Adaptive subspace Bayesian optimization over molecular descriptor libraries for data-efficient chemical design
MolDAIS enables data-efficient molecular discovery by adaptively learning sparse, task-relevant subspaces from descriptor libraries, outperforming prior methods in predictive accuracy, optimization efficiency, and interpretability.
Authors
- Farshud Sorourifar (ORCID: https://orcid.org/0000-0002-1611-8658)
- Joel A. Paulson (ORCID: https://orcid.org/0000-0002-1518-7985)
- Thomas Banker (ORCID: https://orcid.org/0000-0002-3519-0823)
Institutions
- The Ohio State University (US)
- University of California, Berkeley (US)
Publication Details
- Journal
- Digital Discovery
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1039/d5dd00188a
- Citations
- 2
- Primary Topic
- Computational Drug Discovery Methods
- Type
- article
- Field-Weighted Citation Impact
- 3.01