BioML Seminar 4.1 - Designing proteins with language models

​​​​​​[IN PERSON EVENT IN BERKELEY WITH ZOOM OPTION]

​​​​​​​​Join us for a new seminar from the BioML group in Machine Learning at Berkeley, sponsored by Amplify Partners. This week, we're excited to host Jeff Ruffolo, ML scientist and Head of Protein Design at Profluent!

​Talk Details
Protein language models learn from diverse sequences spanning the evolutionary tree and have proven to be powerful tools for sequence design, variant effect prediction, and structure prediction. This presentation will discuss the recent work on scaling protein language models, both in terms of sequence data and model parameters, and explore their behavior in generative and predictive tasks, then present a case study on designing highly functional genome editing proteins using these models.

​Speaker Bio
Jeff Ruffolo is Head of Protein Design at Profluent Bio, where he develops machine learning methods for functional protein design. He obtained his PhD in biophysics at Johns Hopkins University, where he worked in the lab of Jeffrey Gray. During this time, he developed deep learning tools for antibody structure prediction, language modeling, and representation learning. At Profluent, he has contributed to the OpenCRISPR initiative and led the development of next-generation protein language models with atomistic control for function protein generation.