feat!: typed PRA#run

Snakefile

@@ -25,7 +25,7 @@ algorithm_params = _config.config.algorithm_params
 algorithm_directed = _config.config.algorithm_directed
 pca_params = _config.config.pca_params
 hac_params = _config.config.hac_params
-FRAMEWORK = _config.config.container_settings.framework
+container_settings = _config.config.container_settings
 include_aggregate_algo_eval = _config.config.analysis_include_evaluation_aggregate_algo
 
 # Return the dataset or gold_standard dictionary from the config file given the label
@@ -273,16 +273,12 @@ rule reconstruct:
     run:
         # Create a copy so that the updates are not written to the parameters logfile
         params = reconstruction_params(wildcards.algorithm, wildcards.params).copy()
-        # Add the input files
-        params.update(dict(zip(runner.get_required_inputs(wildcards.algorithm), *{input}, strict=True)))
-        # Add the output file
-        # All run functions can accept a relative path to the output file that should be written that is called 'output_file'
-        params['output_file'] = output.pathway_file
-        # Remove the default placeholder parameter added for algorithms that have no parameters
-        if 'spras_placeholder' in params:
-            params.pop('spras_placeholder')
-        params['container_framework'] = FRAMEWORK
-        runner.run(wildcards.algorithm, params)
+        # Declare the input files as a dictionary.
+        inputs = dict(zip(runner.get_required_inputs(wildcards.algorithm), *{input}, strict=True))
+        # Remove the _spras_run_name parameter added for keeping track of the run name for parameters.yml
+        if '_spras_run_name' in params:
+            params.pop('_spras_run_name')
+        runner.run(wildcards.algorithm, inputs, output.pathway_file, params, container_settings)
 
 # Original pathway reconstruction output to universal output
 # Use PRRunner as a wrapper to call the algorithm-specific parse_output
@@ -313,7 +309,7 @@ rule viz_cytoscape:
     output: 
         session = SEP.join([out_dir, '{dataset}-cytoscape.cys'])
     run:
-        cytoscape.run_cytoscape(input.pathways, output.session, FRAMEWORK)
+        cytoscape.run_cytoscape(input.pathways, output.session, container_settings)
 
 
 # Write a single summary table for all pathways for each dataset

config/config.yaml

@@ -3,6 +3,7 @@
 # The length of the hash used to identify a parameter combination
 hash_length: 7
 
+# Collection of container options
 containers:
   # Specify the container framework used by each PRM wrapper. Valid options include:
   # - docker (default if not specified)
@@ -28,17 +29,17 @@ containers:
     # For example, "reedcompbio" if the image is available as docker.io/reedcompbio/allpairs
     owner: reedcompbio
 
-# Enabling profiling adds a file called 'usage-profile.tsv' to the output directory of each algorithm.
-# The contents of this file describe the CPU utilization and peak memory consumption of the algorithm
-# as seen by its runtime container.
-# NOTE: Profiling is currently supported only when the container framework is set to apptainer/singularity
-#       and when the host system supports the 'cgroup' filesystem.
-#       When profiling via HTCondor, this assumes the current process is already in a two-level nested cgroup
-#       (introduced in HTCondor 24.8.0). To specify a minimum HTCondor version, use the following `requirements`
-#       expression:
-#
-#       requirements = versionGE(split(Target.CondorVersion)[1], "24.8.0") && (isenforcingdiskusage =!= true)
-enable_profiling: false
+  # Enabling profiling adds a file called 'usage-profile.tsv' to the output directory of each algorithm.
+  # The contents of this file describe the CPU utilization and peak memory consumption of the algorithm
+  # as seen by its runtime container.
+  # NOTE: Profiling is currently supported only when the container framework is set to apptainer/singularity
+  #       and when the host system supports the 'cgroup' filesystem.
+  #       When profiling via HTCondor, this assumes the current process is already in a two-level nested cgroup
+  #       (introduced in HTCondor 24.8.0). To specify a minimum HTCondor version, use the following `requirements`
+  #       expression:
+  #
+  #       requirements = versionGE(split(Target.CondorVersion)[1], "24.8.0") && (isenforcingdiskusage =!= true)
+  enable_profiling: false
 
 # This list of algorithms should be generated by a script which checks the filesystem for installs.
 # It shouldn't be changed by mere mortals. (alternatively, we could add a path to executable for each algorithm
@@ -60,23 +61,23 @@ enable_profiling: false
 
 algorithms:
   - name: "pathlinker"
-    params:
-      include: true
+    include: true
+    runs:
       run1:
         k: range(100,201,100)
 
