Where in the Drug Discovery Pipeline Does Virtual Cell Have the Most to Contribute?
tl;dr: The most impactful virtual cell initiatives will be those that make better drugs rather than those that push more drugs through to clinical trials faster.
Inside Valence
A behind-the-scenes look at the research at Valence Labs, exploring new ways to predict, explain, and ultimately decode biology.
Live Last read · last published · next check
Latest posts
The Evolution of Phenomics: From Supervised Transfer Learning to Generative Foundation Models
Historically, AI-driven drug discovery has been constrained by data scarcity.
Reflections on ICML 2026
Reflections from ICML 2026 where over 22,500 (in-person and virtual) attendees discussed the latest breakthroughs in the AI community.
Truly All-Atom Boltzmann sampling with AquaGen
We built a model that shows it’s possible to train a Boltzmann sampler that still works with a key ingredient of biochemical molecular dynamics: water.
f-Trajectory Balance: a loss family that enables exploration in molecule generation, LLMs and generative models
Connect with us: Valence is constantly seeking talented individuals with diverse backgrounds and expertise to join our team.
How AI Experts Can Drive Better Collaboration in Drug Discovery
Connect with us: Valence is constantly seeking talented individuals with diverse backgrounds and expertise to join our team.
Deep Learning for Microscopy: What Are We Really Learning?
Why the field of machine learning is still struggling to know what it knows about microscopy imaging
From Crystals to Drugs: What Drug Discovery Can Learn From Materials Science as Revealed at ICLR’s AI4Mat 2026
tl;dr: ICLR’s AI4Mat 2026 revealed that the tools built to simulate materials science are the same tools that could simulate biology.
Grounding Perturbation Prediction in Biological Knowledge
Decoding Transcriptomics Responses with TxPert
Virtual Cell @ ICLR: A Sea of Silos
Reflections from ICLR 2026