Expanding accessible chemical space for fragment-based enumeration by orders of magnitude through optimization of the Chemically Reasonable Mutations (CReM) framework.
- 1TandemAI, New York, NY, 10036, USA.
- 2TandemAI, New York, NY, 10036, USA. [email protected].
- 3TandemAI, New York, NY, 10036, USA. [email protected].
Abstract
The size of synthetically accessible small molecule chemical space has rapidly grown to billions, and even trillions, of molecules, unlocking tremendous new opportunities for drug discovery. Fully leveraging these ultralarge chemical libraries, however, will strain existing computational tools, requiring novel approaches to efficiently search and process this vast space. The Chemically Reasonable Mutations (CReM) method is a powerful approach for the generation of novel and synthesizable molecules using precomputed fragment libraries. While expanding the size of these libraries could greatly enhance CReM's ability to afford higher quality ideas, improving the scalability of the current framework is needed to take advantage of these larger libraries in practice. Here, we introduce an optimized fragment library framework, oCReM, that eliminates redundancies in the fragment database along with modifying corresponding core functions in CReM. oCReM affords a reduction of storage requirements and query times by significantly over 50%, enabling the use of ultralarge fragment libraries on the scale of tens of billions of fragments and dramatically expanding the size of chemical space available for generative design. We show that the molecules generated using the larger fragment libraries enabled by oCReM are more diverse, drug-like, and potent compared to those generated using a smaller library. SCIENTIFIC CONTRIBUTIONS: We introduce oCReM, an open-source software framework that broadens the scope of the Chemically ReasonableMutations (CReM) method by enabling the use of billion-level fragment databases derived from ultralarge chemicallibraries. oCReM achieves this scalability through an optimized fragment database architecture and associated queryprotocols, signifi cantly reducing both storage requirements and query times. We demonstrate that expanding thefragment base leads to quantitative improvements in the diversity and quality of generated molecules, highlightingoCReM's potential to advance large-scale, fragment-based molecular design.
Related
- Beyond Orbital Rotations: Correlation-Rank Limits and Clifford-Accessible Measurement, from Algebra and Global Optimization
- Broadly Accessible and Highly Active Hydrophosphination Catalysis with Simple Calcium Compounds in DMSO Solution
- Enhancing electronic conductivity and solvent accessible porosity via oxidative deinsertion in a vanadium catecholate framework
- Macroscopic two-dimensional sheets by chemically triggered self-assembly.
- Biobased Cyclic Enoate Monomers: Enabling Intrinsically Crystalline, Chemically Recyclable, Ultratough Polymers
BibTeX
@article{hu2026expanding,
title = {{Expanding accessible chemical space for fragment-based enumeration by orders of magnitude through optimization of the Chemically Reasonable Mutations (CReM) framework.}},
author = {Shaojin Hu and Qinyu Chen and Yinhui Yi and Paul Pillot and James Xu and Evgeny Gutkin and Abir Ganguly and Albert C Pan},
journal = {Journal of cheminformatics},
year = {2026},
month = aug,
doi = {10.1186/s13321-026-01265-8},
url = {https://europepmc.org/article/MED/42958572},
note = {CC BY},
}
RIS
TY - JOUR
TI - Expanding accessible chemical space for fragment-based enumeration by orders of magnitude through optimization of the Chemically Reasonable Mutations (CReM) framework.
AU - Shaojin Hu
AU - Qinyu Chen
AU - Yinhui Yi
AU - Paul Pillot
AU - James Xu
AU - Evgeny Gutkin
AU - Abir Ganguly
AU - Albert C Pan
PY - 2026
DA - 2026/08/01
JO - Journal of cheminformatics
DO - 10.1186/s13321-026-01265-8
UR - https://europepmc.org/article/MED/42958572
AB - The size of synthetically accessible small molecule chemical space has rapidly grown to billions, and even trillions, of molecules, unlocking tremendous new opportunities for drug discovery. Fully leveraging these ultralarge chemical libraries, however, will strain existing computational tools, requiring novel approaches to efficiently search and process this vast space. The Chemically Reasonable Mutations (CReM) method is a powerful approach for the generation of novel and synthesizable molecules using precomputed fragment libraries. While expanding the size of these libraries could greatly enhance CReM's ability to afford higher quality ideas, improving the scalability of the current framework is needed to take advantage of these larger libraries in practice. Here, we introduce an optimized fragment library framework, oCReM, that eliminates redundancies in the fragment database along with modifying corresponding core functions in CReM. oCReM affords a reduction of storage requirements and query times by significantly over 50%, enabling the use of ultralarge fragment libraries on the scale of tens of billions of fragments and dramatically expanding the size of chemical space available for generative design. We show that the molecules generated using the larger fragment libraries enabled by oCReM are more diverse, drug-like, and potent compared to those generated using a smaller library. SCIENTIFIC CONTRIBUTIONS: We introduce oCReM, an open-source software framework that broadens the scope of the Chemically ReasonableMutations (CReM) method by enabling the use of billion-level fragment databases derived from ultralarge chemicallibraries. oCReM achieves this scalability through an optimized fragment database architecture and associated queryprotocols, signifi cantly reducing both storage requirements and query times. We demonstrate that expanding thefragment base leads to quantitative improvements in the diversity and quality of generated molecules, highlightingoCReM's potential to advance large-scale, fragment-based molecular design.
SN - 1758-2946
ER -