AlphaFold predictions are valuable hypotheses and accelerate but do not replace experimental structure determination

Artificial intelligence-based protein structure prediction methods such as AlphaFold have revolutionized structural biology. The accuracies of these predictions vary, however, and they do not take into account ligands, covalent modifications or other environmental factors. Here, we evaluate how well AlphaFold predictions can be expected to describe the structure of a protein by comparing predictions directly with experimental crystallographic maps. In many cases, AlphaFold predictions matched experimental maps remarkably closely. In other cases, even very high-confidence predictions differed from experimental maps on a global scale through distortion and domain orientation, and on a local scale in backbone and…

• W
  Wellcome

  Award: 209407/Z/17/Z
• WT
  Wellcome Trust

  Awards: Z/17/Z, 209407/Z/17/Z
• NI
  National Institutes of Health

  Awards: GM063210, DE-AC02-05CH11231
• NI
  National Institute of General Medical Sciences

  Award: GM063210
• LB
  Lawrence Berkeley National Laboratory

  Awards: DE-AC02-05CH11231, 05CH11231, AC02-05CH11231