CLIPZyme:反应条件下的酶虚拟筛选
CLIPZyme: Reaction-Conditioned Virtual Screening of Enzymes
AI总结:
提出CLIPZyme框架,利用对比学习对齐酶结构与反应对,实现酶虚拟筛选,在反应信息有限时优于现有EC预测器,并展现良好泛化能力。
摘要:
对天然存在的蛋白质进行计算筛选,有潜力在数百万未表征的序列中识别出高效催化剂。目前的实验方法耗时、昂贵且劳动密集,限制了可合理筛选的酶数量。在本工作中,我们提出了一种用于酶虚拟筛选的计算框架。通过对比学习目标,我们训练CLIPZyme来编码并对齐酶结构表示与反应对。在没有标准计算基线的情况下,我们将CLIPZyme与现有的EC(酶委员会)预测器应用于虚拟酶筛选进行比较,并显示在反应信息有限的情景下性能更优(BEDROC$_{85}$为44.69%)。此外,我们评估了将EC预测器与CLIPZyme结合的效果,并展示了其在未见反应和蛋白质簇上的泛化能力。
英文摘要:
Computational screening of naturally occurring proteins has the potential to identify efficient catalysts among the hundreds of millions of sequences that remain uncharacterized. Current experimental methods remain time, cost and labor intensive, limiting the number of enzymes they can reasonably screen. In this work, we propose a computational framework for in-silico enzyme screening. Through a contrastive objective, we train CLIPZyme to encode and align representations of enzyme structures and reaction pairs. With no standard computational baseline, we compare CLIPZyme to existing EC (enzyme commission) predictors applied to virtual enzyme screening and show improved performance in scenarios where limited information on the reaction is available (BEDROC$_{85}$ of 44.69%). Additionally, we evaluate combining EC predictors with CLIPZyme and show its generalization capacity on both unseen reactions and protein clusters.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。