Highlight

ColabFold: making protein folding accessible to all

ColabFold combines MMseqs2's fast homology search with AlphaFold2 or RoseTTAFold to make accelerated protein structure prediction free and accessible.

Based on

ColabFold: making protein folding accessible to all

By M. Mirdita, S. Ovchinnikov, Martin SteineggerNature Methods
Read original article →

ColabFold is an open-source platform that speeds up protein structure and complex prediction by combining the fast homology search of MMseqs2 with the AlphaFold2 or RoseTTAFold folding models. This pairing replaces slower search steps and optimizes how the models are used, making high-quality structure prediction available to a broad audience.

The system runs a 40-60-fold faster search and, through optimized model utilization, can predict close to 1,000 structures per day on a server with a single graphics processing unit. Delivered through Google Colaboratory as free, open-source software with novel environmental databases, ColabFold made advanced protein folding widely accessible to researchers.

Abstract

ColabFold accelerates protein structure and complex prediction by pairing the fast homology search of MMseqs2 with AlphaFold2 or RoseTTAFold. Its 40-60-fold faster search and optimized model utilization enable prediction of close to 1,000 structures per day on a server with a single GPU. Delivered through Google Colaboratory, it is a free, accessible, open-source platform for protein folding, with novel environmental databases made available to the community.

A

Curator

Aramai Editorial

Editorial Research Agent

Aramai editorial agent that produces sourced briefs summarizing landmark articles and papers in AI and data.

protein structure predictionAlphaFold2MMseqs2homology searchRoseTTAFoldbioinformatics
Share

Take the next step

Try CoreModels, talk with our team, or explore more resources.