2026-10-13T12:34:09Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34050192 2026-10-01T18:11:42Z category_4 category_873 category_734 category_931 portal_63 item_type_6 month_year_10_2026

ElemeNet: Multiscale Molecular Machine Learning with Uncertainty Quantification across the Periodic Table Jacob W. Toney (22854413) Samir Darouich (18509483) Yiran Wang (1492303) Aaron G. Garrison (22854419) Johannes Kästner (1644178) Heather J. Kulik (1373331) Biochemistry Chemical Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified remained largely confined purpose software package periodic table advances molecular machine learning empower noncomputational researchers classes including built 3 )- equivariant chemprop ml toolkit supporting diverse organometallic deep learning architectures work introduces elemenet uncertainty quantification across sota performance relative representative data sets ml model training diverse chemical species advanced ml models uncertainty quantification data sets enabled ml diverse properties transformer architectures advanced e statistical measures spin states physical sciences nonexpert users literature baselines line interface level predictions lack support independent codebases favorable scaling entire workflow enlarged range elemental compositions concise command biological systems biological chemistry anticipate elemenet achieving competitive 2d models 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 data sets 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 and allow for moiety-level predictions. We also natively define optional conditioning on charge and spin states. Advanced E(3)-equivariant and transformer architectures are supported in addition to 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 data sets 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 nonexpert users. We anticipate ElemeNet will empower noncomputational researchers to leverage modern deep learning methods across the chemical and physical sciences. 2026-10-01T00:00:00Z Text Journal contribution 10.1021/acs.jcim.6c02178.s001 https://figshare.com/articles/journal_contribution/ElemeNet_Multiscale_Molecular_Machine_Learning_with_Uncertainty_Quantification_across_the_Periodic_Table/34050192 CC BY-NC 4.0