Mapping transcriptional responses to cellular perturbation dictionaries with RNA fingerprinting [K562_drug]

Single-cell perturbation dictionaries systematically measure how cells respond to genetic and chemical perturbations, creating the opportunity to assign causal interpretations to observational data. We introduce RNA fingerprinting, a statistical framework that maps transcriptional responses from new experiments onto reference perturbation dictionaries. RNA fingerprinting learns representations of perturbations, or ``fingerprints," from single-cell data, then probabilistically assigns query cells to one or more candidate perturbations. We benchmark our method across ground-truth datasets, demonstrating accurate assignments at single-cell resolution, scalability to genome-wide screens, and the ability to resolve combinatorial perturbations. We demonstrate its broad utility across diverse biological settings: identifying context-specific regulators of p53 under ribosomal stress, characterizing drug mechanisms of action and dose-dependent off-target effects, and uncovering cytokine-driven B cell heterogeneity during secondary influenza infection in vivo. Together, these results establish RNA fingerprinting as a versatile framework for interpreting single-cell datasets by linking cellular states to the underlying perturbations which generated them.