feat: seeds

CONTRIBUTING.md

@@ -142,8 +142,6 @@ and your editor's interpreter is set to using the SPRAS environment over the bas
 Note the behaviors of the `request_node_columns` function when there are missing values in that column of the node table and when multiple columns are requested.
 `request_node_columns` always returns the `NODEID` column in addition to the requested columns.
 
-Note: If you encounter a `'property' object is not iterable` error arising from inside the Snakefile, this means that `required_inputs` is not set. This is because when `required_inputs` is not set inside an algorithm wrapper, it falls back to the underlying unimplemented function inside the PRM base class, which, while it is marked as a property function, is non-static; therefore, when the runner utility class tries to dynamically fetch `required_inputs` with reflection, it ends up grabbing the `property` function instead of the underlying error, and tries to iterate over it (since `required_inputs` is usually a list.)
-
 Now implement the `generate_inputs` function.
 Start by inspecting the `omicsintegrator1.py` example, but note the differences in the expected file formats generated for the two algorithms with respect to the header rows and node prize column.
 The selected nodes should be any node in the dataset that has a prize set, any node that is active, any node that is a source, or any node that is a target.

Snakefile

@@ -5,7 +5,7 @@ import yaml
 from spras.dataset import Dataset
 from spras.evaluation import Evaluation
 from spras.analysis import ml, summary, cytoscape
-import spras.config as _config
+import spras.config.config as _config
 
 # Snakemake updated the behavior in the 6.5.0 release https://github.com/snakemake/snakemake/pull/1037
 # and using the wrong separator prevents Snakemake from matching filenames to the rules that can produce them
@@ -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_framework
+FRAMEWORK = _config.config.container_settings.framework
 
 # Return the dataset or gold_standard dictionary from the config file given the label
 def get_dataset(_datasets, label):

config/config.yaml

@@ -1,32 +1,36 @@
+# yaml-language-server: $schema=./schema.json
+
 # Global workflow control
 
 # The length of the hash used to identify a parameter combination
 hash_length: 7
 
-# Specify the container framework used by each PRM wrapper. Valid options include:
-# - docker (default if not specified)
-# - singularity -- Also known as apptainer, useful in HPC/HTC environments where docker isn't allowed
-# - dsub -- experimental with limited support, used for running on Google Cloud with the All of Us cloud environment.
-#   - There is no support for other environments at the moment.
-container_framework: docker
-
-# Only used if container_framework is set to singularity, this will unpack the singularity containers
-# to the local filesystem. This is useful when PRM containers need to run inside another container,
-# such as would be the case in an HTCondor/OSPool environment.
-# NOTE: This unpacks singularity containers to the local filesystem, which will take up space in a way
-# that persists after the workflow is complete. To clean up the unpacked containers, the user must
-# manually delete them. For convenience, these unpacked files will exist in the current working directory
-# under `unpacked`.
-unpack_singularity: false
-
-# Allow the user to configure which container registry containers should be pulled from
-# Note that this assumes container names are consistent across registries, and that the
-# registry being passed doesn't require authentication for pull actions
-container_registry:
-  base_url: docker.io
-  # The owner or project of the registry
-  # For example, "reedcompbio" if the image is available as docker.io/reedcompbio/allpairs
-  owner: reedcompbio
+# Collection of container options
+containers:
+  # Specify the container framework used by each PRM wrapper. Valid options include:
+  # - docker (default if not specified)
+  # - singularity -- Also known as apptainer, useful in HPC/HTC environments where docker isn't allowed
+  # - dsub -- experimental with limited support, used for running on Google Cloud with the All of Us cloud environment.
+  #   - There is no support for other environments at the moment.
+  framework: docker
+
+  # Only used if container_framework is set to singularity, this will unpack the singularity containers
+  # to the local filesystem. This is useful when PRM containers need to run inside another container,
+  # such as would be the case in an HTCondor/OSPool environment.
+  # NOTE: This unpacks singularity containers to the local filesystem, which will take up space in a way
+  # that persists after the workflow is complete. To clean up the unpacked containers, the user must
+  # manually delete them. For convenience, these unpacked files will exist in the current working directory
+  # under `unpacked`.
+  unpack_singularity: false
+
+  # Allow the user to configure which container registry containers should be pulled from
+  # Note that this assumes container names are consistent across registries, and that the
+  # registry being passed doesn't require authentication for pull actions
+  registry:
+    base_url: docker.io
+    # The owner or project of the registry
+    # For example, "reedcompbio" if the image is available as docker.io/reedcompbio/allpairs
+    owner: reedcompbio
 
 # 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
@@ -48,23 +52,23 @@ container_registry:
 
 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
@@ -73,48 +77,46 @@ 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
         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
 
 # Here we specify which pathways to run and other file location information.
 # DataLoader.py can currently only load a single dataset
@@ -164,8 +166,6 @@ reconstruction_settings:
     # TODO move to global
     reconstruction_dir: "output"
 
-  run: true
-
 analysis:
   # Create one summary per pathway file and a single summary table for all pathways for each dataset
   summary:

config/egfr.yaml

@@ -1,116 +1,76 @@
-# The length of the hash used to identify a parameter combination
-hash_length: 7
-
-# Specify the container framework used by each PRM wrapper. Valid options include:
-# - docker (default if not specified)
-# - singularity -- Also known as apptainer, useful in HPC/HTC environments where docker isn't allowed
-# - dsub -- experimental with limited support, used for running on Google Cloud
-container_framework: docker
-
-# Only used if container_framework is set to singularity, this will unpack the singularity containers
-# to the local filesystem. This is useful when PRM containers need to run inside another container,
-# such as would be the case in an HTCondor/OSPool environment.
-# NOTE: This unpacks singularity containers to the local filesystem, which will take up space in a way
-# that persists after the workflow is complete. To clean up the unpacked containers, the user must
-# manually delete them.
-unpack_singularity: false
+# yaml-language-server: $schema=./schema.json
 
-# Allow the user to configure which container registry containers should be pulled from
-# Note that this assumes container names are consistent across registries, and that the
-# registry being passed doesn't require authentication for pull actions
-container_registry:
-  base_url: docker.io
-  # The owner or project of the registry
-  # For example, "reedcompbio" if the image is available as docker.io/reedcompbio/allpairs
-  owner: reedcompbio
+hash_length: 7
+containers:
+  framework: docker
+  unpack_singularity: false
+  registry:
+    base_url: docker.io
+    owner: reedcompbio
 
 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
 datasets:
   - data_dir: input
     edge_files:
@@ -129,7 +89,6 @@ gold_standards:
 reconstruction_settings:
   locations:
     reconstruction_dir: output/egfr
-  run: true
 analysis:
   cytoscape:
     include: true