Deep Learning in Protein Structural Modeling and Design

Abstract

Deep learning is catalyzing a scientific revolution fueled by big data, accessible toolkits, and powerful computational resources, impacting many fields including protein structural modeling. Protein structural modeling, such as predicting structure from amino acid sequence and evolutionary information, designing proteins toward desirable functionality, or predicting properties or behavior of a protein, is critical to understand and engineer biological systems at the molecular level. In this review, we summarize the recent advances in applying deep learning techniques to tackle problems in protein structural modeling and design. We dissect the emerging approaches using deep learning techniques for protein structural modeling, and discuss advances and challenges that must be addressed. We argue for the central importance of structure, following the "sequence → structure → function" paradigm. This review is directed to help both computational biologists to gain familiarity with the deep learning methods applied in protein modeling, and computer scientists to gain perspective on the biologically meaningful problems that may benefit from deep learning techniques.

Advances to tackle backbone flexibility in protein docking

“…Although protein folding has been one prime focus of deep learning methods in biology (e.g., AlphaFold [63,64] and RaptorX [65]), in recent years, a few studies have explicitly addressed challenges relevant to protein docking [66]. Protein binding sites can be thought of as an information-rich molecular space that can be mined for elucidating protein interactions [67,68,69].…”

Fast end-to-end learning on protein surfaces

“…predict a sequence that will fold into a partic-ular structure), has also benefited from deep learning methods [23]. We refer to [21] for a comprehensive overview.…”

“…Deep learning methods have increasingly been applied to a broad range of problems in protein science [21], with the particularly notorious success of DeepMind's AlphaFold to predict 3D protein structure from sequence [37]. Recently, Gainza et al [20] introduced MaSIF, one of the first conceptual approaches for geometric deep learning on protein molecular surfaces allowing to predict their binding.…”