Skip to main content

Please join us for a Statistics and DSI joint colloquium.

Thursday, February 6
2:00pm – 3:00pm
Jones Hall 303
5747 S Ellis Avenue
Chicago, IL 60637

Abstract: Generative modeling offers a powerful paradigm for designing novel functional DNA, RNA and protein sequences. In this talk, I introduce experimental design methods to efficiently manufacture samples from generative models of biomolecules in the real world. The algorithms merge statistical techniques for approximate sampling with physical randomness. I also develop tools to rigorously evaluate the quality of manufactured samples, including nonparametric two-sample tests with consistency guarantees and scalable algorithms. I demonstrate synthesizing ~10^16 samples from a generative model of human antibodies, at a sample quality comparable to state-ofthe-art protein language models, and a cost of ~$10^3. The library yields candidate therapeutics for “undruggable” cancer targets. Using previous methods, manufacturing a DNA library of the same size and quality would cost roughly ~$10^15.

Bio:  Eli Weinstein, The Data Science Institute, Columbia University. I’m a postdoctoral research scientist with David Blei at Columbia University. Broadly, I work in probabilistic machine learning and its application to the natural sciences. If you would like to learn about some of my recent work, I recommend my papers on hierarchical causal modeling and its application to immune receptors, or on experimental design and its application to DNA synthesis.

I received my PhD in Biophysics from Harvard University in 2022, advised by Debora Marks and Jeff Miller, as a Hertz Foundation Fellow. I received my A.B. in Chemistry and Physics with highest honors from Harvard in 2016, working with Adam Cohen. I lead machine learning research at Jura Bio, a genomic medicines startup.

arrow-left-smallarrow-right-large-greyarrow-right-large-yellowarrow-right-largearrow-right-long-yellowarrow-right-smallclosefacet-arrow-down-whitefacet-arrow-downCheckedCheckedlink-outmag-glass