Longread only functionality

.github/workflows/ci.yml

@@ -109,6 +109,7 @@ jobs:
             test_virus_identification,
             test_single_end,
             test_concoct,
+            test_longread,
           ]
     steps:
       - name: Free some space

CHANGELOG.md

@@ -24,10 +24,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#707](https://github.com/nf-core/mag/pull/707) - Make Bin QC a subworkflow (added by @dialvarezs)
 - [#707](https://github.com/nf-core/mag/pull/707) - Added CheckM2 as an alternative bin completeness and QC tool (added by @dialvarezs)
 - [#708](https://github.com/nf-core/mag/pull/708) - Added `--exclude_unbins_from_postbinning` parameter to exclude unbinned contigs from post-binning processes, speeding up Prokka in some cases (added by @dialvarezs)
+- [#718](https://github.com/nf-core/mag/pull/718) - Added metaMDBG and Flye as longread assemblers (added by @muabnezor)
+- [#718](https://github.com/nf-core/mag/pull/718) - Added host removal for long reads using minimap2 as aligner (added by @muabnezor)
 - [#732](https://github.com/nf-core/mag/pull/732) - Added support for Prokka's compliance mode with `--prokka_with_compliance --prokka_compliance_centre <xyz>` (reported by @audy and @Thomieh73, added by @jfy133)
 
 ### `Changed`
 
+- [#718](https://github.com/nf-core/mag/pull/718) - Longread only input (added by @muabnezor)
 - [#731](https://github.com/nf-core/mag/pull/731) - Updated to nf-core 3.1.0 `TEMPLATE` (by @jfy133)
 
 ### `Fixed`
@@ -37,16 +40,22 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#716](https://github.com/nf-core/mag/pull/692) - Make short read processing a subworkflow (added by @muabnezor)
 - [#708](https://github.com/nf-core/mag/pull/708) - Fixed channel passed as GUNC input (added by @dialvarezs)
 - [#729](https://github.com/nf-core/mag/pull/729) - Fixed misspecified multi-FASTQ input for single-end data in MEGAHIT (reported by John Richards, fix by @jfy133)
+- [#718](https://github.com/nf-core/mag/pull/718) - refactoring assembly into subworkflow (added by @muabnezor)
 
 ### `Dependencies`
 
-| Tool    | Previous version | New version |
-| ------- | ---------------- | ----------- |
-| CheckM  | 1.2.1            | 1.2.3       |
-| CheckM2 |                  | 1.0.2       |
-| chopper |                  | 0.9.0       |
-| GUNC    | 1.0.5            | 1.0.6       |
-| nanoq   |                  | 0.10.0      |
+| Tool     | Previous version | New version |
+| -------- | ---------------- | ----------- |
+| chopper  |                  | 0.9.0       |
+| nanoq    |                  | 0.10.0      |
+| flye     |                  | 2.9.5       |
+| metamdbg |                  | 1.0         |
+| minimap2 |                  | 2.28        |
+| CheckM   | 1.2.1            | 1.2.3       |
+| CheckM2  |                  | 1.0.2       |
+| chopper  |                  | 0.9.0       |
+| GUNC     | 1.0.5            | 1.0.6       |
+| nanoq    |                  | 0.10.0      |
 
 ### `Deprecated`
 

CITATIONS.md

@@ -66,6 +66,10 @@
 
 - [Filtlong](https://github.com/rrwick/Filtlong)
 
+- [Flye](https://www.nature.com/articles/s41592-020-00971-x)
+
+  > Kolmogorov, M., Bickhart, D.M., Behsaz, B. et al. metaFlye: scalable long-read metagenome assembly using repeat graphs. Nat Methods 17, 1103–1110 (2020). https://doi.org/10.1038/s41592-020-00971-x
+
 - [Freebayes](https://arxiv.org/abs/1207.3907)
 
   > Garrison E, Marth G. Haplotype-based variant detection from short-read sequencing. arXiv preprint arXiv:1207.3907 [q-bio.GN] 2012
@@ -106,6 +110,14 @@
 
