adding local neighborhood

.github/workflows/test-spras.yml

@@ -83,6 +83,7 @@ jobs:
         docker pull reedcompbio/mincostflow:latest
         docker pull reedcompbio/allpairs:latest
         docker pull reedcompbio/domino:latest
+        docker pull sumedhars/local-neighborhood:latest
     - name: Build Omics Integrator 1 Docker image
       uses: docker/build-push-action@v1
       with:
@@ -155,6 +156,15 @@ jobs:
         tags: v2
         cache_froms: reedcompbio/py4cytoscape:v2
         push: false
+    - name: Build Local Neighborhood Docker image
+      uses: docker/build-push-action@v1
+      with:
+        path: docker-wrappers/LocalNeighborhood/.
+        dockerfile: docker-wrappers/LocalNeighborhood/Dockerfile
+        repository: sumedhars/local-neighborhood
+        tags: v2
+        cache_froms: sumedhars/local-neighborhood:latest
+        push: false
 
   # Run pre-commit checks on source files
   pre-commit:

config/config.yaml

@@ -14,15 +14,15 @@ 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
+   owner: sumedhars
 
 # 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
+# algorithm-specific parsameters 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"
@@ -43,15 +43,15 @@ algorithms:
 
       - name: "omicsintegrator1"
         params:
-              include: true
+              include: false
               run1:
                   b: [5, 6]
                   w: np.linspace(0,5,2)
                   d: [10]
 
       - name: "omicsintegrator2"
         params:
-              include: true
+              include: false
               run1:
                   b: [4]
                   g: [0]
@@ -61,29 +61,33 @@ algorithms:
 
       - name: "meo"
         params:
-              include: true
+              include: false
               run1:
                   max_path_length: [3]
                   local_search: ["Yes"]
                   rand_restarts: [10]
 
       - name: "mincostflow"
         params:
-              include: true
+              include: false
               run1:
                   flow: [1] # The flow must be an int
                   capacity: [1]
 
       - name: "allpairs"
         params:
-              include: true
+              include: false
 
       - name: "domino"
         params:
-              include: true
+              include: false
               run1:
                   slice_threshold: [0.3]
                   module_threshold: [0.05]
+
+      - name: "localneighborhood"
+        params:
+              include: true
 
 
 # Here we specify which pathways to run and other file location information.

docker-wrappers/LocalNeighborhood/Dockerfile

@@ -1 +1,14 @@
 # Create a Docker image for the Local Neighborhood algorithm here
+
+# Local Neighborhood wrapper
+
+FROM python:3.12.3-alpine3.20
+
+WORKDIR /LocalNeighborhood
+
+# Copy the py file to the working directory
+COPY local_neighborhood.py .
+
+# Copy the data subfolder to the working directory
+COPY ln-network.txt .
+COPY ln-nodes.txt .

