JURA Bio Model — это революционная языковая модель для белков, которая делает синтез биологических последовательностей в триллион раз дешевле. Благодаря учету производственных ограничений, ИИ генерирует структуры, которые можно массово и эффективно создавать в реальных лабораториях.
We introduce a method to reduce the cost of synthesizing proteins and other biological sequences designed by a generative model by as much as a trillion-fold. In particular, we make our generative models manufacturing-aware, such that model-designed sequences can be efficiently synthesized in the real world with extreme parallelism. We demonstrate by training and synthesizing samples from generative models of antibodies, T cell antigens and DNA polymerases. For example, we train a manufacturing-aware generative model on 300 million observed human antibodies and synthesize ∼1017 generated designs from the model, achieving a sample quality comparable to a state-of-the-art protein language model, at a cost of 103 dollars. Using previous methods, synthesis of a library of the same accuracy and size would cost roughly a quadrillion (1015) dollars.