Merge branch 'dev' into bump-metaspades

CHANGELOG.md

@@ -8,15 +8,18 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### `Added`
 
 - [#665](https://github.com/nf-core/mag/pull/648) - Add support for supplying pre-made bowtie host reference index (requested by @simone-pignotti, added by @jfy133)
+- [#670](https://github.com/nf-core/mag/pull/670) - Added --gtdbtk_pplacer_useram to run GTDBTk in memory mode rather than write to disk (reported by @harper357, fixed by @jfy133)
 
 ### `Changed`
 
 - [#664](https://github.com/nf-core/mag/pull/664) - Update GTDBTk to latest version, with updated column names, update GTDB to release 220 (by @dialvarezs)
+- [#676](https://github.com/nf-core/mag/pull/676) - Added exit code 12 to valid SPAdes retry codes, due to OOM errors from spades-hammer (reported by @bawee, fix by @jfy133)
 - [#666](https://github.com/nf-core/mag/pull/666) - Update SPAdes to version 4.0.0 (requested by @elsherbini, fix by @jfy133)
 
 ### `Fixed`
 
 - [#667](https://github.com/nf-core/mag/pull/667) - Fix pipeline crashing if only CONCOCT selected during binning (reported and fixed by @jfy133)
+- [#670](https://github.com/nf-core/mag/pull/670) - Re-add missing GTDBTk parameters into GTDBTk module (reported by harper357, fixed by @jfy133)
 - [#672](https://github.com/nf-core/mag/pull/673) - Fix GTDB-Tk per-sample TSV files not being published in output directory (reported by @jhayer, fix by @jfy133)
 
 ### `Dependencies`
@@ -28,6 +31,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Deprecated`
 
+- [#670](https://github.com/nf-core/mag/pull/670) - Deprecated --gtdbtk_pplacer_scratch due to unintuitive usage (reported by harper357, fixed by @jfy133)
+
 ## 3.0.3 [2024-08-27]
 
 ### `Added`

conf/base.config

@@ -123,15 +123,15 @@ process {
         cpus          = { check_megahit_cpus(8, task.attempt) }
         memory        = { check_max(40.GB * task.attempt, 'memory') }
         time          = { check_max(16.h * task.attempt, 'time') }
-        errorStrategy = { task.exitStatus in [143, 137, 104, 134, 139, 250] ? 'retry' : 'finish' }
+        errorStrategy = { task.exitStatus in ((130..145) + 104 + 250) ? 'retry' : 'finish' }
     }
     //SPAdes returns error(1) if it runs out of memory (and for other reasons as well...)!
     //exponential increase of memory and time with attempts, keep number of threads to enable reproducibility
     withName: METASPADES {
         cpus          = { check_spades_cpus(10, task.attempt) }
         memory        = { check_max(64.GB * (2 ** (task.attempt - 1)), 'memory') }
         time          = { check_max(24.h * (2 ** (task.attempt - 1)), 'time') }
-        errorStrategy = { task.exitStatus in [143, 137, 21, 1] ? 'retry' : 'finish' }
+        errorStrategy = { task.exitStatus in ((130..145) + 104 + 21 + 12 + 1) ? 'retry' : 'finish' }
         maxRetries    = 5
     }
     withName: METASPADESHYBRID {
@@ -146,7 +146,7 @@ process {
         cpus          = { check_max(2 * task.attempt, 'cpus') }
         memory        = { check_max(8.GB * task.attempt, 'memory') }
         time          = { check_max(8.h * task.attempt, 'time') }
-        errorStrategy = { task.exitStatus in [143, 137, 104, 134, 139, 247] ? 'retry' : 'finish' }
+        errorStrategy = { task.exitStatus in ((130..145) + 104 + 247) ? 'retry' : 'finish' }
     }
     withName: METABAT2_METABAT2 {
         cpus   = { check_max(8 * task.attempt, 'cpus') }
@@ -166,6 +166,6 @@ process {
     }
 
     withName: DASTOOL_DASTOOL {
-        errorStrategy = { task.exitStatus in [143, 137, 104, 134, 139] ? 'retry' : task.exitStatus == 1 ? 'ignore' : 'finish' }
+        errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : task.exitStatus == 1 ? 'ignore' : 'finish' }
     }
 }

conf/modules.config

@@ -392,7 +392,12 @@ process {
     }
 
     withName: GTDBTK_CLASSIFYWF {
-        ext.args   = "--extension fa"
+        ext.args   = [
+            "--extension fa",
+            "--min_perc_aa ${params.gtdbtk_min_perc_aa}",
+            "--min_af ${params.gtdbtk_min_af}",
+            "--pplacer_cpus ${params.gtdbtk_pplacer_cpus}"
+        ].join(' ')
         ext.prefix = { "${meta.assembler}-${meta.binner}-${meta.domain}-${meta.refinement}-${meta.id}" }
         publishDir = [
             path: { "${params.outdir}/Taxonomy/GTDB-Tk/${meta.assembler}/${meta.binner}/${meta.id}" },

modules.json

@@ -124,7 +124,7 @@
                     },
                     "gtdbtk/classifywf": {
                         "branch": "master",
-                        "git_sha": "3fb6803fd1cf5a63998216f4254d6d4e487fab21",
+                        "git_sha": "7b9ce4b817926f17ec82cc0099d2d0ff095a2fac",
                         "installed_by": ["modules"]
                     },
                     "gunc/downloaddb": {

nextflow.config

@@ -95,7 +95,7 @@ params {
     gtdbtk_min_perc_aa                   = 10
     gtdbtk_min_af                        = 0.65
     gtdbtk_pplacer_cpus                  = 1
-    gtdbtk_pplacer_scratch               = true
+    gtdbtk_pplacer_useram            = false
 
     // long read preprocessing options
     skip_adapter_trimming                = false

nextflow_schema.json

@@ -584,11 +584,11 @@
                     "description": "Number of CPUs used for the by GTDB-Tk run tool pplacer.",
                     "help_text": "A low number of CPUs helps to reduce the memory required/reported by GTDB-Tk. See also the [GTDB-Tk documentation](https://ecogenomics.github.io/GTDBTk/faq.html#gtdb-tk-reaches-the-memory-limit-pplacer-crashes)."
                 },
-                "gtdbtk_pplacer_scratch": {
+                "gtdbtk_pplacer_useram": {
                     "type": "boolean",
-                    "default": true,
-                    "description": "Reduce GTDB-Tk memory consumption by running pplacer in a setting writing to disk.",
-                    "help_text": "Will be slower. Set to `false` to turn this off."
+                    "default": false,
+                    "description": "Speed up pplacer step of GTDB-Tk by loading to memory.",
+                    "help_text": "Will be faster than writing to disk (default setting), however at the expense of much larger memory (RAM) requirements for GDTBTK/CLASSIFY."
                 },
                 "genomad_db": {
                     "type": "string",

subworkflows/local/gtdbtk.nf

@@ -90,6 +90,7 @@ workflow GTDBTK {
     GTDBTK_CLASSIFYWF (
         ch_filtered_bins.passed.groupTuple(),
         ch_db_for_gtdbtk,
+        params.gtdbtk_pplacer_useram ? false : true,
         gtdb_mash
     )