Neil Thomas @countablyfinite

Building AI for biological design @evoscaleai 🧬 Formerly: @Theteamatx 🌘 PhD @UCBerkeley 🙈 thomas-a-neil.github.io Act V, Scene II Joined November 2015

Tweets

404
Followers

819
Following

1K
Likes

1K

Yun S. Song @yun_s_song

a week ago

We are excited to share GPN-Star, a cost-effective, biologically grounded genomic language modeling framework that achieves state-of-the-art performance across a wide range of variant effect prediction tasks relevant to human genetics. biorxiv.org/content/10.110… (1/n)

17 156 505 73K 283

Download Image

Clara Fannjiang @clara_fannjiang

3 months ago

✨ new work with @jiwoncpark #icml2025! a zoo of algos exists for designing new proteins & molecules w/ AI🧬🧪how do you pick which one to use? our method selects design algos that will achieve user-specified, population-level success criteria w/ high-prob guarantees.👇

1 7 28 4K 8

Download Image

The Align Foundation @Align_Bio

3 months ago

1/4 🚀 Announcing the 2025 Protein Engineering Tournament. This year’s challenge: design PETase enzymes, which degrade the type of plastic in bottles. Can AI-guided protein design help solve the climate crisis? Let’s find out! ⬇️ #AIforBiology #ClimateTech #ProteinEngineering…

6 73 192 38K 102

Download Image

EvolutionaryScale @EvoscaleAI

3 months ago

We're sponsoring the use of ESM3 and EMSC to help researchers engineer improved PETase enzymes in the @AlignBio 2025 Protein Engineering Tournament. Get started using ESMC to predict protein function and ESM3 to generate new enzymes here: github.com/evolutionarysc…

The Align Foundation @Align_Bio

3 months ago

6 73 192 38K 102

Download Image

0 2 19 2K 2

Yun S. Song @yun_s_song

6 months ago

Thrilled to see my digital art on the cover of @TrendsGenetics! The two binary strings represent reverse-complementary DNA sequences (00=A, 01=C, 10=G, 11=T) and the connecting rectangles represent “embeddings” learned by DNA language models. Our article: doi.org/10.1016/j.tig.…

3 26 152 8K 31

Download Image

Romero lab @romerolab1

6 months ago

Happy Sunday to all! This morning, we are excited to share Chase’s work developing a simple, scalable method to assemble 100s-1000s of custom genes from oligo pools using standard lab tools! (Small 🧵 below)

5 51 189 29K 100

Download Image

Kevin K. Yang 楊凱筌 @KevinKaichuang

6 months ago

Gene synthesis is often the most expensive part of protein engineering with generative models. Happy to have played a small part in this work, where Chase developed a method for precision library construction at scale, with per-gene costs as low as $1.50. @romerolab1

Romero lab @romerolab1

6 months ago

5 51 189 29K 100

Download Image

7 43 261 61K 152

Download Image

Gina El Nesr @ginaelnesr

6 months ago

Protein function often depends on protein dynamics. To design proteins that function like natural ones, how do we predict their dynamics? @HWaymentSteele and I are thrilled to share the first big, experimental datasets on protein dynamics and our new model: Dyna-1! 🧵

8 133 697 97K 425

Download Image

Kevin K. Yang 楊凱筌 @KevinKaichuang

2 years ago

Machine learning guided directed evolution beats directed evolution and hit recombination head-to-head for enzyme engineering. @countablyfinite @LucyColwell37

3 55 241 24K 110

Download Image

Anthony Gitter @anthonygitter

2 years ago

"Engineering of highly active and diverse nuclease enzymes by combining machine learning and ultra-high-throughput screening" from @countablyfinite @LucyColwell37 and team looks amazing. They compare directed evolution, hit recombination, and ML-guided design of NucB.

3 28 109 12K 53

Download Image

Etowah Adams @etowah0

8 months ago

Can we learn protein biology from a language model? In new work led by @liambai21 and me, we explore how sparse autoencoders can help us understand biology—going from mechanistic interpretability to mechanistic biology.