Profile avatar
gcorso.bsky.social
PhD student @MIT • Research on Generative Models for Biophysics and Drug Discovery
64 posts 2,742 followers 100 following
Regular Contributor
Active Commenter
Posts 21 Comments 29

Lol 😅

submitted 64 days ago • 0 comments

Excitement is in the air for accelerating new discoveries in 2025! 🚀 Here’s a short holiday message brought to you by the creators of Boltz-1: @gcorso.bsky.social and @jeremywohlwend.bsky.social ☃️ What are you excited to use Boltz-1 for in 2025?

submitted 64 days ago • 0 comments

This is the kind of benchmarking work the field needs!

submitted 64 days ago • 0 comments

Here's a year-end update from #PLINDER. It's been really great working on this project and all the other projects that it has kickstarted - the gift that keeps on giving. Happy holidays everyone! www.plinder.sh/blog/updates

submitted 64 days ago • 0 comments

Two major life updates: - I'm moving to Senior Applied Research Scientist in Digital Biology at NVIDIA (Jan '25) - I'm starting a new lab at Duke as Visiting Assistant Prof (early '25) Both roles focus on tackling hard problems in biological machine learning through collaborative research. Long 🧵

submitted 65 days ago • 16 comments

MIT researchers introduce Boltz-1, a fully open-source model for predicting biomolecular structures With models like AlphaFold3 limited to academic research, the team built an equivalent alternative, to encourage innovation more broadly www.eurekalert.org/news-release...

submitted 66 days ago • 0 comments

Boltz v0.4.0 is here! Today, we’re releasing our full data processing pipeline, making it easier than ever to build on top of Boltz. This release also includes our evaluation code and new results. Oh, and also pocket conditioning :)

submitted 67 days ago • 1 comment

After AlphaFold3 was released with a limited license, a global race began to build the first fully open source replica of the biomolecular prediction model that could be available for commercial use. Read more in MIT News: news.mit.edu/2024/researc...

submitted 71 days ago • 0 comments

New Title Alert: Boltz-1- an open-source model which predicts the 3D structure of proteins, rna, dna and small molecules; it handles modified residues, covalent ligands & glycans. Learn more here: https://buff.ly/3ZAPowA #SBGridSoftware #SBGrid

submitted 72 days ago • 0 comments

I've created a new plugin for #PyMOL (called PyMOLfold) that allows you to fold protein sequences right in the GUI. Simply select your model of choice (e.g., #ESM3, Boltz-1) and paste in your amino acid sequence. github.com/colbyford/Py... #ai #proteinfolding #alphafold

submitted 75 days ago • 0 comments

Starting in 5! Join us for an exciting day of invited talks, posters, and a panel with our invited speakers. Schedule: mlsb.io Room: East Building Meeting Rooms 11-12 (2nd floor)

submitted 73 days ago • 0 comments

You are welcome! 🤗

submitted 75 days ago • 0 comments

I guess we have Boltz-1 to thank for pushing all these other AF3 clones to adopt fully open-source licenses and models.

submitted 75 days ago • 1 comment

Our paper describing our winning submission (tied with @olexandr.bsky.social) is out with some extra computational analysis of the predicted binding modes. We didn't do anything fancy (but the hits weren't that great either...). pubs.acs.org/doi/10.1021/...

submitted 78 days ago • 0 comments

new preprint on chemical synthesis ML models - showing how to combine multiple models in a principled way - modern Transformers + GNN to featurize chemical reaction: - new insights in where the models shine + bonus: find the quirky named reaction! Feedback welcome! arxiv.org/abs/2412.05269

submitted 80 days ago • 4 comments

After two years, our paper on generative models for structure-based drug design is finally out in @natcomputsci.bsky.social www.nature.com/articles/s43...

submitted 79 days ago • 2 comments

We trained a model to co-generate protein sequence and structure by working in the ESMFold latent space, which encodes both. PLAID only requires sequences for training but generates all-atom structures! Really proud of @amyxlu.bsky.social 's effort leading this project end-to-end!

submitted 79 days ago • 2 comments

Re docking: @workshopmlsb.bsky.social has been piloting a leaderboard for the PLINDER benchmark. It would be awesome to get submissions using existing methods, then everyone can see comparisons better 😁 leaderboard & instructions are on mlsb.io

submitted 79 days ago • 1 comment

Starting from tomorrow I will be in Vancouver for NeurIPS! Come talk to me about research, Boltz-1, Boltz-2... !

submitted 79 days ago • 0 comments

You may have seen a recent pre-print [1] from Jain et al. with strongly worded claims against the experimental results in our DiffDock paper [2]. Here is our response, as also outlined in 's quoted Bluesky post.

submitted 80 days ago • 1 comment

Response by the DiffDock authors on the recent preprint by Jain and colleagues.

submitted 80 days ago • 2 comments