Machine learning in protein structure prediction

Prediction of protein structure from sequence has been intensely studied for many decades, owing to the problem's importance and its uniquely well-defined physical and computational bases. While progress has historically ebbed and flowed, the past two years saw dramatic advances driven by the increasing neuralization of structure prediction pipelines, whereby computations previously based on energy models and sampling procedures are replaced by neural networks. The extraction of physical contacts from the evolutionary record; the distillation of sequence-structure patterns from known structures; the incorporation of templates from homologs in the Protein Databank; and the refinement of coarsely predicted structures into finely resolved ones have all been reformulated using neural networks. Cumulatively, this transformation has resulted in algorithms that can now predict single protein domains with a median accuracy of 2.1 angstrom, setting the stage for a foundational reconfiguration of the role of biomolecular modeling within the life sciences.

Automated summary

Prediction of protein structure from sequence has made significant progress in the past two years, driven by the increasing use of neural networks in structure prediction pipelines. These neural networks have optimized the previous energy models and sampling procedures, resulting in algorithms that can now predict protein structures with a median accuracy of 2.1 angstroms.