arXiv subjects

Aaron G. Garrison

Publications and source records attributed to Aaron G. Garrison.

3 recordsLinked to original sources

arXiv2026

ElemeNet: Multiscale Molecular Machine Learning with Uncertainty Quantification Across the Periodic Table

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.

physics.chem-ph↗

arXiv2026

The BOS-TMC Dataset: DFT Properties of 159k Experimentally Characterized Transition Metal Complexes Spanning Multiple Charge and Spin States

We present the Boston Open-Shell Transition Metal Complex (BOS-TMC) dataset, a set of density functional theory (DFT) properties for 159k experimentally characterized mononuclear transition metal complexes (TMCs) in multiple spin states with a range of formal charges derived from the Cambridge Structural Database (CSD). To curate this set, we carried out an iterative procedure to confidently assign overall TMC charge. From this information, we then obtained properties in up to three spin states, i.e., low-, intermediate-, and high-spin for 3d metals and low- and intermediate-spin for 4d and 5d metals, depending on compatibility with the metal electron configuration, for a total of 343.8k TMC/spin combinations. At odds with prior sets, we preserved experimental heavy-atom coordinates in these structures during optimization. We report all properties using PBE0/def2-TZVP single-point energies on these structures. We introduce a scheme for computing metal-spin-dependent atomization energies, which we report for each TMC. Alongside electronic energies, we report up to seven additional properties including: HOMO, LUMO, HOMO-LUMO gap, atomic partial charges, dipole moments, atomization energies, and spin-splitting energies for a total of over 2.9M TMC-associated properties. For a representative subset of over 10k complexes chosen based on size, we evaluate the sensitivity of computed properties to exchange-correlation (xc) functional choice from a set of twelve xcs spanning rungs of "Jacob's ladder", highlighting hotspots of TMC space that have the greatest uncertainty. In comparison to prior transition-metal datasets, BOS-TMC is both larger and more diverse in terms of charge and spin configurations and, as a result, more diverse in its range of properties. This dataset is expected to provide a high-fidelity foundation for machine-learning model development, DFT benchmarking, and exploration.

physics.chem-ph↗

arXiv2026

The BOS-Lig Dataset: Accurate Ligand Charges from a Consensus Approach for 66,810 Experimentally Synthesized Ligands

Understanding ligand properties is essential for computational high-throughput screening of transition metal complexes. However, ligand properties such as net charge and other information such as their application area are often absent or inconsistently recorded in crystallographic datasets. Here, we construct a ligand dataset from 126,985 mononuclear transition metal complexes curated from the Cambridge Structural Database. Using an iterative charge-balancing workflow that combines complex charges, metal oxidation states, and consensus across crystallographic observations, we confidently assign net charges to 66,810 ligands among 94,581 identified unique ligand structures to curate the Boston Open-Shell Ligand (BOS-Lig) dataset. The workflow assigns ligand charges in homoleptic complexes first and then iteratively propagates these assignments across heteroleptic environments, allowing charges to be inferred even when direct charge information is unavailable. We analyze cases where simple heuristics such as the octet rule would have failed and introduce a purity metric to identify when our charge assignments may be incorrect. Each ligand is also classified in terms of its metal coordinating atoms and whether there are multiple variants (i.e., hemilability). We then link complexes to their associated journal abstracts and apply a topic-modeling workflow to link 25,146 ligands with functional application areas spanning reactivity, redox chemistry, biological chemistry, and photophysical chemistry. Together, we provide an experimentally grounded dataset of ligand chemical space that connects charge and functional application as a foundation for computational screening and data-driven ligand design.

physics.chem-ph↗