Release review comments

CHANGELOG.md

@@ -3,7 +3,7 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [v1.0.0](https://github.com/nf-core/reportho/releases/tag/1.0.0) - Magnificent Mainsail - [2024-06-06]
+## [v1.0.0](https://github.com/nf-core/reportho/releases/tag/1.0.0) - Magnificent Mainsail - [2024-06-07]
 
 Although its location and design may vary greatly, the mainsail is always a key source of propulsion for a ship.
 
@@ -30,10 +30,6 @@ The pipeline was created. In particular, it has the following features:
 - basic downstream analysis of the obtained ortholog list
 - generation of a human-readable report
 
-### `Fixed`
-
-Nothing yet.
-
 ### `Dependencies`
 
 The pipeline has the following notable dependencies:
@@ -60,7 +56,3 @@ At release date, the following database versions were current and used for testi
 | PANTHER        | 18            |
 | OrthoInspector | Eukaryota2023 |
 | EggNOG         | 5.0           |
-
-### `Deprecated`
-
-Nothing.

conf/test_fasta.config

@@ -11,8 +11,8 @@
 */
 
 params {
-    config_profile_name        = 'Test profile'
-    config_profile_description = 'Minimal test dataset to check pipeline function'
+    config_profile_name        = 'Test profile with FASTA input'
+    config_profile_description = 'Minimal test dataset to check pipeline function with FASTA input'
 
     // Limit resources so that this can run on GitHub Actions
     max_cpus   = 2

conf/test_offline.config

@@ -11,8 +11,8 @@
 */
 
 params {
-    config_profile_name        = 'Test profile'
-    config_profile_description = 'Minimal test dataset to check pipeline function'
+    config_profile_name        = 'Test profile with offline databases'
+    config_profile_description = 'Minimal test dataset to check pipeline function with offline databases'
 
     // Limit resources so that this can run on GitHub Actions
     max_cpus   = 2

modules/local/dump_params.nf

@@ -2,6 +2,7 @@ process DUMP_PARAMS {
     tag "$meta.id"
     label 'process_single'
 
+    conda "conda-forge::coreutils=9.5"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
     'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
     'nf-core/ubuntu:20.04' }"

modules/local/fetch_panther_group_online.nf

@@ -11,7 +11,7 @@ process FETCH_PANTHER_GROUP_ONLINE {
     tuple val(meta), path(uniprot_id), path(taxid), path(exact)
 
     output:
-    tuple val(meta), path("*_panther_group.csv"), emit:panther_group
+    tuple val(meta), path("*_panther_group.csv"), emit: panther_group
     path "versions.yml"                         , emit: versions
 
     when:

modules/local/plot_orthologs.nf

@@ -14,7 +14,7 @@ process PLOT_ORTHOLOGS {
     tuple val(meta), path("*_supports_light.png"), path("*_supports_dark.png"), emit: supports
     tuple val(meta), path("*_venn_light.png"), path("*_venn_dark.png")        , emit: venn
     tuple val(meta), path("*_jaccard_light.png"), path("*_jaccard_dark.png")  , emit: jaccard
-    path "versions.yml"                          , emit: versions
+    path "versions.yml"                                                       , emit: versions
 
     when:
     task.ext.when == null || task.ext.when

modules/local/plot_tree.nf

@@ -13,7 +13,7 @@ process PLOT_TREE {
 
     output:
     tuple val(meta), path("*_light.png"), path("*_dark.png") , emit: plot
-    path "versions.yml"                 , emit: versions
+    path "versions.yml"                                      , emit: versions
 
     when:
     task.ext.when == null || task.ext.when

nextflow_schema.json

@@ -65,7 +65,7 @@
                 "local_databases": {
                     "type": "boolean",
                     "default": "false",
-                    "description": "Use local databases for the analysis. If use_all is set to `true`, online databases might still be used.",
+                    "description": "Use local databases for the analysis.",
                     "help_text": "If set to `true`, the pipeline will use local databases for the analysis.",
                     "fa_icon": "fas fa-database"
                 },

subworkflows/local/get_orthologs.nf

@@ -23,19 +23,18 @@ workflow GET_ORTHOLOGS {
     take:
     ch_samplesheet_query
     ch_samplesheet_fasta
+    ch_oma_groups
+    ch_oma_uniprot
+    ch_oma_ensembl
+    ch_oma_refseq
+    ch_panther
+    ch_eggnog
+    ch_eggnog_idmap
 
     main:
     ch_versions     = Channel.empty()
     ch_orthogroups  = Channel.empty()
 
-    ch_oma_groups   = params.oma_path ? Channel.value(file(params.oma_path)) : Channel.empty()
-    ch_oma_uniprot  = params.oma_uniprot_path ? Channel.value(file(params.oma_uniprot_path)) : Channel.empty()
-    ch_oma_ensembl  = params.oma_ensembl_path ? Channel.value(file(params.oma_ensembl_path)) : Channel.empty()
-    ch_oma_refseq   = params.oma_refseq_path ? Channel.value(file(params.oma_refseq_path)) : Channel.empty()
-    ch_panther      = params.panther_path ? Channel.value(file(params.panther_path)) : Channel.empty()
-    ch_eggnog       = params.eggnog_path ? Channel.value(file(params.eggnog_path)) : Channel.empty()
-    ch_eggnog_idmap = params.eggnog_idmap_path ? Channel.value(file(params.eggnog_idmap_path)) : Channel.empty()
-
     ch_samplesheet_fasta.map {
         if (params.offline_run) {
             error "Tried to use FASTA input in an offline run. Aborting pipeline for user safety."
@@ -53,7 +52,6 @@ workflow GET_ORTHOLOGS {
         ch_fasta
     )
 
-    ch_query = IDENTIFY_SEQ_ONLINE.out.seqinfo
     ch_versions = ch_versions.mix(IDENTIFY_SEQ_ONLINE.out.versions)
 
     WRITE_SEQINFO (

workflows/reportho.nf

@@ -11,12 +11,13 @@ include { softwareVersionsToYAML } from '../subworkflows/nf-core/utils_nfcore_pi
 include { methodsDescriptionText } from '../subworkflows/local/utils_nfcore_reportho_pipeline'
 
 include { GET_ORTHOLOGS          } from '../subworkflows/local/get_orthologs'
-include { FETCH_SEQUENCES        } from '../subworkflows/local/fetch_sequences'
-include { FETCH_STRUCTURES       } from '../subworkflows/local/fetch_structures'
 include { ALIGN                  } from '../subworkflows/local/align'
 include { MAKE_TREES             } from '../subworkflows/local/make_trees'
 include { REPORT                 } from '../subworkflows/local/report'
 
+include { FETCH_SEQUENCES_ONLINE } from '../subworkflows/local/fetch_sequences_online'
+include { FETCH_AFDB_STRUCTURES  } from '../subworkflows/local/fetch_afdb_structures'
+
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     RUN MAIN WORKFLOW
@@ -35,9 +36,24 @@ workflow REPORTHO {
     ch_multiqc_files = Channel.empty()
     ch_fasta_query   = ch_samplesheet_query.map { [it[0], []] }.mix(ch_samplesheet_fasta.map { [it[0], file(it[1])] })
 
+    ch_oma_groups   = params.oma_path ? Channel.value(file(params.oma_path)) : Channel.empty()
+    ch_oma_uniprot  = params.oma_uniprot_path ? Channel.value(file(params.oma_uniprot_path)) : Channel.empty()
+    ch_oma_ensembl  = params.oma_ensembl_path ? Channel.value(file(params.oma_ensembl_path)) : Channel.empty()
+    ch_oma_refseq   = params.oma_refseq_path ? Channel.value(file(params.oma_refseq_path)) : Channel.empty()
+    ch_panther      = params.panther_path ? Channel.value(file(params.panther_path)) : Channel.empty()
+    ch_eggnog       = params.eggnog_path ? Channel.value(file(params.eggnog_path)) : Channel.empty()
+    ch_eggnog_idmap = params.eggnog_idmap_path ? Channel.value(file(params.eggnog_idmap_path)) : Channel.empty()
+
     GET_ORTHOLOGS (
         ch_samplesheet_query,
-        ch_samplesheet_fasta
+        ch_samplesheet_fasta,
+        ch_oma_groups,
+        ch_oma_uniprot,
+        ch_oma_ensembl,
+        ch_oma_refseq,
+        ch_panther,
+        ch_eggnog,
+        ch_eggnog_idmap
     )
 
     ch_versions    = ch_versions.mix(GET_ORTHOLOGS.out.versions)
@@ -55,30 +71,31 @@ workflow REPORTHO {
     ch_fastme    = ch_samplesheet.map { [it[0], []] }
 
     if (!params.skip_downstream) {
-        FETCH_SEQUENCES (
-            GET_ORTHOLOGS.out.orthologs,
-            ch_fasta_query
+        ch_sequences_input = GET_ORTHOLOGS.out.orthologs.join(ch_fasta_query)
+
+        FETCH_SEQUENCES_ONLINE (
+            ch_sequences_input
         )
 
-        ch_seqhits = FETCH_SEQUENCES.out.hits
+        ch_seqhits = FETCH_SEQUENCES_ONLINE.out.hits
 
-        ch_seqmisses = FETCH_SEQUENCES.out.misses
+        ch_seqmisses = FETCH_SEQUENCES_ONLINE.out.misses
 
-        ch_versions = ch_versions.mix(FETCH_SEQUENCES.out.versions)
+        ch_versions = ch_versions.mix(FETCH_SEQUENCES_ONLINE.out.versions)
 
         if (params.use_structures) {
-            FETCH_STRUCTURES (
+            FETCH_AFDB_STRUCTURES (
                 GET_ORTHOLOGS.out.orthologs
             )
 
-            ch_strhits = FETCH_STRUCTURES.out.hits
+            ch_strhits = FETCH_AFDB_STRUCTURES.out.hits
 
-            ch_strmisses = FETCH_STRUCTURES.out.misses
+            ch_strmisses = FETCH_AFDB_STRUCTURES.out.misses
 
-            ch_versions = ch_versions.mix(FETCH_STRUCTURES.out.versions)
+            ch_versions = ch_versions.mix(FETCH_AFDB_STRUCTURES.out.versions)
         }
 
-        ch_structures = params.use_structures ? FETCH_STRUCTURES.out.structures : Channel.empty()
+        ch_structures = params.use_structures ? FETCH_AFDB_STRUCTURES.out.structures : Channel.empty()
 
         ALIGN (
             FETCH_SEQUENCES.out.sequences,