MutFormer: A context-dependent transformer-based model to predict deleterious missense mutations from protein sequences in the human genome. (arXiv:2110.14746v3 [q-bio.GN] UPDATED)

Various machine-learning models, including deep neural network models, have
already been developed to predict deleteriousness of missense (non-synonymous)
mutations. Still, potential improvements to the current state of the art may
benefit from a fresh look at the biological problem using more sophisticated
self-adaptive machine-learning approaches. Recent advances in the natural
language processing field show transformer models-a type of deep neural
network-to be particularly powerful at modeling sequence information with
context dependence. In this study, we introduce MutFormer, a transformer-based
model …

arxiv bio context genome human protein transformer