Wrapped BTB algorithm for SPRAS integration

.github/workflows/build-containers.yml

@@ -43,6 +43,11 @@ jobs:
     with:
       path: docker-wrappers/DOMINO
       container: reedcompbio/domino
+  build-and-remove-btb:
+    uses: "./.github/workflows/build-and-remove-template.yml"
+    with:
+      path: docker-wrappers/BowTieBuilder
+      container: reedcompbio/bowtiebuilder
   build-and-remove-cytoscape:
     uses: "./.github/workflows/build-and-remove-template.yml"
     with:

.github/workflows/test-spras.yml

@@ -61,6 +61,155 @@ jobs:
       shell: bash --login {0}
       run: snakemake --cores 2 --configfile config/config.yaml --show-failed-logs
 
+  # Builds the Docker images
+  docker:
+    name: Build Docker images
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest]
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v2
+      # Pull from Docker Hub to use the cache
+      # https://medium.com/mobileforgood/coding-tips-patterns-for-continuous-integration-with-docker-on-travis-ci-9cedb8348a62
+      # https://github.com/docker/build-push-action/issues/7
+    - name: Pull Docker images
+      run: |
+        docker pull reedcompbio/omics-integrator-1:latest
+        docker pull reedcompbio/omics-integrator-2:v2
+        docker pull reedcompbio/pathlinker:v2
+        docker pull reedcompbio/meo:latest
+        docker pull reedcompbio/mincostflow:latest
+        docker pull reedcompbio/allpairs:v2
+        docker pull reedcompbio/domino:latest
+        docker pull reedcompbio/py4cytoscape:v3
+        docker pull reedcompbio/bowtiebuilder:v2
+        docker pull reedcompbio/spras:v0.1.0
+
+    - name: Build Omics Integrator 1 Docker image
+      uses: docker/build-push-action@v1
+      with:
+        path: docker-wrappers/OmicsIntegrator1/.
+        dockerfile: docker-wrappers/OmicsIntegrator1/Dockerfile
+        repository: reedcompbio/omics-integrator-1
+        tags: latest
+        cache_froms: reedcompbio/omics-integrator-1:latest
+        push: false
+    - name: Remove Omics Integrator 1 Docker image
+      # Remove the image to prevent the cache from being used. Here we use
+      # `|| true` to prevent the job from failing if the image doesn't exist or
+      # can't be removed for some reason
+      run: docker rmi reedcompbio/omics-integrator-1:latest || true
+
+    - name: Build Omics Integrator 2 Docker image
+      uses: docker/build-push-action@v1
+      with:
+        path: docker-wrappers/OmicsIntegrator2/.
+        dockerfile: docker-wrappers/OmicsIntegrator2/Dockerfile
+        repository: reedcompbio/omics-integrator-2
+        tags: v2
+        cache_froms: reedcompbio/omics-integrator-2:latest
+        push: false
+    - name: Remove Omics Integrator 2 Docker image
+      run: docker rmi reedcompbio/omics-integrator-2:latest || true
+
+    - name: Build PathLinker Docker image
+      uses: docker/build-push-action@v1
+      with:
+        path: docker-wrappers/PathLinker/.
+        dockerfile: docker-wrappers/PathLinker/Dockerfile
+        repository: reedcompbio/pathlinker
+        tags: v2
+        cache_froms: reedcompbio/pathlinker:latest
+        push: false
+    - name: Remove PathLinker Docker image
+      run: docker rmi reedcompbio/pathlinker:latest || true
+
+    - name: Build Maximum Edge Orientation Docker image
+      uses: docker/build-push-action@v1
+      with:
+        path: docker-wrappers/MEO/.
+        dockerfile: docker-wrappers/MEO/Dockerfile
+        repository: reedcompbio/meo
+        tags: latest
+        cache_froms: reedcompbio/meo:latest
+        push: false
+    - name: Remove MEO Docker image
+      run: docker rmi reedcompbio/meo:latest || true
+
+    - name: Build MinCostFlow Docker image
+      uses: docker/build-push-action@v1
+      with:
+        path: docker-wrappers/MinCostFlow/.
+        dockerfile: docker-wrappers/MinCostFlow/Dockerfile
+        repository: reedcompbio/mincostflow
+        tags: latest
+        cache_froms: reedcompbio/mincostflow:latest
+        push: false
+    - name: Remove MinCostFlow Docker image
+      run: docker rmi reedcompbio/mincostflow:latest || true
+
+    - name: Build All Pairs Shortest Paths Docker image
+      uses: docker/build-push-action@v1
+      with:
+        path: docker-wrappers/AllPairs/.
+        dockerfile: docker-wrappers/AllPairs/Dockerfile
+        repository: reedcompbio/allpairs
+        tags: v2
+        cache_froms: reedcompbio/allpairs:latest
+        push: false
+    - name: Remove All Pairs Shortest Paths Docker image
+      run: docker rmi reedcompbio/allpairs:latest || true
+
+    - name: Build DOMINO Docker image
+      uses: docker/build-push-action@v1
+      with:
+        path: docker-wrappers/DOMINO/.
+        dockerfile: docker-wrappers/DOMINO/Dockerfile
+        repository: reedcompbio/domino
+        tags: latest
+        cache_froms: reedcompbio/domino:latest
+        push: false
+    - name: Remove DOMINO Docker image
+      run: docker rmi reedcompbio/domino:latest || true
+
+    - name: Build Cytoscape Docker image
+      uses: docker/build-push-action@v1
+      with:
+        path: docker-wrappers/Cytoscape/.
+        dockerfile: docker-wrappers/Cytoscape/Dockerfile
+        repository: reedcompbio/py4cytoscape
+        tags: v3
+        cache_froms: reedcompbio/py4cytoscape:v3
+        push: false
+    - name: Remove Cytoscape Docker image
+      run: docker rmi reedcompbio/py4cytoscape:v3 || true
+
+    - name: Build BowTieBuilder Docker Image
+      uses: docker/build-push-action@v1
+      with:
+        path: docker-wrappers/BowTieBuilder/.
+        dockerfile: docker-wrappers/BowTieBuilder/Dockerfile
+        repository: reedcompbio/bowtiebuilder
+        tags: v2
+        cache_froms: reedcompbio/bowtiebuilder:v2
+        push: false
+    - name: Remove BowTieBuilder Docker image
+      run: docker rmi reedcompbio/bowtiebuilder:v2 || true
+
+    - name: Build SPRAS Docker image
+      uses: docker/build-push-action@v1
+      with:
+        path: .
+        dockerfile: docker-wrappers/SPRAS/Dockerfile
+        repository: reedcompbio/spras
+        tags: v0.2.0
+        cache_froms: reedcompbio/spras:v0.2.0
+        push: false
+    - name: Remove SPRAS Docker image
+      run: docker rmi reedcompbio/spras:v0.2.0 || true
+
   # Run pre-commit checks on source files
   pre-commit:
     name: Run pre-commit checks

