Machine Learning Model Building Floes
v1.0.2 September 2025
This package is built using
OpenEye-orionplatform==6.7.0
,OpenEye-toolkits==2025.1.1
,OpenEye-Snowball==0.29.2
, andOpenEye-floereport==6.7.0
.
Feature Updates
New floes have been added to allow for model building and property prediction using Graph Convolutional Neural Network (GCNN) models. GCNNs can learn directly from the molecular graph using atom and bond features from OpenEye toolkits rather than features derived from the molecule (e.g., fingerprints), resulting in fewer parameters for the model to learn. GCNNs are also not limited to interaction radii from complex structures, therefore building more generalizable models.
A new parameter, Graph Feature Vector Generation, has been added to the Data Processing of Small Molecule for ML Model Building Floe. This parameter builds graph feature tensors and outputs a collection with graph nodes and edge features that will be used as input for the GCNN model building floe.
There is an informative new chapter on How to Build Optimal Property-Predicting Graph Convolutional Neural Network Machine Learning Models by Tweaking Neural Network Architecture.
New Floes
These floes have been introduced and described in the new ML Build and Predict: Optimal Property-Predicting Graph Convolutional Neural Network Model tutorial: