Cytoscape

PRRunner.py

@@ -1,11 +1,13 @@
 import Dataset
-
+import os
 # supported algorithm imports
 from src.meo import MEO as meo
 from src.omicsintegrator1 import OmicsIntegrator1 as omicsintegrator1
 from src.omicsintegrator2 import OmicsIntegrator2 as omicsintegrator2
 from src.pathlinker import PathLinker as pathlinker
 
+ROOT = os.path.dirname(os.path.abspath(__file__))
+
 def run(algorithm, params):
     """
     A generic interface to the algorithm-specific run functions
@@ -67,4 +69,7 @@ def parse_output(algorithm, raw_pathway_file, standardized_pathway_file):
         algorithm_runner = globals()[algorithm.lower()]
     except KeyError:
         raise NotImplementedError(f'{algorithm} is not currently supported')
+
+    with open(os.path.join(ROOT, 'output', 'pathways.txt'), 'a') as f:
+        f.write(f"{standardized_pathway_file}\n")
     return algorithm_runner.parse_output(raw_pathway_file, standardized_pathway_file)

Snakefile

@@ -2,13 +2,17 @@ import os
 import PRRunner
 import shutil
 import yaml
+import sys
 from src.util import process_config
 from src.analysis.summary import summary
 from src.analysis.viz import graphspace
 
+from src.analysis.cytoscape import cytoscape
+
 # 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
 SEP = '/'
+ROOT = os.path.abspath(__file__)
 
 wildcard_constraints:
     params="params-\w+"
@@ -66,6 +70,9 @@ def make_final_input(wildcards):
         # add graph and style JSON files.
         final_input.extend(expand('{out_dir}{sep}{dataset}-{algorithm_params}{sep}gs.json',out_dir=out_dir,sep=SEP,dataset=dataset_labels,algorithm_params=algorithms_with_params))
         final_input.extend(expand('{out_dir}{sep}{dataset}-{algorithm_params}{sep}gsstyle.json',out_dir=out_dir,sep=SEP,dataset=dataset_labels,algorithm_params=algorithms_with_params))
+
+    if config["analysis"]["cytoscape"]["include"]:
+        final_input.extend(expand('{out_dir}{sep}cytoscape-session.cys',out_dir=out_dir,sep=SEP))
 
     if len(final_input) == 0:
         # No analysis added yet, so add reconstruction output files if they exist.
@@ -76,6 +83,7 @@ def make_final_input(wildcards):
     final_input.extend(expand('{out_dir}{sep}logs{sep}parameters-{algorithm_params}.yaml', out_dir=out_dir, sep=SEP, algorithm_params=algorithms_with_params))
     final_input.extend(expand('{out_dir}{sep}logs{sep}datasets-{dataset}.yaml', out_dir=out_dir, sep=SEP, dataset=dataset_labels))
 
+
     return final_input
 
 # A rule to define all the expected outputs from all pathway reconstruction
@@ -219,6 +227,14 @@ rule viz_graphspace:
     run:
         graphspace.write_json(input.standardized_file,output.graph_json,output.style_json,directed=algorithm_directed[wildcards.algorithm])
 
+rule viz_cytoscape:
+    input: pathways = expand('{out_dir}{sep}{dataset}-{algorithm_params}{sep}pathway.txt', out_dir=out_dir, sep=SEP, dataset=dataset_labels, algorithm_params=algorithms_with_params)
+
+    output: 
+        session = SEP.join([out_dir, 'cytoscape-session.cys'])
+    run:
+        cytoscape.run_cytoscape_container(input.pathways, out_dir)
+
 # Remove the output directory
 rule clean:
     shell: f'rm -rf {out_dir}'

config/config.yaml

@@ -28,8 +28,8 @@
  algorithms:
         - name: "pathlinker"
           params:
-                include: false
-                directed: true
+                include: true
+                directed: True
                 run1:
                     k: range(100,201,100)
 
@@ -56,7 +56,7 @@
                     g: [3]
         - name: "meo"
           params:
-                include: false
+                include: true
                 directed: true
                 run1:
                     max_path_length: [3]
@@ -107,3 +107,7 @@
         graphspace:
 
           include: true
+
+        cytoscape:
+
+          include: true

config/config_cyto.yaml

@@ -0,0 +1,113 @@
+ # Global workflow control
+
+ # The length of the hash used to identify a parameter combination
+ hash_length: 7
+ # If true, use Singularity instead of Docker
+ # Singularity support is only available on Unix
+ singularity: 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
+ # in the list to reduce the number of assumptions of the program at the cost of making the config a little more involved)
+ # Each algorithm has an 'include' parameter. By toggling 'include' to true/false the user can change
+ # which algorithms are run in a given experiment.
+ #
+ # algorithm-specific parameters are embedded in lists so that users can specify multiple. If multiple
+ # parameters are specified then the algorithm will be run as many times as needed to cover all parameter
+ # combinations. For instance if we have the following:
+ # - name: "myAlg"
+ #   params:
+ #         include: true
+ #         directed: true
+ #         a: [1,2]
+ #         b: [0.5,0.75]
+ #
+ # then myAlg will be run on (a=1,b=0.5),(a=1,b=0.75),(a=2,b=0.5), and (a=2,b=0,75). Pretty neat, but be
+ # careful: too many parameters might make your runs take a long time.
+
+ algorithms:
+        - name: "pathlinker"
+          params:
+                include: true
+                directed: true
+                run1:
+                    k: range(100,201,100)
+
+        - name: "omicsintegrator1"
+          params:
+                include: true
+                directed: false
+                run1:
+                    r: [5]
+                    b: [5, 10]
+                    w: [5]
+                    g: [3]
+                    d: [10]
+
+        - name: "omicsintegrator2"
+          params:
+                include: false
+                directed: false
+                run1:
+                    b: [4]
+                    g: [0]
+                run2:
+                    b: [2]
+                    g: [3]
+        - name: "meo"
+          params:
+                include: true
+                directed: true
+                run1:
+                    max_path_length: [3]
+                    local_search: ["Yes"]
+                    rand_restarts: [10]
+
+ # Here we specify which pathways to run and other file location information.
+ # DataLoader.py can currently only load a single dataset
+ # Assume that if a dataset label does not change, the lists of associated input files do not change
+ datasets:
+     -
+       label: data0
+       node_files: ["node-prizes.txt", "sources.txt", "targets.txt"]
+       # DataLoader.py can currently only load a single edge file, which is the primary network
+       edge_files: ["network.txt"]
+       # Placeholder
+       other_files: []
+       # Relative path from the spras directory
+       data_dir: "input"
+     -
+       label: data1
+       # Reuse some of the same sources file as 'data0' but different network and targets
+       node_files: ["sources.txt", "alternative-targets.txt"]
+       edge_files: ["alternative-network.txt"]
+       other_files: []
+       # Relative path from the spras directory
+       data_dir: "input"
+
+ # If we want to reconstruct then we should set run to true.
+ # TODO: if include is true above but run is false here, algs are not run.
+ # is this the behavior we want?
+ reconstruction_settings:
+
+         #set where everything is saved
+         locations:
+
+                #place the save path here
+                # TODO move to global
+                reconstruction_dir: "output"
+
+         run: true
+
+ analysis:
+        summary:
+
+          include: true
+
+        graphspace:
+
+          include: true
+
+        cytoscape:
+
+          include: true

config/egfr.yaml

@@ -0,0 +1,84 @@
+# The length of the hash used to identify a parameter combination
+hash_length: 7
+
+# If true, use Singularity instead of Docker
+# Singularity support is only available on Unix
+singularity: false
+
+algorithms: 
+  - 
+    name: pathlinker
+    params: 
+      directed: true
+      include: true
+      run1: 
+        k: 
+          - 20
+          - 200
+  - 
+    name: omicsintegrator1
+    params: 
+      directed: false
+      include: true
+      run1: 
+        b: 
+          - 0.55
+          - 2
+          - 10
+        d: 
+          - 10
+        g: 
+          - 1e-3
+        r: 
+          - 0.01
+        w: 
+          - 0.5
+        mu:
+          - 0.008
+  - 
+    name: omicsintegrator2
+    params: 
+      directed: false
+      include: false
+      run1: 
+        b: 
+          - 4
+        g: 
+          - 0
+      run2: 
+        b: 
+          - 2
+        g: 
+          - 3
+  - 
+    name: meo
+    params: 
+      directed: true
+      include: false
+      run1: 
+        local_search: 
+          - "Yes"
+        max_path_length: 
+          - 3
+        rand_restarts: 
+          - 10
+datasets: 
+  - 
+    data_dir: input
+    edge_files: 
+      - phosphosite-irefindex13.0-uniprot.txt
+    label: tps-egfr
+    node_files: 
+      - tps-egfr-prizes.txt
+    other_files: []
+reconstruction_settings: 
+  locations: 
+    reconstruction_dir: output/egfr
+  run: true
+analysis: 
+  graphspace: 
+    include: false
+  summary: 
+    include: true
+  cytoscape:
+    include: true