Valence Labs (@valence

Valence Labs

945 posts

Valence Labs

@valence_ai

Decoding biology to radically improve lives. Décrypter la biologie pour radicalement améliorer les vies. Powered by | Propulsé par @recursionpharma.

Montreal

Joined April 2018

Pinned
Valence Labs
@valence_ai
May 20, 2025
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 🧵
11K
Valence Labs
@valence_ai
Nov 21, 2022
We are excited to announce that Valence, @graphcoreai & @Mila_Quebec have placed 1st in the molecular property prediction (MPP) track of the Open Graph Benchmark Large-Scale Challenge (OGB-LSC) at @NeurIPSConf 2022! (1/7)🧵
Valence Labs
@valence_ai
Jul 26, 2023
Today we begin our new journey as Valence Labs: a semi-autonomous research engine within @RecursionPharma, dedicated to advancing the frontier of deep learning in #drugdiscovery. We’ve got a lot in store. A thread 🧵(1/5)
49K
Valence Labs
@valence_ai
Dec 14, 2024
Generative models often create molecules that are hard to synthesize. Tomorrow, we present SynFlowNet, a GFlowNet designed to generate synthesizable molecules using documented reactions and purchasable materials. Learn more at the MLSB workshop: arxiv.org/abs/2405.01155
00:00
Valence Labs
@valence_ai
Dec 2, 2024
Replying to @valence_ai and @jasonhartford
"SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraints" Where: Machine Learning in Structural Biology workshop in Easy Meeting Room Rooms 11 & 12 When: Dec 15th at 8:15 AM PST arxiv.org/abs/2405.01155 @MirunaCretu2 @folinoid
7.1K
Valence Labs
@valence_ai
Aug 4, 2023
(1/8) We propose a rigorous framework for investigating Molecular Out-of-Distribution (MOOD) performance in real-world applications of molecular modeling. It’s time to close the validation-deployment gap! 🎯 Paper: chemrxiv.org/engage/chemrxi… Experiments: github.com/valence-labs/m…
chemrxiv.org
Real-World Molecular Out-Of-Distribution: Specification and Investigation | ChemRxiv
This study presents a rigorous framework for investigating Molecular Out-Of-Distribution (MOOD) generalization in drug discovery. The concept of MOOD is first clarified through a problem specificat...
18K
Valence Labs
@valence_ai
Dec 16, 2022
What are the next breakthroughs in molecular simulation that will drive the future of drug discovery? Next week at M2D2, Prof. @wellingmax will describe how GNNs and other converging advances are accelerating molecular simulation. Join us on Tues, Dec 20th at 11am ET!
13K
Valence Labs
@valence_ai
May 8, 2023
We are incredibly excited to integrate our powerful chemistry engine into @RecursionPharma’s OS to enable the future of AI-first drug discovery! We’ll be expanding our ML research team at @Mila_Quebec with the aim of solving the hardest problems in drug discovery Stay tuned!
Recursion
@RecursionPharma
May 8, 2023
#BREAKING: We’re excited to announce we have entered into agreements to acquire @valence_ai and @Cyclica - two leading AI-enabled drug discovery companies - to bolster our chemistry and generative AI capabilities. Learn more: bit.ly/42caoJ5
11K
Valence Labs
@valence_ai
Dec 14, 2023
Introducing SAFE, Sequential Attachment-based Fragment Embedding, a novel molecular line notation that redefines molecular design tasks as simple autoregressive sequence generation. 🧵
00:00
13K
Valence Labs
@valence_ai
Dec 9, 2022
How can we quickly and accurately predict the binding structure of a small molecule ligand to a protein? Next week at M2D2, @HannesStaerk will show us how a generative modelling approach via diffusion is improving molecular docking. Join us on Tuesday, Dec 13th at 11am ET!
Valence Labs
@valence_ai
Dec 15, 2021
We are excited to announce US$8.5M in seed funding co-led by @fiftyyears and @airstreet to continue building the world’s most powerful chemistry engine, an important step in our mission of unlocking new therapeutic options for previously intractable diseases
Valence Labs
@valence_ai
May 1, 2024
🧵Can GNNs scale? This question has divided the community for years. For the first time, we demonstrate the positive scaling effects of GNNs and introduce MolGPS - a 1B parameter model for molecular property prediction.
Inside Valence | Substack
From valencelabs.substack.com
17K
Valence Labs
@valence_ai
Sep 21, 2023
Valence Labs is actively hiring across multiple roles! We’re looking for Research Engineers, Research Scientists, a DevOps Engineer, and a Community Manager. Join us in pushing the frontier of AI research in drug discovery.
Valence Labs | Careers
From valencelabs.com
22K
Valence Labs
@valence_ai
Sep 2, 2022
We are excited to announce that Yoshua Bengio will be kicking off the new M2D2 Talks series next Tuesday, September 6 at 11am ET, discussing how machine learning is changing scientific discovery! Join us in person @Mila_Quebec, or attend online!👇
Valence Labs
@valence_ai
Sep 9, 2022
Uncertainty quantification and calibration are still a challenge for ML models. Next week at M2D2, @avapamini will discuss how evidential DL can provide better uncertainty quantification useful for molecular property prediction and more! Join us on Tuesday (Sept 13) at 11am ET!