Add busco list datasets component (#18)

* add script and config to list busco datasets

* update test

* update busco to point to busco_list_datasets component

* add changelog entry

* update changelog

* Update CHANGELOG.md

Co-authored-by: Robrecht Cannoodt <[email protected]>

* rename busco to busco run

---------

Co-authored-by: Robrecht Cannoodt <[email protected]>

CHANGELOG.md

@@ -8,7 +8,9 @@
 
 * `fastp`: An ultra-fast all-in-one FASTQ preprocessor (PR #3).
 
-* `busco`: Assess genome assembly and annotation completeness with single copy orthologs (PR #6).
+* `busco`: 
+    - `busco/busco_run`: Assess genome assembly and annotation completeness with single copy orthologs (PR #6).
+    - `busco/busco_list_datasets`: Lists available busco datasets (PR #18)
 
 * `featurecounts`: Assign sequence reads to genomic features (PR #11).
 

src/busco/busco_list_datasets/config.vsh.yaml

@@ -0,0 +1,36 @@
+functionality:
+  name: busco
+  description: Lists the available busco datasets
+  info:
+    keywords: [lineage datasets]
+    homepage: https://busco.ezlab.org/
+    documentation: https://busco.ezlab.org/busco_userguide.html
+    repository: https://gitlab.com/ezlab/busco
+    reference: "10.1007/978-1-4939-9173-0_14"
+    licence: MIT
+  argument_groups:
+    - name: Outputs
+      arguments:
+        - name: --output
+          alternatives: ["-o"]
+          direction: output
+          type: file
+          description: |
+            Output file of the available busco datasets
+          required: false
+          default: busco_dataset_list.txt
+          example: file.txt
+  resources:
+    - type: bash_script
+      path: script.sh
+  test_resources:
+    - type: bash_script
+      path: test.sh
+platforms:
+  - type: docker
+    image: quay.io/biocontainers/busco:5.6.1--pyhdfd78af_0
+    setup:
+      - type: docker
+        run: |
+          busco --version | sed 's/BUSCO\s\(.*\)/busco: "\1"/' > /var/software_versions.txt
+  - type: nextflow

src/busco/busco_list_datasets/script.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+
+## VIASH START
+## VIASH END
+
+busco --list-datasets | awk '/^#{40}/{flag=1; next} flag{print}' > $par_output

src/busco/busco_list_datasets/test.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+
+## VIASH START
+## VIASH END
+
+"$meta_executable" \
+    --output datasets.txt 
+
+echo ">> Checking output"
+[ ! -f "datasets.txt" ] && echo "datasets.txt does not exist" && exit 1
+
+echo ">> Checking if output is empty"
+[ ! -s "datasets.txt" ] && echo "datasets.txt is empty" && exit 1
+
+rm datasets.txt

src/busco/config.vsh.yaml → src/busco/busco_run/config.vsh.yaml

@@ -1,5 +1,5 @@
 functionality:
-  name: busco
+  name: busco_run
   description: Assessment of genome assembly and annotation completeness with single copy orthologs
   info:
     keywords: [Genome assembly, quality control]
@@ -35,7 +35,7 @@ functionality:
           required: false
           description: |
             Specify a BUSCO lineage dataset that is most closely related to the assembly or gene set being assessed. 
-            The full list of available datasets can be viewed [here](https://busco-data.ezlab.org/v5/data/lineages/) or by running `busco --list-datasets` (which requires installing the tool).
+            The full list of available datasets can be viewed [here](https://busco-data.ezlab.org/v5/data/lineages/) or by running the busco/busco_list_datasets component.
             When unsure, the "--auto_lineage" flag can be set to automatically find the optimal lineage path.
             Requested datasets will automatically be downloaded if not already present in the download folder.
           example: stramenopiles_odb10