Merge remote-tracking branch 'upstream/dev' into fixes

.nf-core.yml

@@ -1,2 +1,4 @@
 repository_type: pipeline
 nf_core_version: "2.14.1"
+lint:
+  files_exist: conf/igenomes.config

README.md

@@ -19,13 +19,13 @@
 
 ## Introduction
 
-**nf-core/reportho** is a bioinformatics pipeline that compares and assembles orthology predictions for a query protein. It fetches ortholog lists for a query (or its closest annotated homolog) from public sources, calculates pairwise and global agreement, and generates a consensus list with the desired level of confidence. Optionally, it offers common analysis on the consensus orthologs, such as MSA and phylogeny reconstruction. Additionally, it generates a clean, human-readable report of the results.
+**nf-core/reportho** is a bioinformatics pipeline that compares and summarizes orthology predictions for one or a set of query proteins. For each query (or its closest annotated homolog), it fetches ortholog lists from public databases, calculates the agreement of the obtained predictions(pairwise and global) and finally generates a consensus list of orthologs with the desired level of confidence. Optionally, it offers common analysis on the consensus orthologs, such as MSA and phylogeny reconstruction. Additionally, it generates a clean, human-readable report of the results.
 
 <!-- Tube map -->
 
 ![nf-core-reportho tube map](docs/images/reportho_tube_map.svg?raw=true "nf-core-reportho tube map")
 
-1. **Obtain Query Information**: (depends on provided input) identification of Uniprot ID and taxon ID for the query or its closest homolog.
+1. **Obtain Query Information**: identification of Uniprot ID and taxon ID for the query (or its closest homolog if the fasta file is used as input instead of the Uniprot ID).
 2. **Fetch Orthologs**: fetching of ortholog predictions from public databases, either through API or from local snapshot.
 3. **Compare and Assemble**: calculation of agreement statistics, creation of ortholog lists, selection of the consensus list.
 
@@ -47,13 +47,15 @@ First, prepare a samplesheet with your input data that looks as follows:
 ```csv title="samplesheet_fasta.csv"
 id,fasta
 BicD2,data/bicd2.fasta
+HBB,data/hbb.fasta
 ```
 
 or if you know the UniProt ID of the protein you can provide it directly:
 
 ```csv title="samplesheet.csv"
 id,query
 BicD2,Q8TD16
+HBB,P68871
 ```
 
 > [!NOTE]
@@ -82,13 +84,13 @@ For more details about the output files and reports, please refer to the
 
 ## Credits
 
-nf-core/reportho was originally written by Igor Trujnara (@itrujnara).
+nf-core/reportho was originally written by Igor Trujnara ([@itrujnara](https://github.com/itrujnara)).
 
 We thank the following people for their extensive assistance in the development of this pipeline:
 
-- Luisa Santus (@lsantus)
-- Alessio Vignoli (@avignoli)
-- Jose Espinosa-Carrasco (@JoseEspinosa)
+- Luisa Santus ([@luisas](https://github.com/luisas))
+- Alessio Vignoli ([@alessiovignoli](https://github.com/alessiovignoli))
+- Jose Espinosa-Carrasco ([@JoseEspinosa](https://github.com/JoseEspinosa))
 
 ## Contributions and Support
 

bin/fetch_oma_by_sequence.py

@@ -9,6 +9,14 @@
 from Bio import SeqIO
 from utils import fetch_seq
 
+# Script overview:
+# Fetches the OMA entry for a given protein sequence
+# The sequence is passed as a FASTA file
+# If the sequence is not found, the script exits with an error
+# It outputs 3 files:
+# 1. The canonical ID of the sequence
+# 2. The taxonomy ID of the species
+# 3. A boolean indicating if the sequence was an exact match
 
 def main() -> None:
     if len(sys.argv) < 5:

docs/usage.md

@@ -25,13 +25,15 @@ A final samplesheet file may look something like the one below:
 ```csv title="samplesheet.csv"
 id,query
 BicD2,Q8TD16
+HBB,P68871
 ```
 
 or the one below, if you provide the sequence of the protein in FASTA format:
 
 ```csv title="samplesheet.csv"
 id,fasta
 BicD2,/home/myuser/data/bicd2.fa
+HBB,/home/myuser/data/hbb.fa
 ```
 
 | Column  | Description                                                                                                                                       |

main.nf

@@ -46,8 +46,8 @@ workflow NFCORE_REPORTHO {
         samplesheet_fasta,
     )
 
