Merge pull request #494 from jfy133/save-mapped-reads

Add ability to save assembly-mapped reads

CHANGELOG.md

@@ -7,13 +7,14 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### `Added`
 
-- [#395](https://github.com/nf-core/mag/pull/395) - Add support for fast domain-level classification of bins using Tiara, to allow bins to be separated into eukaryotic and prokaryotic-specific processes.
+- [#395](https://github.com/nf-core/mag/pull/395) - Adds support for fast domain-level classification of bins using Tiara, to allow bins to be separated into eukaryotic and prokaryotic-specific processes.
 - [#422](https://github.com/nf-core/mag/pull/422) - Adds support for normalization of read depth with BBNorm (added by @erikrikarddaniel and @fabianegli)
 - [#439](https://github.com/nf-core/mag/pull/439) - Adds ability to enter the pipeline at the binning stage by providing a CSV of pre-computed assemblies (by @prototaxites)
 - [#459](https://github.com/nf-core/mag/pull/459) - Adds ability to skip damage correction step in the ancient DNA workflow and just run pyDamage (by @jfy133)
 - [#364](https://github.com/nf-core/mag/pull/364) - Adds geNomad nf-core modules for identifying viruses in assemblies (by @PhilPalmer and @CarsonJM)
 - [#481](https://github.com/nf-core/mag/pull/481) - Adds MetaEuk for annotation of eukaryotic MAGs, and MMSeqs2 to enable downloading databases for MetaEuk (by @prototaxites)
 - [#437](https://github.com/nf-core/mag/pull/429) - `--gtdb_db` also now supports directory input of an pre-uncompressed GTDB archive directory (reported by @alneberg, fix by @jfy133)
+- [#494](https://github.com/nf-core/mag/pull/494) - Adds support for saving the BAM files from Bowtie2 mapping of input reads back to assembly (fix by @jfy133)
 
 ### `Changed`
 
@@ -38,7 +39,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#449](https://github.com/nf-core/mag/pull/447) - Fix results file overwriting in Ancient DNA workflow (reported by @alexhbnr, fix by @jfy133)
 - [#470](https://github.com/nf-core/mag/pull/470) - Fix binning preparation from running even when binning was requested to be skipped (reported by @prototaxites, fix by @jfy133)
 - [#480](https://github.com/nf-core/mag/pull/480) - Improved `-resume` reliability through better meta map preservation (reported by @prototaxites, fix by @jfy133)
-- [#493](https://github.com/nf-core/mag/pull/493) - Update `METABAT2` nf-core module so that it reduced the number of unnecessary file moves, enabling virtual filesystems, fix by @adamrtalbot)
+- [#493](https://github.com/nf-core/mag/pull/493) - Update `METABAT2` nf-core module so that it reduced the number of unnecessary file moves, enabling virtual filesystems (fix by @adamrtalbot)
 
 ### `Dependencies`
 

conf/modules.config

@@ -305,9 +305,17 @@ process {
         ext.args = params.bowtie2_mode ? params.bowtie2_mode : params.ancient_dna ? '--very-sensitive -N 1' : ''
         ext.prefix = { "${meta.id}.assembly" }
         publishDir = [
-            path: { "${params.outdir}/Assembly/${assembly_meta.assembler}/QC/${assembly_meta.id}" },
-            mode: params.publish_dir_mode,
-            pattern: "*.log"
+            [
+                path: { "${params.outdir}/Assembly/${assembly_meta.assembler}/QC/${assembly_meta.id}" },
+                mode: params.publish_dir_mode,
+                pattern: "*.log"
+            ],
+            [
+                path: { "${params.outdir}/Assembly/${assembly_meta.assembler}/QC/${assembly_meta.id}" },
+                mode: params.publish_dir_mode,
+                pattern: "*.{bam,bai}",
+                enabled: params.save_assembly_mapped_reads
+            ],
         ]
     }
 

docs/output.md

@@ -193,6 +193,7 @@ Trimmed (short) reads are assembled with both megahit and SPAdes. Hybrid assembl
   - `QC/[sample/group]/`: Directory containing QUAST files and Bowtie2 mapping logs
     - `MEGAHIT-[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.
     - `MEGAHIT-[sample/group]-[sampleToMap].bowtie2.log`: Bowtie2 log file indicating how many reads have been mapped from the respective sample ("sampleToMap").
+    - `MEGAHIT-[sample].[bam/bai]`: Optionally saved BAM file of the Bowtie2 mapping of reads against the assembly.
 
 </details>
 
@@ -211,6 +212,7 @@ Trimmed (short) reads are assembled with both megahit and SPAdes. Hybrid assembl
   - `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").
+    - `SPAdes-[sample].[bam/bai]`: Optionally saved BAM file of the Bowtie2 mapping of reads against the assembly.
 
 </details>
 
@@ -229,6 +231,7 @@ SPAdesHybrid is a part of the [SPAdes](http://cab.spbu.ru/software/spades/) soft
   - `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").
+    - `SPAdesHybrid-[sample].[bam/bai]`: Optionally saved BAM file of the Bowtie2 mapping of reads against the assembly.
 
 </details>
 

nextflow.config

@@ -43,6 +43,7 @@ params {
     // binning options
     bowtie2_mode                         = null
     binning_map_mode                     = 'group'
+    save_assembly_mapped_reads           = false
     skip_binning                         = false
     min_contig_size                      = 1500
     min_length_unbinned_contigs          = 1000000

nextflow_schema.json

@@ -513,8 +513,7 @@
                 },
                 "skip_gtdbtk": {
                     "type": "boolean",
-                    "description": "Skip the running of GTDB, as well as the automatic download of the database",
-                    "default": "false"
+                    "description": "Skip the running of GTDB, as well as the automatic download of the database"
                 },
                 "gtdb_db": {
                     "type": "string",
@@ -523,23 +522,23 @@
                 },
                 "gtdbtk_min_completeness": {
                     "type": "number",
-                    "default": 50.0,
+                    "default": 50,
                     "description": "Min. bin completeness (in %) required to apply GTDB-tk classification.",
                     "help_text": "Completeness assessed with BUSCO analysis (100% - %Missing). Must be greater than 0 (min. 0.01) to avoid GTDB-tk errors. If too low, GTDB-tk classification results can be impaired due to not enough marker genes!",
                     "minimum": 0.01,
                     "maximum": 100
                 },
                 "gtdbtk_max_contamination": {
                     "type": "number",
-                    "default": 10.0,
+                    "default": 10,
                     "description": "Max. bin contamination (in %) allowed to apply GTDB-tk classification.",
                     "help_text": "Contamination approximated based on BUSCO analysis (%Complete and duplicated). If too high, GTDB-tk classification results can be impaired due to contamination!",
                     "minimum": 0,
                     "maximum": 100
                 },
                 "gtdbtk_min_perc_aa": {
                     "type": "number",
-                    "default": 10.0,
+                    "default": 10,
                     "description": "Min. fraction of AA (in %) in the MSA for bins to be kept.",
                     "minimum": 0,
                     "maximum": 100
@@ -553,7 +552,7 @@
                 },
                 "gtdbtk_pplacer_cpus": {
                     "type": "number",
-                    "default": 1.0,
+                    "default": 1,
                     "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)."
                 },
@@ -649,7 +648,6 @@
             "properties": {
                 "run_virus_identification": {
                     "type": "boolean",
-                    "default": false,
                     "description": "Run virus identification."
                 },
                 "genomad_min_score": {
@@ -715,6 +713,11 @@
                     "description": "Bowtie2 alignment mode",
                     "help_text": "Bowtie2 alignment mode options, for example: `--very-fast` , `--very-sensitive-local -N 1` , ..."
                 },
+                "save_assembly_mapped_reads": {
+                    "type": "boolean",
+                    "description": "Save the output of mapping raw reads back to assembled contigs",
+                    "help_text": "Specify to save the BAM and BAI files generated when mapping input reads back to the assembled contigs (performed in preparation for binning and contig depth estimations)."
+                },
                 "bin_domain_classification": {
                     "type": "boolean",
                     "description": "Enable domain-level (prokaryote or eukaryote) classification of bins using Tiara. Processes which are domain-specific will then only receive bins matching the domain requirement.",