Merge pull request #5 from leilayesufu/main

Adds the model code for the Prediction of hERG Channel Blockers with Directed Message Passing Neural Networks

.gitattributes

@@ -1 +1 @@
-mock.txt filter=lfs diff=lfs merge=lfs -text
+*.pkl.gz filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -1,7 +1,18 @@
-FROM bentoml/model-server:0.11.0-py37
+FROM bentoml/model-server:0.11.0-py38
 MAINTAINER ersilia
 
 RUN pip install rdkit
+RUN pip install git+https://github.com/bp-kelley/descriptastorus
+RUN pip install tqdm>=4.62.2
+RUN pip install typed-argument-parser==1.6.1
+RUN pip install scikit-learn
+RUN pip install torch
+RUN pip install pandas
+RUN pip install tensorboardX==2.0
+RUN pip install scipy>=1.4.1
+RUN pip install hyperopt
+RUN pip install protobuf==3.18.3
+
 
 WORKDIR /repo
 COPY . /repo

metadata.json

@@ -1,26 +1,25 @@
 {
     "Identifier": "eos30f3",
-    "Slug": "hERG-Channel-Blockers-Prediction",
+    "Slug": "dmpnn-herg",
     "Status": "In progress",
     "Title": "Prediction of hERG Channel Blockers with Directed Message Passing Neural Networks",
-    "Description": [
-        "The model uses invertible flow-based model for generating unique molecules with desired properties. The model ultimately generates molecular graphs. In this model",
-        "the directed message passing neural network (D-MPNN) is applied to construct classification models for identifying hERG blockers based on diverse datasets."
-    ],
-    "Mode": "",
-    "Task": [],
-    "Input": [],
-    "Input Shape": "",
-    "Output": [],
-    "Output Type": [],
-    "Output Shape": "",
-    "Interpretation": "",
+    "Description": 
+        "This model leverages the ChemProp network (D-MPNN, see original Stokes et al, Cell, 2020 for more information) to build a predictor of hERG-mediated cardiotoxicity. The model has been trained using a dataset published by Cai et al, J Chem Inf Model, 2019, which contains 7889 molecules with several cut-offs for hERG blocking activity. The authors select a 10 uM cut-off. This implementation of the model does not use any specific featurizer, though the authors suggest the moe206 descriptors (closed-source) improve performance even further.",
+    "Mode": "Pretrained",
+    "Task": ["Classification"],
+    "Input": ["Compound"],
+    "Input Shape": "Single",
+    "Output": ["Score"],
+    "Output Type": ["Float"],
+    "Output Shape": "Single",
+    "Interpretation": "Probability of blocking hERG (cut-off: 10uM)",
     "Tag": [
+        "Cardiotoxicity",
         "hERG",
-        "channel-blockers",
-        "DMPNN"
+        "Toxicity",
+        "Descriptor"
     ],
     "Publication": "https://pubs.rsc.org/en/content/articlehtml/2022/ra/d1ra07956e",
     "Source Code": "https://github.com/AI-amateur/DMPNN-hERG",
-    "License": "MIT"
+    "License": "None"
 }

model/framework/code/chemprop/__init__.py

@@ -0,0 +1,20 @@
+import chemprop.data
+import chemprop.features
+import chemprop.models
+import chemprop.train
+import chemprop.uncertainty
+# import chemprop.web
+
+import chemprop.args
+import chemprop.constants
+import chemprop.hyperparameter_optimization
+import chemprop.interpret
+import chemprop.nn_utils
+import chemprop.utils
+import chemprop.rdkit
+import chemprop.sklearn_predict
+import chemprop.sklearn_train
+import chemprop.spectra_utils
+import chemprop.hyperopt_utils
+
+__version__ = "1.6.1"