add model

Dockerfile

@@ -1,7 +1,7 @@
-FROM bentoml/model-server:0.11.0-py37
+FROM bentoml/model-server:0.11.0-py311
 MAINTAINER ersilia
 
-RUN pip install rdkit
+RUN pip install rdkit==2023.9.5
 
 WORKDIR /repo
 COPY . /repo

metadata.json

@@ -1,17 +1,17 @@
 {
     "Identifier": "eos5guo",
     "Slug": "erg-descs",
-    "Status": "In progress",
+    "Status": "Ready",
     "Title": "ErG 2D Descriptors",
     "Description": "The Extended Reduced Graph (ErG) approach uses the description of pharmacophore nodes to encode molecular properties, with the goal of correctly describing pharmacophoric properties, size and shape of molecules. It was benchmarked against Daylight fingerprints and outperformed them in 10 out of 11 cases. ErG descriptors are well suited for scaffold hopping approaches.",
-    "Mode": "",
-    "Task": [],
-    "Input": [],
-    "Input Shape": "",
-    "Output": [],
-    "Output Type": [],
-    "Output Shape": "",
-    "Interpretation": "",
+    "Mode": "Pretrained",
+    "Task": ["Representation"],
+    "Input": ["Compound"],
+    "Input Shape": "Single",
+    "Output": ["Descriptor"],
+    "Output Type": ["Integer"],
+    "Output Shape": "List",
+    "Interpretation": "Vector representing SMILES",
     "Tag": [
         "Descriptor",
         "Fingerprint"

model/framework/code/main.py

@@ -1,9 +1,11 @@
 # imports
 import os
 import csv
+import numpy as np
 import sys
 from rdkit import Chem
-from rdkit.Chem.Descriptors import MolWt
+from rdkit.Chem import rdReducedGraphs
+
 
 # parse arguments
 input_file = sys.argv[1]
@@ -13,8 +15,11 @@
 root = os.path.dirname(os.path.abspath(__file__))
 
 # my model
-def my_model(smiles_list):
-    return [MolWt(Chem.MolFromSmiles(smi)) for smi in smiles_list]
+def erg_desc(smiles_list):
+    mols = [Chem.MolFromSmiles(smi) for smi in smiles_list]
+    ergfps = [rdReducedGraphs.GetErGFingerprint(mol) for mol in mols]
+    array_ergfps = [np.array(fp) for fp in ergfps]
+    return array_ergfps
 
 
 # read SMILES from .csv file, assuming one column with header
@@ -24,16 +29,17 @@ def my_model(smiles_list):
     smiles_list = [r[0] for r in reader]
 
 # run model
-outputs = my_model(smiles_list)
+outputs = erg_desc(smiles_list)
 
 #check input and output have the same lenght
 input_len = len(smiles_list)
 output_len = len(outputs)
 assert input_len == output_len
 
+
 # write output in a .csv file
 with open(output_file, "w") as f:
     writer = csv.writer(f)
-    writer.writerow(["value"])  # header
+    writer.writerow(["erg-{}".format(i) for i in range(len(outputs[0]))])  # header
     for o in outputs:
-        writer.writerow([o])
+        writer.writerow(o)