Introducing RNAFlow, a protein-conditioned RNA🧬generative model for structure and sequence design. Excited to present this work, mentored by @WengongJin, @icmlconf in a few weeks!
Paper: arxiv.org/pdf/2405.18768
Thread: ⬇️🧵
Divya Nori
67 posts
- 🔥 Introducing BindEnergyCraft (BECraft), the BindCraft pipeline you know and love, now enhanced with an energy-based loss to boost in silico binder success! Thrilled to present this as an oral at ICML @genbio_workshop next week 📄 Paper: arxiv.org/abs/2505.21241 🧵Thread⬇️
- How well do zero-shot in silico metrics predict experimental success of AI-designed antibodies? I’ll be at @NeurIPSConf this week with @abscibio, presenting work that explores this question. Paper: arxiv.org/abs/2312.05273 Collaborators: @amirshanehsaz @SimMat20 🧵Thread:👇 1/5
- for the past few years, pushing the frontier of generative biology has been my driving goal. this summer as part of the team @ValthosTech, i realized that as these capabilities advance, it’s more important than ever to deploy and operationalize them to safeguard humanity againstValthos builds next-generation biodefense. Of all AI applications, biotechnology has the highest upside and most catastrophic downside. Heroes at the frontlines of biodefense are working every day to protect the world against the worst case. But the pace of biotech is against
00:00 - Poster #109 at 1:30 pm today!Introducing RNAFlow, a protein-conditioned RNA🧬generative model for structure and sequence design. Excited to present this work, mentored by @WengongJin, @icmlconf in a few weeks! Paper: arxiv.org/pdf/2405.18768 Thread: ⬇️🧵
- Replying to @divnoriThis experimental insight shows that the development of robust, zero-shot filters is an important research gap. Excited to chat about new strategies for antibody scoring and design this week! Check out our poster at @workshopmlsb @AI4D3 @genbio_workshop 5/5
- Had some downtime before starting my PhD and decided to get back into creative writing. Ended up with a short essay on taste—in writing, in research, and why it feels hard to cultivate yet more important in the AI era. Sharing if you’d like to read :) divnori.github.io/blog/
- Replying to @divnoriRNAs can be engineered to perform versatile functions, particularly through their interactions with specific protein binding partners.
- Replying to @divnoriWe evaluate whether RNAFlow can design the sequence and structure of an aptamer that binds to GRK2, a target of interest for chronic heart failure. We provide a known binding motif of 4-nucleotides. RNAFlow’s predictions resemble the true aptamer’s sequence and structure!
- Replying to @divnoriAI-based antibody design protocols have shown success in generating highly-specific binders, but due to prohibitive screening costs, the diverse candidate designs need to be filtered. 2/5
- Replying to @divnoriFurther, we model the dynamic nature of RNA. Over the course of flow matching inference, RNAFlow generates a trajectory of structures. The final RNA sequence design is conditioned on the last few inference outputs which approximate a conformational ensemble.







