Etowah Adams
@etowah0.bsky.social
enjoying and bemoaning biology. phd student
@columbia prev. @harvardmed @ginkgo @yale
@columbia prev. @harvardmed @ginkgo @yale
Pinned
Etowah Adams
@etowah0.bsky.social
· Feb 10
Can we learn protein biology from a language model?
In new work led by @liambai.bsky.social and me, we explore how sparse autoencoders can help us understand biology—going from mechanistic interpretability to mechanistic biology.
In new work led by @liambai.bsky.social and me, we explore how sparse autoencoders can help us understand biology—going from mechanistic interpretability to mechanistic biology.
OpenBind intends to collect 10,000s of protein-ligand structures & affinities. To prioritize what we collect next, we need cofolding models trained on the latest data. Today we're releasing OpenBind-0 and 717 new ligand-bound structures.
August 21, 2026 at 6:15 PM
OpenBind intends to collect 10,000s of protein-ligand structures & affinities. To prioritize what we collect next, we need cofolding models trained on the latest data. Today we're releasing OpenBind-0 and 717 new ligand-bound structures.
Reposted by Etowah Adams
1/ We're excited to announce that @rs-station.bsky.social is joining the Open Molecular Software Foundation @omsf.io!
July 21, 2026 at 4:19 PM
1/ We're excited to announce that @rs-station.bsky.social is joining the Open Molecular Software Foundation @omsf.io!
Huge resource for the community. Turning compute into data to train models to turn more compute into data...the cycle must go on
bsky.app/profile/moal...
bsky.app/profile/moal...
We're also releasing a massive self-distillation set, a key ingredient in training AF3, comprising millions of diverse MSAs and structures. We estimate its cost to near $20M, representing perhaps the largest compute investment by an academic effort for a biological dataset. 6/9
March 13, 2026 at 4:25 PM
Huge resource for the community. Turning compute into data to train models to turn more compute into data...the cycle must go on
bsky.app/profile/moal...
bsky.app/profile/moal...
Reposted by Etowah Adams
New OpenFold3 preview out! (OF3p2)
It closes the gap to AlphaFold3 for most modalities.
Most critically, we're releasing everything, including training sets & configs, making OF3p2 the only current AF3-based model that is functionally trainable & reproducible from scratch🧵1/9
It closes the gap to AlphaFold3 for most modalities.
Most critically, we're releasing everything, including training sets & configs, making OF3p2 the only current AF3-based model that is functionally trainable & reproducible from scratch🧵1/9
March 13, 2026 at 3:00 PM
New OpenFold3 preview out! (OF3p2)
It closes the gap to AlphaFold3 for most modalities.
Most critically, we're releasing everything, including training sets & configs, making OF3p2 the only current AF3-based model that is functionally trainable & reproducible from scratch🧵1/9
It closes the gap to AlphaFold3 for most modalities.
Most critically, we're releasing everything, including training sets & configs, making OF3p2 the only current AF3-based model that is functionally trainable & reproducible from scratch🧵1/9
Reposted by Etowah Adams
Excited to share PoET-2, our next breakthrough in protein language modeling. It represents a fundamental shift in how AI learns from evolutionary sequences. 🧵 1/13
February 11, 2025 at 2:30 PM
Excited to share PoET-2, our next breakthrough in protein language modeling. It represents a fundamental shift in how AI learns from evolutionary sequences. 🧵 1/13
Reposted by Etowah Adams
It's long seemed that molecular biology is a natural home for ML interpretability research, given the maturity of human-constructed models of biological mechanisms—permitting direct comparison with their ML-derived counterparts—unlike vision and NLP. Our first foray below👇.
Can we learn protein biology from a language model?
In new work led by @liambai.bsky.social and me, we explore how sparse autoencoders can help us understand biology—going from mechanistic interpretability to mechanistic biology.
In new work led by @liambai.bsky.social and me, we explore how sparse autoencoders can help us understand biology—going from mechanistic interpretability to mechanistic biology.
February 10, 2025 at 4:15 PM
It's long seemed that molecular biology is a natural home for ML interpretability research, given the maturity of human-constructed models of biological mechanisms—permitting direct comparison with their ML-derived counterparts—unlike vision and NLP. Our first foray below👇.
Reposted by Etowah Adams
This might be the best paper on applying sparse autoencoders to protein language models. The authors identify how neural networks trained on amino acid sequences "discover" different features, some specific to individual protein families, other for substructures
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
February 10, 2025 at 12:15 PM
This might be the best paper on applying sparse autoencoders to protein language models. The authors identify how neural networks trained on amino acid sequences "discover" different features, some specific to individual protein families, other for substructures
www.biorxiv.org/content/10.1...
www.biorxiv.org/content/10.1...
Can we learn protein biology from a language model?
In new work led by @liambai.bsky.social and me, we explore how sparse autoencoders can help us understand biology—going from mechanistic interpretability to mechanistic biology.
In new work led by @liambai.bsky.social and me, we explore how sparse autoencoders can help us understand biology—going from mechanistic interpretability to mechanistic biology.
February 10, 2025 at 4:12 PM
Can we learn protein biology from a language model?
In new work led by @liambai.bsky.social and me, we explore how sparse autoencoders can help us understand biology—going from mechanistic interpretability to mechanistic biology.
In new work led by @liambai.bsky.social and me, we explore how sparse autoencoders can help us understand biology—going from mechanistic interpretability to mechanistic biology.