DeepChem Equivariant: SE(3)-Equivariant Support in an Open-Source Molecular Machine Learning Library
This work addresses the accessibility gap for researchers in molecular sciences by providing an open-source toolkit with complete training pipelines, though it is incremental as it builds on existing methods.
The authors extended the DeepChem library to include SE(3)-equivariant neural network support, enabling scientists with minimal deep learning expertise to build, train, and evaluate models for molecular applications like property prediction and protein structure modeling.
Neural networks that incorporate geometric relationships respecting SE(3) group transformations (e.g. rotations and translations) are increasingly important in molecular applications, such as molecular property prediction, protein structure modeling, and materials design. These models, known as SE(3)-equivariant neural networks, ensure outputs transform predictably with input coordinate changes by explicitly encoding spatial atomic positions. Although libraries such as E3NN [4] and SE(3)-TRANSFORMER [3 ] offer powerful implementations, they often require substantial deep learning or mathematical prior knowledge and lack complete training pipelines. We extend DEEPCHEM [ 13] with support for ready-to-use equivariant models, enabling scientists with minimal deep learning background to build, train, and evaluate models, such as SE(3)-Transformer and Tensor Field Networks. Our implementation includes equivariant models, complete training pipelines, and a toolkit of equivariant utilities, supported with comprehensive tests and documentation, to facilitate both application and further development of SE(3)-equivariant models.