Causal Models Need Causal Data: Xaira's X-Cell with Bo Wang & Ci Chu

Why it matters

In this Latent Space interview, Bo Wang and Ci Chu from Xaira Therapeutics present X-Cell, a foundation model for cellular biology. They argue that causal models require causal data — not just vast observational datasets — and show how designed perturbation experiments can yield truly causal signals. The conversation covers cell state representation, multi-omics integration, and generative modeling for drug discovery, offering a fresh perspective on AI in biology.

Key takeaways

• Causal models cannot be built from observational data alone; they require active perturbation experiments.
• X-Cell integrates multi-modal data with generative learning to map cell states into computable latent representations.
• Causal models enable better prediction of intervention effects, markedly improving target identification accuracy.
• Unifying data across scales — from molecules to tissues — remains a key challenge for clinical translation.