Merge pull request #161 from sanger-tol/kmer_plot

Output k-mer spectra
sanger-tol · Oct 18, 2023 · 83de0c3 · 83de0c3
2 parents 2413fe5 + c23127c
commit 83de0c3
Show file tree

Hide file tree

Showing 12 changed files with 460 additions and 18 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -45,7 +45,7 @@ jobs:
         run: |
           nextflow run ${GITHUB_WORKSPACE} -entry RAPID -profile test_github,docker --outdir ./results-rapid
 
-      - name: Run FULL pipeline with test data
-        # Remember that you can parallelise this by using strategy.matrix
-        run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test_github,docker --outdir ./results-full
+      #- name: Run FULL pipeline with test data
+      #  # Remember that you can parallelise this by using strategy.matrix
+      #  run: |
+      #    nextflow run ${GITHUB_WORKSPACE} -profile test_github,docker --outdir ./results-full
diff --git a/conf/base.config b/conf/base.config
@@ -101,14 +101,14 @@ process {
     withName: '.*:.*:LONGREAD_COVERAGE:(MINIMAP2_ALIGN|MINIMAP2_ALIGN_SPLIT)' {
         cpus    = { check_max( 16       * 1, 'cpus'                 ) }
         memory  = { check_max( 100.GB   * task.attempt, 'memory'    ) }
-        time    = { check_max( 18.h     * task.attempt, 'time'      ) }
+        time    = { check_max( 20.h     * task.attempt, 'time'      ) }
     }
 
-    // For Large complex genomes > 4Gb
-    // withName: '.*:.*:LONGREAD_COVERAGE:(MINIMAP2_ALIGN|MINIMAP2_ALIGN_SPLIT)' {
-        //cpus    = { check_max( 20       * 1, 'cpus'                 ) }
-        //memory  = { check_max( 400.GB   * task.attempt, 'memory'    ) }
-        // time    = { check_max( 300.h    * task.attempt, 'time'      ) }
+// For Large complex genomes > 4Gb
+    //withName: '.*:.*:LONGREAD_COVERAGE:(MINIMAP2_ALIGN|MINIMAP2_ALIGN_SPLIT)' {
+    //    cpus    = { check_max( 20       * 1, 'cpus'                 ) }
+    //    memory  = { check_max( 400.GB   * task.attempt, 'memory'    ) }
+    //    time    = { check_max( 300.h    * task.attempt, 'time'      ) }
     //}
 
     withName: '.*:.*:LONGREAD_COVERAGE:SAMTOOLS_SORT' {
@@ -121,6 +121,12 @@ process {
         memory  = { check_max( 25.GB   * Math.ceil( task.attempt * 2 ), 'memory'   ) }
     }
 
+    // For larger
+    //withName:MUMMER {
+    //    cpus    = { check_max( 12      * task.attempt, 'cpus'                      ) }
+    //    memory  = { check_max( 50.GB   * Math.ceil( task.attempt * 2 ), 'memory'   ) }
+    //}
+
     withName:UCSC_BEDGRAPHTOBIGWIG {
         cpus   = { check_max( 2        * task.attempt, 'cpus'   ) }
         memory = { check_max( 20.GB    * task.attempt, 'memory' ) }
@@ -174,8 +180,14 @@ process {
 
     // Large Genomes > 4Gb
     //withName: BUSCO {
-        //cpus   = { check_max( 30     * task.attempt, 'cpus'    ) }
-        //memory = { check_max( 120.GB * task.attempt, 'memory'  ) }
-        //time   = { check_max( 300.h  * task.attempt, 'time'    ) }
+    //    cpus   = { check_max( 30     * task.attempt, 'cpus'    ) }
+    //    memory = { check_max( 100.GB * task.attempt, 'memory'  ) }
+    //    time   = { check_max( 300.h  * task.attempt, 'time'    ) }
     //}
+
+    // Large Genomes > 4Gb
+    withName: FASTK_FASTK {
+        cpus   = { check_max( 25     * task.attempt, 'cpus'    ) }
+        memory = { check_max( 100.GB * task.attempt, 'memory'  ) }
+    }
 }
diff --git a/conf/modules.config b/conf/modules.config
@@ -41,7 +41,7 @@ process {
 
