Scholarlink

Abstract <p>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.</p> Scientific Contributions <p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Expanding accessible chemical space for fragment-based enumeration by orders of magnitude through optimization of the Chemically Reasonable Mutations (CReM) framework

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月1日

查看全文
  • Shaojin Hu,
  • Qinyu Chen,
  • Yinhui Yi,
  • Paul Pillot,
  • James Xu,
  • Evgeny Gutkin,
  • Abir Ganguly,
  • Albert C. Pan

摘要

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.