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.

SummaryColabFold is an easy-to-use Notebook based environment for fast and convenient protein structure predictions. Its structure prediction is powered by AlphaFold2 and RoseTTAFold combined with a fast multiple sequence alignment generation stage using MMseqs2. MMseqs2’s MSAs produce more accurate predictions while being ~16 faster compared to the AlphaFold2’s MSA stage. ColabFold also offers many advanced features, such as homo- and hetero-complex modeling and exposes AlphaFold2 internals. When coupled with Google Colab, ColabFold becomes a free and accessible platform for protein folding that does not require any installation or expensive hardware.CodeColabFold is free open-source (MIT) [1] software available at https://github.com/sokrypton/ColabFold.Contactmilot.mirdita@mpibpc.mpg.de, so@fas.harvard.edu, martin.steinegger@snu.ac.kr

ColabFold offers accelerated protein structure and complex predictions by combining the fast homology search of MMseqs2 with AlphaFold2 or RoseTTAFold. ColabFold's 20-30x faster search and optimized model use allows predicting thousands of proteins per day on a server with one GPU. Coupled with Google Colaboratory, ColabFold becomes a free and accessible platform for protein folding. ColabFold is open-source software available at github.com/sokrypton/ColabFold. Its novel environmental databases are available at colabfold.mmseqs.com.

The quality of model structures generated by contemporary protein structure prediction methods strongly depends on the degree of similarity between the target and available template structures. Therefore, the importance of improving template-based model structures beyond the accuracy available from template information has been emphasized in the structure prediction community. The GalaxyRefine web server, freely available at http://galaxy.seoklab.org/refine, is based on a refinement method that has been successfully tested in CASP10. The method first rebuilds side chains and performs side-chain repacking and subsequent overall structure relaxation by molecular dynamics simulation. According to the CASP10 assessment, this method showed the best performance in improving the local structure quality. The method can improve both global and local structure quality on average, when used for refining the models generated by state-of-the-art protein structure prediction servers.

Three-dimensional protein structures provide invaluable information for understanding and regulating biological functions of proteins. The GalaxyWEB server predicts protein structure from sequence by template-based modeling and refines loop or terminus regions by ab initio modeling. This web server is based on the method tested in CASP9 (9th Critical Assessment of techniques for protein Structure Prediction) as ‘Seok-server’, which was assessed to be among top performing template-based modeling servers. The method generates reliable core structures from multiple templates and re-builds unreliable loops or termini by using an optimization-based refinement method. In addition to structure prediction, a user can also submit a refinement only job by providing a starting model structure and locations of loops or termini to refine. The web server can be freely accessed at http://galaxy.seoklab.org/.

We present the results for CAPRI Round 30, the first joint CASP-CAPRI experiment, which brought together experts from the protein structure prediction and protein-protein docking communities. The Round comprised 25 targets from amongst those submitted for the CASP11 prediction experiment of 2014. The targets included mostly homodimers, a few homotetramers, and two heterodimers, and comprised protein chains that could readily be modeled using templates from the Protein Data Bank. On average 24 CAPRI groups and 7 CASP groups submitted docking predictions for each target, and 12 CAPRI groups per target participated in the CAPRI scoring experiment. In total more than 9500 models were assessed against the 3D structures of the corresponding target complexes. Results show that the prediction of homodimer assemblies by homology modeling techniques and docking calculations is quite successful for targets featuring large enough subunit interfaces to represent stable associations. Targets with ambiguous or inaccurate oligomeric state assignments, often featuring crystal contact-sized interfaces, represented a confounding factor. For those, a much poorer prediction performance was achieved, while nonetheless often providing helpful clues on the correct oligomeric state of the protein. The prediction performance was very poor for genuine tetrameric targets, where the inaccuracy of the homology-built subunit models and the smaller pair-wise interfaces severely limited the ability to derive the correct assembly mode. Our analysis also shows that docking procedures tend to perform better than standard homology modeling techniques and that highly accurate models of the protein components are not always required to identify their association modes with acceptable accuracy.

Protein–peptide interactions are involved in a wide range of biological processes and are attractive targets for therapeutic purposes because of their small interfaces. Therefore, effective protein–peptide docking techniques can provide the basis for potential therapeutic applications by enabling an atomic-level understanding of protein interactions. With the increasing number of protein–peptide structures deposited in the protein data bank, the prediction accuracy of protein-peptide docking can be enhanced by utilizing the information provided by the database. The GalaxyPepDock web server, which is freely accessible at http://galaxy.seoklab.org/pepdock, performs similarity-based docking by finding templates from the database of experimentally determined structures and building models using energy-based optimization that allows for structural flexibility. The server can therefore effectively model the structural differences between the template and target protein–peptide complexes. The performance of GalaxyPepDock is superior to those of the other currently available web servers when tested on the PeptiDB set and on recently released complex structures. When tested on the CAPRI target 67, GalaxyPepDock generates models that are more accurate than the best server models submitted during the CAPRI blind prediction experiment.

The family of G-protein coupled receptors (GPCRs) is one of the largest protein families in the human genome. GPCRs transduct chemical signals from extracellular to intracellular regions via a conformational switch between active and inactive states upon ligand binding. While experimental structures of GPCRs remain limited, highaccuracy computational predictions are now possible with AlphaFold2. However, AlphaFold2 only predicts one state and is biased toward either the active or inactive conformation depending on the GPCR class. Here, a multi-state prediction protocol is introduced that extends AlphaFold2 to predict either active or inactive states at very high accuracy using state-annotated templated GPCR databases. The predicted models accurately capture the main structural changes upon activation of the GPCR at the atomic level. For most of the benchmarked GPCRs (10 out of 15), models in the active and inactive states were closer to their corresponding activation state structures. Median RMSDs of the transmembrane regions were 1.12 Å and 1.41 Å for the active and inactive state models, respectively. The models were more suitable for protein-ligand docking than the original AlphaFold2 models and template-based models. Finally, our prediction protocol predicted accurate GPCR structures and GPCR-peptide complex structures in GPCR Dock 2021, a blind GPCR-ligand complex modeling competition. We expect that high accuracy GPCR models in both activation states will promote understanding in GPCR activation mechanisms and drug discovery for GPCRs. At the time, the new protocol paves the way towards capturing the dynamics of proteins at high-accuracy via machine-learning methods.