FALCON2 web interface for automated high-quality protein structure prediction

Accurate prediction of protein tertiary structures is highly desired as the knowledge of protein structures provides invaluable insights into protein functions.
FALCON2 is a web server for high-quality prediction of protein tertiary structures. FALCON2 incorporates two prediction approaches, namely, ProALIGN and ProFOLD. ProALIGN is a template-based modeling approach, which aligns a target protein with templates through exploiting the patterns of context-specific alignment motifs and then builds the final structure with reference to the homologous templates. In contrast, ProFOLD is an {\it ab initio} prediction approach: it uses an end-to-end neural network to estimate inter-residue distances of target proteins and builds structure that satisfies these distance constraints. For a target protein, FALCON2 executes ProALIGN and ProFOLD simultaneously to predict possible structures and selects the most likely one as the final prediction result.
We evaluated FALCON2 on widely-used benchmarks, including 104 CASP13 (the 13th Critical Assessment of protein Structure Prediction) targets and 91 CASP14 targets. On these targets, FALCON2 achieves state-of-the-art performance compared with existing approaches.
FALCON2 server has been developed to automatically predict the three-dimensional structure of proteins. FALCON2 provides an easy-to-use prediction web service for the community and we expect it to enable insights into deep understanding of protein functions.