PRiMeFlow: Capturing Complex Expression Heterogeneity in Perturbation Response Modelling

TL;DR

PRiMeFlow is a novel flow-based model that accurately predicts perturbation effects on single-cell gene expression, capturing heterogeneity and complex dependencies to aid drug discovery.

Contribution

It introduces a distribution-fitting, flow matching approach for modeling perturbation effects directly in gene expression space, validated through extensive benchmarking and scaling strategies.

Findings

PRiMeFlow accurately models empirical gene expression distributions.

It outperforms existing methods on PerturBench and ARC Virtual Cell Challenge.

Model design choices like gene expression space operation and U-Net velocity parameterization are validated.

Abstract

Predicting the effects of perturbations in-silico on cell state can identify drivers of cell behavior at scale and accelerate drug discovery. However, modeling challenges remain due to the inherent heterogeneity of single cell gene expression and the complex, latent gene dependencies. Here, we present PRiMeFlow, an end-to-end flow matching based approach to directly model the effects of genetic and small molecule perturbations in the gene expression space. The distribution-fitting approach taken by PRiMeFlow enables it to accurately approximate the empirical distribution of single-cell gene expression, which we demonstrate through extensive benchmarking inside PerturBench. Through ablation studies, we also validate important model design choices such as operating in gene expression space and parameterizing the velocity field with a U-Net architecture. Finally, by scaling PRiMeFlow to a broad perturbation data atlas spanning multiple datasets and employing a carefully designed pretraining-finetuning strategy, we demonstrate its outstanding performance on the H1 human embryonic stem cells from the ARC Virtual Cell Challenge benchmark.