<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
<div class="" style="word-wrap:break-word">This is an announcement of Matthew McPartlon's MS Presentation<br class="">
===============================================<br class="">
Candidate: Matthew McPartlon<br class="">
<br class="">
Date: Wednesday, December 07, 2022<br class="">
<br class="">
Time: 9 am CST<br class="">
<br class="">
Remote Location: Join Zoom Meeting <a href="https://uchicago.zoom.us/j/95724648133?pwd=YnBPVjNUeEdUVEpkTkQ5eDFuWFk5dz09" class="">https://uchicago.zoom.us/j/95724648133?pwd=YnBPVjNUeEdUVEpkTkQ5eDFuWFk5dz09</a> Meeting ID: 957 2464 8133 Passcode: 004376<br class="">
<br class="">
M.S. Paper Title: MACHINE LEARNING METHODS FOR INVERSE PROTEIN FOLDING<br class="">
<br class="">
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<br class="">
<br class="">
Advisors: Jinbo Xu
<div class=""><br class="">
</div>
<div class="">Co-advisor: Janos Simon</div>
<div class=""><br class="">
</div>
<div class="">Committee: Andrew Drucker, Janos Simon, Jinbo Xu</div>
<div class=""><br class="">
</div>
<div class=""></div>
</div>
<div class="" style="word-wrap:break-word">
<div class=""></div>
<div class=""><br class="">
</div>
<div class=""><br class="">
</div>
</div>
</body>
</html>