A basic workflow now running successfully

Plant-Food-Research-Open · Feb 20, 2024 · 8198830 · 8198830
1 parent 24151a6
commit 8198830
Show file tree

Hide file tree

Showing 51 changed files with 1,007 additions and 1,676 deletions.
diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml
@@ -2,53 +2,53 @@ name: Bug report
 description: Report something that is broken or incorrect
 labels: bug
 body:
-- type: textarea
-  id: description
-  attributes:
-    label: Description of the bug
-    description: A clear and concise description of what the bug is.
-  validations:
-    required: true
-- type: textarea
-  id: command_used
-  attributes:
-    label: Command used and terminal output
-    description: Steps to reproduce the behaviour. Please paste the command you used
-      to launch the pipeline and the output from your terminal.
-    render: console
-    placeholder: '$ nextflow run ...
-
-
-      Some output where something broke
-
-      '
-- type: textarea
-  id: files
-  attributes:
-    label: Relevant files
-    description: 'Please drag and drop the relevant files here. Create a `.zip` archive
-      if the extension is not allowed.
-
-      Your verbose log file `.nextflow.log` is often useful _(this is a hidden file
-      in the directory where you launched the pipeline)_ as well as custom Nextflow
-      configuration files.
-
-      '
-- type: textarea
-  id: system
-  attributes:
-    label: System information
-    description: '* Nextflow version _(eg. 23.04.0)_
-
-      * Hardware _(eg. HPC, Desktop, Cloud)_
-
-      * Executor _(eg. slurm, local, awsbatch)_
-
-      * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter, Charliecloud,
-      or Apptainer)_
-
-      * OS _(eg. CentOS Linux, macOS, Linux Mint)_
-
-      * Version of plant-food-research-open/assemblyqc _(eg. 1.1, 1.5, 1.8.2)_
-
-      '
+  - type: textarea
+    id: description
+    attributes:
+      label: Description of the bug
+      description: A clear and concise description of what the bug is.
+    validations:
+      required: true
+  - type: textarea
+    id: command_used
+    attributes:
+      label: Command used and terminal output
+      description: Steps to reproduce the behaviour. Please paste the command you used
+        to launch the pipeline and the output from your terminal.
+      render: console
+      placeholder: "$ nextflow run ...
+
+
+        Some output where something broke
+
+        "
+  - type: textarea
+    id: files
+    attributes:
+      label: Relevant files
+      description: "Please drag and drop the relevant files here. Create a `.zip` archive
+        if the extension is not allowed.
+
+        Your verbose log file `.nextflow.log` is often useful _(this is a hidden file
+        in the directory where you launched the pipeline)_ as well as custom Nextflow
+        configuration files.
+
+        "
+  - type: textarea
+    id: system
+    attributes:
+      label: System information
+      description: "* Nextflow version _(eg. 23.04.0)_
+
+        * Hardware _(eg. HPC, Desktop, Cloud)_
+
+        * Executor _(eg. slurm, local, awsbatch)_
+
+        * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter, Charliecloud,
+        or Apptainer)_
+
+        * OS _(eg. CentOS Linux, macOS, Linux Mint)_
+
+        * Version of plant-food-research-open/assemblyqc _(eg. 1.1, 1.5, 1.8.2)_
+
+        "
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -24,7 +24,7 @@ jobs:
     strategy:
       matrix:
         NXF_VER:
-          - "23.04.0"
+          - "22.04.3"
           - "latest-everything"
     steps:
       - name: Check out pipeline code

diff --git a/.github/workflows/download_pipeline.yml b/.github/workflows/download_pipeline.yml
@@ -64,4 +64,4 @@ jobs:
         env:
           NXF_SINGULARITY_CACHEDIR: ./
           NXF_SINGULARITY_HOME_MOUNT: true
-        run: nextflow run ./${{ env.REPOTITLE_LOWERCASE }}/$( sed 's/\W/_/g' <<< ${{ env.REPO_BRANCH }}) -stub -profile test,singularity --outdir ./results 
+        run: nextflow run ./${{ env.REPOTITLE_LOWERCASE }}/$( sed 's/\W/_/g' <<< ${{ env.REPO_BRANCH }}) -stub -profile test,singularity --outdir ./results
diff --git a/.nf-core.yml b/.nf-core.yml
@@ -1,23 +1,23 @@
 lint:
   files_exist:
-  - CODE_OF_CONDUCT.md
-  - assets/nf-core-assemblyqc_logo_light.png
-  - docs/images/nf-core-assemblyqc_logo_light.png
-  - docs/images/nf-core-assemblyqc_logo_dark.png
-  - .github/ISSUE_TEMPLATE/config.yml
-  - .github/workflows/awstest.yml
-  - .github/workflows/awsfulltest.yml
+    - CODE_OF_CONDUCT.md
+    - assets/nf-core-assemblyqc_logo_light.png
+    - docs/images/nf-core-assemblyqc_logo_light.png
+    - docs/images/nf-core-assemblyqc_logo_dark.png
+    - .github/ISSUE_TEMPLATE/config.yml
+    - .github/workflows/awstest.yml
+    - .github/workflows/awsfulltest.yml
   files_unchanged:
-  - CODE_OF_CONDUCT.md
-  - assets/nf-core-assemblyqc_logo_light.png
-  - docs/images/nf-core-assemblyqc_logo_light.png
-  - docs/images/nf-core-assemblyqc_logo_dark.png
-  - .github/ISSUE_TEMPLATE/bug_report.yml
+    - CODE_OF_CONDUCT.md
+    - assets/nf-core-assemblyqc_logo_light.png
+    - docs/images/nf-core-assemblyqc_logo_light.png
+    - docs/images/nf-core-assemblyqc_logo_dark.png
+    - .github/ISSUE_TEMPLATE/bug_report.yml
   multiqc_config:
-  - report_comment
+    - report_comment
   nextflow_config:
-  - manifest.name
-  - manifest.homePage
+    - manifest.name
+    - manifest.homePage
 repository_type: pipeline
 template:
   prefix: plant-food-research-open