   > Levy Karin, E., Mirdita, M. & Söding, J. MetaEuk—sensitive, high-throughput gene discovery, and annotation for large-scale eukaryotic metagenomics. Microbiome 8, 48 (2020). 10.1186/s40168-020-00808-x
 
+- [metaMDBG](https://www.nature.com/articles/s41587-023-01983-6)
+
+  > Benoit, G., Raguideau, S., James, R. et al. High-quality metagenome assembly from long accurate reads with metaMDBG. Nat Biotechnol 42, 1378–1383 (2024). https://doi.org/10.1038/s41587-023-01983-6
+
+- [minimap2](https://academic.oup.com/bioinformatics/article/34/18/3094/4994778?login=true)
+
+  > Li, H. (2018). Minimap2: pairwise alignment for nucleotide sequences. Bioinformatics , 34(18), 3094–3100. https://doi.org/10.1093/bioinformatics/bty191
+
 - [MMseqs2](https://www.nature.com/articles/nbt.3988)
 
   > Steinegger, M., Söding, J. MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat Biotechnol 35, 1026–1028 (2017).10.1038/nbt.3988

assets/schema_input.json

@@ -42,11 +42,11 @@
                 "pattern": "^\\S+\\.f(ast)?q\\.gz$"
             }
         },
-        "required": ["sample", "group", "short_reads_1"]
+        "required": ["sample", "group"],
+        "anyOf": [{ "required": ["short_reads_1"] }, { "required": ["long_reads"] }]
     },
     "uniqueEntries": ["sample", "run"],
     "dependentRequired": {
-        "short_reads_2": ["short_reads_1"],
-        "long_reads": ["short_reads_1", "short_reads_2"]
+        "short_reads_2": ["short_reads_1"]
     }
 }

conf/modules.config

@@ -179,13 +179,13 @@ process {
     }
 
     withName: FILTLONG {
-        ext.args   = [
+        ext.args  = { [
             "--min_length ${params.longreads_min_length}",
             "--keep_percent ${params.longreads_keep_percent}",
-            "--trim",
+            shortreads ? "--trim" : "",
             "--length_weight ${params.longreads_length_weight}",
             params.longreads_min_quality ? "--min_mean_q ${params.longreads_min_quality}" : ''
-        ].join(' ').trim()
+        ].join(' ').trim() }
         publishDir = [
             path: { "${params.outdir}/QC_longreads/Filtlong" },
             mode: params.publish_dir_mode,
@@ -286,6 +286,60 @@ process {
         ]
     }
 
+    withName: MINIMAP2_HOST_INDEX {
+        ext.args = '-x map-ont'
+    //    publishDir = [
+    //        path: { "${params.outdir}/QC_longreads/minimap2/index" },
+    //       mode: params.publish_dir_mode,
+    //        pattern: '*.mmi',
+    //        enabled: params.save_hostremoved_reads
+    //    ]
+    }
+
+    withName: MINIMAP2_HOST_ALIGN {
+        ext.prefix = { "${meta.id}_run${meta.run}.host.minimap" }
+        publishDir = [
+            path: { "${params.outdir}/QC_longreads/minimap2/align}" },
+            mode: params.publish_dir_mode,
+            pattern: "*.bam",
+            enabled: params.save_hostremoved_reads
+        ]
+    }
+
+    withName: MINIMAP2_ASSEMBLY_ALIGN {
+        ext.prefix = { "${meta2.assembler}-${meta2.id}-${meta.id}" }
+        publishDir = [
+            path: { "${params.outdir}/Assembly/${meta2.assembler}/QC/${meta2.id}" },
+            mode: params.publish_dir_mode,
+            pattern: "*.{bam,bai}",
+            enabled: params.save_assembly_mapped_reads
+        ]
+    }
+
+    withName: SAMTOOLS_HOSTREMOVED_VIEW {
+        ext.args = '-f 4'
+        ext.prefix = { "${meta.id}_${meta.run}.hostremoved" }
+    }
+
+    withName: SAMTOOLS_HOSTREMOVED_FASTQ {
+        ext.prefix = { "${meta.id}_${meta.run}.hostremoved" }
+        publishDir = [
+            path: { "${params.outdir}/QC_longreads/samtools/fastq" },
+            mode: params.publish_dir_mode,
+            pattern: '*_other.fastq.gz',
+            enabled: params.save_hostremoved_reads
+        ]
+    }
+
+    withName: SAMTOOLS_HOSTREMOVED_STATS {
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/QC_longreads/samtools/stats" },
+            mode: params.publish_dir_mode,
+            pattern: '*stats'
+        ]
+    }
+
     withName: CENTRIFUGE_CENTRIFUGE {
         publishDir = [path: { "${params.outdir}/Taxonomy/centrifuge/${meta.id}" }, mode: params.publish_dir_mode, pattern: "*.txt"]
     }
@@ -330,6 +384,17 @@ process {
         publishDir = [path: { "${params.outdir}/Assembly/SPAdesHybrid" }, mode: params.publish_dir_mode, pattern: "*.{fasta.gz,gfa.gz,fa.gz,log}"]
     }
 
