Neil Thomas

nthomas@berkeley.edu

twitter, github, linkedin, cv

• CS PhD Student in the Song Lab (378J Stanley Hall)
• AI Resident at [Google] X 2021
• former Software Engineer at 23andMe
• supported by the NIH Genomics Training Grant, 2018-2020
• BS Engineering Mathematics and Statistics, UC Berkeley, 2015
• machine learning, biology, Andrey Markov, comedy, rap, ultimate

Publications

Minding the gaps: The importance of navigating holes in protein fitness landscapes
Lucy Colwell, Neil Thomas
Cell Systems (2021)

End-to-end learning of multiple sequence alignments with differentiable Smith-Waterman
Samantha Petti, Nicholas Bhattacharya, Roshan Rao, Justas Dauparas, Neil Thomas, Juannan Zhou, Alexander M. Rush, Peter K. Koo, Sergey Ovchinnikov
bioRxiv (2021)
[code] [tweetorial]

Interpreting Potts and Transformer Protein Models Through the Lens of Simplified Attention
Nicholas Bhattacharya*, Neil Thomas*, Roshan Rao, Justas Dauparas, Peter K. Koo, David Baker, Yun S. Song, Sergey Ovchinnikov
Pacific Symposium on Biocomputing (2022)
[code] [tweetorial] [ismb workshop talk, 13 min]

Evaluating Protein Transfer Learning with TAPE
Roshan Rao*, Nicholas Bhattacharya*, Neil Thomas*, Yan Duan, Xi Chen, John Canny, Pieter Abbeel, Yun S. Song
Advances in Neural Information Processing Systems 32 (NeurIPS 2019)
[code] [blog] [tweetorial] [podcast] [neurips lightning talk, 5 min] (talk starts @ 10:15)

Teaching

Concepts of Statistics (Stat 135) Fall 2020

Teaching Statement