Merge pull request #38 from sanger-tol/release-0.9.1

Release 0.10.0
sanger-tol · Apr 16, 2024 · 0276f81 · 0276f81
2 parents 24e5df8 + eb3f9a6
commit 0276f81
Show file tree

Hide file tree

Showing 13 changed files with 156 additions and 67 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,15 +3,27 @@
 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).
 
-## v0.9.1dev - [date]
+## [[0.10.0](https://github.com/sanger-tol/genomeassembly/releases/tag/0.10.0)] - Hideous Zippleback - [2024-04-16]
 
-### `Added`
+### 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
 
-### `Fixed`
+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.
 
-### `Dependencies`
+| Dependency | Old version | New version |
+| ---------- | ----------- | ----------- |
+| mitohifi   | 3.0.0       | 3.1.1       |
+| oatk       |             | 1.0         |
 
-### `Deprecated`
+**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]
 
@@ -60,6 +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                              |

diff --git a/README.md b/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].

diff --git a/assets/schema_input.json b/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"]

diff --git a/assets/test.yaml b/assets/test.yaml
@@ -16,3 +16,5 @@ mito:
   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
diff --git a/conf/modules.config b/conf/modules.config
@@ -218,7 +218,7 @@ process {
                 saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
             ]
         }
-        withName: '.*OATK' {
+        withName: '.*ORGANELLES:OATK' {
             ext.args = "-k1001 -c90 -Ttmp"
             publishDir = [
                 path: { "${params.outdir}/${meta.id}.${params.hifiasm}/oatk" },

diff --git a/conf/test.config b/conf/test.config
@@ -26,11 +26,3 @@ params {
     polishing_on = true
     hifiasm_hic_on = true
 }
-
-process {
-    // Set up of the scffolding pipeline
-    withName: 'YAHS' {
-        // Skip the initial assembly error correction step
-        ext.args = '-r 1000,2000,5000'
-    }
-}