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+"
@@ -66,16 +70,21 @@ 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.
         # (if analysis is specified, these should be implicitly run).
+        output = expand('{out_dir}{sep}{dataset}-{algorithm_params}{sep}pathway.txt', 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}pathway.txt', out_dir=out_dir, sep=SEP, dataset=dataset_labels, algorithm_params=algorithms_with_params))
 
     # Create log files for the parameters and datasets
     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 +228,9 @@ rule viz_graphspace:
     run:
         graphspace.write_json(input.standardized_file,output.graph_json,output.style_json,directed=algorithm_directed[wildcards.algorithm])
 
+        # just run local cytoscape with graphspace for now
+        cytoscape.viz_cytoscape_local(input.standardized_file, directed=algorithm_directed[wildcards.algorithm])
+
 # 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)
 

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: false
+                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: false
+                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

cytoscape.py

@@ -0,0 +1,4 @@
+from src.analysis.cytoscape.src import cytoscape_util
+
+if __name__ == '__main__':
+    cytoscape_util.main()

cytoscape_env.yml

@@ -0,0 +1,9 @@
+name: py2cytoscape_env
+channels:
+  - conda-forge
+  - defaults
+dependencies:
+  - python=3.6
+  - pip=20.0
+  - pip:
+      - py2cytoscape==0.7.1

full_dag.gv

@@ -0,0 +1,50 @@
+digraph snakemake_dag {
+    graph[bgcolor=white, margin=0];
+    node[shape=box, style=rounded, fontname=sans,                 fontsize=10, penwidth=2];
+    edge[penwidth=2, color=grey];
+	0[label = "all", color = "0.20 0.6 0.85", style="rounded,dashed"];
+	1[label = "summarize", color = "0.40 0.6 0.85", style="rounded,dashed"];
+	2[label = "parse_output", color = "0.07 0.6 0.85", style="rounded,dashed"];
+	3[label = "summarize", color = "0.40 0.6 0.85", style="rounded,dashed"];
+	4[label = "parse_output", color = "0.07 0.6 0.85", style="rounded,dashed"];
+	5[label = "summarize", color = "0.40 0.6 0.85", style="rounded,dashed"];
+	6[label = "parse_output", color = "0.07 0.6 0.85", style="rounded,dashed"];
+	7[label = "summarize", color = "0.40 0.6 0.85", style="rounded,dashed"];
+	8[label = "parse_output", color = "0.07 0.6 0.85", style="rounded,dashed"];
+	9[label = "viz_graphspace", color = "0.60 0.6 0.85", style="rounded,dashed"];
+	10[label = "viz_graphspace", color = "0.60 0.6 0.85", style="rounded,dashed"];
+	11[label = "viz_graphspace", color = "0.60 0.6 0.85", style="rounded,dashed"];
+	12[label = "viz_graphspace", color = "0.60 0.6 0.85", style="rounded,dashed"];
+	13[label = "log_parameters\nalgorithm: omicsintegrator1\nparams: params-J6Q3GKS", color = "0.53 0.6 0.85", style="rounded,dashed"];
+	14[label = "log_parameters\nalgorithm: omicsintegrator1\nparams: params-O4PE2OB", color = "0.53 0.6 0.85", style="rounded,dashed"];
+	15[label = "log_datasets\ndataset: data0", color = "0.47 0.6 0.85", style="rounded,dashed"];
+	16[label = "log_datasets\ndataset: data1", color = "0.47 0.6 0.85", style="rounded,dashed"];
+	17[label = "reconstruct\nalgorithm: omicsintegrator1\ndataset: data0\nparams: params-J6Q3GKS", color = "0.00 0.6 0.85", style="rounded,dashed"];
+	18[label = "reconstruct\nalgorithm: omicsintegrator1\ndataset: data0\nparams: params-O4PE2OB", color = "0.00 0.6 0.85", style="rounded,dashed"];
+	19[label = "reconstruct\nalgorithm: omicsintegrator1\ndataset: data1\nparams: params-J6Q3GKS", color = "0.00 0.6 0.85", style="rounded,dashed"];
+	20[label = "reconstruct\nalgorithm: omicsintegrator1\ndataset: data1\nparams: params-O4PE2OB", color = "0.00 0.6 0.85", style="rounded,dashed"];
+	1 -> 0
+	3 -> 0
+	5 -> 0
+	7 -> 0
+	9 -> 0
+	10 -> 0
+	11 -> 0
+	12 -> 0
+	13 -> 0
+	14 -> 0
+	15 -> 0
+	16 -> 0
+	2 -> 1
+	17 -> 2
+	4 -> 3
+	18 -> 4
+	6 -> 5
+	19 -> 6
+	8 -> 7
+	20 -> 8
+	2 -> 9
+	4 -> 10
+	6 -> 11
+	8 -> 12
+}