     // Files to be used for pretext, likely to be deleted once the hic workflow is complete.
     // .bed, .hr.pretext, .lr.pretext, needs centromere}
-    withName: 'SEQTK_CUTN|GAP_LENGTH|PRETEXTMAP_HIGHRES|PRETEXTMAP_STANDRD|COOLER_ZOOMIFY|COV_FOLDER|UCSC_BEDGRAPHTOBIGWIG|EXTRACT_TELO|JUICER_TOOLS_PRE|SNAPSHOT_SRES|SNAPSHOT_HRES|GET_PAIRED_CONTACT_BED' {
+    withName: 'SEQTK_CUTN|GAP_LENGTH|PRETEXTMAP_HIGHRES|PRETEXTMAP_STANDRD|COOLER_ZOOMIFY|COV_FOLDER|UCSC_BEDGRAPHTOBIGWIG|EXTRACT_TELO|JUICER_TOOLS_PRE|SNAPSHOT_SRES|SNAPSHOT_HRES' {
         publishDir = [
             path: { "${params.outdir}/hic_files" },
             mode: params.publish_dir_mode,
@@ -278,4 +278,15 @@ process {
         ext.args    = { '-k2,2 -nr' }
     }
 
+    withName: FASTK_FASTK {
+        ext.args   = "-k31 -t"
+    }
+
+    withName: MERQURYFK_MERQURYFK {
+        publishDir = [
+            path: { "${params.outdir}/hic_files" },
+            mode: params.publish_dir_mode,
+            pattern: '*.ref.spectra-cn.ln.png'
+        ]
+    }
 }
diff --git a/docs/output.md b/docs/output.md
@@ -21,6 +21,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
 - [selfcomp](#selfcomp) - Identifies regions of self-complementary sequence.
 - [synteny](#synteny) - Generates syntenic alignments between other high quality genomes.
 - [busco-analysis](#busco-analysis) - Uses BUSCO to identify ancestral elements. Also use to identify ancestral Lepidopteran genes (merian units).
+- [kmer](#kmer) - Counts k-mer and generates a copy number spectra plot.
 
 - [pipeline-information](#pipeline-information) - Report metrics generated during the workflow execution
 
@@ -218,6 +219,20 @@ This worflows searches along predetermined path for syntenic genome files based
 
 ![Workflow Legend](https://raw.githubusercontent.com/sanger-tol/treeval/dev/docs/images/treeval_1_0_legend.jpeg)
 
+## kmer
+
+This worflows performs a k-mer count using [FASTK_FASTK](https://nf-co.re/modules/fastk_fastk) then passes the results to [MERQURYFK_MERQURYFK](https://nf-co.re/modules/merquryfk_merquryfk) to plot a copy-number k-mer spectra.
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `hic_files/`
+  - `*.ref.spectra-cn.ln.png`: .png file of copy number k-mer spectra.
+
+</details>
+
+![Workflow Legend](https://raw.githubusercontent.com/sanger-tol/treeval/dev/docs/images/treeval_1_0_legend.jpeg)
+
 ## pipeline-information
 
 [Nextflow](https://www.nextflow.io/docs/latest/tracing.html) provides excellent functionality for generating various reports relevant to the running and execution of the pipeline. This will allow you to troubleshoot errors with the running of the pipeline, and also provide you with other information such as launch commands, run times and resource usage.

diff --git a/modules.json b/modules.json
@@ -76,11 +76,21 @@
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/custom/getchromsizes/custom-getchromsizes.diff"
                     },
+                    "fastk/fastk": {
+                        "branch": "master",
+                        "git_sha": "29e87a37ae1887fc8289f2f56775604a71715cb9",
+                        "installed_by": ["modules"]
+                    },
                     "gnu/sort": {
                         "branch": "master",
                         "git_sha": "88f6e982fb8bd40488d837b3b08a65008e602840",
                         "installed_by": ["modules"]
                     },
+                    "merquryfk/merquryfk": {
+                        "branch": "master",
+                        "git_sha": "6f150e1503c0826c21fedf1fa566cdbecbe98ec7",
+                        "installed_by": ["modules"]
+                    },
                     "minimap2/align": {
                         "branch": "master",
                         "git_sha": "603ecbd9f45300c9788f197d2a15a005685b4220",

diff --git a/modules/nf-core/fastk/fastk/main.nf b/modules/nf-core/fastk/fastk/main.nf
diff --git a/modules/nf-core/fastk/fastk/meta.yml b/modules/nf-core/fastk/fastk/meta.yml
diff --git a/modules/nf-core/merquryfk/merquryfk/main.nf b/modules/nf-core/merquryfk/merquryfk/main.nf