Merge pull request #39 from sanger-tol/dev

Release 0.10.0

.github/workflows/ci.yml

@@ -22,13 +22,19 @@ jobs:
     name: Run pipeline with test data
     # Only run on push if this is the nf-core dev branch (merged PRs)
     if: "${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'sanger-tol/genomeassembly') }}"
-    runs-on: ubuntu2204-16c
+    runs-on: ubuntu2204-4c
     strategy:
       matrix:
         NXF_VER:
           - "22.10.1"
           - "latest-everything"
     steps:
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
       - name: Check out pipeline code
         uses: actions/checkout@v3
 
@@ -37,9 +43,13 @@ jobs:
         with:
           version: "${{ matrix.NXF_VER }}"
 
+      - name: Set up nextflow secrets
+        run: |
+          nextflow secrets set NCBI_API_KEY ${{ secrets.NCBI_API_KEY }}
+
       - name: Download test data
         run: |
-          curl https://darwin.cog.sanger.ac.uk/genomeassembly_test_data.tar.gz | tar xzf -
+          curl https://tolit.cog.sanger.ac.uk/test-data/resources/genomeassembly/genomeassembly_test_data.tar.gz | tar xzf -
 
       - name: Setup apptainer
         uses: eWaterCycle/setup-apptainer@main

CHANGELOG.md

@@ -3,6 +3,28 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [[0.10.0](https://github.com/sanger-tol/genomeassembly/releases/tag/0.10.0)] - Hideous Zippleback - [2024-04-16]
+
+### Enhancements & fixes
+
+- OATK module is added into the ORGANELLES subworkflow
+- ORGANELLES subworkflow is now called once in the main workflow and runs MITOHIFI in read and assembly mode along with OATK
+- ORGANELLES module is now tested in github CI
+- NCBI API secret introduced to run MITOHIFI_FINDMITOREFERENCE module
+- hifiasm haplotigs are not purged anymore
+- Longranger container version is updated
+
+### Software dependencies
+
+Note, since the pipeline is using Nextflow DSL2, each process will be run with its own [Biocontainer](https://biocontainers.pro/#/registry). This means that on occasion it is entirely possible for the pipeline to be using different versions of the same tool. However, the overall software dependency changes compared to the last release have been listed below for reference.
+
+| Dependency | Old version | New version |
+| ---------- | ----------- | ----------- |
+| mitohifi   | 3.0.0       | 3.1.1       |
+| oatk       |             | 1.0         |
+
+**NB:** Dependency has been **added** if just the new version information is present.
+
 ## [[0.9.0](https://github.com/sanger-tol/genomeassembly/releases/tag/0.9.0)] - Night Fury - [2023-12-15]
 
 Initial release of sanger-tol/genomeassembly, created with the [nf-core](https://nf-co.re/) template.
@@ -50,6 +72,7 @@ Note, since the pipeline is using Nextflow DSL2, each process will be run with i
 | fastk           |             | f18a4e6d2207539f7b84461daebc54530a9559b0 |
 | freebayes       |             | 1.3.6                                    |
 | gatk4           |             | 4.4.0.0                                  |
+| genescope       |             | 380815c420f50171f9234a0fd1ff426b39829b91 |
 | gfastats        |             | 1.3.5                                    |
 | GNU Awk         |             | 5.1.0                                    |
 | hifiasm         |             | 0.19.3-r572                              |

README.md

@@ -35,7 +35,8 @@ While the steps are described in a sequential order, many of them can be execute
    1. Illumina 10X reads to the joined primary and alt contigs.
    2. polish initial assembly based on the aligment produced in [9i]. Set polished primary contigs as the primary assembly and polished haplotigs as the haplotig assembly.
    3. produce numerical stats, BUSCO score and QV, completeness metrics, and kmer spectra for [9ii].
-10. Run organelles subworkflow on the joined primary and haplotigs contigs.
+10. If <code>organelles_on</code>
+    1. Run organelles subworkflow on the raw HiFi read data and the joined primary and haplotigs contigs.
 11. Map HiC data onto primary contigs.
 12. Run scaffolding for primary contigs.
 13. Produce numerical stats, BUSCO score and QV, completeness metrics, and kmer spectra for [12].

assets/schema_input.json

@@ -44,6 +44,40 @@
                         "errorMessage": "busco lineage to run"
                     }
                 }
+            },
+            "mito": {
+                "type": "object",
+                "properties": {
+                    "species": {
+                        "type": "string",
+                        "errorMessage": "Latin name"
+                    },
+                    "min_length": {
+                        "type": "string",
+                        "errorMessage": "Minimal allowed length of the mito reference"
+                    },
+                    "email": {
+                        "type": "string",
+                        "errorMessage": "email to query NCBI"
+                    },
+                    "code": {
+                        "type": "string",
+                        "errorMessage": "Mitochondrial code"
+                    },
+                    "fam": {
+                        "type": "string",
+                        "errorMessage": "Path to mitochondrial HMM for OATK"
+                    }
+                }
+            },
+            "plastid": {
+                "type": "object",
+                "properties": {
+                    "fam": {
+                        "type": "string",
+                        "errorMessage": "Path to plastid HMM for OATK"
+                    }
+                }
             }
         },
         "required": ["dataset", "busco"]

assets/test.yaml

@@ -4,7 +4,7 @@ dataset:
     reads: /lustre/scratch123/tol/resources/nextflow/test-data/Undibacterium_unclassified/genomic_data/baUndUnlc1/10x/
   pacbio:
     reads:
-      - reads: /lustre/scratch123/tol/resources/nextflow/test-data/Undibacterium_unclassified/genomic_data/baUndUnlc1/pacbio/fasta/HiFi.reads.fasta
+      - reads: /lustre/scratch124/tol/projects/darwin/users/kk16/development/test/test/HiFi.reads.BIG.fasta
   HiC:
     reads:
       - reads: /lustre/scratch123/tol/resources/nextflow/test-data/Undibacterium_unclassified/genomic_data/baUndUnlc1/hic-arima2/41741_2#7.sub.cram
@@ -15,3 +15,6 @@ mito:
   species: Caradrina clavipalpis
   min_length: 15000
   code: 5
+  fam: /lustre/scratch124/tol/projects/darwin/users/cz3/organelle_asm/hmm_db/insecta_mito.fam
+plastid:
+  fam: /lustre/scratch124/tol/projects/darwin/users/cz3/organelle_asm/hmm_db/acrogymnospermae_pltd.fam

assets/test_github.yaml

@@ -15,3 +15,4 @@ mito:
   species: Caradrina clavipalpis
   min_length: 15000
   code: 5
+  fam: /home/runner/work/genomeassembly/genomeassembly/Undibacterium_unclassified/hmm_db/insecta_mito.fam