Merge pull request #90 from nf-core/add-metagroot-domain-annot

Add metagroot domain annot

Author: vagkaratzas

CHANGELOG.md

@@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
+- [#90](https://github.com/nf-core/proteinannotator/pull/90) - Added the option to download and use the latest `metagRoot` HMM library (or use path to an existing one) for domain annotation. (by @angelphanth)
 - [#87](https://github.com/nf-core/proteinannotator/pull/87) - Added the option to download and use the latest `NMPFams` HMM library (or use path to an existing one) for domain annotation. (by @npechl)
 - [#85](https://github.com/nf-core/proteinannotator/pull/85) - Added zenodo doi in `nextflow.config`. (by @vagkaratzas)
 

README.md

@@ -37,7 +37,7 @@ Generate input amino acid sequence statistics with ([`SeqFu`](https://github.com
 ### Annotate sequences
 
 1. Conserved domain annotation with ([`hmmer`](https://github.com/EddyRivasLab/hmmer/)) against databases
-   such as [Pfam](https://ftp.ebi.ac.uk/pub/databases/Pfam/), [FunFam](https://download.cathdb.info/cath/releases/all-releases/), and [NMPFams](https://pavlopoulos-lab.org/envofams/databases/hmmer/)
+   such as [Pfam](https://ftp.ebi.ac.uk/pub/databases/Pfam/), [FunFam](https://download.cathdb.info/cath/releases/all-releases/), and [NMPFams and metagRoot](https://pavlopoulos-lab.org/envofams/databases/hmmer/)
 2. Functional annotation:
    - ([`InterProScan`](https://interproscan-docs.readthedocs.io/en/v5/)) a software tool used to analyze protein sequences by scanning them against the signatures of protein families, domains, and sites in the [InterPro](https://www.ebi.ac.uk/interpro/) database, helping to identify their functional characteristics.
 3. Predict secondary structure compositional features such as α-helices, β-strands and coils with ([`s4pred`](https://github.com/psipred/s4pred))

conf/modules.config

@@ -98,6 +98,14 @@ process {
         ]
     }
 
+    withName: 'NFCORE_PROTEINANNOTATOR:PROTEINANNOTATOR:DOMAIN_ANNOTATION:ARIA2_METAGROOT' {
+        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:HMMSEARCH_PFAM' {
         ext.args   = { "-E ${params.hmmsearch_evalue_cutoff}" }
         publishDir = [
@@ -128,6 +136,16 @@ process {
         ]
     }
 
+    withName: 'NFCORE_PROTEINANNOTATOR:PROTEINANNOTATOR:DOMAIN_ANNOTATION:HMMSEARCH_METAGROOT' {
+        ext.args   = { "-E ${params.hmmsearch_evalue_cutoff}" }
+        publishDir = [
+            path: { "${params.outdir}/domain_annotation/metagroot/" },
+            mode: params.publish_dir_mode,
+            pattern: "*.domtbl.gz",
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: 'NFCORE_PROTEINANNOTATOR:PROTEINANNOTATOR:FUNCTIONAL_ANNOTATION:ARIA2' {
         publishDir = [
             path: { "${params.outdir}/downloaded_dbs/" },

conf/test.config

@@ -25,9 +25,10 @@ params {
     // Input data
     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'
-    nmpfams_latest_link = params.pipelines_testdata_base_path + 'proteinannotator/testdata/nmpfams/nmpfamsdb_test.hmm.gz'
+    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'
+    nmpfams_latest_link     = params.pipelines_testdata_base_path + 'proteinannotator/testdata/nmpfams/nmpfamsdb_test.hmm.gz'
+    metagroot_latest_link   = params.pipelines_testdata_base_path + 'proteinannotator/testdata/metagroot/metagroot_test.hmm.gz'
     // Functional annotation
     interproscan_db_url       = params.pipelines_testdata_base_path + 'proteinannotator/testdata/interproscan/interproscan_test.tar.gz'
     interproscan_applications = 'Hamap,TIGRFAM,sfld'

