Researchers have developed JEDEL, a novel framework designed for the zero-shot generation of DNA-encoded libraries (DELs) directly from three-dimensional pharmacophore representations of active ligands. This system is the first to translate pharmacophore interaction patterns into scalable synthesis instructions, capable of designing libraries with millions of molecules. Unlike previous generative models that produce virtual compounds requiring subsequent synthesis planning, JEDEL ensures all outputs are experimentally feasible by operating within the constraints of purchasable building blocks and validated reactions. JEDEL has demonstrated superior performance in generating focused libraries for 18 protein targets compared to random and diversity-based baselines, showing improved binding affinity, pharmacophore recovery, and sample efficiency without the need for target-specific retraining. AI
IMPACT This framework could accelerate early-stage drug discovery by enabling the rapid design of targeted, experimentally viable molecule libraries.
RANK_REASON The cluster contains an academic paper detailing a new computational framework for drug discovery. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