+    withName: FLYE {
+        ext.args   = ' --meta'
+        ext.prefix = { "FLYE-${meta.id}" }
+        publishDir = [path: { "${params.outdir}/Assembly/FLYE" }, mode: params.publish_dir_mode, pattern: "*.{fasta.gz,gfa.gz,log}"]
+    }
+
+    withName: METAMDBG_ASM {
+        ext.prefix = { "METAMDBG-${meta.id}" }
+        publishDir = [path: { "${params.outdir}/Assembly/METAMDBG" }, mode: params.publish_dir_mode, pattern: "*.{fasta.gz,log}"]
+    }
+
     withName: QUAST {
         publishDir = [path: { "${params.outdir}/Assembly/${meta.assembler}/QC/${meta.id}" }, mode: params.publish_dir_mode, saveAs: { filename -> filename.equals('versions.yml') ? null : filename }]
     }
@@ -580,6 +645,7 @@ process {
     }
 
     withName: METABAT2_JGISUMMARIZEBAMCONTIGDEPTHS {
+        ext.args = { meta.assembler in ['FLYE', 'METAMDBG'] ? "--percentIdentity ${params.longread_percentidentity}" : '' }
         publishDir = [path: { "${params.outdir}/GenomeBinning/depths/contigs" }, mode: params.publish_dir_mode, pattern: '*-depth.txt.gz']
         ext.prefix = { "${meta.assembler}-${meta.id}-depth" }
     }

conf/test_longread.config

@@ -0,0 +1,34 @@
+/*
+========================================================================================
+    Nextflow config file for running minimal tests
+========================================================================================
+    Defines input files and everything required to run a fast and simple pipeline test.
+
+    Use as follows:
+        nextflow run nf-core/mag -profile test_longread,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+// Limit resources so that this can run on GitHub Actions
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
+
+params {
+    config_profile_name         = 'Test profile'
+    config_profile_description  = 'Minimal test dataset to check pipeline function'
+
+    // Input data
+    input                       = params.pipelines_testdata_base_path + 'mag/samplesheets/samplesheet.long_read.csv'
+    min_length_unbinned_contigs = 1
+    max_unbinned_contigs        = 2
+    busco_db                    = "https://busco-data.ezlab.org/v5/data/lineages/bacteria_odb10.2024-01-08.tar.gz"
+    skip_gtdbtk                 = true
+    gtdbtk_min_completeness     = 0.01
+    skip_concoct                = true
+}

docs/output.md

@@ -263,6 +263,37 @@ SPAdesHybrid is a part of the [SPAdes](http://cab.spbu.ru/software/spades/) soft
 
