Data-driven computational protein design

Computational protein design can generate proteins not found in nature that adopt desired structures and perform novel functions. Although proteins could, in theory, be designed with ab initio methods, practical success has come from using large amounts of data that describe the sequences, structures, and functions of existing proteins and their variants. We present recent creative uses of multiple-sequence alignments, protein structures, and high-throughput functional assays in computational protein design. Approaches range from enhancing structure-based design with experimental data to building regression models to training deep neural nets that generate novel sequences. Looking ahead, deep learning will be increasingly important for maximizing the value of data for protein design.

Automated summary

Computational protein design has the capability to generate proteins with desired structures and novel functions not found in nature. The success of this approach relies heavily on utilizing extensive data on existing proteins and their variants, ranging from sequences to structures and functions. Creative uses of multiple-sequence alignments, protein structures, and high-throughput functional assays have been demonstrated in recent studies, with the potential for deep learning to play an increasingly important role in maximizing the value of data for protein design.