Add hostile as alternative decontamination tool

CITATIONS.md

@@ -69,6 +69,10 @@
 
   > Danecek, P., Bonfield, J. K., Liddle, J., Marshall, J., Ohan, V., Pollard, M. O., Whitwham, A., Keane, T., McCarthy, S. A., Davies, R. M., & Li, H. (2021). Twelve years of SAMtools and BCFtools. GigaScience, 10(2). https://doi.org/10.1093/gigascience/giab008
 
+- [Hostile](https://doi.org/10.1093/bioinformatics/btad728)
+
+  > Constantinides, B., Hunt, M., Crook, D.W., 2023. Hostile: accurate decontamination of microbial host sequences. Bioinformatics 39. https://doi.org/10.1093/bioinformatics/btad728
+
 - [Bracken](https://doi.org/10.7717/peerj-cs.104)
 
   > Lu, J., Breitwieser, F. P., Thielen, P., & Salzberg, S. L. (2017). Bracken: estimating species abundance in metagenomics data. PeerJ. Computer Science, 3(e104), e104. https://doi.org/10.7717/peerj-cs.104

README.md

@@ -33,7 +33,7 @@
 2. Performs optional read pre-processing
    - Adapter clipping and merging (short-read: [fastp](https://github.com/OpenGene/fastp), [AdapterRemoval2](https://github.com/MikkelSchubert/adapterremoval); long-read: [porechop](https://github.com/rrwick/Porechop), [Porechop_ABI](https://github.com/bonsai-team/Porechop_ABI))
    - Low complexity and quality filtering (short-read: [bbduk](https://jgi.doe.gov/data-and-tools/software-tools/bbtools/), [PRINSEQ++](https://github.com/Adrian-Cantu/PRINSEQ-plus-plus); long-read: [Filtlong](https://github.com/rrwick/Filtlong)), [Nanoq](https://github.com/esteinig/nanoq)
-   - Host-read removal (short-read: [BowTie2](http://bowtie-bio.sourceforge.net/bowtie2/); long-read: [Minimap2](https://github.com/lh3/minimap2))
+   - Host-read removal (short-read: [BowTie2](http://bowtie-bio.sourceforge.net/bowtie2/); long-read: [Minimap2](https://github.com/lh3/minimap2), both: [Hostile](https://github.com/bede/hostile))
    - Run merging
 3. Supports statistics metagenome coverage estimation ([Nonpareil](https://nonpareil.readthedocs.io/en/latest/)) and for host-read removal ([Samtools](http://www.htslib.org/))
 4. Performs taxonomic classification and/or profiling using one or more of:

assets/multiqc_config.yml

@@ -35,6 +35,8 @@ report_section_order:
     order: 200
   samtools:
     order: 100
+  hostile:
+    order: 95
   kraken:
     order: 90
   bracken:
@@ -71,6 +73,7 @@ run_modules:
   - nanoq
   - bowtie2
   - samtools
+  - hostile
   - kraken
   - kaiju
   - diamond
@@ -138,6 +141,8 @@ top_modules:
       name: "bowtie2"
   - "samtools":
       name: "Samtools Stats"
+  - "hostile":
+      name: "Hostile"
   - "kraken":
       name: "Kraken"
       path_filters:

conf/modules.config

@@ -518,6 +518,66 @@ process {
         ]
     }
 
+    withName: HOSTILE_FETCH_SHORTREADS {
+        ext.args   = '--bowtie2'
+        publishDir = [
+            [
+                path: { "${params.outdir}/hostile/fetch" },
+                mode: params.publish_dir_mode,
+                enabled: params.save_hostremoval_index,
+                saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+            ]
+        ]
+    }
+
+    withName: HOSTILE_CLEAN_SHORTREADS {
+        ext.args   = "--aligner bowtie2"
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            [
+                path: { "${params.outdir}/hostile/clean" },
+                mode: params.publish_dir_mode,
+                pattern: '*.json',
+            ],
+            [
+                path: { "${params.outdir}/hostile/clean" },
+                mode: params.publish_dir_mode,
+                pattern: '*.{fastq.gz,json}',
+                enabled: params.save_hostremoval_unmapped,
+            ],
+        ]
+    }
+
+    withName: HOSTILE_FETCH_LONGREADS {
+        ext.args   = '--minimap2'
+        publishDir = [
+            [
+                path: { "${params.outdir}/hostile/fetch" },
+                mode: params.publish_dir_mode,
+                enabled: params.save_hostremoval_index,
+                saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+            ]
+        ]
+    }
+
+    withName: HOSTILE_CLEAN_LONGREADS {
+        ext.args   = "--aligner minimap2"
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            [
+                path: { "${params.outdir}/hostile/clean" },
+                mode: params.publish_dir_mode,
+                pattern: '*.json',
+            ],
+            [
+                path: { "${params.outdir}/hostile/clean" },
+                mode: params.publish_dir_mode,
+                pattern: '*.{fastq.gz,json}',
+                enabled: params.save_hostremoval_unmapped,
+            ],
+        ]
+    }
+
     withName: MERGE_RUNS {
         ext.prefix = { "${meta.id}" }
         publishDir = [

