Theis on virtual cell modeling: insufficient data for perturbation prediction
Understand this story
Fabian Theis of Helmholtz Munich said in a Latent Space interview that perturbation prediction with existing datasets is not sufficient to support complex algorithms. He believes a more worthwhile direction is to use large-scale, high-precision, multi-scale, registered biological data to predict evolution from molecules to cells, microenvironments, tissues, organs, and ultimately organisms. This judgment targets the approach of "using existing data for perturbation prediction" in virtual cell modeling; Theis did not deny the value of this approach, but pointed out that its data foundation is not yet sufficient to support complex algorithms.
AI overview based on source reports · Updated 36 min ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Latent SpaceControlling Biology - Fabian Theis, Helmholtz Munich
This piece discusses Fabian Theis's work on algorithms for multi-scale, multi-modal, time-varying biological data and the Virtual Cell concept, alongside the recent $1.8B Biohub commitment from Biohub, NIH, DOE, Google and Meta. It notes that the 2025 Arc Virtual Cell Challenge showed constant baselines often beating sophisticated perturbation-prediction models, though a cited paper argues better-calibrated metrics let deep learning outperform the mean baseline. Theis argues perturbation prediction on existing datasets isn't hard enough to warrant complex algorithms, and that focus should shift to large, high-precision, co-registered data spanning molecules through organisms.
Activity for this story
Not enough continuous observations to show a trend yet.