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/mirrors-prettier
-    rev: "v3.1.1"
+    rev: "v3.1.0"
     hooks:
       - id: prettier
   - repo: https://github.com/editorconfig-checker/editorconfig-checker.python

diff --git a/README.md b/README.md
@@ -1,7 +1,7 @@
 [![GitHub Actions CI Status](https://github.com/plant-food-research-open/assemblyqc/workflows/nf-core%20CI/badge.svg)](https://github.com/plant-food-research-open/assemblyqc/actions?query=workflow%3A%22nf-core+CI%22)
 [![GitHub Actions Linting Status](https://github.com/plant-food-research-open/assemblyqc/workflows/nf-core%20linting/badge.svg)](https://github.com/plant-food-research-open/assemblyqc/actions?query=workflow%3A%22nf-core+linting%22)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX)
 
-[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A523.04.0-23aa62.svg)](https://www.nextflow.io/)
+[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A522.04.3-23aa62.svg)](https://www.nextflow.io/)
 [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)
 [![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/)
 [![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/)

diff --git a/assets/assemblysheet.csv b/assets/assemblysheet.csv
@@ -0,0 +1,2 @@
+tag,fasta,gff3,monoploid_ids,hic_reads,synteny_labels
+FI1,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/814/445/GCA_003814445.1_ASM381444v1/GCA_003814445.1_ASM381444v1_genomic.fna.gz,,,,
diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
diff --git a/assets/schema_input.json b/assets/schema_input.json
@@ -7,22 +7,61 @@
     "items": {
         "type": "object",
         "properties": {
-            "sample": {
+            "tag": {
                 "type": "string",
-                "pattern": "^\\S+$",
-                "errorMessage": "Sample name must be provided and cannot contain spaces"
+                "pattern": "^\\w+$",
+                "errorMessage": "Assembly tags must be provided and can only contain alphanumeric characters including '_'"
             },
-            "fastq_1": {
+            "fasta": {
                 "type": "string",
-                "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+                "pattern": "^\\S+\\.f(ast|as|sa|na)?\\.gz$",
+                "errorMessage": "FASTA file path cannot contain spaces and must have extension '.f(ast|as|sa|na)' or '.f(ast|as|sa|na).gz'"
             },
-            "fastq_2": {
-                "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'",
+            "gff3": {
+                "type": "string",
+                "pattern": "^\\S+\\.gff(3)?\\.gz$",
+                "errorMessage": "GFF3 file path cannot contain spaces and must have extension '.gff.gz' or '.gff3.gz'"
+            },
+            "monoploid_ids": {
+                "errorMessage": "Monoploid IDs txt file path cannot contain spaces and must have extension '.txt'",
+                "anyOf": [
+                    {
+                        "type": "string",
+                        "pattern": "^\\S+\\.txt$"
+                    },
+                    {
+                        "type": "string",
+                        "maxLength": 0
+                    }
+                ]
+            },
+            "hic_reads": {
+                "errorMessage": "HiC reads should either be provided as a SRA ID or as a path to paired reads with pattern '*_R{1,2}.(fastq|fq).gz'",
+                "anyOf": [
+                    {
+                        "type": "string",
+                        "pattern": "^SR\\w+$"
+                    },
+                    {
+                        "type": "string",
+                        "pattern": "^\\S+_R\\{1,2\\}\\.f(ast)?q\\.gz$"
+                    },
+                    {
+                        "type": "string",
+                        "maxLength": 0
+                    }
+                ]
+            },
+            "synteny_labels": {
+                "errorMessage": "Synteny labels tsv path cannot contain spaces and must have extension '.tsv'",
                 "anyOf": [
                     {
                         "type": "string",
-                        "pattern": "^\\S+\\.f(ast)?q\\.gz$"
+                        "pattern": "^SR\\w+$"
+                    },
+                    {
+                        "type": "string",
+                        "pattern": "^\\S+_R\\{1,2\\}\\.f(ast)?q\\.gz$"
                     },
                     {
                         "type": "string",
@@ -31,6 +70,6 @@
                 ]
             }
         },
-        "required": ["sample", "fastq_1"]
+        "required": ["tag", "fasta"]
     }
 }