# ESM-2 Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/esm-2
> Markdown URL: https://aitinkerers.org/technologies/esm-2.md
> Technology record last updated: 2026-02-23T20:24:30Z
> Generated: 2026-09-23T10:35:02Z

Meta AI's transformer-based protein language model for high-resolution structure prediction and sequence analysis.

Meta AI (FAIR) engineered ESM-2 to interpret biological data through the lens of large language models. Trained on 138 million sequences from the UniRef database, the architecture scales up to 15 billion parameters. It serves as the backbone for ESMFold: a folding engine that generates atomic-level protein structures up to 60x faster than AlphaFold2. This speed allows researchers to map the metagenomic world (billions of proteins) with precision (predicting functional sites and mutation effects) using standard GPU hardware.

- Official technology site: https://github.com/facebookresearch/esm
- Public AI Tinkerers demos and talks: 2
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Meta Modeling for drug discovery.](https://dc.aitinkerers.org/talks/rsvp_SBMb6DF9kMI)

I am training a meta model for ml based chemical binding prediction on open data. I already have about 1500 hundred fine tunes of binding predictions and the meta model will be used to predict the viability of future fine tunes. I am also investigating applying symmetry breaking to align binding symmetries with chemical point groups. This could tune the meta model to specific chemistries. If done this would be a new architecture. I currently have a simple web interface to show the results of my training runs and will be adapting it to output the results of the meta model. It is running locally but I may be able to have it open by the meeting. A lot of my work has been created with assistance from chatgpt and codex.

- Event context: AI Tinkerers - DC Metro Meetup - February 24th, 2026 — 2026-02-24 — DC
- Public talk page: https://dc.aitinkerers.org/talks/rsvp_SBMb6DF9kMI

### [Apple Protein Vision and LLMs for Bioinformatics](https://la.aitinkerers.org/talks/rsvp_fiy7Fw_wI9s)

AI driven in-silico tools like Alphafold, DiffDock, and protein language models are rapidly changing the way scientists conduct bioinformatics research, and usering in a new level of accessibility to start of the art tools in drug discovery and genomic science. The Apple Vision Protein project is an open source initiative to build a 3D visualization and orchestration system for these new cutting edge tools: https://www.youtube.com/watch?v=RiYIahSL45g The system allows for the user/scientist to inspect and interact with the proteins they are engineering/studying in high definition 3D, to explore the particular geometry of their interactions with medicine molecules, and to configure and run the cutting edge AI tools mentioned. The app is being built by a local team from the KINN community, and recently won 'most revolutionary project' at the first Apple Vision Dev con: https://www.youtube.com/watch?v=RiYIahSL45g

- Event context: June 25th - LA AI Tinkerers Meetup & Demos — 2024-06-26 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_fiy7Fw_wI9s

## Related Technologies

- [3D visualization](https://aitinkerers.org/technologies/3d-visualization) ([Markdown](https://aitinkerers.org/technologies/3d-visualization.md)) — 1 public demo
- [AlphaFold](https://aitinkerers.org/technologies/alphafold) ([Markdown](https://aitinkerers.org/technologies/alphafold.md)) — 1 public demo
- [Apple Vision Pro](https://aitinkerers.org/technologies/apple-vision-pro) ([Markdown](https://aitinkerers.org/technologies/apple-vision-pro.md)) — 3 public demos
- [ChatGPT](https://aitinkerers.org/technologies/chatgpt) ([Markdown](https://aitinkerers.org/technologies/chatgpt.md)) — 83 public demos
- [Codex](https://aitinkerers.org/technologies/codex) ([Markdown](https://aitinkerers.org/technologies/codex.md)) — 44 public demos
- [DiffDock](https://aitinkerers.org/technologies/diffdock) ([Markdown](https://aitinkerers.org/technologies/diffdock.md)) — 1 public demo
- [ESM-1b](https://aitinkerers.org/technologies/esm-1b) ([Markdown](https://aitinkerers.org/technologies/esm-1b.md)) — 1 public demo
- [ESM2](https://aitinkerers.org/technologies/esm2) ([Markdown](https://aitinkerers.org/technologies/esm2.md)) — 1 public demo
- [Hugging Face](https://aitinkerers.org/technologies/hugging-face) ([Markdown](https://aitinkerers.org/technologies/hugging-face.md)) — 41 public demos
- [PEFT](https://aitinkerers.org/technologies/peft) ([Markdown](https://aitinkerers.org/technologies/peft.md)) — 4 public demos
- [ProGen](https://aitinkerers.org/technologies/progen) ([Markdown](https://aitinkerers.org/technologies/progen.md)) — 1 public demo
- [ProtBERT](https://aitinkerers.org/technologies/protbert) ([Markdown](https://aitinkerers.org/technologies/protbert.md)) — 1 public demo
- [ProtBERT-BFD](https://aitinkerers.org/technologies/protbert-bfd) ([Markdown](https://aitinkerers.org/technologies/protbert-bfd.md)) — 1 public demo
- [ProtGPT2](https://aitinkerers.org/technologies/protgpt2) ([Markdown](https://aitinkerers.org/technologies/protgpt2.md)) — 1 public demo
- [ProtT5](https://aitinkerers.org/technologies/prott5) ([Markdown](https://aitinkerers.org/technologies/prott5.md)) — 1 public demo
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 664 public demos
- [PyTorch](https://aitinkerers.org/technologies/pytorch) ([Markdown](https://aitinkerers.org/technologies/pytorch.md)) — 273 public demos