Merge branch 'rel-0.5.1'

# Conflicts:
#	README.md

Author: alpae

.github/workflows/docker-image.yml

@@ -17,7 +17,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v6.0.1
         with:
           submodules: recursive
 

.github/workflows/nf-test.yml

@@ -40,15 +40,15 @@ jobs:
 
     steps:
       - name: Check out pipeline code
-        uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
+        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v4
         with:
           fetch-depth: 0
 
       - uses: actions/setup-python@f677139bbe7f9c59b41e40162b753c062f5d49a3 # v5
         with:
           python-version: "3.11"
 
-      - uses: actions/setup-java@8df1039502a15bceb9433410b1a100fbe190c53b # v4
+      - uses: actions/setup-java@f2beeb24e141e01a676f977032f5a29d81c9e27e # v4
         with:
           distribution: "temurin"
           java-version: "17"
@@ -78,7 +78,7 @@ jobs:
 
       - name: Set up miniconda
         if: matrix.profile == 'conda'
-        uses: conda-incubator/setup-miniconda@a4260408e20b96e80095f42ff7f1a15b27dd94ca # v3
+        uses: conda-incubator/setup-miniconda@835234971496cad1653abb28a638a281cf32541f # v3
         with:
           miniconda-version: "latest"
           auto-update-conda: true
@@ -136,14 +136,14 @@ jobs:
           echo "Some test(s) failed :cold_sweat:" >> $GITHUB_STEP_SUMMARY
 
       - name: Publish Test Report
-        uses: mikepenz/action-junit-report@v4
+        uses: mikepenz/action-junit-report@v6
         if: success() || failure() # always run even if the previous step fails
         with:
           report_paths: "TEST-*.xml"
 
       - name: Upload test results
         if: always()  # run even if tests fail
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v6
         with:
           name: nf-test-results-${{ matrix.filter }}-${{ matrix.profile }}-${{ matrix.NXF_VER }}-${{ matrix.shard }}
           path: |

.github/workflows/publish-pypi-release.yml

@@ -14,7 +14,7 @@ jobs:
       id-token: write
 
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v6.0.1
     - name: Set up Python
       uses: actions/setup-python@v6
       with:

FastOMA.nf

@@ -365,6 +365,41 @@ def detectInputType(input) {
     }
 }
 
+// Helper to prefer user-specified value if set, else derive from input_root
+def resolveFolderParam(input_root_ch, param_value, default_subdir, required=true) {
+    if (param_value) {
+        return Channel.fromPath(param_value, type: 'dir', checkIfExists: true)
+    } else {
+        return resolveSubPath(input_root_ch, default_subdir, 'dir', required)
+    }
+}
+
+
+//Resolve a subpath inside an input directory and return a path channel
+def resolveSubPath(base_ch, subpath, type='dir', required=true) {
+    base_ch.map { base ->
+      def fullPath = "${base}/${subpath}"
+      def targetFile =  file(fullPath)
+
+      if (required) {
+        if (type == 'dir' && (!targetFile.exists() || !targetFile.isDirectory())){
+            log.error "Required directory not found: ${fullPath}"
+            exit 1
+        } else if (type == 'file' && (!targetFile.exists() || !targetFile.isFile())) {
+            log.error "Required file not found: ${fullPath}"
+            exit 1
+        }
+      }
+      return targetFile
+    }
+}
+
+// Resolve a single file (emit once)
+def resolveFile(base_ch, filename, required=true) {
+    resolveSubPath(base_ch, filename, 'file', required).first()
+}
+
+
 // handle deprecated parameters
 def handleDeprecatedParameters() {
     if (params.input_folder && !params.input) {
@@ -405,41 +440,37 @@ workflow {
 
     // Detect input type 
     def inputType = detectInputType(params.input)
-    if (inputType == "directory") {
-        // Local/custom dataset - allow parameter overrides
-        proteome_folder = Channel.value(params.proteome_folder)
-        proteomes = Channel.fromPath("${params.proteome_folder}/*.{fa,fasta}", checkIfExists: true)
-        species_tree = Channel.value(params.species_tree)
-        splice_folder = Channel.value(params.splice_folder)
-        hogmap_in = Channel.value(params.hogmap_in)
-    } else {
-        // Input is either a URL or an archive file - fetch and extract
-        // Fetch test dataset from remote URL
-        if (inputType == "url") {
-            input_path = fetchRemoteData(Channel.value(params.input))
-        } else if (inputType == "archive") {
-            input_path = extractLocalArchive(Channel.fromPath(params.input))
-        }
-        
-        // Set up all channels based on the downloaded folder structure
-        proteome_folder = input_path.map { "${it}/proteome" }
-        proteomes = input_path.flatMap { dir ->
-            file("${dir}/proteome").listFiles().findAll {
-                it.name.endsWith('.fa') || it.name.endsWith('.fasta') || it.name.endsWith('.faa')
-            }
-        }
-        species_tree = input_path.map { "${it}/species_tree.nwk" }
-        splice_folder = input_path.map { "${it}/splice" }
-        hogmap_in = input_path.map { "${it}/hogmap_in" }
-    } 
+    if (inputType == 'directory') {
+        input_root = Channel.fromPath(params.input, type: 'dir', checkIfExists: true)
+
+    } else if (inputType == 'url') {
+        input_root = fetchRemoteData(Channel.value(params.input)).testDataDir
+
+    } else if (inputType == 'archive') {
+        input_root = extractLocalArchive(Channel.fromPath(params.input)).extractedDir
+    }
+    // Now resolve each folder
+    proteome_folder = resolveFolderParam(input_root, params.proteome_folder, 'proteome')
+    splice_folder   = resolveFolderParam(input_root, params.splice_folder, 'splice', false)
+    hogmap_in       = resolveFolderParam(input_root, params.hogmap_in, 'hogmap_in', false)
+    species_tree    = params.species_tree ?
+                     Channel.fromPath(params.species_tree, type: 'file', checkIfExists: true).first() :
+                     resolveFile(input_root, 'species_tree.nwk')
+    proteomes = proteome_folder.flatMap { dir ->
+        // Use file() to list files, don't create new channels
+        def proteomeDir = file(dir.toString())
+        return proteomeDir.listFiles().findAll { 
+            it.name.endsWith('.fa') || it.name.endsWith('.fasta')
+        } 
+    }
 
     // Static channels
     omamerdb = Channel.fromPath(params.omamer_db)
     notebook = Channel.fromPath("$workflow.projectDir/FastOMA/fastoma_notebook_stat.ipynb", type: "file", checkIfExists: true).first()
 
     // Run the pipeline
     (species_tree_checked, ready_input_check) = check_input(proteome_folder, hogmap_in, species_tree, omamerdb, splice_folder)
-    omamer_input_channel = proteomes
+        omamer_input_channel = proteomes
         .combine(omamerdb)
         .combine(hogmap_in)
         .combine(ready_input_check)

FastOMA/__init__.py

@@ -1,6 +1,6 @@
 
 __packagename__ = "FastOMA"
-__version__ = "0.5.0"
+__version__ = "0.5.1"
 
 import logging
 logger = logging.getLogger("FastOMA")

README.md

@@ -60,7 +60,7 @@ installed.
 ```bash
 nextflow run dessimozlab/FastOMA -profile docker  --input /path/to/in_folder --output_folder /path/to/out_folder 
 ```
-You could also add specific version to be used by adding `-r v0.5.0` to the command line. Without any `-r` argument, 
+You could also add specific version to be used by adding `-r v0.5.1` to the command line. Without any `-r` argument, 
 always the latest available release will be used. With `-r dev` the latest development release can be used.
 
 > [!WARNING]
@@ -99,10 +99,10 @@ There are four ways to run/install FastOMA detailed below:
 The FastOMA workflow can be run directly without any installation using nextflow's ability to fetch a workflow from github. A specific version can be selected by specifying the `-r` option to nextflow to select a specific version of FastOMA:
 
 ```bash
-nextflow run dessimozlab/FastOMA -r v0.5.0 -profile conda 
+nextflow run dessimozlab/FastOMA -r v0.5.1 -profile conda 
 ```
 
-This will fetch version v0.5.0 from github and run the FastOMA workflow using the conda profile. See section [How to run fastOMA](#how-to-run-fastoma). 
+This will fetch version v0.5.1 from github and run the FastOMA workflow using the conda profile. See section [How to run fastOMA](#how-to-run-fastoma). 
 
