Plate II.2
Generative and foundation models for cells
Pl. II.2 Placeholder summary about models that learn the distribution of cellular states. On the map of publications (Plate II) the 3 works of this theme are drawn large and ringed in the colour of their island, every other work a small ink dot; the key beside it lists them.
3 of 742 works marked · data synced 6 Nov 2026
Placeholder narrative. This paragraph stands in for the description of the lab’s work on generative and foundation models of cells. The theme’s leads write the real text before launch.
Placeholder second paragraph about current directions. People, publications and tools on this page are derived from the theme’s topics.
People4
Publications3
Research area: Representations, Single CellPredicting cellular responses to complex perturbations in high‐throughput screens
Research area: Cell Atlas, IntegrationMapping single-cell data to reference atlases by transfer learning
Research area: Representations, Single CellscGen predicts single-cell perturbation responses
Software5
scArches
Reference mapping for single-cell genomics.
414v0.5.13 y agoJupyter Notebook
scGen
Single cell perturbation prediction.
361v2.1.05 y agoPython
regvelo
inferring regulatory cellular dynamics
200v0.4.210 mo agoPython
CPA
The Compositional Perturbation Autoencoder (CPA) is a deep generative framework to learn effects of perturbations at the single-cell level.
157v0.5.03 y agoPython
trVAE
Conditional out-of-distribution prediction
63v1.1.26 y agoPython