Suppr超能文献

ColabFold:让蛋白质折叠变得人人可用。

ColabFold: making protein folding accessible to all.

机构信息

Quantitative and Computational Biology, Max Planck Institute for Multidisciplinary Sciences, Göttingen, Germany.

School of Biological Sciences, Seoul National University, Seoul, South Korea.

出版信息

Nat Methods. 2022 Jun;19(6):679-682. doi: 10.1038/s41592-022-01488-1. Epub 2022 May 30.

Abstract

ColabFold offers accelerated prediction of protein structures and complexes by combining the fast homology search of MMseqs2 with AlphaFold2 or RoseTTAFold. ColabFold's 40-60-fold faster search and optimized model utilization enables prediction of close to 1,000 structures per day on a server with one graphics processing unit. Coupled with Google Colaboratory, ColabFold becomes a free and accessible platform for protein folding. ColabFold is open-source software available at https://github.com/sokrypton/ColabFold and its novel environmental databases are available at https://colabfold.mmseqs.com .

摘要

ColabFold 通过将 MMseqs2 的快速同源搜索与 AlphaFold2 或 RoseTTAFold 相结合,提供了蛋白质结构和复合物的加速预测。ColabFold 的搜索速度快 40-60 倍,并且优化了模型的使用,使得在具有一个图形处理单元的服务器上,每天可以预测近 1000 个结构。结合 Google Colaboratory,ColabFold 成为了一个免费且易于访问的蛋白质折叠平台。ColabFold 是一个开源软件,可在 https://github.com/sokrypton/ColabFold 上获得,其新颖的环境数据库可在 https://colabfold.mmseqs.com 上获得。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1794/9184281/e1b362e94302/41592_2022_1488_Fig1_HTML.jpg

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验