Scholarlink

<p>We present FLOWR.ROOT, an <i>S</i><i>E</i>(3)-equivariant flow-matching foundation model that unifies pocket-aware 3D ligand generation with multi-endpoint binding affinity prediction (pIC<sub>50</sub>, p<i>K</i><sub>i</sub>, p<i>K</i><sub>d</sub>, pEC<sub>50</sub>) and pLDDT-based confidence estimation in a single backbone. One trained model supports de novo pocket-conditional generation, interaction- and pharmacophore-conditional sampling, scaffold hopping and elaboration, and fragment growing or replacement, enabled by a mixed isotropic–anisotropic prior placement strategy. Training proceeds in three stages: large-scale pre-training on billions of ligand conformations and millions of mixed-fidelity protein–ligand complexes, refinement on curated co-crystal data, and project-specific adaptation via parameter-efficient LoRA finetuning. Joint structure–affinity modelling enables inference-time importance-sampling guidance for single- and multi-objective design without external scoring functions. Case studies on kinase selectivity (CK2<i>α</i>/CLK3) and scaffold elaboration on TYK2, ER<i>α</i>, and BACE1 illustrate utility from hit identification through lead optimization.</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

FLOWR.ROOT – A flow matching-based foundation model for joint multi-purpose structure-aware 3D ligand generation and affinity prediction

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月6日

查看全文
  • Julian Cremer,
  • Tuan Le,
  • Mohammad M. Ghahremanpour,
  • Emilia Sługocka,
  • Filipe Menezes,
  • Djork-Arné Clevert

摘要

We present FLOWR.ROOT, an SE(3)-equivariant flow-matching foundation model that unifies pocket-aware 3D ligand generation with multi-endpoint binding affinity prediction (pIC50, pKi, pKd, pEC50) and pLDDT-based confidence estimation in a single backbone. One trained model supports de novo pocket-conditional generation, interaction- and pharmacophore-conditional sampling, scaffold hopping and elaboration, and fragment growing or replacement, enabled by a mixed isotropic–anisotropic prior placement strategy. Training proceeds in three stages: large-scale pre-training on billions of ligand conformations and millions of mixed-fidelity protein–ligand complexes, refinement on curated co-crystal data, and project-specific adaptation via parameter-efficient LoRA finetuning. Joint structure–affinity modelling enables inference-time importance-sampling guidance for single- and multi-objective design without external scoring functions. Case studies on kinase selectivity (CK2α/CLK3) and scaffold elaboration on TYK2, ERα, and BACE1 illustrate utility from hit identification through lead optimization.