category
Cell Systems
date
Jan 13, 2026
slug
status
Published
summary
创新性地利用蛋白质语言模型的嵌入表示,从序列信息预测无序区域与结合伙伴间的接触图和界面残基,实现了对IDR介导相互作用的大规模表征与调控。
tags
蛋白质组学
type
Post
📄 原文题目
Disobind: A sequence-based, partner-dependent contact map and interface residue predictor for intrinsically disordered regions
🔗 原文链接
💡 AI 核心解读
创新性地利用蛋白质语言模型的嵌入表示,从序列信息预测无序区域与结合伙伴间的接触图和界面残基,实现了对IDR介导相互作用的大规模表征与调控。
📝 英文原版摘要
Identifying binding sites of intrinsically disordered regions (IDRs) is challenging, as they adopt diverse binding modes with different partners. Our method, Disobind, predicts inter-protein contact maps and interface residues for IDRs and their partners from their sequences, leveraging embeddings from protein language models. It can be used to characterize and modulate IDR-mediated binding at the proteome scale.
