Nature

Expanding functional protein sequence spaces using generative adversarial networks

A protein’s three-dimensional (3D) structure, physicochemical properties and molecular function are defined by its amino-acid sequence. From the 20 commonly occurring proteinogenic amino acids, a ...
Nature

Large language models generate functional protein sequences across diverse families

Deep-learning language models have shown promise in various biotechnological applications, including protein design and engineering. Here we describe ProGen, a language model that can generate protein ...