Merge pull request #511 from genomic-medicine-sweden/porechop_abi

Add porechop_abi to the pipeline

CHANGELOG.md

@@ -11,6 +11,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [#466](https://github.com/nf-core/taxprofiler/pull/466) - Input database sheets now require a `db_type` column to distinguish between short- and long-read databases (added by @LilyAnderssonLee)
 - [#505](https://github.com/nf-core/taxprofiler/pull/505) - Add small files to the file `tower.yml` (added by @LilyAnderssonLee)
 - [#508](https://github.com/nf-core/taxprofiler/pull/508) - Add `nanoq` as a filtering tool for nanopore reads (added by @LilyAnderssonLee)
+- [#511](https://github.com/nf-core/taxprofiler/pull/511) - Add `porechop_abi` as an alternative adapter removal tool for long reads nanopore data (added by @LilyAnderssonLee)
 
 ### `Fixed`
 

CITATIONS.md

@@ -38,6 +38,10 @@
 
   > Wick, R. R., Judd, L. M., Gorrie, C. L., & Holt, K. E. (2017). Completing bacterial genome assemblies with multiplex MinION sequencing. Microbial Genomics, 3(10), e000132. https://doi.org/10.1099/mgen.0.000132
 
+- [Porechop_ABI](https://github.com/bonsai-team/Porechop_ABI)
+
+  > Bonenfant, Q., Noé, L., & Touzet, H. (2023). Porechop_ABI: discovering unknown adapters in Oxford Nanopore Technology sequencing reads for downstream trimming. Bioinformatics Advances, 3(1):vbac085. https://10.1093/bioadv/vbac085
+
 - [Filtlong](https://github.com/rrwick/Filtlong)
 
   > Wick R (2021) Filtlong, URL: https://github.com/rrwick/Filtlong

README.md

@@ -29,7 +29,7 @@
 
 1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/) or [`falco`](https://github.com/smithlabcode/falco) as an alternative option)
 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))
+   - 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))
    - Run merging

assets/multiqc_config.yml

@@ -25,6 +25,8 @@ report_section_order:
     order: 500
   porechop:
     order: 400
+  porechop_abi:
+    order: 450
   bbduk:
     order: 300
   prinseqplusplus:
@@ -106,7 +108,21 @@ top_modules:
         - "*raw*"
       extra: "If used in this run, Falco is a drop-in replacement for FastQC producing the same output, written by Guilherme de Sena Brandine and Andrew D. Smith."
   - "porechop":
+      name: "Porechop"
+      anchor: "porechop"
+      target: "Porechop"
+      path_filters:
+        - "*porechop.log"
       extra: "ℹ️: if you get the error message 'Error - was not able to plot data.' this means that porechop did not detect any adapters and therefore no statistics generated."
+  - "porechop":
+      name: "Porechop_ABI"
+      anchor: "porechop_abi"
+      target: "Porechop_ABI"
+      doi: "10.1093/bioadv/vbac085"
+      info: "find and remove adapters from Oxford Nanopore reads."
+      path_filters:
+        - "*porechop_abi.log"
+      extra: "ℹ️: if you get the error message 'Error - was not able to plot data.' this means that porechop_abi did not detect any adapters and therefore no statistics generated."
   - "bowtie2":
       name: "bowtie2"
   - "samtools":
@@ -177,6 +193,14 @@ table_columns_placement:
     End Trimmed Percent: 440
     Middle Split: 450
     Middle Split Percent: 460
+  Porechop_ABI:
+    Input Reads: 400
+    Start Trimmed: 410
+    Start Trimmed Percent: 420
+    End Trimmed: 430
+    End Trimmed Percent: 440
+    Middle Split: 450
+    Middle Split Percent: 460
   Filtlong:
     Target bases: 500
   BBDuk:
@@ -250,6 +274,14 @@ table_columns_visible:
     End Trimmed Percent: True
     Middle Split: False
     Middle Split Percent: True
+  porechop_abi:
+    Input reads: False
+    Start Trimmed:
+    Start Trimmed Percent: True
+    End Trimmed: False
+    End Trimmed Percent: True
+    Middle Split: False
+    Middle Split Percent: True
   fastp:
     pct_adapter: True
     pct_surviving: True
@@ -315,6 +347,8 @@ extra_fn_clean_exts:
   - ".bbduk"
   - ".unmapped"
   - "_filtered"
+  - "porechop"
+  - "porechop_abi"
   - type: remove
     pattern: "_falco"
 

conf/modules.config

@@ -241,12 +241,12 @@ process {
     }
 
     withName: PORECHOP_PORECHOP {
-        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        ext.prefix = { "${meta.id}_${meta.run_accession}_porechop" }
         publishDir = [
             [
                 path: { "${params.outdir}/porechop" },
                 mode: params.publish_dir_mode,
-                pattern: '*_porechopped.fastq.gz',
+                pattern: '*.fastq.gz',
                 enabled: params.save_preprocessed_reads
             ],
             [
@@ -257,7 +257,31 @@ process {
             [
                 path: { "${params.outdir}/analysis_ready_fastqs" },
                 mode: params.publish_dir_mode,
-                pattern: '*_porechopped.fastq.gz',
+                pattern: '*.fastq.gz',
+                enabled: params.save_analysis_ready_fastqs,
+                saveAs: { ( params.perform_runmerging == false || ( params.perform_runmerging && !meta.is_multirun ) ) && !params.perform_longread_hostremoval && params.longread_qc_skipqualityfilter && !params.longread_qc_skipadaptertrim && params.perform_longread_qc && params.save_analysis_ready_fastqs ? it : null }
+            ]
+        ]
+    }
+
+    withName: PORECHOP_ABI {
+        ext.prefix = { "${meta.id}_${meta.run_accession}_porechop_abi" }
+        publishDir = [
+            [
+                path: { "${params.outdir}/porechop_abi" },
+                mode: params.publish_dir_mode,
+                pattern: '*.fastq.gz',
+                enabled: params.save_preprocessed_reads
+            ],
+            [
+                path: { "${params.outdir}/porechop_abi" },
+                mode: params.publish_dir_mode,
+                pattern: '*.log'
+            ],
+            [
+                path: { "${params.outdir}/analysis_ready_fastqs" },
+                mode: params.publish_dir_mode,
+                pattern: '*.fastq.gz',
                 enabled: params.save_analysis_ready_fastqs,
                 saveAs: { ( params.perform_runmerging == false || ( params.perform_runmerging && !meta.is_multirun ) ) && !params.perform_longread_hostremoval && params.longread_qc_skipqualityfilter && !params.longread_qc_skipadaptertrim && params.perform_longread_qc && params.save_analysis_ready_fastqs ? it : null }
             ]

docs/output.md

@@ -16,6 +16,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 - [fastp](#fastp) - Adapter trimming for Illumina data
 - [AdapterRemoval](#adapterremoval) - Adapter trimming for Illumina data
 - [Porechop](#porechop) - Adapter removal for Oxford Nanopore data
+- [Porechop_ABI](#porechop_abi) - Adapter removal for Oxford Nanopore data
 - [Nonpareil](#nonpareil) - Read redundancy and metagenome coverage estimation for short reads
 - [BBDuk](#bbduk) - Quality trimming and filtering for Illumina data
 - [PRINSEQ++](#prinseq) - Quality trimming and filtering for Illunina data
@@ -178,6 +179,23 @@ You will only find the `.fastq` files in the results directory if you provide `
 We do **not** recommend using Porechop if you are already trimming the adapters with ONT's basecaller Guppy.
 :::
 
+### Porechop_ABI
+
+[Porechop_ABI](https://github.com/bonsai-team/Porechop_ABI) is an extension of [Porechop](https://github.com/rrwick/Porechop). Porechop_ABI does not use any external knowledge or database for the adapters. Adapters are discovered directly from the reads using approximate k-mers counting and assembly. Then these sequences can be used for trimming, using all standard Porechop options. The software is able to report a combination of distinct sequences if a mix of adapters is used. It can also be used to check whether a dataset has already been trimmed out or not, or to find leftover adapters in datasets that have been previously processed with Guppy.
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `porechop_abi/`
+  - `<sample_id>.log`: Log file containing trimming statistics
+  - `<sample_id>.fastq.gz`: Adapter-trimmed file
+
+</details>
+
+The output logs are saved in the output folder and are part of MultiQC report.You do not normally need to check these manually.
+
+You will only find the `.fastq` files in the results directory if you provide ` --save_preprocessed_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_reads`, in which case the reads will be in the folder `analysis_ready_reads`.
+
 ### BBDuk
 
 [BBDuk](https://jgi.doe.gov/data-and-tools/software-tools/bbtools/bb-tools-user-guide/bbduk-guide/) stands for Decontamination Using Kmers. BBDuk was developed to combine most common data-quality-related trimming, filtering, and masking operations into a single high-performance tool.

docs/usage.md

@@ -252,7 +252,7 @@ By default, paired-end merging is not activated. In this case paired-end 'alignm
 You can also turn off clipping and only perform paired-end merging, if requested. This can be useful when processing data downloaded from the ENA, SRA, or DDBJ (`--shortread_qc_skipadaptertrim`).
 Both tools support length filtering of reads and can be tuned with `--shortread_qc_minlength`. Performing length filtering can be useful to remove short (often low sequencing complexity) sequences that result in unspecific classification and therefore slow down runtime during classification/profiling, with minimal gain.
 
-There is currently one option for long-read Oxford Nanopore processing: [`porechop`](https://github.com/rrwick/Porechop).
+There are currently two options for long-read Oxford Nanopore processing: [`porechop`](https://github.com/rrwick/Porechop), [`porechop_abi`](https://github.com/bonsai-team/Porechop_ABI).
 
 For both short-read and long-read preprocessing, you can optionally save the resulting processed reads with `--save_preprocessed_reads`.
 

modules.json

@@ -215,6 +215,12 @@
                         "git_sha": "729335dda8ba226323edc54dec80ae959079207e",
                         "installed_by": ["modules"]
                     },
+                    "porechop/abi": {
+                        "branch": "master",
+                        "git_sha": "870f9af2eaf0000c94d74910d762cf153752af98",
+                        "installed_by": ["modules"],
+                        "patch": "modules/nf-core/porechop/abi/porechop-abi.diff"
+                    },
                     "porechop/porechop": {
                         "branch": "master",
                         "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",