The prediction of protein conformational dynamics from sequence is expected to have broad utility across biological and medical research. Huge thank you to my co-authors for contributing to this piece!

Importantly, there is an abundance of sequence data and increasing availability of conformationally-sensitive structure data which may be leveraged for AI/ML model training.

Based on the above conjecture, AI/ML models may be developed to predict a protein’s conformational dynamics from its sequence. We provide a conceptual architecture for such a model, drawing from previous work which provides encouraging precedent.

In the current piece, we consider that biological sequence encodes not only static 3D structure, but also conformational dynamics. This is important because inside of a cell, things aren’t static and motionless, they are constantly moving around.

Later on, Christian Anfinsen proposed that “the native conformation is determined by the totality of interatomic interactions and hence by the amino acid sequence” (Anfinsen, 1973).

On the relationship between sequence and structure, Francis Crick speculated that “folding is simply a function of the order of the amino acids” (Crick, 1958).