Falak Pabari
Computational biology · Azizi Lab, Columbia University
Computational biology, Azizi Lab, Columbia. Generative models for single-cell genomics.
Previously Brown, Sc.B. in Applied Mathematics–Computer Science. DNA methylation and aging with Ritambhara Singh; CRISPR perturbation screens with Ying Ma.
Interested in probabilistic and generative methods for biological data, and in what structure they actually recover.
Research
- Deep Learning Models for Robust Latent Structure in Single-Cell and Methylation Data
- Contrastive Disentanglement of Methylation Variation Reveals Population-Structured Aging Trajectories
- Uncertainty-Aware Detection of Perturbation Escapees in Large-Scale CRISPR Screens
- Find It Like a Dog: Using Gesture to Improve Robot Object Search