conf/test_full.config

@@ -17,9 +17,10 @@ params {
     // Input data for full size test
     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'
-    nmpfams_latest_link = params.pipelines_testdata_base_path + 'proteinannotator/testdata/nmpfams/nmpfamsdb_test.hmm.gz'
+    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'
+    nmpfams_latest_link     = params.pipelines_testdata_base_path + 'proteinannotator/testdata/nmpfams/nmpfamsdb_test.hmm.gz'
+    metagroot_latest_link   = params.pipelines_testdata_base_path + 'proteinannotator/testdata/metagroot/metagroot_test.hmm.gz'
     // Functional annotation
     interproscan_db_url       = params.pipelines_testdata_base_path + 'proteinannotator/testdata/interproscan_test.tar.gz'
     interproscan_applications = 'Hamap,TIGRFAM,sfld'

docs/output.md

@@ -14,9 +14,9 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
   - [SeqFu](#seqfu) for input amino acid sequences quality control (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)
 - [Database download](#database-download) Optionally download selected databases for annotation.
-  - [aria2](#aria2) - To optionally download the Pfam, FunFam, NMPFams and/or InterProScan databases through the pipeline.
+  - [aria2](#aria2) - To optionally download the Pfam, FunFam, NMPFams, metagRoot and/or InterProScan databases through the pipeline.
 - [Domain annotation](#domain-annotation) Annotate proteins with domains from established repositories.
-  - [hmmer](#hmmer) - To optionally match the input sequence to known Pfam, FunFam and/or NMPFams domains through `hmmer/hmmsearch`
+  - [hmmer](#hmmer) - To optionally match the input sequence to known Pfam, FunFam, NMPFams and/or metagRoot domains through `hmmer/hmmsearch`
 - [Functional annotation](#functional-annotation) Annotate proteins with functional domains
   - [InterProScan](#Interproscan) - Search the InterProScan database for functional domains
 - [s4pred](#s4pred) - Predict secondary structures of sequences, producing amino acid level probabilities of forming an α-helix, a β-strand or a coil.
@@ -73,10 +73,11 @@ The `seqkit` module is used for initial preprocessing (i.e., gap removal, conver
   - `interproscan_test.tar.gz`: (optional) the downloaded InterProScan archive of member databases according to the optional user-provided url
   - `funfam-hmm3-v4_3_0*.lib.gz`: (optional) The latest (v4_3_0) full, or a minimal test, FunFam HMM database that can be downloaded through the pipeline.
   - `nmpfamsdb.hmm.gz`: (optional) The latest full, or a minimal test, NMPFams HMM database that can be downloaded through the pipeline.
+  - `metagroot.hmm.gz`: (optional) The latest full, or a minimal test, metagRoot HMM database that can be downloaded through the pipeline.
 
 </details>
 
-If the `skip_*` flags (e.g., `skip_pfam`, `skip_funfam`, `skip_nmpfams`, `skip_interproscan`) for each annotation database is set to `true`, or the `*_db` parameter paths (e.g., `pfam_db`, `funfam_db`, `nmpfams_db`, `interproscan_db`) are set (i.e., not `null`), or the run is resumed after a successful database download, then the respective database will not be (re)downloaded. The full database links can be found in the main `nextflow.config` file, while minimal test versions can be found in the `test` and `test_full` profiles (i.e., `conf/test.config`, `conf/test_full.config`).
+If the `skip_*` flags (e.g., `skip_pfam`, `skip_funfam`, `skip_nmpfams`, `skip_metagroot`, `skip_interproscan`) for each annotation database is set to `true`, or the `*_db` parameter paths (e.g., `pfam_db`, `funfam_db`, `nmpfams_db`, `metagroot_db`, `interproscan_db`) are set (i.e., not `null`), or the run is resumed after a successful database download, then the respective database will not be (re)downloaded. The full database links can be found in the main `nextflow.config` file, while minimal test versions can be found in the `test` and `test_full` profiles (i.e., `conf/test.config`, `conf/test_full.config`).
 
 [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.
 
