Merge pull request #666 from nf-core/bump-metaspades

Update SPAdes module to official nf-core and version bump

CHANGELOG.md

@@ -12,6 +12,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### `Changed`
 
 - [#674](https://github.com/nf-core/mag/pull/674) - Changed to porechop-abi as default adapter trimming tool for long reads. User can still use porechop if preferred (added by @muabnezor)
+- [#666](https://github.com/nf-core/mag/pull/666) - Update SPAdes to version 4.0.0, replace both METASPADES and MEGAHIT with official nf-core modules (requested by @elsherbini, fix by @jfy133)
+- [#666](https://github.com/nf-core/mag/pull/666) - Update URLs to GTDB database downloads due to server move (reported by @Jokendo-collab, fix by @jfy133)
 - [#695](https://github.com/nf-core/mag/pull/695) - Updated to nf-core 3.0.2 `TEMPLATE` (by @jfy133)
 - [#695](https://github.com/nf-core/mag/pull/695) - Switch more stable Zenodo link for CheckM data (by @jfy133)
 
@@ -29,6 +31,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 | ------------ | ---------------- | ----------- |
 | Porechop_ABI |                  | 0.5.0       |
 | Filtlong     | 0.2.0            | 0.2.1       |
+| SPAdes       | 3.15.3           | 4.0.0       |
 
 ### `Deprecated`
 

conf/base.config

@@ -10,9 +10,8 @@
 
 process {
 
-    // TODO nf-core: Check the defaults for all processes
     cpus          = { 1 * task.attempt }
-    memory        = { 6.GB * task.attempt }
+    memory        = { 7.GB * task.attempt }
     time          = { 4.h * task.attempt }
 
     errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' }

conf/test_full.config

@@ -16,30 +16,30 @@ params {
 
     // Input data for full size test
     // hg19 reference with highly conserved and low-complexity regions masked by Brian Bushnell
-    host_fasta    = "s3://ngi-igenomes/test-data/mag/hg19_main_mask_ribo_animal_allplant_allfungus.fa.gz"
-    input         = "s3://ngi-igenomes/test-data/mag/samplesheets/samplesheet.full.csv"
+    host_fasta                 = "s3://ngi-igenomes/test-data/mag/hg19_main_mask_ribo_animal_allplant_allfungus.fa.gz"
+    input                      = "s3://ngi-igenomes/test-data/mag/samplesheets/samplesheet.full.csv"
 
     //centrifuge_db = "s3://ngi-igenomes/test-data/mag/p_compressed+h+v.tar.gz"
-    kraken2_db    = "s3://ngi-igenomes/test-data/mag/minikraken_8GB_202003.tgz"
-    cat_db        = "s3://ngi-igenomes/test-data/mag/CAT_prepare_20210107.tar.gz"
+    kraken2_db                 = "s3://ngi-igenomes/test-data/mag/minikraken_8GB_202003.tgz"
+    cat_db                     = "s3://ngi-igenomes/test-data/mag/CAT_prepare_20210107.tar.gz"
     // gtdb_db       = "s3://ngi-igenomes/test-data/mag/gtdbtk_r214_data.tar.gz" ## This should be updated to release 220, once we get GTDB-Tk working again
-    skip_gtdbtk   = true
+    skip_gtdbtk                = true
 
     // TODO TEMPORARY: deactivate SPAdes due to incompatibility of container with fusion file system
-    skip_spades       = true
-    skip_spadeshybrid = true
+    skip_spades                = false
+    skip_spadeshybrid          = false
 
     // reproducibility options for assembly
-    spades_fix_cpus       = 10
-    spadeshybrid_fix_cpus = 10
-    megahit_fix_cpu_1     = true
+    spades_fix_cpus            = 10
+    spadeshybrid_fix_cpus      = 10
+    megahit_fix_cpu_1          = true
 
     // available options to enable reproducibility for BUSCO (--busco_db) not used here
     // to allow detection of possible problems in automated lineage selection mode using public databases
 
