CFM-GP: Unified Conditional Flow Matching to Learn Gene Perturbation Across Cell Types
Published in NAR Genomics and Bioinformatics, Volume 8, Issue 3, 2026
CFM-GP learns a continuous, cell-type-conditioned transformation from control to perturbed single-cell expression profiles. A unified conditional flow model captures shared and cell-type-specific response dynamics across multiple biological settings.
Recommended citation: Abir, Abrar Rahman, Sajib Acharjee Dip, and Liqing Zhang. (2026). "CFM-GP: Unified Conditional Flow Matching to Learn Gene Perturbation Across Cell Types." NAR Genomics and Bioinformatics 8(3): lqag087.
Download Paper