feat!: typed PRA#run

Snakefile

@@ -22,7 +22,6 @@ _config.init_global(config)
 
 out_dir = _config.config.out_dir
 algorithm_params = _config.config.algorithm_params
-algorithm_directed = _config.config.algorithm_directed
 pca_params = _config.config.pca_params
 hac_params = _config.config.hac_params
 container_settings = _config.config.container_settings
@@ -273,16 +272,12 @@ 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_settings'] = container_settings
-        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

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)
@@ -60,23 +61,23 @@ containers:
 
 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:

docker-wrappers/SPRAS/example_config.yaml

@@ -79,7 +79,7 @@ algorithms:
       include: true
       run1:
         max_path_length: [3]
-        local_search: ["Yes"]
+        local_search: [true]
         rand_restarts: [10]
 
   - name: "mincostflow"

docs/_static/config/intermediate.yaml

@@ -52,7 +52,7 @@ algorithms:
     params:
       include: true
       run1:
-        local_search: ["Yes", "No"]
+        local_search: [true, false]
         max_path_length: [2, 3]
         rand_restarts: 10
   - name: allpairs

docs/contributing/index.rst

@@ -181,6 +181,8 @@ wrapper functions for the Local Neighborhood algorithm. Use
 Call the new class within ``local_neighborhood.py``
 ``LocalNeighborhood`` and set ``__all__`` so the class can be
 `imported <https://docs.python.org/3/tutorial/modules.html#importing-from-a-package>`__.
+Make sure to specify the type of parameters passed in to ``LocalNeighborhood`` as ``Empty``
+(see ``AllPairs`` for an example of this.)
 Specify the list of ``required_input`` files to be ``network`` and
 ``nodes``, and set the ``dois`` property to be an empty list. These
 entries are used to tell Snakemake what input files should be present
@@ -242,7 +244,7 @@ the format ``<vertex1>|<vertex2>``, which also differs from the
 ``omicsintegrator1.py`` example. ``spras/dataset.py`` provides functions
 that provide access to node information and the interactome (edge list).
 
-Implement the ``run`` function, following the PathLinker example. The
+Implement the ``run`` function, following the AllPairs example. The
 ``prepare_volume`` utility function is needed to prepare the network and
 nodes input files to be mounted and used inside the container. It is
 also used to prepare the path for the output file, which is different

docs/prms/meo.rst

@@ -9,6 +9,6 @@ MEO takes in three optional parameters:
 
 * max_path_length: The maximal path (from any source to any target) lengths to return when orienting the graph (note: paths
   may contain duplicate vertices, but never duplicate edges.)
-* local_search: a "Yes"/"No" parameter that enables MEO's local search functionality. See "Improving approximations with local search" in
-  the associated paper for more information. This should almost always be yes.
+* local_search: a boolean parameter that enables MEO's local search functionality. See "Improving approximations with local search" in
+  the associated paper for more information. This should almost always be true.
 * rand_restarts: the number (int) of random restarts to use.

spras/allpairs.py

@@ -2,6 +2,7 @@
 from pathlib import Path
 
 from spras.config.container_schema import ProcessedContainerSettings
+from spras.config.util import Empty
 from spras.containers import prepare_volume, run_container_and_log
 from spras.dataset import Dataset
 from spras.interactome import (
@@ -15,7 +16,7 @@
 __all__ = ['AllPairs']
 
 
-class AllPairs(PRM):
+class AllPairs(PRM[Empty]):
     required_inputs = ['nodetypes', 'network', 'directed_flag']
     dois = []
 
@@ -70,27 +71,19 @@ def generate_inputs(data: Dataset, filename_map):
                                       header=["#Interactor1", "Interactor2", "Weight"])
 
     @staticmethod
-    def run(nodetypes=None, network=None, directed_flag=None, output_file=None, container_settings=None):
-        """
-        Run All Pairs Shortest Paths with Docker
-        @param nodetypes: input node types with sources and targets (required)
-        @param network: input network file (required)
-        @param container_settings: configure the container runtime
-        @param output_file: path to the output pathway file (required)
-        """
+    def run(inputs, output_file, args=None, container_settings=None):
         if not container_settings: container_settings = ProcessedContainerSettings()
-        if not nodetypes or not network or not output_file or not directed_flag:
-            raise ValueError('Required All Pairs Shortest Paths arguments are missing')
+        AllPairs.validate_required_run_args(inputs)
 
         work_dir = '/apsp'
 
         # Each volume is a tuple (src, dest)
         volumes = list()
 
-        bind_path, node_file = prepare_volume(nodetypes, work_dir, container_settings)
+        bind_path, node_file = prepare_volume(inputs["nodetypes"], work_dir, container_settings)
         volumes.append(bind_path)
 
-        bind_path, network_file = prepare_volume(network, work_dir, container_settings)
+        bind_path, network_file = prepare_volume(inputs["network"], work_dir, container_settings)
         volumes.append(bind_path)
 
         # Create the parent directories for the output file if needed
@@ -104,7 +97,7 @@ def run(nodetypes=None, network=None, directed_flag=None, output_file=None, cont
                    '--network', network_file,
                    '--nodes', node_file,
                    '--output', mapped_out_file]
-        if Path(directed_flag).read_text().strip() == "true":
+        if Path(inputs["directed_flag"]).read_text().strip() == "true":
             command.append("--directed")
 
         container_suffix = "allpairs:v4"