 </details>
 
+</details>
+
+### Flye
+
+[Flye](https://github.com/mikolmogorov/Flye) assembler is optionally run on long reads.
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `Assembly/FLYE/`
+  - `[sample/group].assembly_graph.gfa.gz`: Compressed assembly graph in gfa format
+  - `[sample/group].assembly.fa.gz`: Compressed assembled contigs in fasta format
+  - `[sample/group].flye.log`: Log file
+  - `QC/[sample/group]/`: Directory containing QUAST files
+
+</details>
+
+### metaMDBG
+
+[metaMDBG](https://github.com/GaetanBenoitDev/metaMDBG) assembler is optionally run on long reads.
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `Assembly/METAMDBG/`
+  - `[sample/group].contigs.fa.gz`: Compressed assembled contigs in fasta format
+  - `[sample/group].metaMDBG.log`: Log file
+  - `QC/[sample/group]/`: Directory containing QUAST files
+
+</details>
+
 ### Metagenome QC with QUAST
 
 [QUAST](http://cab.spbu.ru/software/quast/) is a tool that evaluates metagenome assemblies by computing various metrics. The QUAST output is also included in the MultiQC report, as well as in the assembly directories themselves.

docs/usage.md

@@ -43,14 +43,23 @@ sample2,0,0,data/sample2_R1.fastq.gz,data/sample2_R2.fastq.gz,data/sample2.fastq
 sample3,1,0,data/sample3_R1.fastq.gz,data/sample3_R2.fastq.gz,
 ```
 
+If only long read data is available, the columns `short_reads_1` and `short_reads_2` is simply left empty:
+
+```csv title="samplesheet.csv"
+sample,run,group,short_reads_1,short_reads_2,long_reads
+sample1,1,0,,,data/sample1.fastq.gz
+sample1,2,0,,,data/sample1.fastq.gz
+sample2,0,0,,,data/sample2.fastq.gz
+sample3,1,0,,,data/sample3.fastq.gz
+```
+
 Please note the following requirements:
 
 - a minimum 5 of comma-separated columns
 - Valid file extension: `.csv`
 - Must contain the header `sample,group,short_reads_1,short_reads_2,long_reads` (where `run` can be optionally added)
 - Run IDs must be unique within a multi-run sample. A sample with multiple runs will be automatically concatenated.
 - FastQ files must be compressed (`.fastq.gz`, `.fq.gz`)
-- `long_reads` can only be provided in combination with paired-end short read data
 - Within one samplesheet either only single-end or only paired-end reads can be specified
 - If single-end reads are specified, the command line parameter `--single_end` must be specified as well
 

modules.json

@@ -127,6 +127,11 @@
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
                         "installed_by": ["modules"]
                     },
+                    "flye": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "freebayes": {
                         "branch": "master",
                         "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",
@@ -207,6 +212,21 @@
                         "git_sha": "30d06da5bd7ae67be32758bf512cd75a4325d386",
                         "installed_by": ["modules"]
                     },
+                    "metamdbg/asm": {
+                        "branch": "master",
+                        "git_sha": "7c08494acb5aba0763c5c6db87f82b249de87ea8",
+                        "installed_by": ["modules"]
+                    },
+                    "minimap2/align": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
+                    "minimap2/index": {
+                        "branch": "master",
+                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "installed_by": ["modules"]
+                    },
                     "mmseqs/databases": {
                         "branch": "master",
                         "git_sha": "699e078133f580548aeb43114f93ac29928c6143",
@@ -267,6 +287,26 @@
                         "git_sha": "fd742419940e01ba1c5ecb172c3e32ec840662fe",
                         "installed_by": ["modules"]
                     },
+                    "samtools/fastq": {
+                        "branch": "master",
+                        "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
+                        "installed_by": ["modules"]
+                    },
+                    "samtools/index": {
+                        "branch": "master",
+                        "git_sha": "b13f07be4c508d6ff6312d354d09f2493243e208",
+                        "installed_by": ["modules"]
+                    },
+                    "samtools/stats": {
+                        "branch": "master",
+                        "git_sha": "2d20463181b1c38981a02e90d3084b5f9fa8d540",
+                        "installed_by": ["modules"]
+                    },
+                    "samtools/view": {
+                        "branch": "master",
+                        "git_sha": "2d20463181b1c38981a02e90d3084b5f9fa8d540",
+                        "installed_by": ["modules"]
+                    },
                     "seqtk/mergepe": {
                         "branch": "master",
                         "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",