Files and links (1)
Published, Version of Record (VoR) Open Access via Drexel Libraries Read and Publish Program 2026 Open CC BY V4.0
Journal article
Property-Driven Cocrystal Discovery via Gaussian Processes and Active Learning
Crystal growth & design, v 26(7), pp 2688-2702
16 Mar 2026
Featured in Collection : Research Supported by Drexel Libraries' OA Programs
Abstract
Cocrystallization can be used to tune key drug properties, such as aqueous solubility, without altering molecular structure; however, the space of possible coformers is enormous and design rules are empirical. We present a Bayesian optimization framework that couples Gaussian process (GP) classification and regression that can accelerate cocrystal discovery and solubility enhancement. Starting from 6338 literature-derived binary coformer pairs, vector fingerprints that combine 2D structural information (fragment and MQN fingerprints) with low-cost shape and polarity descriptors were engineered for cocrystal prediction. A GP classifier, trained on an actively constructed training set of ∼1000 coformer pairs selected by uncertainty sampling achieves up to 94% accuracy and Matthews correlation coefficient of 0.79 on a test set of >5000 unseen pairs. Property-driven coformer selection was formulated as a Bayesian optimization problem, using a machine learning model as a surrogate for aqueous solubility and Tanimoto-similarity to guide campaigns across several discovery scenarios. In simulations, the framework rapidly identifies highly soluble cocrystals, typically recovering top-5 candidates after fewer than 10 evaluations. Finally, we validate the workflow experimentally with 12 pharmaceutical and pharmaceutical-like compounds, discovering two new cocrystals, resveratrol + praziquantel and purin-6-amine + thiazole-4-carboxylic acid, with markedly enhanced aqueous solubility. These results demonstrate a practical, data-efficient route to Bayesian optimization for cocrystal design.
Metrics
1 Record Views
Details
- Title
- Property-Driven Cocrystal Discovery via Gaussian Processes and Active Learning
- Creators
- Samuel A. Appiah - Drexel UniversityMatthew A. McDonald (Corresponding Author) - Drexel University
- Publication Details
- Crystal growth & design, v 26(7), pp 2688-2702
- Publisher
- ACS Publications
- Number of pages
- 15
- Grant note
- Drexel University: NA
We would like to thank Shima Khaheshi and Myint Htoo for help with HPLC experiments. We acknowledge Carl Furner for help with DSC and TGA experiments. PXRD analyses were performed at the Materials Characterization Core at Drexel University; we thank Dr. Dmitri Barbash for expert assistance with XRD experiments. We would like to thank Pritam Roychowdhury and the UPenn X-ray Crystallography Facility for help with structural characterization.
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Chemical and Biological Engineering
- Web of Science ID
- WOS:001716348100001
- Other Identifier
- 991022171481704721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
Source: SDGs in the Output
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Chemistry, Multidisciplinary
- Crystallography
- Materials Science, Multidisciplinary