Problem
Research questions and friction points this paper is trying to address.
protein binder design
wet-lab validation
shortlisting
candidate selection
Natural-Language-Guided Generator-Agnostic Shortlisting for Protein Binder Design
๐ค AI Summary
็ ็ฉถไฝฟ็จLLMไป้ข่ฎก็ฎ็็ปๆ็ฝฎไฟกๅบฆๅ็้ข่ดจ้ไปฃ็ๅๆฐ็ๆๅคๆๆ ๆๅบ็ญ็ฅ๏ผไปฅ่งฃๅณ่็ฝ่ดจ็ปๅๅ่ฎพ่ฎกไธญๅ้่
็ญ้็้ฎ้ขใ
๐ Abstract
Modern de novo design workflows generate many candidate protein binders, but wet-lab validation capacity remains limited, making shortlisting a major bottleneck. We study whether LLMs can generate multi-metric ranking policies from precomputed structural-confidence and interface-quality proxy scores. Rather than proposing a new protein binder design pipeline, we focus on post-generation binder shortlisting: selecting the final top-K candidates from already generated binder pools using a shared panel of precomputed proxy scores. On the 10-target held-out split, averaging performance over five sampled global iterative gpt-4o policies reaches 0.589 Recall@10, modestly improving over the strongest single-feature fixed baseline, Protenix binder ipTM, which reaches 0.571 Recall@10. On the 3-target held-out subset comprising Nipah, RBX1, and TREM2, target-conditioned iterative gpt-5.4 policies reach the strongest LLM performance, with 0.519 Recall@10 and 0.583 NDCG@10. These results suggest that LLM-generated ranking policies can act as an interpretable post-generation decision layer for combining heterogeneous proxy metrics to prioritize binders from large candidate pools.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Large Language Models
Multi-metric Ranking Policies
Post-generation Shortlisting
Protein Binder Design
๐ Similar Papers
