Adds dockerisation and ML inference

.github/workflows/deploy_docker.yaml

@@ -0,0 +1,48 @@
+#
+name: Create and publish a Docker image
+
+# Configures this workflow to run every time a change is pushed to the branch called `release`.
+on:
+  push:
+    branches: ['main']
+
+# Defines two custom environment variables for the workflow. These are used for the Container registry domain, and a name for the Docker image that this workflow builds.
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+    # Sets the permissions granted to the `GITHUB_TOKEN` for the actions in this job.
+    permissions:
+      contents: read
+      packages: write
+      # 
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      # Uses the `docker/login-action` action to log in to the Container registry registry using the account and password that will publish the packages. Once published, the packages are scoped to the account defined here.
+      - name: Log in to the Container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      # This step uses [docker/metadata-action](https://github.com/docker/metadata-action#about) to extract tags and labels that will be applied to the specified image. The `id` "meta" allows the output of this step to be referenced in a subsequent step. The `images` value provides the base name for the tags and labels.
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+      # This step uses the `docker/build-push-action` action to build the image, based on your repository's `Dockerfile`. If the build succeeds, it pushes the image to GitHub Packages.
+      # It uses the `context` parameter to define the build's context as the set of files located in the specified path. For more information, see "[Usage](https://github.com/docker/build-push-action#usage)" in the README of the `docker/build-push-action` repository.
+      # It uses the `tags` and `labels` parameters to tag and label the image with the output from the "meta" step.
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

Dockerfile

@@ -0,0 +1,22 @@
+# Use the conda-forge base image with Python
+FROM mambaorg/micromamba:1.5.8
+
+
+# set environment variables
+ENV PYTHONUNBUFFERED 1
+
+RUN micromamba config append channels conda-forge
+RUN micromamba config append channels openeye
+
+COPY --chown=$MAMBA_USER:$MAMBA_USER  devtools/conda-envs/falcbot.yaml /tmp/env.yaml
+COPY --chown=$MAMBA_USER:$MAMBA_USER  .  /home/mambauser/FALCBot
+
+RUN micromamba install -y -n base git -f /tmp/env.yaml && \
+    micromamba clean --all --yes
+
+ARG MAMBA_DOCKERFILE_ACTIVATE=1
+
+WORKDIR /home/mambauser/FALCBot
+
+RUN mkdir /home/mambauser/.OpenEye
+ENV OE_LICENSE=/home/mambauser/.OpenEye/oe_license.txt

compose.yml

@@ -0,0 +1,15 @@
+version: '3'
+
+services:
+  falcbot:
+    command: python falcbot/falcbot.py
+    build: .
+    container_name: "slackbot"
+    ports:
+      - 80:80
+    volumes:
+      - type: bind
+        source: $HOME/.OpenEye/
+        target: /home/mambauser/.OpenEye/
+    env_file:
+      - .env

devtools/conda-envs/falcbot.yaml

@@ -20,6 +20,23 @@ dependencies:
   - pydantic<2.0a0
 
 
+  # ml
+  - pytorch
+  - pytorch_geometric >=2.5.0
+  - pytorch_cluster
+  - pytorch_scatter
+  - pytorch_sparse
+  - numpy
+  - h5py
+  - e3nn
+  - dgl
+  - dgllife
+  - pooch
+  - mtenn >=0.5.1
+  - wandb
+  - semver
+
+
   # alchemy
   - numpy
   - gufe =>0.9.5
@@ -45,5 +62,7 @@ dependencies:
     - git+https://github.com/choderalab/asapdiscovery@main#egg=asapdiscovery-data&subdirectory=asapdiscovery-data
     - git+https://github.com/choderalab/asapdiscovery@main#egg=asapdiscovery-modeling&subdirectory=asapdiscovery-modeling
     - git+https://github.com/choderalab/asapdiscovery@main#egg=asapdiscovery-docking&subdirectory=asapdiscovery-docking
+    - git+https://github.com/choderalab/asapdiscovery@main#egg=asapdiscovery-ml&subdirectory=asapdiscovery-ml
+
 
 

devtools/deployment/.env.example

@@ -0,0 +1 @@
+BLAH=BLAH

falcbot/falcbot.py

@@ -25,10 +25,16 @@
 from asapdiscovery.data.services.aws.cloudfront import CloudFront
 from asapdiscovery.data.services.aws.s3 import S3
 
+from asapdiscovery.ml.inference import GATInference
+from asapdiscovery.data.services.postera.manifold_data_validation import TargetTags
+
+
+from rdkit import Chem
+
 from multiprocessing import cpu_count
 
 # logger in a global context
-logging.basicConfig(level=logging.INFO)
+logging.basicConfig(level=logging.DEBUG)
 
 
 class SlackSettings(BaseSettings):
@@ -80,15 +86,18 @@ def _link_to_block_data(link, text):
     }
 
 
-@app.message(re.compile("(hi|hello|hey)"))
-def say_hello_regex(say, context):
-    # regular expression matches are inside of context.matches
-    print(context)
-    greeting = context["matches"][0]
-    say(f"{greeting}, how are you?")
-
+def _is_valid_smiles(smi):
+    m = Chem.MolFromSmiles(smi)
+    if m is None:
+        return False
+    else:
+        return True
+
+def _rdkit_smiles_roundtrip(smi: str) -> str:
+    mol = Chem.MolFromSmiles(smi)
+    return Chem.MolToSmiles(mol)
 
-@app.message(re.compile("(.*)are you alive(.*)"))
+@app.message(re.compile("(.*)are you alive falcbot(.*)"))
 def are_you_alive(say, context):
     say(f"yes im alive!")
 
@@ -379,6 +388,33 @@ def plan_and_submit_from_ligand_and_receptor(): ...
 def submit_from_planned_network(): ...  # do something with settings
 
 
+@app.message(re.compile("infer pIC50 from SMILES"))
+def make_pic50_pred(message, say, context, logger):
+    content = message.get("text")
+    # parse message for molset using regex
+    pattern = r"infer pIC50 from SMILES ([\w-]+) for target ([\w-]+)"
+    match = re.search(pattern, content)
+    if match:
+        smiles = match.group(1)
+        target = match.group(2)
+    else:
+        say("Could not find SMILES and Target in the message, unable to proceed")
+        return
+    if not _is_valid_smiles(smiles):
+        say(f"Invalid SMILES {smiles}, unable to proceed")
+        return
+    if not target in TargetTags.get_values():
+        say(f"Invalid target {target}, unable to proceed")
+        return
+    # make prediction
+    smiles = _rdkit_smiles_roundtrip(smiles)
+    gs = GATInference.from_latest_by_target(target)
+    pred = gs.predict_from_smiles(smiles)
+    say(f"Predicted pIC50 for {smiles} is {pred} using model {gs.model_name} :test_tube:")
+
+
+
+
 @app.event("message")
 def base_handle_message_events(body, logger):
     logger.debug(body)

falcbot/tests/test_falcbot.py

@@ -2,14 +2,6 @@
 Unit and regression test for the falcbot package.
 """
 
-# Import package, test suite, and other packages as needed
-import sys
 
-import pytest
-
-import falcbot
-
-
-def test_falcbot_imported():
-    """Sample test, will always pass so long as import statement worked."""
-    assert "falcbot" in sys.modules
+def  test_placeholder():
+    assert 1 == 1