Merge pull request #635 from nf-core/dev

Patch release 3.0.2 for fixing BUSCO, CONCOCT and Docker container errors
nf-core · Jul 4, 2024 · bb74c46 · bb74c46
2 parents aac4962 + 4e12465
commit bb74c46
Show file tree

Hide file tree

Showing 64 changed files with 2,181 additions and 177 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,6 +3,29 @@
 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).
 
+## 3.0.2 [2024-07-04]
+
+### `Added`
+
+### `Changed`
+
+- [#633](https://github.com/nf-core/mag/pull/633/) - Changed BUSCO to use offline mode when the database is specified by the user (reported by @ChristophKnapp and many others, fix by @jfy133)
+- [#632](https://github.com/nf-core/mag/pull/632) - Use default NanoLyse log of just removed reads rather than custom (by @jfy133)
+
+### `Fixed`
+
+- [#630](https://github.com/nf-core/mag/pull/630) - Fix CONCOCT empty bins killing the pipeline, and allow for true multithreading again (removing OPENBLAS loop) (reported by @maxibor, fix by @maxibor and @jfy133)
+
+### `Dependencies`
+
+| Tool     | Previous version | New version |
+| -------- | ---------------- | ----------- |
+| Porechop | 0.2.3_seqan2.1.1 | 0.2.4       |
+| NanoPlot | 1.26.3           | 1.41.6      |
+| NanoLyse | 1.1.0            | 1.2.0       |
+
+### `Deprecated`
+
 ## 3.0.1 [2024-06-10]
 
 ### `Added`

diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml
@@ -1,7 +1,7 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/mag/releases/tag/3.0.1" target="_blank">nf-core/mag</a>
+  This report has been generated by the <a href="https://github.com/nf-core/mag/releases/tag/3.0.2" target="_blank">nf-core/mag</a>
   analysis pipeline. For information about how to interpret these results, please see the
-  <a href="https://nf-co.re/mag/3.0.1/docs/output" target="_blank">documentation</a>.
+  <a href="https://nf-co.re/mag/3.0.2/docs/output" target="_blank">documentation</a>.
 report_section_order:
   "nf-core-mag-methods-description":
     order: -1000

diff --git a/bin/run_busco.sh b/bin/run_busco.sh
@@ -11,6 +11,7 @@ bin=$4
 task_cpus=$5
 lineage_dataset_provided=$6
 busco_clean=$7
+extra_args=$8
 
 # ensure augustus has write access to config directory
 if [ ${cp_augustus_config} = "Y" ]; then
@@ -30,11 +31,14 @@ shopt -s nullglob
 # only used for saving busco downloads
 most_spec_db="NA"
 
-if busco ${p} \
-    --mode genome \
-    --in ${bin} \
-    --cpu ${task_cpus} \
-    --out "BUSCO" >${bin}_busco.log 2>${bin}_busco.err; then
+if
+    busco ${p} \
+        --mode genome \
+        --in ${bin} \
+        --cpu ${task_cpus} \
+        ${extra_args} \
+    --out "BUSCO" >${bin}_busco.log 2>${bin}_busco.err
+then
 
     # get name of used specific lineage dataset
     summaries=(BUSCO/short_summary.specific.*.BUSCO.txt)

diff --git a/conf/base.config b/conf/base.config
@@ -77,7 +77,7 @@ process {
         memory = { check_max (8.GB * task.attempt, 'memory' ) }
         time   = { check_max (6.h  * task.attempt, 'time'   ) }
     }
-    withName: PORECHOP {
+    withName: PORECHOP_PORECHOP {
         cpus   = { check_max (4     * task.attempt, 'cpus'   ) }
         memory = { check_max (30.GB * task.attempt, 'memory' ) }
         time   = { check_max (4.h   * task.attempt, 'time'   ) }
@@ -93,7 +93,7 @@ process {
         memory = { check_max (64.GB * (2**(task.attempt-1)), 'memory' ) }
         time   = { check_max (24.h  * (2**(task.attempt-1)), 'time'   ) }
     }
-    withName: CENTRIFUGE {
+    withName: CENTRIFUGE_CENTRIFUGE {
         cpus   = { check_max (8     * task.attempt, 'cpus'   ) }
         memory = { check_max (40.GB * task.attempt, 'memory' ) }
         time   = { check_max (12.h  * task.attempt, 'time'   ) }
@@ -103,7 +103,7 @@ process {
         memory = { check_max (40.GB * task.attempt, 'memory' ) }
         time   = { check_max (12.h  * task.attempt, 'time'   ) }
     }
-    withName: KRONA {
+    withName: KRONA_KTIMPORTTAXONOMY {
         cpus   = { check_max (8     * task.attempt, 'cpus'   ) }
         memory = { check_max (20.GB * task.attempt, 'memory' ) }
         time   = { check_max (12.h  * task.attempt, 'time'   ) }

