Reticular (YC F24)
@ReticularAI
Followers
148
Following
11
Media
1
Statuses
6
Reticular is making protein design steerable and interpretable. @ycombinator F24
Joined November 2024
A First Step Towards Interpretable Protein Structure Prediction With SAEFold, we enable mechanistic interpretability on ESMFold, a protein structure prediction model, for the first time. Watch @NithinParsan demo a case study here w/ links for paper & open-source code 👇
4
20
93
For anyone going to ICLR, we'll be presenting our poster at the GEM, LMRL, SciFM, XAI4Science, and MLMP workshops. Stop by if you're curious about bio interp!
1
0
5
Longer 🧵 breaking down our paper 👇 https://t.co/OfMxg7jQBX
If you’ve ever - thought AI protein folding is magical ✨ - wanted more than a pLDDT score 🔎 - or just think mech interp in bio is cool 🤓 then read the 🧵 👇 on our first paper towards interpretable protein structure prediction just accepted to workshops at ICLR
1
0
4
ICLR Workshop Paper: https://t.co/va2Gy6ZbQs Code (w/ hosted dataset!): https://t.co/rv66HmYNsn Visualizer: https://t.co/tOfKQcso32 Website:
github.com
Official repo of "Towards Interpretable Protein Structure Prediction with Sparse Autoencoders" published at ICLR 2025 GEM workshop. - johnyang101/reticular-sae
1
0
6
@NithinParsan shoutout @liambai21 and @etowah0 for beating us to the punch on translating mech interp to protein language models. excited to see where these techniques will lead given the dense amt of coevolutionary + structure info learned by these models.
1
1
8
Incredibly excited to launch publicly as part of @ycombinator's Fall 2024 Batch. Send us a DM if you're in the interpretability space or working in biotech. @johnyang100 and @NithinParsan
YC F24's @ReticularAI makes protein AI models controllable and interpretable to help steer protein design with limited biological data, reducing costly validation cycles. https://t.co/vIesWS3rkh Congrats on the launch, @NithinParsan and @johnyang100!
0
3
6