 ### 2. Cloning the FastOMA repo and running from there
 
@@ -195,7 +195,7 @@ nextflow run FastOMA.nf -profile docker \
     --output_folder myresult/
 ```
 This will use the container that is tagged with the current commit id. Similarly, one could also use 
-`--container_version "0.5.0"` to use the container with version `dessimozlab/fastoma:0.5.0` from dockerhub. Check the latest version on the [DockerHub](https://hub.docker.com/r/dessimozlab/fastoma/tags).
+`--container_version "0.5.1"` to use the container with version `dessimozlab/fastoma:0.5.1` from dockerhub. Check the latest version on the [DockerHub](https://hub.docker.com/r/dessimozlab/fastoma/tags).
 
 ### Singularity
 Since Docker needs administrator privileges (root access), [Singluarity](https://apptainer.org/index.html) (a.k.a Apptainer) is a good alternative. This can be installed using [Conda](https://anaconda.org/conda-forge/singularity) with `conda install conda-forge::singularity`. However, in most of the academic HPC cluster, singluarity is already installed and can be called with `module load`.
@@ -467,7 +467,9 @@ Citation:  Majidian, Sina, Yannis Nevers, Ali Yazdizadeh Kharrazi, Alex Warwick
 
 
 ## Change log
-=======
+- Update  v0.5.1:
+  - Bug with input handling fixed.
+  - upgraded github actions for CI/CD.
 - Update  v0.5.0:
   - renamed input_folder parameter to input. input accepts now also (remote) archive tarball files.
   - better configuration setup (close to nf-core)

conf/test.config

@@ -11,10 +11,4 @@ params {
     omamer_db             = "${projectDir}/testdata/test.h5"
     input                 = "${projectDir}/testdata/in_folder"
     report                = true
-
-    // derived parameters
-    proteome_folder       = "${params.input}/proteome"
-    hogmap_in             = "${params.input}/hogmap_in"
-    splice_folder         = "${params.input}/splice"
-    species_tree          = "${params.input}/species_tree.nwk"
 }

nextflow.config

@@ -8,7 +8,7 @@ manifest {
   nextflowVersion = ">=22.10.4"
   defaultBranch = "main"
   doi = "10.1101/2024.01.29.577392"
-  version = "0.5.0"
+  version = "0.5.1"
   contributors = [
         [
             name: 'Sina Majidian',
@@ -32,10 +32,10 @@ params {
   // these can be overridden by the user on the command line
   input           = null
   // input sub-folders, can also be somewhere else
-  proteome_folder = "${params.input}/proteome"
-  hogmap_in       = "${params.input}/hogmap_in"
-  splice_folder   = "${params.input}/splice"
-  species_tree    = "${params.input}/species_tree.nwk"
+  proteome_folder = null
+  hogmap_in       = null
+  splice_folder   = null
+  species_tree    = null
   // cache path for (remote) archive input files
   test_data_cache = null
   // Keep deprecated parameter for backward compatibility
@@ -51,7 +51,7 @@ params {
 
   // container settings
   container_name = "dessimozlab/fastoma"
-  container_version = "0.5.0"
+  container_version = "0.5.1"
 
   // OMAmer database for mapping to precomputed HOGs
   omamer_db = "https://omabrowser.org/All/LUCA.h5"

nextflow_schema.json

@@ -9,7 +9,7 @@
       "title": "Input options",
       "type": "object",
       "description": "Define where the pipeline should find input data ",
-      "required": ["input", "species_tree"],
+      "required": ["input"],
       "properties": {
         "input": {
           "type": "string",
@@ -230,7 +230,7 @@
         },
         "container_version": {
           "type": "string",
-          "default": "0.5.0"
+          "default": "0.5.1"
         }
       }
     }