Integrating multi-covariate disentanglement with counterfactual analysis on synthetic data enables cell type discovery and counterfactual predictions
Abstract
CellDISECT (Cell DISentangled Experts for Covariate counTerfactuals) is a powerful causal generative model that enhances single-cell analysis by disentangling variations to separate covariate variations at test time, learning to make accurate counterfactual predictions, achieving flexible fairness through expert models for each latent space, and capturing both covariate-specific information and novel biological insights. *These authors contributed equally.
Arian Amani
Machine Learning Scientist
I am a Machine Learning Scientist at AI VIVO and a Data Scientist at the Wellcome Sanger Institute. My work is at the intersection of computational biology and drug discovery, where I develop deep generative and foundation models for molecules and cells. I specialize in molecule generation and single-cell perturbation modeling using advanced techniques like VAEs, Diffusions, Transformers, and Flow Matchings. I’m passionate about building AI methods that accelerate target discovery and therapeutic design.