AI助力生物研究突破

Fabian Theis has been one of the key players in the various iterations of the Virtual Cell concept and initiatives. His lab has been pushing the frontier of algorithms to understand multi-scale, multi-modal (”multiomics”), time-varying biological data. He has shaped the large scale vision and data collection through his leadership at Helmholtz, various startups and probably at Biohub itself. Much of the recent attention in AI x Bio has been on protein and molecular design. After a lot of initial excitement, Virtual Cell projects have received less attention due to questions about the effectiveness of large-scale models in solving even basic Virtual Cell problems. The Biohub announcement got a lot of press for $1.8B of commitments from Biohub, NIH, DOE, Google and Meta. These organizations are doubling down on these big bets now because new measurement capabilities and scale infrastructure are coming online that make Biohub’s push likely lead to big impact on science. DOE and NIH are developing lab-in-the-loop automation capabilities at scale. Google is scaling and broadening its connectomics capabilities. Biohub itself has worked with various labs to develop and improve imaging platforms like laser phase plate microscopy, light sheet microscopy and advanced post-processing for regular microscopes that reveal deep phenotypic data. These technologies are quickly maturing and will likely play a big part in the Biohub initiative. Virtual Cell modeling has run into problems that have dampened excitement about systems biology. The 2025 Arc Virtual Cell Challenge shined a light on the problem: a slew of papers pointed out that constant baselines often beat sophisticated models for “Perturbation Prediction”. Many models fail to beat even the most basic baselines. This situation is not actually so bad: many existing evaluation metrics are poorly calibrated. With better-calibrated metrics, deep learning models can outperform the mean baseline. Fabian Theis believes that perturbation prediction under the existing data sets just isn’t a hard enough problem to warrant complex algorithms. Instead, we should be focused on using large, high precision, multi-scale, co-registered biological data to predict the evolution of molecules → cells → niches → tissues → organs → organisms, and how all these scales effect one another. This is a happy situation: at this very moment, AI is enabling us to tackle dramatically larger problems, and this problem is very, very big. We lack understanding of the “scale interfaces” between these different different “domains of applicability,” and we lack the data. The Biohub initiative aims to solve the data problem. Fabian Theis has been working on the algorithms to model these larger problems for years.