-    // emit:
-    // multiqc_report = REPORTHO.out.multiqc_report // channel: /path/to/multiqc_report.html
+    emit:
+    multiqc_report = REPORTHO.out.multiqc_report // channel: /path/to/multiqc_report.html
 
 }
 /*

modules.json

@@ -12,7 +12,7 @@
                     },
                     "csvtk/join": {
                         "branch": "master",
-                        "git_sha": "5e0c5677ea33b3d4c3793244035a191bd03e6736",
+                        "git_sha": "614abbf126f287a3068dc86997b2e1b6a93abe20",
                         "installed_by": ["modules"]
                     },
                     "fastme": {

modules/local/create_tcoffeetemplate.nf

@@ -11,6 +11,7 @@ process CREATE_TCOFFEETEMPLATE {
 
     output:
     tuple val (meta), path("*_template.txt"), emit: template
+    path("versions.yml"), emit: versions
 
     when:
     task.ext.when == null || task.ext.when

modules/local/dump_params.nf

@@ -17,6 +17,7 @@ process DUMP_PARAMS {
 
     output:
     tuple val(meta), path("params.yml"), emit: params
+    path("versions.yml"), emit: versions
 
     when:
     task.ext.when == null || task.ext.when

modules/local/fetch_eggnog_group_local.nf

@@ -2,10 +2,8 @@ process FETCH_EGGNOG_GROUP_LOCAL {
     tag "$meta.id"
     label 'process_single'
 
-    conda "conda-forge::python=3.11.0 conda-forge::biopython=1.83.0 conda-forge::requests=2.31.0"
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/mulled-v2-bc54124b36864a4af42a9db48b90a404b5869e7e:5258b8e5ba20587b7cbf3e942e973af5045a1e59-0' :
-        'biocontainers/mulled-v2-bc54124b36864a4af42a9db48b90a404b5869e7e:5258b8e5ba20587b7cbf3e942e973af5045a1e59-0' }"
+    conda "conda-forge::python=3.12.3 conda-forge::ripgrep=14.1.0"
+    container "community.wave.seqera.io/library/python_ripgrep:324b372792aae9ce"
 
     input:
     tuple val(meta), path(uniprot_id), path(taxid), path(exact)
@@ -34,6 +32,7 @@ process FETCH_EGGNOG_GROUP_LOCAL {
     cat <<- END_VERSIONS > versions.yml
     "${task.process}":
         Python: \$(python --version | cut -f2)
+        ripgrep: \$(rg --version | head -n1 | cut -d' ' -f2)
     END_VERSIONS
     """
 
@@ -46,6 +45,7 @@ process FETCH_EGGNOG_GROUP_LOCAL {
     cat <<- END_VERSIONS > versions.yml
     "${task.process}":
         Python: \$(python --version | cut -f2)
+        ripgrep: \$(rg --version | head -n1 | cut -d' ' -f2)
     END_VERSIONS
     """
 }

modules/local/fetch_oma_group_local.nf

@@ -2,10 +2,8 @@ process FETCH_OMA_GROUP_LOCAL {
     tag "$meta.id"
     label 'process_single'
 
-    conda "conda-forge::python=3.11.0 conda-forge::biopython=1.83.0 conda-forge::requests=2.31.0"
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/mulled-v2-bc54124b36864a4af42a9db48b90a404b5869e7e:5258b8e5ba20587b7cbf3e942e973af5045a1e59-0' :
-        'biocontainers/mulled-v2-bc54124b36864a4af42a9db48b90a404b5869e7e:5258b8e5ba20587b7cbf3e942e973af5045a1e59-0' }"
+    conda "conda-forge::python=3.12.3 conda-forge::ripgrep=14.1.0"
+    container "community.wave.seqera.io/library/python_ripgrep:324b372792aae9ce"
 
     input:
     tuple val(meta), path(uniprot_id), path(taxid), path(exact)
@@ -24,15 +22,23 @@ process FETCH_OMA_GROUP_LOCAL {
     script:
     prefix = task.ext.prefix ?: meta.id
     """
+    # Obtain the OMA ID for the given Uniprot ID of the query protein
     omaid=\$(uniprot2oma_local.py $uniprot_idmap $uniprot_id)
-    zcat $db | grep \$omaid | head -1 | cut -f3- | awk '{gsub(/\\t/,"\\n"); print}' > ${prefix}_oma_group_oma.txt || test -f ${prefix}_oma_group_oma.txt
+
+    # Perform the database search for the given query in OMA
+    zcat $db | rg \$omaid | head -1 | cut -f3- | awk '{gsub(/\\t/,"\\n"); print}' > ${prefix}_oma_group_oma.txt || test -f ${prefix}_oma_group_oma.txt
+
+    # Convert the OMA ids to Uniprot, Ensembl and RefSeq ids
     oma2uniprot_local.py $uniprot_idmap ${prefix}_oma_group_oma.txt > ${prefix}_oma_group_raw.txt
     uniprotize_oma_local.py ${prefix}_oma_group_raw.txt $ensembl_idmap $refseq_idmap > ${prefix}_oma_group.txt
+
+    # Add the OMA column to the csv file
     csv_adorn.py ${prefix}_oma_group.txt OMA > ${prefix}_oma_group.csv
 
