In healthcare, AI is used to:
Me, I think that there is huge potential to use AI to develop therapies.
https://xcancel.com/bravo_abad/status/2047272548795093416#m
Flow matching is emerging as a unifying framework for generative biology
Biology is full of mappings between states: a healthy cell turning diseased, amino acids folding into a functional protein, a ligand docking into its target. Deriving such transformations analytically is intractable—which is where generative AI steps in, and flow matching is quickly becoming its backbone.
Morehead and coauthors review how flow matching (FM) is reshaping generative modeling in bioinformatics. Unlike diffusion models, FM doesn’t force the source distribution to be Gaussian: it learns a time-dependent vector field that transports samples between any two distributions along straight-line, optimal-transport paths. The payoff: fewer inference steps, simulation-free training, and built-in support for geometric priors like SE(3) equivariance—essential for 3D biomolecules.
What’s striking is how fast FM has spread across biological scales. For molecules, FoldFlow, FrameFlow, and Multiflow generate protein backbones on SE(3)ᴺ manifolds, SemlaFlow produces valid small molecules up to 100× faster than diffusion, and Dirichlet FM handles discrete DNA/RNA sequences. FlowDock and NeuralPLexer3 predict protein–ligand complexes that match or exceed AlphaFold 3 on key benchmarks, while AlphaFlow and MDGen generate conformational ensembles and MD trajectories. At the cellular scale, CellFlow and Meta FM map unperturbed populations to perturbed states, and CryoFM and FlowSDF extend FM to cryo-EM and microscopy.
The deeper point: FM subsumes diffusion models, continuous normalizing flows, and optimal transport as special cases, providing scaffolding for an AI-based virtual cell—simulating molecular, structural, and phenotypic effects of perturbations across scales.
Overall, this signals a shift in what’s computationally tractable. Instead of narrow, stage-specific models, FM points to unified conditional generators that design sequences, predict complexes, and model perturbation responses in one framework—shortening wet-lab cycles and making closed-loop, active-learning workflows practical.
Paper:
https://www.nature.com/articles/s42256-026-01220-0
This reminds me of something I had thought about before, which is that if many transitions from one biological state to another is governed by phase-transitions, then you might overlook many drugs that when taken in the wrong dose have little to no effect – you never cross the threshold from current state to a more healthy state. The transition can be as abrupt as when you change the temperature of water from just a degree or two, from below freezing to above freezing. (However, if you measure what effect the drug is having on the body you might notice that it’s doing something, but the body just never quite crosses the threshold.)