CLEAN Database: providing enzyme function coverage for over 55 million sequences.
酶功能注释对解析生物系统和推动理性酶设计至关重要,但已知蛋白质序列中仅有少部分具有实验表征的酶功能,序列空间快速扩张与可靠功能注释之间的差距不断加大。人工智能进展促进了基于蛋白质序列的准确、高通量酶功能预测。本文介绍CLEAN数据库(CLEAN DB),该资源涵盖1098305株菌株的超过5500万条酶功能注释,由CLEAN人工智能模型预测。数据库提供直观网页界面,用户可通过灵活查询选项高效搜索、浏览和下载酶功能数据;基于蛋白质语言模型,CLEAN DB还支持通过交互式热图、结构叠加和表格数据可视化进行突变效应预测。CLEAN DB可望成为推动酶发现及其在合成生物学、代谢工程、酶工程、逆合成和药物发现中应用的平台。数据库免费开放,网址为https://cleandb.platform.moleculemaker.org/。
查看扩展信息
完整作者
Le Yuan、Jianan Canal Li、Miaoyuan Wen、David M Bianchi、Katherine Arneson、Bingji Guo、Sara Lambert、Chris Stephens、Tianhao Yu、Lijiang Fu、Christopher Pond、Matthew J Berry、Huimin Zhao
作者机构
- Department of Chemical and Biomolecular Engineering, University of Illinois Urbana-Champaign, Urbana, IL 61801, United States.
- Carl R. Woese Institute for Genomic Biology, University of Illinois Urbana-Champaign, Urbana, IL 61801, United States.
- NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign, Urbana, IL 61801, United States.
- Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720, United States.
- School of Information Sciences, University of Illinois Urbana-Champaign, Champaign, IL 61820, United States.
- National Center for Supercomputing Applications, University of Illinois Urbana-Champaign, Urbana, IL 61801, United States.
- NSF iBioFoundry, University of Illinois Urbana-Champaign, Urbana, IL 61801, United States.
- NSF Global Center for Biofoundry Applications, University of Illinois Urbana-Champaign, Urbana, IL 61801, United States.
技术路线
数据/样本:汇总1,098,305株菌株的蛋白序列,由CLEAN AI模型预测获得>5500万条酶功能注释;分析:通过网页界面提供灵活查询的检索、浏览与下载功能,并以蛋白语言模型支持突变效应预测,结果以交互热图、结构叠合和表格可视化展示;验证:原文未报告对预测注释或突变效应预测的实验验证。
最近 5 个完整年度引用趋势
不含 2026 年,仅展示最近 5 个完整年度。

为什么值得关注
暂未整理