Rachel (Menghua) Wu
@menghua_wu
MIT PhD '25 BS '19. Machine learning for graphs, molecules, and biology.
Come visit my ICML poster W-308 from 11-1:30 today :D tl;dr – you want to take cells from A → B. - option 1: try *lots* of stuff on A and hope for the best - option 2 (this paper): predict root causes (e.g. genes) of differences between A and B .. efficiently and scalably!
Excited to share our new ProxelGen paper! Completely different from RFDiffusion etc., we generate proteins as densities instead of point clouds. Turns out this works just as well and e.g. does better on some scaffolding tasks. arxiv.org/abs/2506.19820 (1/8)
Today, we're releasing the fuel for the next generation of AI in biology 🧬 X-Atlas/Orion is now the largest public genome-wide Perturb-seq dataset, built to create better “virtual cell” models and accelerate drug discovery. Learn more: businesswire.com/news/home/2025…
Excited to unveil Boltz-2, our new model capable not only of predicting structures but also binding affinities! Boltz-2 is the first AI model to approach the performance of FEP simulations while being more than 1000x faster! All open-sourced under MIT license! A thread… 🤗🚀
If you're interested in predicting drug targets or designing perturbation screens or causality in general, come listen to my reading group talk today :D (or drop by my poster at ICML next month!)
Reading group tomorrow: Identifying perturbation targets through causal differential networks arxiv.org/abs/2410.03380 With @menghua_wu! Join us on Zoom at 9am PT 12pm ET 6pm CEST: portal.valencelabs.com/starklyspeaking
🚀 Excited to release a major update to the Boltz-1 model: Boltz-1x! Boltz-1x introduces inference-time steering for much higher physical quality, CUDA kernels for faster, more memory-efficient inference and training, and more! 🔥🧵
At #ICLR2025 in Singapore now. Looking for people to chat with :) Also presenting ProtComposer: arxiv.org/abs/2503.05025
I won't be at ICLR 🥲 but you can talk to these other cool people at my poster, Thursday 3-5:30 PM in Hall 3+2B #10!
Excited to share my #ICLR2025 paper, with JC Hütter and friends! Genetic perturbation screens allow biologists to manipulate and measure the genes in cells = discover causal relationships! BUT they are expensive to run, expensive to interpret. ... We use LLMs to help!
I'll be at ICLR. Come check out our generative modeling work! Reach out if you want to chat. Proteina: x.com/karsten_kreis/… Protcomposer: x.com/HannesStaerk/s… Generator matching: x.com/peholderrieth/…
New paper out! We introduce “Generator Matching” (GM), a method to build GenAI models for any data type (incl. multimodal) with any Markov process. GM unifies a range of state-of-the-art models and enables new designs of generative models. arxiv.org/abs/2410.20587 (1/5)
📢 Excited to announce the #ICML2025 workshop on *Scaling Up Intervention Models (SIM)*! Let’s bring together state-of-the-art ideas on modeling novel interventions and distribution shifts. :) 🙌🏻 Submissions are welcome! Link: sites.google.com/view/sim-icml2…
New paper (and #ICLR2025 Oral :)): ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids arxiv.org/abs/2503.05025 Condition on your 3D layout (of ellipsoids) to generate proteins like this or to get better designability/diversity/novelty tradeoffs. 1/6
Congrats! :D Hope people are able to do cool stuff with this!
Thrilled to announce Boltz-1, the first open-source and commercially available model to achieve AlphaFold3-level accuracy on biomolecular structure prediction! An exciting collaboration with @jeremyWohlwend, @pas_saro and an amazing team at MIT and Genesis Therapeutics. A thread!
Many people are in the middle of the @CVPR deadline. So I'm sharing my guide to writing a CVPR paper (or any paper). My students have had this for years but I haven't shared it publicly before. I hope you find it useful and write a great paper. #CVPR2025 medium.com/@black_51980/w…