STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations

TL;DR

STRAND is a novel generative model that predicts single-cell transcriptional responses to genetic perturbations by conditioning on regulatory DNA sequences, enabling zero-shot inference and improved accuracy across cell types.

Contribution

It introduces sequence-based perturbation representation and a conditional transport process, significantly expanding inference coverage and accuracy over gene-level models.

Findings

Improves discrimination scores by up to 33% in low-sample regimes.

Achieves best average rank on unseen gene perturbation benchmarks.

Enhances transfer to new cell lines with up to 0.14 increase in Pearson correlation.

Abstract

Predicting how genetic perturbations change cellular state is a core problem for building controllable models of gene regulation. Perturbations targeting the same gene can produce different transcriptional responses depending on their genomic locus, including different transcription start sites and regulatory elements. Gene-level perturbation models collapse these distinct interventions into the same representation. We introduce STRAND, a generative model that predicts single-cell transcriptional responses by conditioning on regulatory DNA sequence. STRAND represents a perturbation by encoding the sequence at its genomic locus and uses this representation to parameterize a conditional transport process from control to perturbed cell states. Representing perturbations by sequence, rather than by a fixed set of gene identifiers, supports zero-shot inference at loci not seen during training and expands inference-time genomic coverage from ~1.5% for gene-level single-cell foundation models to ~95% of the genome. We evaluate STRAND on CRISPR perturbation datasets in K562, Jurkat, and RPE1 cells. STRAND improves discrimination scores by up to 33% in low-sample regimes, achieves the best average rank on unseen gene perturbation benchmarks, and improves transfer to novel cell lines by up to 0.14 in Pearson correlation. Ablations isolate the gains to sequence conditioning and transport, and case studies show that STRAND resolves functionally alternative transcription start sites missed by gene-level models.