@@ -94,10 +95,12 @@ If the `skip_*` flags (e.g., `skip_pfam`, `skip_funfam`, `skip_nmpfams`, `skip_i
     - `<samplename>.domtbl.gz`: `hmmer/hmmsearch` results along parameters info.
   - `nmpfams/`
     - `<samplename>.domtbl.gz`: `hmmer/hmmsearch` results along parameters info.
+  - `metagroot/`
+    - `<samplename>.domtbl.gz`: `hmmer/hmmsearch` results along parameters info.
 
 </details>
 
-Each of the `domain_annotation/` subfolders (e.g., `pfam`, `funfam`, `nmpfams`) contain a `.domtbl.gz` annotation file per input sample, depending on which domain annotation databases were used in the pipeline execution.
+Each of the `domain_annotation/` subfolders (e.g., `pfam`, `funfam`, `nmpfams`, `metagroot`) contain a `.domtbl.gz` annotation file per input sample, depending on which domain annotation databases were used in the pipeline execution.
 
 [hmmer](https://github.com/EddyRivasLab/hmmer) is a fast and flexible alignment trimming tool that keeps phylogenetically informative sites and removes others.
 

docs/usage.md

@@ -7,7 +7,7 @@
 ## Introduction
 
 **nf-core/proteinannotator** is a bioinformatics pipeline that computes statistics and generates sequence-level annotations for amino acid sequences.
-It takes a protein FASTA file as input and performs conserved domain annotation (using Pfam, FunFam and NMPFams HMM databases), functional annotation (using InterProScan), and secondary structure prediction (using s4pred).
+It takes a protein FASTA file as input and performs conserved domain annotation (using Pfam, FunFam, NMPFams and metagRoot HMM databases), functional annotation (using InterProScan), and secondary structure prediction (using s4pred).
 Optionally, paths to pre-downloaded databases can be provided to skip the automatic download steps and speed up repeated runs.
 
 ## Samplesheet input

main.nf

@@ -49,6 +49,9 @@ workflow NFCORE_PROTEINANNOTATOR {
         params.skip_nmpfams,
         params.nmpfams_db,
         params.nmpfams_latest_link,
+        params.skip_metagroot,
+        params.metagroot_db,
+        params.metagroot_latest_link,
         params.skip_interproscan,
         params.interproscan_db_url,
         params.interproscan_db,

nextflow.config

@@ -28,6 +28,9 @@ params {
     skip_nmpfams            = false
     nmpfams_db              = null
     nmpfams_latest_link     = "https://pavlopoulos-lab.org/envofams/databases/hmmer/nmpfamsdb.hmm.gz"
+    skip_metagroot          = false
+    metagroot_db            = null
+    metagroot_latest_link   = "https://pavlopoulos-lab.org/envofams/databases/hmmer/metagroot.hmm.gz"
     hmmsearch_evalue_cutoff = 0.001
 
     // Functional annotation

nextflow_schema.json

@@ -293,6 +293,23 @@
                     "default": "https://pavlopoulos-lab.org/envofams/databases/hmmer/nmpfamsdb.hmm.gz",
                     "description": ""
                 },
+                "skip_metagroot": {
+                    "type": "boolean",
+                    "fa_icon": "fas fa-ban",
+                    "description": "Skip the domain annotation with the metagRoot database.",
+                    "help": "Skips the domain annotation of input sequence against a metagRoot database."
+                },
+                "metagroot_db": {
+                    "type": "string",
+                    "format": "file-path",
+                    "description": "Path to an already installed metagRoot HMM database (.hmm.gz).",
+                    "help_text": "If left null and skip_metagroot is false, the pipeline will start downloading the latest metagRoot HMM library."
+                },
+                "metagroot_latest_link": {
+                    "type": "string",
+                    "default": "https://pavlopoulos-lab.org/envofams/databases/hmmer/metagroot.hmm.gz",
+                    "description": "metagRoot hosted link to the latest available metagRoot HMM database file."
+                },
                 "hmmsearch_evalue_cutoff": {
                     "type": "number",
                     "default": 0.001,
@@ -379,7 +396,6 @@
         {
             "$ref": "#/$defs/domain_annotation_params"
         },
-
         {
             "$ref": "#/$defs/functional_annotation_options"
         },