conf/test_alternativepreprocessing.config

@@ -33,10 +33,12 @@ params {
     longread_filter_tool               = 'filtlong'
     perform_shortread_complexityfilter = true
     shortread_complexityfilter_tool    = 'prinseqplusplus'
+    hostremoval_hostile_referencename  = 'test-human-mit'
     perform_shortread_hostremoval      = true
+    shortread_hostremoval_tool         = "hostile"
     perform_longread_hostremoval       = true
+    longread_hostremoval_tool          = "hostile"
     perform_runmerging                 = true
-    hostremoval_reference              = params.pipelines_testdata_base_path + 'modules/data/genomics/homo_sapiens/genome/genome.fasta'
     run_kaiju                          = true
     run_kraken2                        = true
     run_bracken                        = false

docs/output.md

@@ -345,6 +345,30 @@ This directory will be present and contain the unmapped reads from the `.fastq`
 For short-read unmapped reads, see [bowtie2](#bowtie2).
 :::
 
+### Hostile
+
+[Hostile](https://github.com/bede/hostile) removes host sequences from short and long read (meta)genomes, consuming single or paired FASTQ using specialised reference genomes.
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `hostile/`
+  - `fetch/`
+    - `*.{bt2,fa.gz,*mmi}`: bowtie2 indices (short read) or minimap2 index (long reads) of downloaded reference genome, only if `--save_hostremoval_index` supplied.
+  - `clean/`  
+    -`<sample_id>_<accession_id>.clean_{1,2}.fastq.gz`: FASTQ file(s) with host reads removed, only if `-- save_hostremoval_unmapped` supplied.  
+    -`<sample_id>_<accession_id>.json`: host removal statistics in JSON format.
+
+</details>
+
+By default nf-core/taxprofiler will only provide the `.json` file if host removal is turned on.
+You will only get FASTQ files if you specify to save `--save_hostremoval_unmapped` - these contain only unmapped reads.
+Alternatively, if you wish only to have the 'final' reads that go into classification/profiling (i.e., that may have additional processing), do not specify this flag but rather specify `--save_analysis_ready_fastqs`, in which case the reads will be in the folder `analysis_ready_reads`.
+
+:::info
+The resulting `.fastq` files may _not_ always be the 'final' reads that go into taxprofiling, if you also run other steps such as run merging etc..
+:::
+
 ### Analysis Ready Reads
 
 :::info

modules.json

@@ -95,6 +95,16 @@
                         "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
                         "installed_by": ["modules"]
                     },
+                    "hostile/clean": {
+                        "branch": "master",
+                        "git_sha": "dbc43f924a7410a2b828f2a022305f1d6e71ed84",
+                        "installed_by": ["modules"]
+                    },
+                    "hostile/fetch": {
+                        "branch": "master",
+                        "git_sha": "f9e0c7508d84c6bbb6aef566bb1f23cf44c2b5bf",
+                        "installed_by": ["modules"]
+                    },
                     "kaiju/kaiju": {
                         "branch": "master",
                         "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
@@ -252,22 +262,22 @@
                     },
                     "samtools/fastq": {
                         "branch": "master",
-                        "git_sha": "c8be52dba1166c678e74cda9c3a3c221635c8bb1",
+                        "git_sha": "156feda0cb6589cd29c04902004fa3b53bc00205",
                         "installed_by": ["modules"]
                     },
                     "samtools/index": {
                         "branch": "master",
-                        "git_sha": "c8be52dba1166c678e74cda9c3a3c221635c8bb1",
+                        "git_sha": "156feda0cb6589cd29c04902004fa3b53bc00205",
                         "installed_by": ["modules"]
                     },
                     "samtools/stats": {
                         "branch": "master",
-                        "git_sha": "5cb9a8694da0a0e550921636bb60bc8c56445fd7",
+                        "git_sha": "156feda0cb6589cd29c04902004fa3b53bc00205",
                         "installed_by": ["modules"]
                     },
                     "samtools/view": {
                         "branch": "master",
-                        "git_sha": "5cb9a8694da0a0e550921636bb60bc8c56445fd7",
+                        "git_sha": "2057a0a8dbd67000d08613a556570aa7184a7c89",
                         "installed_by": ["modules"]
                     },
                     "sylph/profile": {