config/config.yaml

@@ -45,6 +45,7 @@ container_registry:
 # careful: too many parameters might make your runs take a long time.
 
 algorithms:
+
       - name: "pathlinker"
         params:
               include: true
@@ -96,6 +97,10 @@ algorithms:
                   slice_threshold: [0.3]
                   module_threshold: [0.05]
 
+      - name: "bowtiebuilder"
+        params:
+              include: true
+
 
 # Here we specify which pathways to run and other file location information.
 # DataLoader.py can currently only load a single dataset

docker-wrappers/BowTieBuilder/Dockerfile

@@ -0,0 +1,5 @@
+FROM python:3.8-bullseye
+
+WORKDIR /btb
+RUN wget https://raw.githubusercontent.com/Reed-CompBio/BowTieBuilder-Algorithm/main/btb.py
+RUN pip install networkx==2.8

docker-wrappers/BowTieBuilder/README.md

@@ -0,0 +1,15 @@
+# BowTieBuilder Docker image
+
+A Docker image for [BowTieBuilder](https://github.com/Reed-CompBio/BowTieBuilder-Algorithm) that is available on [DockerHub](https://hub.docker.com/repository/docker/reedcompbio/bowtiebuilder).
+
+To create the Docker image run:
+```
+docker build -t reedcompbio/bowtiebuilder:v2 -f Dockerfile .
+```
+from this directory.
+
+## Original Paper
+
+The original paper for [BowTieBuilder] can be accessed here:
+
+Supper, J., Spangenberg, L., Planatscher, H. et al. BowTieBuilder: modeling signal transduction pathways. BMC Syst Biol 3, 67 (2009). https://doi.org/10.1186/1752-0509-3-67