docker-wrappers/LocalNeighborhood/ln-bad-network.txt

@@ -0,0 +1,5 @@
+A|B|E
+C|B
+C|D
+D|E
+A|E

docker-wrappers/LocalNeighborhood/ln-network.txt

@@ -0,0 +1,5 @@
+A|B
+C|B
+C|D
+D|E
+A|E

docker-wrappers/LocalNeighborhood/ln-nodes.txt

@@ -0,0 +1,2 @@
+A
+B

docker-wrappers/LocalNeighborhood/ln-output.txt

@@ -0,0 +1,3 @@
+A|B
+C|B
+A|E

docker-wrappers/LocalNeighborhood/output1.txt

@@ -0,0 +1,3 @@
+A|B
+C|B
+A|E

spras/local_neighborhood.py

@@ -0,0 +1,136 @@
+from spras.prm import PRM
+from pathlib import Path
+from spras.containers import prepare_volume, run_container
+from spras.util import add_rank_column
+import pandas as pd
+from spras.interactome import reinsert_direction_col_undirected
+
+__all__ = ['LocalNeighborhood']
+
+
+class LocalNeighborhood(PRM):
+    required_inputs = ['network', 'nodetypes']
+
+    @staticmethod
+    def generate_inputs(data, filename_map):
+        # both edge list and prizes
+        """
+        Access fields from the dataset and write the required input files
+        @param data: dataset
+        @param filename_map: a dict mapping file types in the required_inputs to the filename for that type
+        @return:
+        """
+        # print(filename_map)
+        # print(data)
+
+        for input_type in LocalNeighborhood.required_inputs:
+            if input_type not in filename_map:
+                raise ValueError(f"{input_type} filename is missing")
+
+        node_df = None
+
+        if data.contains_node_columns('prize'):
+            node_df = data.request_node_columns(['prize'])
+        elif data.contains_node_columns(['active', 'sources', 'targets']):
+            node_df = data.request_node_columns(['active', 'sources', 'targets'])
+            node_df['prize'] = 0.0  # Initialize 'prize' column
+            node_df.loc[node_df['active'] == True, 'prize'] = 1.0
+            node_df.loc[node_df['sources'] == True, 'prize'] = 1.0
+            node_df.loc[node_df['targets'] == True, 'prize'] = 1.0
+        else:
+            raise ValueError("Local Neighborhood requires node prizes or sources and targets")
+
+        print(node_df) 
+
+        node_df.to_csv(filename_map['nodetypes'],sep='\t',index=False,columns=['NODEID'],header=False)
+
+        edges_df = data.get_interactome()
+
+        print(edges_df)
+
+        edges_df.to_csv(filename_map['network'],sep='|',index=False,
+                        columns=['Interactor1','Interactor2'],
+                        header=False)
+
+
+    #TODO: ?????
+    @staticmethod
+    def run(nodetypes=None, network=None, output_file=None, container_framework="docker"):
+        """
+        Run PathLinker with Docker
+        @param nodetypes:  input node types with sources and targets (required)
+        @param network:  input network file (required)
+        @param output_file: path to the output pathway file (required)
+        @param k: path length (optional)
+        @param container_framework: choose the container runtime framework, currently supports "docker" or "singularity" (optional)
+        """
+        # Add additional parameter validation
+        # Do not require k
+        # Use the PathLinker default
+        # Could consider setting the default here instead
+        if not nodetypes or not network or not output_file:
+            raise ValueError('Required Local Neighborhood arguments are missing')
+
+        work_dir = '/spras'
+
+        # Each volume is a tuple (src, dest)
+        volumes = list()
+
+        bind_path, node_file = prepare_volume(nodetypes, work_dir)
+        volumes.append(bind_path)
+
+        bind_path, network_file = prepare_volume(network, work_dir)
+        volumes.append(bind_path)
+
+        # PathLinker does not provide an argument to set the output directory
+        # Use its --output argument to set the output file prefix to specify an absolute path and prefix
+        # out_dir = Path(output_file).parent
+        # PathLinker requires that the output directory exist
+        # out_dir.mkdir(parents=True, exist_ok=True)
+        bind_path, mapped_out_file = prepare_volume(output_file, work_dir)
+        volumes.append(bind_path)
+        # mapped_out_prefix = mapped_out_dir + '/out'  # Use posix path inside the container
+
+        # print(mapped_out_prefix)
+        #TODO: change for local neighborhood
+        command = ['python',
+                   '/LocalNeighborhood/local_neighborhood.py',
+                   '--network', network_file,
+                   '--nodes', node_file,
+                   '--output', mapped_out_file]
+
+        print('Running Local Neighborhood with arguments: {}'.format(' '.join(command)), flush=True)
+
+        container_suffix = "local-neighborhood" #TODO change
+        out = run_container(container_framework,
+                            container_suffix,
+                            command,
+                            volumes,
+                            work_dir)
+        print(out)
+
+        # Rename the primary output file to match the desired output filename
+        # Currently PathLinker only writes one output file so we do not need to delete others
+        # We may not know the value of k that was used
+        # output_edges = Path(next(out_dir.glob('out*-ranked-edges.txt')))
+        # output_edges.rename(output_file)
+
+
+    @staticmethod
+    def parse_output(raw_pathway_file, standardized_pathway_file):
+        """
+        Convert a predicted pathway into the universal format
+        @param raw_pathway_file: pathway file produced by an algorithm's run function
+        @param standardized_pathway_file: the same pathway written in the universal format
+        """
+        try:
+            df = pd.read_csv(raw_pathway_file, sep='|', header=None)
+        except pd.errors.EmptyDataError:
+            with open(standardized_pathway_file, 'w'):
+                pass
+            return
+        # df.columns = ["vertex1", "vertex2", "1"]
+        df = add_rank_column(df)
+        df = reinsert_direction_col_undirected(df)
+        df.to_csv(standardized_pathway_file, index=False,header=False, sep='\t')
+

spras/runner.py

@@ -7,6 +7,7 @@
 from spras.omicsintegrator1 import OmicsIntegrator1 as omicsintegrator1
 from spras.omicsintegrator2 import OmicsIntegrator2 as omicsintegrator2
 from spras.pathlinker import PathLinker as pathlinker
+from spras.local_neighborhood import LocalNeighborhood as localneighborhood
 
 
 def run(algorithm, params):

test/generate-inputs/expected/local_neighborhood-network-expected.txt

@@ -0,0 +1,3 @@
+A|B
+C|B
+A|E

test/generate-inputs/test_generate_inputs.py

@@ -16,7 +16,8 @@
     'omicsintegrator2': 'edges',
     'domino': 'network',
     'pathlinker': 'network',
-    'allpairs': 'network'
+    'allpairs': 'network',
+    'local_neighborhood':'network'
     }
 
 

test/parse-outputs/expected/local_neighborhood-pathway-expected.txt

@@ -0,0 +1,6 @@
+A	B	1	U
+B	C	1	U
+A	D	1	U
+C	D	1	U
+C	E	1	U
+C	F	1	U

test/parse-outputs/input/local_neighborhood-raw-pathway.txt

@@ -0,0 +1,6 @@
+A|B
+B|C
+A|D
+C|D
+C|E
+C|F

test/parse-outputs/test_parse_outputs.py

@@ -11,7 +11,7 @@
 # the DOMINO output of the network dip.sif and the nodes tnfa_active_genes_file.txt
 # from https://github.com/Shamir-Lab/DOMINO/tree/master/examples
 
-algorithms = ['mincostflow', 'meo', 'omicsintegrator1', 'omicsintegrator2', 'pathlinker', 'allpairs', 'domino']
+algorithms = ['mincostflow', 'meo', 'omicsintegrator1', 'omicsintegrator2', 'pathlinker', 'allpairs', 'domino','local_neighborhood']
 
 
 class TestParseOutputs: