@ params {
     config_profile_description = 'Full test dataset to check pipeline function'
 
     // Input data for full size test
-    // TODO nf-core: Specify the paths to your full test data ( on nf-core/test-datasets or directly in repositories, e.g. SRA)
-    // TODO nf-core: Give any required params for the test so that command line flags are not needed
     input = params.pipelines_testdata_base_path + 'proteinannotator/samplesheet/snap25-isoforms.csv'
+    // Domain annotation
+    pfam_latest_link = params.pipelines_testdata_base_path + 'proteinannotator/testdata/pfam/Pfam-A_test.hmm.gz'
 }

docs/output.md

@@ -16,7 +16,11 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
   - [SeqFu](#seqfu) for input amino acid sequences quality check (QC)
   - [SeqKit](#seqkit) for preprocessing input amino acid sequences (i.e., gap removal, convert to upper case, validate, filter by length, replace special characters such as `/`, and remove duplicate sequences)
 
-- [Functional Annotation](#functional-annotation) Annotate proteins with functional domains
+- [Domain annotation](#domain-annotation) Annotate proteins with domains from established repositories.
+  - [aria2](#aria2) - To optionally download the latest Pfam database through the pipeline.
+  - [hmmer](#hmmer) - To optionally match the input sequence to known Pfam domains through `hmmer/hmmsearch`
+
+- [Functional annotation](#functional-annotation) Annotate proteins with functional domains
   - [InterProScan](#Interproscan) - Search the InterPro database for functional domains
 
 - [s4pred](#s4pred) - Predict secondary structures of sequences, producing per amino acid probabilities of being an α-helix, a β-strand or a coil.
@@ -60,7 +64,36 @@ The `seqkit` module is used for initial preprocessing (i.e., gap removal, conver
 
 [SeqKit](https://github.com/shenwei356/seqkit) is a cross-platform and ultrafast toolkit for FASTA/Q file manipulation.
 
-### Functional Annotation
+### Domain annotation
+
+#### aria2
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `downloaded_dbs/`
+  - `Pfam-A*.hmm.gz`: (optional) The latest full, or a minimal test, Pfam-A HMM database that can be downloaded through the pipeline.
+
+</details>
+
+[aria2](https://github.com/aria2/aria2/) is a lightweight multi-protocol & multi-source, cross platform download utility operated in command-line. It supports HTTP/HTTPS, FTP, SFTP, BitTorrent and Metalink.
+
+#### hmmer
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `domain_annotation/`
+  - `pfam/`
+    - `<samplename>.domtbl.gz`: `hmmer/hmmsearch` results along parameters info.
+
+</details>
+
+The `domain_annotation/pfam` folder contains a `.domtbl.gz` annotation file per input sample.
+
+[hmmer](https://github.com/EddyRivasLab/hmmer) is a fast and flexible alignment trimming tool that keeps phylogenetically informative sites and removes others.
+
+### Functional annotation
 
 #### InterProScan
 

main.nf

@@ -40,6 +40,9 @@ workflow NFCORE_PROTEINANNOTATOR {
     PROTEINANNOTATOR (
         samplesheet,
         params.skip_preprocessing,
+        params.skip_pfam,
+        params.pfam_latest_link,
+        params.pfam_db,
         params.skip_s4pred
     )
     emit:

modules.json

@@ -5,6 +5,16 @@
         "https://github.com/nf-core/modules.git": {
             "modules": {
                 "nf-core": {
+                    "aria2": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"]
+                    },
+                    "hmmer/hmmsearch": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"]
+                    },
                     "mmseqs/search": {
                         "branch": "master",
                         "git_sha": "81880787133db07d9b4c1febd152c090eb8325dc",