     cat <<- END_VERSIONS > versions.yml
     "${task.process}":
         Python: \$(python --version | cut -f2)
+        ripgrep: \$(rg --version | head -n1 | cut -d' ' -f2)
     END_VERSIONS
     """
 
@@ -44,6 +50,7 @@ process FETCH_OMA_GROUP_LOCAL {
     cat <<- END_VERSIONS > versions.yml
     "${task.process}":
         Python: \$(python --version | cut -f2)
+        ripgrep: \$(rg --version | head -n1 | cut -d' ' -f2)
     END_VERSIONS
     """
 }

modules/local/fetch_panther_group_local.nf

@@ -2,10 +2,8 @@ process FETCH_PANTHER_GROUP_LOCAL {
     tag "$meta.id"
     label 'process_single'
 
-    conda "conda-forge::python=3.11.0 conda-forge::biopython=1.83.0 conda-forge::requests=2.31.0"
-    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/mulled-v2-bc54124b36864a4af42a9db48b90a404b5869e7e:5258b8e5ba20587b7cbf3e942e973af5045a1e59-0' :
-        'biocontainers/mulled-v2-bc54124b36864a4af42a9db48b90a404b5869e7e:5258b8e5ba20587b7cbf3e942e973af5045a1e59-0' }"
+    conda "conda-forge::python=3.12.3 conda-forge::ripgrep=14.1.0"
+    container "community.wave.seqera.io/library/python_ripgrep:324b372792aae9ce"
 
     input:
     tuple val(meta), path(uniprot_id), path(taxid), path(exact)
@@ -22,12 +20,13 @@ process FETCH_PANTHER_GROUP_LOCAL {
     prefix = task.ext.prefix ?: meta.id
     """
     id=\$(cat ${uniprot_id})
-    grep \$id $panther_db | tr '|' ' ' | tr '\\t' ' ' | cut -d' ' -f3,6 | awk -v id="\$id" -F'UniProtKB=' '{ for(i=0;i<=NF;i++) { if(\$i !~ id) s=s ? s OFS \$i : \$i } print s; s="" }' > ${prefix}_panther_group_raw.txt || test -f ${prefix}_panther_group_raw.txt
+    rg \$id $panther_db | tr '|' ' ' | tr '\\t' ' ' | cut -d' ' -f3,6 | awk -v id="\$id" -F'UniProtKB=' '{ for(i=0;i<=NF;i++) { if(\$i !~ id) s=s ? s OFS \$i : \$i } print s; s="" }' > ${prefix}_panther_group_raw.txt || test -f ${prefix}_panther_group_raw.txt
     csv_adorn.py ${prefix}_panther_group_raw.txt PANTHER > ${prefix}_panther_group.csv
 
     cat <<- END_VERSIONS > versions.yml
     "${task.process}":
         Python: \$(python --version | cut -f2)
+        ripgrep: \$(rg --version | head -n1 | cut -d' ' -f2)
     END_VERSIONS
     """
 
@@ -39,6 +38,7 @@ process FETCH_PANTHER_GROUP_LOCAL {
     cat <<- END_VERSIONS > versions.yml
     "${task.process}":
         Python: \$(python --version | cut -f2)
+        ripgrep: \$(rg --version | head -n1 | cut -d' ' -f2)
     END_VERSIONS
     """
 }

subworkflows/local/get_orthologs.nf

@@ -50,8 +50,6 @@ workflow GET_ORTHOLOGS {
         .map { it -> [it[0], file(it[1])] }
         .set { ch_fasta }
 
-    ch_fasta.view()
-
     IDENTIFY_SEQ_ONLINE (
         ch_fasta
     )
@@ -135,6 +133,7 @@ workflow GET_ORTHOLOGS {
 
         ch_versions = ch_versions.mix(FETCH_INSPECTOR_GROUP_ONLINE.out.versions)
 
+        // EggNOG
         FETCH_EGGNOG_GROUP_LOCAL (
             ch_query,
             ch_eggnog,