diff --git a/conf/modules.config b/conf/modules.config
@@ -167,11 +167,11 @@ process {
         ]
     }
 
-    withName: PORECHOP {
+    withName: PORECHOP_PORECHOP {
         publishDir = [
                 path: { "${params.outdir}/QC_longreads/porechop" },
                 mode: params.publish_dir_mode,
-                pattern: "*_porechop.fastq",
+                pattern: "*_trimmed.fastq",
                 enabled: params.save_porechop_reads
             ]
         ext.prefix = { "${meta.id}_run${meta.run}_trimmed" }
@@ -206,6 +206,11 @@ process {
 
     withName: NANOPLOT_RAW {
         ext.prefix = 'raw'
+        ext.args = { [
+            "-p raw_",
+            "--title ${meta.id}_raw",
+            "-c darkblue",
+        ].join(' ').trim() }
         publishDir = [
             path: { "${params.outdir}/QC_longreads/NanoPlot/${meta.id}" },
             mode: params.publish_dir_mode,
@@ -214,7 +219,11 @@ process {
     }
 
     withName: NANOPLOT_FILTERED {
-        ext.prefix = 'filtered'
+        ext.args = { [
+            "-p filtered_",
+            "--title ${meta.id}_filtered",
+            "-c darkblue",
+        ].join(' ').trim() }
         publishDir = [
             path: { "${params.outdir}/QC_longreads/NanoPlot/${meta.id}" },
             mode: params.publish_dir_mode,
@@ -360,6 +369,9 @@ process {
     }
 
     withName: 'BUSCO' {
+        ext.args = [
+                params.busco_db ? '--offline' : ''
+            ].join(' ').trim()
         publishDir = [
             path: { "${params.outdir}/GenomeBinning/QC/BUSCO" },
             mode: params.publish_dir_mode,

diff --git a/docs/output.md b/docs/output.md
@@ -105,7 +105,7 @@ The pipeline uses Nanolyse to map the reads against the Lambda phage and removes
 <summary>Output files</summary>
 
 - `QC_longreads/NanoLyse/`
-  - `[sample]_nanolyse.log`: Contains a brief log file indicating how many reads have been retained.
+  - `[sample]_[run]_lambdafiltered.nanolyse.log`: Contains a brief log file indicating how many reads have been removed.
 
