JEDEL: Zero-Shot DNA-Encoded Library Design for Early-Stage Drug Discovery

πŸ“… 2026-06-21
πŸ“ˆ Citations: 0
✨ Influential: 0
πŸ“„ PDF
πŸ€– AI Summary
This work proposes an end-to-end approach that directly generates synthesizable, focused DNA-encoded libraries (DELs) from the three-dimensional pharmacophores of active ligandsβ€”a capability lacking in conventional generative models, which often produce compounds incompatible with experimental synthesis. By mapping pharmacophoric interaction patterns onto combinatorial synthetic routes constrained by commercially available building blocks and validated reaction rules, the method guarantees that all generated molecules are experimentally accessible without requiring target-specific retraining. Evaluated across 18 protein targets, the resulting DELs significantly outperform random and diversity-based baselines in predicted binding affinity, pharmacophore recovery rate, and sampling efficiency.
πŸ“ Abstract
We present JEDEL, a framework for generating synthesis-ready DNA-encoded libraries (DELs) directly from three-dimensional pharmacophore representations of active ligands. JEDEL is the first model to map pharmacophore interaction patterns to actionable, scalable synthesis instructions, enabling the design of targeted libraries comprising potentially millions of molecules. Unlike existing generative approaches that produce virtual compounds requiring downstream synthesis planning, JEDEL operates within the space of purchasable building blocks and validated reactions, ensuring that every output is experimentally realizable by construction. JEDEL learns a predictive alignment between pharmacophore geometry and molecular structure and decodes this into combinatorial synthesis routes at scale. Across 18 protein targets, it generates focused libraries that outperform random and diversity-based baselines in predicted binding affinity, pharmacophore recovery, and sample efficiency, without target-specific retraining. JEDEL enables a shift from virtual molecule generation to experimentally deployable library design.
Problem

Research questions and friction points this paper is trying to address.

DNA-encoded library
pharmacophore
drug discovery
library design
synthesis-ready
Innovation

Methods, ideas, or system contributions that make the work stand out.

DNA-encoded library
pharmacophore-based design
zero-shot generation
combinatorial synthesis
generative chemistry
πŸ”Ž Similar Papers
No similar papers found.
πŸ’Ό Related Jobs
No related jobs found.
Z
Zygimantas Jocys
School of Electronics and Computer Science, University of Southampton, Southampton, SO17 1BJ, United Kingdom
Zhanxing Zhu
Zhanxing Zhu
Associate Professor, ECS, University of Southampton
Deep learningrobust and trustworthy machine learningtime seriesAI for Science
H
Henriette M. G. Willems
The ALBORADA Drug Discovery Institute, University of Cambridge, Hills Road, Cambridge, CB2 0AH, United Kingdom
K
Katayoun Farrahi
School of Electronics and Computer Science, University of Southampton, Southampton, SO17 1BJ, United Kingdom