PT - JOURNAL ARTICLE AU - Shroff, Raghav AU - Cole, Austin W. AU - Morrow, Barrett R. AU - Diaz, Daniel J. AU - Donnell, Isaac AU - Gollihar, Jimmy AU - Ellington, Andrew D. AU - Thyer, Ross TI - A structure-based deep learning framework for protein engineering AID - 10.1101/833905 DP - 2019 Jan 01 TA - bioRxiv PG - 833905 4099 - http://biorxiv.org/content/early/2019/11/08/833905.short 4100 - http://biorxiv.org/content/early/2019/11/08/833905.full AB - While deep learning methods exist to guide protein optimization, examples of novel proteins generated with these techniques require a priori mutational data. Here we report a 3D convolutional neural network that associates amino acids with neighboring chemical microenvironments at state-of-the-art accuracy. This algorithm enables identification of novel gain-of-function mutations, and subsequent experiments confirm substantive phenotypic improvements in stability-associated phenotypes in vivo across three diverse proteins.