Icon

Generate ChEMBL Predictions

Generate predictions with ONNX

This workfow uses a multitask neural network built using PyTorch and saved to the ONNX format to generate predictions.

The network generates predictions for bioactivity against 560 targets. The results are visually presented in a bisorted heatmap.

The workflow also looks up whatever information is available in ChEMBL itself about the activity of the prediction compounds on the 560 targets and presents that in a second interactive view.

NOTE that in order to use this workflow you also need the contents of the Data folder, which contains the saved network and information about the targets that are being predicted.

URL: CHEMBL-og post about the neural network http://chembl.blogspot.com/2019/05/multi-task-neural-network-on-chembl.html

Input

Predictions

Lookup what's known

Display results

Compare to known results

ONNX Network Reader
ONNX to TensorFlow Network Converter
TensorFlow Network Executor
Display predictions and measurements
Reformat with bisorting
RDKit Fingerprint
Read moleculesto be predicted
File Reader (Complex Format)
Retrieve ChEMBL data when present
Generate statistics for known compounds
Column Resorter
Joiner
Display predictions as heatmap
Expand Bit Vector
Read target ids
File Reader (Complex Format)

Nodes

Extensions

Links