spras/btb.py

@@ -0,0 +1,168 @@
+# need to define a new btb class and contain the following functions
+# - generate_inputs
+# - run
+# - parse_output
+
+import warnings
+from pathlib import Path
+
+import pandas as pd
+
+from spras.containers import prepare_volume, run_container
+from spras.interactome import (
+    reinsert_direction_col_undirected,
+)
+from spras.prm import PRM
+from spras.util import add_rank_column, duplicate_edges, raw_pathway_df
+
+__all__ = ['BowTieBuilder']
+
+"""
+BTB will construct a BowTie-shaped graph from the provided input file.
+BTB works with directed and undirected graphs.
+It generates a graph connecting multiple source nodes to multiple target nodes with the minimal number of intermediate nodes as possible.
+
+Expected raw edge file format:
+Interactor1     Interactor2     Weight
+"""
+
+class BowTieBuilder(PRM):
+    required_inputs = ['sources', 'targets', 'edges']
+
+    #generate input taken from meo.py beacuse they have same input requirements
+    @staticmethod
+    def generate_inputs(data, filename_map):
+        """
+        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:
+        """
+        for input_type in BowTieBuilder.required_inputs:
+            if input_type not in filename_map:
+                raise ValueError(f"{input_type} filename is missing")
+
+        # Get sources and write to file, repeat for targets
+        # Does not check whether a node is a source and a target
+        for node_type in ['sources', 'targets']:
+            nodes = data.request_node_columns([node_type])
+            if nodes is None:
+                raise ValueError(f'No {node_type} found in the node files')
+
+            # TODO test whether this selection is needed, what values could the column contain that we would want to
+            # include or exclude?
+            nodes = nodes.loc[nodes[node_type]]
+            if(node_type == "sources"):
+                nodes.to_csv(filename_map["sources"], sep= '\t', index=False, columns=['NODEID'], header=False)
+            elif(node_type == "targets"):
+                nodes.to_csv(filename_map["targets"], sep= '\t', index=False, columns=['NODEID'], header=False)
+
+
+        # Create network file
+        edges = data.get_interactome()
+
+        # Format into directed graph
+        # edges = convert_undirected_to_directed(edges)
+
+        edges.to_csv(filename_map["edges"], sep="\t", index=False,
+                                      columns=["Interactor1", "Interactor2", "Weight"],
+                                      header=False)
+
+
+
+    # Skips parameter validation step
+    @staticmethod
+    def run(sources=None, targets=None, edges=None, output_file=None, container_framework="docker"):
+        """
+        Run BTB with Docker
+        @param sources:  input source file (required)
+        @param targets:  input target file (required)
+        @param edges:    input edge file (required)
+        @param output_file: path to the output pathway file (required)
+        @param container_framework: choose the container runtime framework, currently supports "docker" or "singularity" (optional)
+        """
+
+        # Tests for pytest (docker container also runs this)
+        # Testing out here avoids the trouble that container errors provide
+
+        if not sources or not targets or not edges or not output_file:
+            raise ValueError('Required BowTieBuilder arguments are missing')
+
+        if not Path(sources).exists() or not Path(targets).exists() or not Path(edges).exists():
+            raise ValueError('Missing input file')
+
+        # Testing for btb index errors
+        # It's a bit messy, but it works \_('_')_/
+        with open(edges, 'r') as edge_file:
+            try:
+                for line in edge_file:
+                    line = line.strip()
+                    line = line.split('\t')
+                    line = line[2]
+
+            except Exception as err:
+                raise(err)
+
+        work_dir = '/btb'
+
+        # Each volume is a tuple (src, dest)
+        volumes = list()
+
+        bind_path, source_file = prepare_volume(sources, work_dir)
+        volumes.append(bind_path)
+
+        bind_path, target_file = prepare_volume(targets, work_dir)
+        volumes.append(bind_path)
+
+        bind_path, edges_file = prepare_volume(edges, work_dir)
+        volumes.append(bind_path)
+
+        # Use its --output argument to set the output file prefix to specify an absolute path and prefix
+        out_dir = Path(output_file).parent
+        out_dir.mkdir(parents=True, exist_ok=True)
+        bind_path, mapped_out_dir = prepare_volume(str(out_dir), work_dir)
+        volumes.append(bind_path)
+        mapped_out_prefix = mapped_out_dir + '/raw-pathway.txt'  # Use posix path inside the container
+
+        command = ['python',
+                   'btb.py',
+                   '--edges',
+                   edges_file,
+                   '--sources',
+                   source_file,
+                   '--targets',
+                   target_file,
+                   '--output_file',
+                   mapped_out_prefix]
+        # command = ['ls', '-R']
+
+
+        print('Running BowTieBuilder with arguments: {}'.format(' '.join(command)), flush=True)
+
+        container_suffix = "bowtiebuilder:v2"
+        out = run_container(container_framework,
+                            container_suffix,
+                            command,
+                            volumes,
+                            work_dir)
+        print(out)
+        # Output is already written to raw-pathway.txt 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
+        """
+        # What about multiple raw_pathway_files
+        df = raw_pathway_df(raw_pathway_file, sep='\t', header=0)
+        if not df.empty:
+            df = add_rank_column(df)
+            df = reinsert_direction_col_undirected(df)
+            df.columns = ['Node1', 'Node2', 'Rank', 'Direction']
+            df, has_duplicates = duplicate_edges(df)
+            if has_duplicates:
+                print(f"Duplicate edges were removed from {raw_pathway_file}")
+        df.to_csv(standardized_pathway_file, index=False, sep='\t', header=True)

spras/runner.py

@@ -1,5 +1,6 @@
 # supported algorithm imports
 from spras.allpairs import AllPairs as allpairs
+from spras.btb import BowTieBuilder as bowtiebuilder
 from spras.dataset import Dataset
 from spras.domino import DOMINO as domino
 from spras.meo import MEO as meo

test/BowTieBuilder/expected/bidirectional-output.txt

@@ -0,0 +1,3 @@
+Node1	Node2
+S1	A
+A	T1

test/BowTieBuilder/expected/btb-output.txt

@@ -0,0 +1,5 @@
+Node1	Node2
+S1	A
+S2	A
+A	T1
+A	T2