 </details>
 

diff --git a/modules.json b/modules.json
@@ -64,27 +64,27 @@
                     },
                     "concoct/concoct": {
                         "branch": "master",
-                        "git_sha": "c684a6edba2c8516a0d2cfeafb12489b99d2fffb",
+                        "git_sha": "baa30accc6c50ea8a98662417d4f42ed18966353",
                         "installed_by": ["fasta_binning_concoct"]
                     },
                     "concoct/concoctcoveragetable": {
                         "branch": "master",
-                        "git_sha": "36aa9d3ce6561d9bd5c240bcf82fe109af543c0d",
+                        "git_sha": "baa30accc6c50ea8a98662417d4f42ed18966353",
                         "installed_by": ["fasta_binning_concoct"]
                     },
                     "concoct/cutupfasta": {
                         "branch": "master",
-                        "git_sha": "36aa9d3ce6561d9bd5c240bcf82fe109af543c0d",
+                        "git_sha": "73a6d7e6077b88aba1c5d6805635d79d6718270c",
                         "installed_by": ["fasta_binning_concoct"]
                     },
                     "concoct/extractfastabins": {
                         "branch": "master",
-                        "git_sha": "36aa9d3ce6561d9bd5c240bcf82fe109af543c0d",
+                        "git_sha": "baa30accc6c50ea8a98662417d4f42ed18966353",
                         "installed_by": ["fasta_binning_concoct"]
                     },
                     "concoct/mergecutupclustering": {
                         "branch": "master",
-                        "git_sha": "36aa9d3ce6561d9bd5c240bcf82fe109af543c0d",
+                        "git_sha": "baa30accc6c50ea8a98662417d4f42ed18966353",
                         "installed_by": ["fasta_binning_concoct"]
                     },
                     "custom/dumpsoftwareversions": {
@@ -197,6 +197,21 @@
                         "git_sha": "b7ebe95761cd389603f9cc0e0dc384c0f663815a",
                         "installed_by": ["modules"]
                     },
+                    "nanolyse": {
+                        "branch": "master",
+                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "installed_by": ["modules"]
+                    },
+                    "nanoplot": {
+                        "branch": "master",
+                        "git_sha": "3135090b46f308a260fc9d5991d7d2f9c0785309",
+                        "installed_by": ["modules"]
+                    },
+                    "porechop/porechop": {
+                        "branch": "master",
+                        "git_sha": "1d68c7f248d1a480c5959548a9234602b771199e",
+                        "installed_by": ["modules"]
+                    },
                     "prodigal": {
                         "branch": "master",
                         "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220",
@@ -243,7 +258,7 @@
                 "nf-core": {
                     "fasta_binning_concoct": {
                         "branch": "master",
-                        "git_sha": "cfd937a668919d948f6fcbf4218e79de50c2f36f",
+                        "git_sha": "c60c14b285b89bdd0607e371417dadb80385ad6e",
                         "installed_by": ["subworkflows"]
                     },
                     "utils_nextflow_pipeline": {

diff --git a/modules/local/busco.nf b/modules/local/busco.nf
@@ -23,6 +23,7 @@ process BUSCO {
     path "versions.yml"                                                                 , emit: versions
 
     script:
+    def args = task.ext.args ?: ''
     def cp_augustus_config = workflow.profile.toString().indexOf("conda") != -1 ? "N" : "Y"
     def lineage_dataset_provided = "${db_meta.lineage}"
     def busco_clean = params.busco_clean ? "Y" : "N"
@@ -36,7 +37,16 @@ process BUSCO {
         lineage_dataset_provided = ""
     }
     """
-    run_busco.sh "${p}" "${cp_augustus_config}" "${db}" "${bin}" ${task.cpus} "${lineage_dataset_provided}" "${busco_clean}"
+    run_busco.sh \\
+        "${p}" \\
+        "${cp_augustus_config}" \\
+        "${db}" \\
+        "${bin}" \\
+        ${task.cpus} \\
+        "${lineage_dataset_provided}" \\
+        "${busco_clean}" \\
+        "${args}"
+
     most_spec_db=\$(<info_most_spec_db.txt)
 
     cat <<-END_VERSIONS > versions.yml

diff --git a/modules/local/centrifuge_db_preparation.nf b/modules/local/centrifuge_db_preparation.nf
diff --git a/modules/local/krona_db.nf b/modules/local/krona_db.nf
diff --git a/modules/local/nanolyse.nf b/modules/local/nanolyse.nf
@@ -17,9 +17,9 @@ process NANOLYSE {
 
     script:
     """
-    cat ${reads} | NanoLyse --reference $nanolyse_db | gzip > ${meta.id}_nanolyse.fastq.gz
+    zcat ${reads} | NanoLyse --reference $nanolyse_db | gzip > ${meta.id}_nanolyse.fastq.gz
     echo "NanoLyse reference: $params.lambda_reference" >${meta.id}_nanolyse.log
-    cat ${reads} | echo "total reads before NanoLyse: \$((`wc -l`/4))" >>${meta.id}_nanolyse.log
+    zcat ${reads} | echo "total reads before NanoLyse: \$((`wc -l`/4))" >>${meta.id}_nanolyse.log
     gunzip -c ${meta.id}_nanolyse.fastq.gz | echo "total reads after NanoLyse: \$((`wc -l`/4))" >> ${meta.id}_nanolyse.log
 
     cat <<-END_VERSIONS > versions.yml

diff --git a/modules/local/nanoplot.nf b/modules/local/nanoplot.nf
diff --git a/modules/local/porechop.nf b/modules/local/porechop.nf
diff --git a/modules/nf-core/concoct/concoct/environment.yml b/modules/nf-core/concoct/concoct/environment.yml