Where to From Here?

Frontiers in Molecular Biosciences

Robert Schleif¹  Manuel Espinosa² 

[1] Department of Biology, Johns Hopkins University, Baltimore, MA, United States;Department of Molecular and Cell Biology, Centro de Investigaciones Biológicas Margarita Salas, CSIC, Madrid, Spain;

关键词: artificial intelligence;    biocomputing;    deep learning;    protein structure and function;    prediction of protein structures;   

DOI  :  10.3389/fmolb.2022.848444

来源: DOAJ

【 摘 要 】

The biological-biochemical community has been shocked and delighted by the remarkable progress that has recently been made on a problem that has consumed the attention, energy, and resources of many, if not most of the scientists in the field for the past 50 years. The problem has been to predict the tertiary structure of a protein merely from its amino acid sequence. Nature does it easily enough, but it has been an incredibly difficult problem, often considered intractable, for humankind. The breakthrough has come in the form of two computer-based approaches, AlphaFold2 and RoseTTAFold in conjunction with factors such as the use of vast computing power, the field of artificial intelligence, and the existence of huge protein sequence databases. The advancement of these tools depended upon and was stimulated by the last 50 years of development of smaller and smaller and more and more powerful electronics components, mainly processors and memory. Along with the problem of protein folding, determining the function or mechanism of action of proteins has similarly limped along as did protein folding until the recent breakthroughs. Perhaps AlphaFold2 and RoseTTAFold can substantially aid in protein mechanistic studies. Now it is not completely insane to consider what might be the next grand challenge in biochemistry-biology. We offer several possibilities.

【 授权许可】

Unknown