# Modeling Gene Expression Distributional Shifts for Unseen Genetic Perturbations

arXiv: https://arxiv.org/abs/2507.02980 · HTML: https://mlsanity.com/paper/2507.02980/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 32 references that are in the map.
- First posted on arXiv 1 Jul 2025.

## Builds on (most cited first, 6 of 6)

- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder](https://mlsanity.com/paper/2311.02794/) (2023)
- [PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis](https://mlsanity.com/paper/2408.10609/) (2024)
- [Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling](https://mlsanity.com/paper/2211.03553/) (2022)
- [Investigating the Histogram Loss in Regression](https://mlsanity.com/paper/2402.13425/) (2024)

## Built on by (most cited first, 2 of 2)

- [scDFM: Distributional Flow Matching Model for Robust Single-Cell Perturbation Prediction](https://mlsanity.com/paper/2602.07103/) (2026)
- [PopPert: Population-level Joint-Distribution Modeling for Single-Cell Perturbation Prediction](https://mlsanity.com/paper/2609.01357/) (2026)

## Abstract (arXiv)

We train a neural network to predict distributional responses in gene expression following genetic perturbations. This is an essential task in early-stage drug discovery, where such responses can offer insights into gene function and inform target identification. Existing methods only predict changes in the mean expression, overlooking stochasticity inherent in single-cell data. In contrast, we offer a more realistic view of cellular responses by modeling expression distributions. Our model predicts gene-level histograms conditioned on perturbations and outperforms baselines in capturing higher-order statistics, such as variance, skewness, and kurtosis, at a fraction of the training cost. To generalize to unseen perturbations, we incorporate prior knowledge via gene embeddings from large language models (LLMs). While modeling a richer output space, the method remains competitive in predicting mean expression changes. This work offers a practical step towards more expressive and biologically informative models of perturbation effects.