   - name: "omicsintegrator1"
-    params:
-      include: true
+    include: true
+    runs:
       run1:
         b: [5, 6]
         w: np.linspace(0,5,2)
         d: 10
         dummy_mode: "file" # Or "terminals", "all", "others"
 
   - name: "omicsintegrator2"
-    params:
-      include: true
+    include: true
+    runs:
       run1:
         b: 4
         g: 0
@@ -85,52 +86,50 @@ algorithms:
         g: 3
 
   - name: "meo"
-    params:
-      include: true
+    include: true
+    runs:
       run1:
         max_path_length: 3
-        local_search: "Yes"
+        local_search: true
         rand_restarts: 10
 
   - name: "mincostflow"
-    params:
-      include: true
+    include: true
+    runs:
       run1:
-        flow: 1 # The flow must be an int
+        flow: 1
         capacity: 1
 
   - name: "allpairs"
-    params:
-      include: true
+    include: true
 
   - name: "domino"
-    params:
-      include: true
+    include: true
+    runs:
       run1:
         slice_threshold: 0.3
         module_threshold: 0.05
 
   - name: "strwr"
-    params:
-      include: true
+    include: true
+    runs:
       run1:
         alpha: [0.85]
         threshold: [100, 200]
 
   - name: "rwr"
-    params:
-      include: true
+    include: true
+    runs:
       run1:
         alpha: [0.85]
         threshold: [100, 200]
 
   - name: "bowtiebuilder"
-    params:
-      include: true
+    include: true
 
   - name: "responsenet"
-    params:
-      include: true
+    include: true
+    runs:
       run1:
         gamma: [10]
 

config/egfr.yaml

@@ -1,4 +1,3 @@
-# The length of the hash used to identify a parameter combination
 hash_length: 7
 
 containers:
@@ -29,108 +28,83 @@ containers:
 
 algorithms:
   - name: pathlinker
-    params:
-      include: true
+    include: true
+    runs:
       run1:
         k:
           - 10
           - 20
           - 70
   - name: omicsintegrator1
-    params:
-      include: true
+    include: true
+    runs:
       run1:
         b:
           - 0.55
           - 2
           - 10
-        d:
-          - 10
-        g:
-          - 1e-3
-        r:
-          - 0.01
-        w:
-          - 0.1
-        mu:
-          - 0.008
+        d: 10
+        g: 1e-3
+        r: 0.01
+        w: 0.1
+        mu: 0.008
         dummy_mode: ["file"]
   - name: omicsintegrator2
-    params:
-      include: true
+    include: true
+    runs:
       run1:
-        b:
-          - 4
-        g:
-          - 0
+        b: 4
+        g: 0
       run2:
-        b:
-          - 2
-        g:
-          - 3
+        b: 2
+        g: 3
   - name: meo
-    params:
-      include: true
+    include: true
+    runs:
       run1:
-        local_search:
-          - "Yes"
-        max_path_length:
-          - 3
-        rand_restarts:
-          - 10
+        local_search: true
+        max_path_length: 3
+        rand_restarts: 10
       run2:
-        local_search:
-          - "No"
-        max_path_length:
-          - 2
-        rand_restarts:
-          - 10
+        local_search: false
+        max_path_length: 2
+        rand_restarts: 10
   - name: allpairs
-    params:
-      include: true
+    include: true
   - name: domino
-    params:
-      include: true
+    include: true
+    runs:
       run1:
-        slice_threshold:
-          - 0.3
-        module_threshold:
-          - 0.05
+        slice_threshold: 0.3
+        module_threshold: 0.05
   - name: mincostflow
-    params:
-      include: true
+    include: true
+    runs:
       run1:
-        capacity:
-          - 15
-        flow:
-          - 80
+        capacity: 15
+        flow: 80
       run2:
-        capacity:
-          - 1
-        flow:
-          - 6
+        capacity: 1
+        flow: 6
       run3:
-        capacity:
-          - 5
-        flow:
-          - 60
+        capacity: 5
+        flow: 60
   - name: "strwr"
-    params:
-      include: true
+    include: true
+    runs:
       run1:
         alpha: [0.85]
         threshold: [100, 200]
 
   - name: "rwr"
-    params:
-      include: true
+    include: true
+    runs:
       run1:
         alpha: [0.85]
         threshold: [100, 200]
 
   - name: "bowtiebuilder"
-    params:
-      include: false
+    include: false
 datasets:
   - data_dir: input
     edge_files: