Generate ChEMBL Predictions

0 ×

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.

Nodes

• Column Filter9 ×
• Column Appender4 ×
• Column Resorter4 ×
• Component Input4 ×
• Component Output4 ×
• Show all 36 nodes

Extensions

• FeatureKNIME Base nodes
• FeatureKNIME Deep Learning - TensorFlow Integration
• FeatureKNIME JavaScript Views
• FeatureKNIME JavaScript Views (Labs)
• FeatureKNIME Javasnippet
• Show all 11 modules

Links

• CHEMBL-og post about the neural network

  http://chembl.blogspot.com/2019/05/multi-task-neural-network-on-chembl.html