Add methurator tool

README.md

@@ -39,20 +39,21 @@ Choose between workflows by using `--aligner bismark` (default, uses bowtie2 for
 
 Note: For faster CPU runs with BWA-Meth, enable the BWA-MEM2 algorithm using `--use_mem2`. The GPU pathway (Parabricks) requires `-profile gpu` and a container runtime (Docker, Singularity, or Podman); Conda/Mamba are not supported for the GPU module.
 
-| Step                                         | Bismark workflow         | bwa-meth workflow     | bwa-mem + TAPS workflow    |
-| -------------------------------------------- | ------------------------ | --------------------- | -------------------------- |
-| Generate Reference Genome Index _(optional)_ | Bismark                  | bwa-meth              | bwa index                  |
-| Merge re-sequenced FastQ files               | cat                      | cat                   | cat                        |
-| Raw data QC                                  | FastQC                   | FastQC                | FastQC                     |
-| Adapter sequence trimming                    | Trim Galore!             | Trim Galore!          | Trim Galore!               |
-| Align Reads                                  | Bismark (bowtie2/hisat2) | bwa-meth              | bwa mem                    |
-| Deduplicate Alignments                       | Bismark                  | Picard MarkDuplicates | Picard MarkDuplicates      |
-| Extract methylation calls                    | Bismark                  | MethylDackel          | TAPS subworkflow (rastair) |
-| Sample report                                | Bismark                  | -                     | -                          |
-| Summary Report                               | Bismark                  | -                     | -                          |
-| Alignment QC                                 | Qualimap _(optional)_    | Qualimap _(optional)_ | Qualimap _(optional)_      |
-| Sample complexity                            | Preseq _(optional)_      | Preseq _(optional)_   | Preseq _(optional)_        |
-| Project Report                               | MultiQC                  | MultiQC               | MultiQC                    |
+| Step                                         | Bismark workflow         | bwa-meth workflow       | bwa-mem + TAPS workflow    |
+| -------------------------------------------- | ------------------------ | ----------------------- | -------------------------- |
+| Generate Reference Genome Index _(optional)_ | Bismark                  | bwa-meth                | bwa index                  |
+| Merge re-sequenced FastQ files               | cat                      | cat                     | cat                        |
+| Raw data QC                                  | FastQC                   | FastQC                  | FastQC                     |
+| Adapter sequence trimming                    | Trim Galore!             | Trim Galore!            | Trim Galore!               |
+| Align Reads                                  | Bismark (bowtie2/hisat2) | bwa-meth                | bwa mem                    |
+| Deduplicate Alignments                       | Bismark                  | Picard MarkDuplicates   | Picard MarkDuplicates      |
+| Extract methylation calls                    | Bismark                  | MethylDackel            | TAPS subworkflow (rastair) |
+| Sample report                                | Bismark                  | -                       | -                          |
+| Summary Report                               | Bismark                  | -                       | -                          |
+| Alignment QC                                 | Qualimap _(optional)_    | Qualimap _(optional)_   | Qualimap _(optional)_      |
+| Sample complexity                            | Preseq _(optional)_      | Preseq _(optional)_     | Preseq _(optional)_        |
+| CpGs-level sequencing saturation             | methurator _(optional)_  | methurator _(optional)_ | methurator _(optional)_    |
+| Project Report                               | MultiQC                  | MultiQC                 | MultiQC                    |
 
 Optional targeted sequencing analysis is available via `--run_targeted_sequencing` and `--target_regions_file`; see the [usage documentation](https://nf-co.re/methylseq/usage) for details.
 

conf/base.config

@@ -66,6 +66,9 @@ process {
     withName: PRESEQ_LCEXTRAP {
         errorStrategy = 'ignore'
     }
+    withName: METHURATOR_GTESTIMATOR {
+        errorStrategy = 'ignore'
+    }
     withName: BISMARK_ALIGN {
         time = { 8.d * task.attempt }
     }

conf/modules/methurator_gtestimator.config

@@ -0,0 +1,17 @@
+process {
+    withName: METHURATOR_GTESTIMATOR {
+        ext.args = [
+            params.compute_ci ? ' --compute_ci' : '',
+            params.rrbs ? ' --rrbs' : '',
+            params.minimum_coverage ? " --minimum-coverage ${params.minimum_coverage}" : "",
+            params.t_max ? " --t-max ${params.t_max}" : ""
+        ].join(" ").trim()
+        publishDir = [
+            [
+                path: { "${params.outdir}/methurator/summaries/" },
+                mode: params.publish_dir_mode,
+                pattern: "*.yml"
+            ]
+        ]
+    }
+}

conf/modules/methurator_plot.config

@@ -0,0 +1,11 @@
+process {
+    withName: METHURATOR_PLOT {
+        publishDir = [
+            [
+                path: { "${params.outdir}/methurator" },
+                mode: params.publish_dir_mode,
+                pattern: "**/*.html"
+            ]
+        ]
+    }
+}

docs/output.md

@@ -355,6 +355,17 @@ Note that these are predictive numbers only, not absolute. The MultiQC plot can
 - `sample_ccurve.txt`
   - This file contains plot values for the complexity curve, plotted in the MultiQC report.
 
+## methurator
+
+[methurator](https://vibtobilab.github.io/methurator/latest/) methurator is a Python package to estimate CpG sequencing saturation for DNA methylation sequencing data.
+
+**Output directory: `results/methurator`**
+
+- `summaries/sample.yml`
+  - This file contains metadata, model parameters, and extrapolation results for each
+- `plots/sample.html`
+  - This folder contains one interactive, HTML file per sample analysed.
+
 ### MultiQC
 
 ![MultiQC - FastQC sequence counts plot](images/mqc_fastqc_counts.png)

docs/usage.md

@@ -66,9 +66,11 @@ flowchart TD
         D1 --> J1["preseq (optional)"]
         D2 --> J1
         D3 --> J1
-        D1 --> J2["Qualimap (optional)"]
+        D1 --> J2["methurator (optional)"]
         D2 --> J2
-        D3 --> J2
+        D1 --> J3["Qualimap (optional)"]
+        D2 --> J3
+        D3 --> J3
     end
 
     subgraph Stage4[Final QC]

main.nf

@@ -71,6 +71,7 @@ workflow NFCORE_METHYLSEQ {
         ch_or_val_bwamem_index,
         params.aligner,
         params.collecthsmetrics,
+        params.run_methurator,
         params.use_mem2
     )
     ch_versions = ch_versions.mix(FASTA_INDEX_METHYLSEQ.out.versions)

modules.json

@@ -80,6 +80,16 @@
                         "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
                         "installed_by": ["fasta_index_bismark_bwameth", "fasta_index_methylseq"]
                     },
+                    "methurator/gtestimator": {
+                        "branch": "master",
+                        "git_sha": "85a3650c949d1146cdb576f986640e84775b7743",
+                        "installed_by": ["modules"]
+                    },
+                    "methurator/plot": {
+                        "branch": "master",
+                        "git_sha": "85a3650c949d1146cdb576f986640e84775b7743",
+                        "installed_by": ["modules"]
+                    },
                     "methyldackel/extract": {
                         "branch": "master",
                         "git_sha": "c8df5757c72362907a43de49a6b20bd4998907a0",