ElemeNet: Multiscale Molecular Machine Learning with Uncertainty Quantification Across the Periodic Table
For computational chemists and non-expert researchers, ElemeNet provides a general-purpose, easy-to-use toolkit that extends ML-driven property prediction to a wider range of chemical species, including organometallics and biological systems.
ElemeNet is a unified software package for molecular machine learning that supports elements 1-100, enabling property prediction across organic, organometallic, and biological systems with built-in uncertainty quantification. It achieves competitive and state-of-the-art performance on diverse benchmarks, scaling to millions of molecules.
Advances in deep learning architectures and representations have enabled ML-driven chemical property prediction, but state-of-the-art (SOTA) models have remained largely confined to independent codebases and lack support for diverse chemical species. This work introduces ElemeNet, a unified, general-purpose software package for molecular machine learning. The ElemeNet software package enables the training of advanced ML models for diverse properties and datasets with an enlarged range of elemental compositions. We define molecular representations compatible with elements 1-100, supporting diverse organometallic and biological systems in addition to organic chemistry already well-served by the Chemprop ML toolkit. As well as more common atom-, bond-, and molecule-level predictions, we introduce moiety predictions. We also natively define optional conditioning on charge and spin states. Advanced E(3)-equivariant and transformer architectures are supported, as well as classical 2D models, with all classes including built-in uncertainty quantification through deterministic and statistical measures. We benchmark our protocols for ML model training against representative datasets from organic, inorganic, coordination, and biological chemistry, achieving competitive and SOTA performance relative to literature baselines and favorable scaling to millions of molecules. The entire workflow is exposed through a concise command-line interface, lowering the barrier to entry for non-expert users. We anticipate ElemeNet will empower non-computational researchers to leverage modern deep learning methods across the chemical and physical sciences.