Sign in

Neil Thomas

@countablyfinite.bsky.social
909 followers 478 following 18 posts

AI x Biology EvolutionaryScale / Biohub PhD UC Berkeley Prev: Google X, 23andMe, thomas-a-neil.github.io

PostsRepliesMedia
Neil Thomas @countablyfinite.bsky.social · 12/03/2025
Multiple Sequence Alignments (MSAs) were also powerful for zero-shot design! Without any assay data, and even without structure or large-scale pretraining, we were able to design improved NucB variants with as many as 9 mutations from the wildtype.
110
Neil Thomas @countablyfinite.bsky.social · 12/03/2025
We found that in a head-to-head comparison of ML-guided design versus high-throughput directed evolution, our ML system could design higher activity variants, with lots more diversity!
110
Neil Thomas @countablyfinite.bsky.social · 12/03/2025
How did we engineer NucB? We used a variety of methods, encapsulated in our “TeleProt” framework (which “teleports” past holes in the protein fitness landscape!) We balance evolutionary (VAEs) and assay-labeled data (CNNs) when designing libraries, and adjust as data accumulates
100
Neil Thomas @countablyfinite.bsky.social · 12/03/2025
Our protein engineering target was NucB, an endonuclease that can break down biofilms and has potential as a treatment for chronic wounds. It is active at pH 9, but needs to be highly active at pH 7 to unlock its potential as a therapeutic.
100
Neil Thomas @countablyfinite.bsky.social · 12/03/2025
How did we engineer NucB? We used a variety of methods, encapsulated in our “TeleProt” framework (which “teleports” past holes in the protein fitness landscape!) We balance evolutionary (VAEs) and assay-labeled data (CNNs) when designing libraries, and adjust as data accumulates
000
Neil Thomas @countablyfinite.bsky.social · 12/03/2025
Our protein engineering target was NucB, an endonuclease that can break down biofilms and has potential as a treatment for chronic wounds. It is active at pH 9, but needs to be highly active at pH 7 to unlock its potential as a therapeutic.
100