Protein tertiary structure prediction and refinement using deep learning and Rosetta in CASP14

The trRosetta structure prediction method employs deep learning to generate predicted residue-residue distance and orientation distributions from which 3D models are built. We sought to improve the method by incorporating as inputs (in addition to sequence information) both language model embeddings and template information weighted by sequence similarity to the target. We also developed a refinement pipeline that recombines models generated by template-free and template utilizing versions of trRosetta guided by the DeepAccNet accuracy predictor. Both benchmark tests and CASP results show that the new pipeline is a considerable improvement over the original trRosetta, and it is faster and requires less computing resources, completing the entire modeling process in a median < 3 h in CASP14. Our human group improved results with this pipeline primarily by identifying additional homologous sequences for input into the network. We also used the DeepAccNet accuracy predictor to guide Rosetta high-resolution refinement for submissions in the regular and refinement categories; although performance was quite good on a CASP relative scale, the overall improvements were rather modest in part due to missing inter-domain or inter-chain contacts.

Automated summary

The trRosetta structure prediction method utilizes deep learning to generate predicted residue-residue distance and orientation distributions to build 3D models. By incorporating language model embeddings and weighted template information based on sequence similarity, along with a refinement pipeline guided by DeepAccNet accuracy predictor, the new pipeline has shown considerable improvement over the original trRosetta in both benchmark tests and CASP results, completing the modeling process faster and with less computing resources.