     // test CAT with official taxonomic ranks only
-    cat_official_taxonomy         = true
+    cat_official_taxonomy      = true
 
     // Skip CONCOCT due to timeout issues
-    skip_concoct                  = true
+    skip_concoct               = true
 }

docs/output.md

@@ -219,10 +219,10 @@ Trimmed (short) reads are assembled with both megahit and SPAdes. Hybrid assembl
 <summary>Output files</summary>
 
 - `Assembly/SPAdes/`
-  - `[sample/group]_scaffolds.fasta.gz`: Compressed assembled scaffolds in fasta format
-  - `[sample/group]_graph.gfa.gz`: Compressed assembly graph in gfa format
-  - `[sample/group]_contigs.fasta.gz`: Compressed assembled contigs in fasta format
-  - `[sample/group].log`: Log file
+  - `[sample/group].scaffolds.fa.gz`: Compressed assembled scaffolds in fasta format
+  - `[sample/group].assembly.gfa.gz`: Compressed assembly graph in gfa format
+  - `[sample/group].contigs.fa.gz`: Compressed assembled contigs in fasta format
+  - `[sample/group].spades.log`: Log file
   - `QC/[sample/group]/`: Directory containing QUAST files and Bowtie2 mapping logs
     - `SPAdes-[sample].bowtie2.log`: Bowtie2 log file indicating how many reads have been mapped from the sample that the metagenome was assembled from, only present if `--coassemble_group` is not set.
     - `SPAdes-[sample/group]-[sampleToMap].bowtie2.log`: Bowtie2 log file indicating how many reads have been mapped from the respective sample ("sampleToMap").
@@ -238,10 +238,10 @@ SPAdesHybrid is a part of the [SPAdes](http://cab.spbu.ru/software/spades/) soft
 <summary>Output files</summary>
 
 - `Assembly/SPAdesHybrid/`
-  - `[sample/group]_scaffolds.fasta.gz`: Compressed assembled scaffolds in fasta format
-  - `[sample/group]_graph.gfa.gz`: Compressed assembly graph in gfa format
-  - `[sample/group]_contigs.fasta.gz`: Compressed assembled contigs in fasta format
-  - `[sample/group].log`: Log file
+  - `[sample/group].scaffolds.fa.gz`: Compressed assembled scaffolds in fasta format
+  - `[sample/group].assembly.gfa.gz`: Compressed assembly graph in gfa format
+  - `[sample/group].contigs.fa.gz`: Compressed assembled contigs in fasta format
+  - `[sample/group].spades.log`: Log file
   - `QC/[sample/group]/`: Directory containing QUAST files and Bowtie2 mapping logs
     - `SPAdesHybrid-[sample].bowtie2.log`: Bowtie2 log file indicating how many reads have been mapped from the sample that the metagenome was assembled from, only present if `--coassemble_group` is not set.
     - `SPAdesHybrid-[sample/group]-[sampleToMap].bowtie2.log`: Bowtie2 log file indicating how many reads have been mapped from the respective sample ("sampleToMap").

modules.json

@@ -172,6 +172,11 @@
                         "git_sha": "283613159e079152f1336cef0db1c836086206e0",
                         "installed_by": ["modules"]
                     },
+                    "megahit": {
+                        "branch": "master",
+                        "git_sha": "7755db15e36b30da564cd67fffdfe18a255092aa",
+                        "installed_by": ["modules"]
+                    },
                     "metabat2/jgisummarizebamcontigdepths": {
                         "branch": "master",
                         "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
@@ -247,6 +252,11 @@
                         "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
                         "installed_by": ["modules"]
                     },
+                    "spades": {
+                        "branch": "master",
+                        "git_sha": "cfebb244d8c83ae533bf2db399f9af361927d504",
+                        "installed_by": ["modules"]
+                    },
                     "tiara/tiara": {
                         "branch": "master",
                         "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",