Valence Labs

894 posts

Valence Labs banner
Valence Labs

Valence Labs

@valence_ai

Decoding biology to radically improve lives. Powered by @recursionpharma

Montreal Katılım Nisan 2018
31 Takip Edilen5.6K Takipçiler
Sabitlenmiş Tweet
Valence Labs
Valence Labs@valence_ai·
1/ At Valence Labs, @RecursionPharma's AI research engine, we’re focused on advancing drug discovery outcomes through cutting-edge computational methods Today, we're excited to share our vision for building virtual cells, guided by the predict-explain-discover framework 🧵
Valence Labs tweet media
English
3
20
92
9.1K
Valence Labs
Valence Labs@valence_ai·
We found that for microscopy data, a simple, relatively standard generative modelling approach (Gaussian noise-to-data via a modified DiT for stability) led to the best performance. Our generative model significantly improved on modeling the underlying distributions.
Valence Labs tweet media
English
1
0
1
150
Valence Labs
Valence Labs@valence_ai·
Generative models that simulate cellular assays could fundamentally change how we use the lab. In our latest preprint, we explore the design space of flow matching models for microscopy. Turns out, the Bitter Lesson holds in biology as well. arxiv.org/abs/2603.26790
Valence Labs tweet media
English
2
7
45
2.7K
Valence Labs
Valence Labs@valence_ai·
Even with today's industrialized labs that can run millions of experiments each week, we can only cover a tiny fraction of all the experiments we may want to run. In this week's Inside Valence, learn more about virtual assays. open.substack.com/pub/valencelab…
Valence Labs tweet media
English
0
0
6
506
Valence Labs
Valence Labs@valence_ai·
Did you hear Virtual Cells are making a comeback? This animation—featured in our inaugural Inside Valence post—is a primer on Virtual Cells through the lens of drug discovery. Go behind the scenes of our research with our new series: valencelabs.substack.com/p/the-virtual-…
English
0
1
5
417
Valence Labs
Valence Labs@valence_ai·
We’re excited to join the conversation with a focus on what matters most to us: drug discovery. In the coming weeks, we’ll dive deeper into these themes and share more about our own progress. If you enjoy this post, consider subscribing! open.substack.com/pub/valencelab…
Valence Labs tweet media
English
0
0
1
214
Valence Labs
Valence Labs@valence_ai·
We’re launching “Inside Valence”—a new series taking you behind-the-scenes of our research, exploring new ways to predict, explain, and ultimately decode biology. In our inaugural post, we discuss why Virtual Cells are making a comeback and why there’s reason to be excited.
Valence Labs tweet media
English
1
2
8
640
Valence Labs
Valence Labs@valence_ai·
3/ We only have 8 presentation slots and sign-ups close on November 3rd. Make sure to RSVP below 👇 RSVP here: luma.com/n47bshdx
English
0
0
0
297
Valence Labs
Valence Labs@valence_ai·
2/ We want to connect the people reimagining how drug discovery happens, to share ideas, spark collaborations, and explore ways to build together. If you want to present a “Show & Tell”, we review submissions on a rolling, first-come, first-served basis.
English
1
0
0
316
Valence Labs
Valence Labs@valence_ai·
1/ Valence Labs is bringing together next generation of Montréal researchers and innovators in Bio-AI. We are hosting a Bio-AI Show & Tell — a quick and fun showcase of ideas, demos and projects in ML. RSVP here: luma.com/n47bshdx
Valence Labs tweet media
English
1
3
11
1.1K
Valence Labs
Valence Labs@valence_ai·
5/ If you’re attending ICML, make sure to connect with @jasonhartford and Ihab to learn more about the research happening at Valence Labs and @Recursion.
English
0
0
1
483
Valence Labs
Valence Labs@valence_ai·
4/ “Towards Scientific Discovery with Dictionary Learning: Extracting Biological Concepts from Microscopy Foundation Models” Link: arxiv.org/abs/2412.16247
English
1
0
0
513
Valence Labs
Valence Labs@valence_ai·
1/ Valence Labs, @Recursion's AI research engine, is at ICML this week! Two of our scientists, @jasonhartford and Ihab Bendidi are presenting posters on work featured in their papers 👇🧵
Valence Labs tweet mediaValence Labs tweet media
English
1
0
15
1.2K
Valence Labs
Valence Labs@valence_ai·
3/ By combining SynFlowNet with Boltz-2, this new release aims to accelerate the design of high-affinity binders for more efficient early-stage drug discovery. Check out the GitHub repository here: github.com/recursionpharm… Learn more about Boltz-2: rxrx.ai/boltz-2
Valence Labs tweet media
English
0
0
9
822
Valence Labs
Valence Labs@valence_ai·
2/ Originally introduced by Valence Labs, Recursion’s AI research engine, SynFlowNet helps ensure generative models propose molecules that are not only novel but also synthetically feasible.
English
1
0
2
711
Valence Labs
Valence Labs@valence_ai·
Pleased to have hosted the 2025 Molecular Machine Learning Conference last week at @Mila_Quebec Thank you to everyone who joined us and shared their valuable insights! We hope to see you all again soon.
Recursion@RecursionPharma

We had a great turnout for the 2025 Molecular Machine Learning Conference (#MoML) at @Mila_Quebec. Sponsored by Recursion and @valence_ai along with Genesis Therapeutics and Braidwell, the annual event convenes researchers from academia and industry to discuss how ML methods can address key scientific goals related to molecular modeling, molecular interactions, and therapeutic design. 💡 Key topics at MoML 2025 included: ML for quantum chemistry, molecule/protein 3D structure prediction, modeling molecular interactions, molecular dynamics simulations, and geometric ML for molecules. 🎤 Speakers included: ▪️ @AaronNewmanLab, professor of biomedical data science at @Stanford ▪️ Smita Krishnaswamy, associate professor in computer science and genetics at @Yale ▪️ @GabriCorso, PhD student at @MIT and lead researcher on Boltz-2 ▪️ @k_neklyudov, assistant professor at Mila ▪️ @ENoutahi, PhD, principal scientist at Valence Labs & Recursion ▪️ Michael V. LeVine, head of computational chemistry at Genesis Therapeutics ✨ Thank you to everyone who joined us and shared their posters and insights! #MOML25 👉 portal.ml4dd.com

English
0
1
9
1.3K