Alex Derry (@awfderry) profile picture

AIxBio Research @Biohub, formerly @EvoscaleAI. Prev Biomedical Informatics @StanfordDBDS

Joined October 2015
Photo by Alex Derry (@awfderry)Photo by Alex Derry (@awfderry)Photo by Alex Derry (@awfderry)Photo by Alex Derry (@awfderry)Photo by Alex Derry (@awfderry)
Alex Derry retweeted
We’re excited to share the full binder design protocol. Check it out here: github.com/Biohub/esm/blob/m…. The notebook includes support for @modal to easily scale up binder generation. Give it a try and let us know how it works! You can read more about ESMFold2, ESMC, ESM Atlas, and the full results in the paper here: biohub.ai/papers/esm_protein….
3
25
4
82
23,105
This is very cool! In general, I’m really excited about the potential for SAE features to help make biology interpretable for agentic workflows.
AI agents are learning to read @biohub protein models @GaoShanghua @AdaFang_ @_yepeng aiscientist.tools/posts/ai-a… We explored how AI agents powered by ToolUniverse @ScientistTools can interact with new ESM models 🧬 Mutation and loss-of-function analysis Agents compare reference and mutant proteins, identify SAE features most affected by a mutation, and connect those perturbations to structural and functional consequences. The agents then relate these changes to experimental evidence, including deep mutational scanning measurements, to explain potential loss-of-function mechanisms 🧪 Functional mechanism exploration Agents analyze protein representations to identify functional tracks associated with specific molecular activities. By linking SAE features to protein regions, structures, and annotations, the agents can generate hypotheses about how proteins carry out their functions Check out new SAE-enabled ToolUniverse skills for variant interpretation, loss-of-function analysis, structural annotation, functional mechanism interpretation, and evaluation against experimental datasets @HarvardDBMI @harvardmed @Harvard @broadinstitute @KempnerInst
2
6
679
AI agents are learning to read @biohub protein models @GaoShanghua @AdaFang_ @_yepeng aiscientist.tools/posts/ai-a… We explored how AI agents powered by ToolUniverse @ScientistTools can interact with new ESM models 🧬 Mutation and loss-of-function analysis Agents compare reference and mutant proteins, identify SAE features most affected by a mutation, and connect those perturbations to structural and functional consequences. The agents then relate these changes to experimental evidence, including deep mutational scanning measurements, to explain potential loss-of-function mechanisms 🧪 Functional mechanism exploration Agents analyze protein representations to identify functional tracks associated with specific molecular activities. By linking SAE features to protein regions, structures, and annotations, the agents can generate hypotheses about how proteins carry out their functions Check out new SAE-enabled ToolUniverse skills for variant interpretation, loss-of-function analysis, structural annotation, functional mechanism interpretation, and evaluation against experimental datasets @HarvardDBMI @harvardmed @Harvard @broadinstitute @KempnerInst
Congratulations @biohub on the release of ESMFold2, ESMC, and ESM Atlas! Excited to share that these models are available on day one to AI agents powered by ToolUniverse @ScientistTools Stay tuned for agentic skills that let AI agents use SAE representations for protein variant interpretation, loss-of-function mechanism analysis, structural annotation, and mechanistic protein reasoning @GaoShanghua @AdaFang_ @_yepeng aiscientist.tools
2
18
5
81
17,259
Super excited to share what we've been working on! ESMC/ESMFold2 show that protein language modeling learns the principles of protein biology and can be used for state-of-the-art structure prediction and design. We also built an interactive atlas of over 6.8 billion proteins!
Today we're announcing ESMFold2, an open scientific engine to power prediction, design, and discovery across protein biology. The new model delivers state of the art performance on protein interactions, especially antibodies, a critical modality for therapeutics. We have designed and validated miniprotein binders and single chain antibodies across five therapeutic targets that are important in cancer and immunology. We are seeing very high success rates, and affinities at levels consistent with therapeutic activity. We’re also releasing an atlas of 6.8 billion proteins, and 1.1 billion predicted structures. ESMFold2 is built on a state of the art language model that has been trained on billions of protein sequences. A world model of protein biology emerges through language modeling. We’ve used the techniques of mechanistic interpretability developed to understand large language models to understand the concepts ESM uses to represent proteins. The model’s representation space has a compositional organization of features across scales, levels of complexity, and abstraction, that reflects and mirrors the understanding of protein biology developed through a century of empirical science. This understanding emerges without prior knowledge, just from language modeling of protein sequences. Language models are becoming a powerful substrate to understand and program biology. The design of protein interactions is one of the most fundamental problems in biophysics, and has critical implications for the discovery of new medicines. A simple gradient based search with the model was able to discover high-affinity protein binders. I'm excited by the potential this has to accelerate basic science and the understanding of proteins. And especially for the new avenues it opens up for therapeutic design and medicine.
1
7
1
34
2,547
Finally, all of these models are made available to the scientific community through permissive commercial and non-commercial license, so you can use them today! Read our preprint here: biohub.ai/papers/esm_protein… Blog post: biohub.ai/esm/protein/about Models: huggingface.co/biohub/collec…
1
80
Alex Derry retweeted
Introducing ESM Cambrian. Unsupervised learning can invert biology at scale to reveal the hidden structure of the natural world. We’ve scaled up compute and data to train a new generation of protein language models. ESM C defines a new state of the art for protein representation learning.
26
156
41
624
207,705
Given up on feature attribution? 📣 Thrilled to share *prospector heads* (aka “prospectors'') ⛏️ — a simple attribution method built for foundation models (FMs) & high-dimensional data. Prospectors are modality-generalizable, time-efficient, & excel in few-shot settings ✨ 🧵👇
3
33
5
97
25,426
As demonstrated by this excellent meme, structure determination methods are very different from each other. How does this affect machine learning models trained on protein structures? @awfderry, myself, & @Rbaltman explore this in our new preprint: biorxiv.org/content/10.1101/… (1/5)
This Post is from an account that no longer exists. Learn more
1
7
1
23
We created a website & Python script that renumbers residues in PDB files with UniProt numbering. It returns mmCIF & PDB format files of the ASU & bio assemblies for any list of entries or UniProtIDs. Plz help us test it. @buildmodels @PDBj_en @PDBeurope dunbrack3.fccc.edu/PDBrenum/
10
64
12
221
There is still quite a bit of mystery around the details of @DeepMind's AlphaFold 2, but equivariance & symmetries may have played a significant role in their success. This is @JustasDauparas's and my take 🧐: fabianfuchsml.github.io/alph…
7
81
19
312
Alex Derry retweeted
Looking for new challenges for machine learning in structural biology? Check out our recent release: ATOM3D, a unified collection of diverse benchmark datasets for biological problems that deal with atom coordinates in 3D space. ⚛️⚛️⚛️ atom3d.ai/ [1/4]
2
29
3
124