[Colloquium] Matthew McPartlon MS Presentation/Dec 7, 2022

[Megan Woodward]

This is an announcement of Matthew McPartlon's MS Presentation
===============================================
Candidate: Matthew McPartlon

Date: Wednesday, December 07, 2022

Time: 9 am CST

Remote Location: Join Zoom Meeting https://uchicago.zoom.us/j/95724648133?pwd=YnBPVjNUeEdUVEpkTkQ5eDFuWFk5dz09  Meeting ID: 957 2464 8133 Passcode: 004376

M.S. Paper Title: MACHINE LEARNING METHODS FOR INVERSE PROTEIN FOLDING

Abstract:   In this work, we establish a framework to tackle the inverse protein design problem; the task of predicting a protein’s primary sequence given its backbone conformation. To this end, we develop a generative SE(3)-equivariant model which significantly improves upon existing autoregressive methods. Conditioned on backbone structure, and trained with our novel partial masking scheme and side-chain conformation loss, we achieve state-of-the-art native sequence recovery on structurally independent CASP13, and CASP14 test sets. On top of accurately recovering native sequences, we demonstrate that our model captures functional aspects of the underlying protein by accurately predicting the effects of point mutations through testing on Deep Mutational Scanning datasets. We further verify the efficacy of our approach by comparing with recently proposed inverse protein folding methods and by rigorous ablation studies

Advisors: Jinbo Xu

Co-advisor: Janos Simon

Committee: Andrew Drucker, Janos Simon, Jinbo Xu



-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20221206/6e8c921b/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: Masters_Thesis (2).pdf
Type: application/pdf
Size: 1349582 bytes
Desc: Masters_Thesis (2).pdf
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20221206/6e8c921b/attachment-0001.pdf>