# In-silico biological discovery with large perturbation models

arXiv: https://arxiv.org/abs/2503.23535 · HTML: https://mlsanity.com/paper/2503.23535/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 96 references that are in the map.
- First posted on arXiv 30 Mar 2025.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Learning Counterfactual Representations for Estimating Individual Dose-Response Curves](https://mlsanity.com/paper/1902.00981/) (2019)
- [Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution](https://mlsanity.com/paper/2204.13545/) (2022)
- [Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling](https://mlsanity.com/paper/2211.03553/) (2022)
- [CausalBench: A Large-scale Benchmark for Network Inference from Single-cell Perturbation Data](https://mlsanity.com/paper/2210.17283/) (2022)
- [Causal machine learning for single-cell genomics](https://mlsanity.com/paper/2310.14935/) (2023)
- [GeneDisco: A Benchmark for Experimental Design in Drug Discovery](https://mlsanity.com/paper/2110.11875/) (2021)
- [DiscoBAX: Discovery of Optimal Intervention Sets in Genomic Experiment Design](https://mlsanity.com/paper/2312.04064/) (2023)
- [Predicting Cellular Responses with Variational Causal Inference and Refined Relational Information](https://mlsanity.com/paper/2210.00116/) (2022)
- [The CausalBench challenge: A machine learning contest for gene network inference from single-cell perturbation data](https://mlsanity.com/paper/2308.15395/) (2023)
- [Variational Causal Inference](https://mlsanity.com/paper/2209.05935/) (2022)
- [Multi-omics Prediction from High-content Cellular Imaging with Deep Learning](https://mlsanity.com/paper/2306.09391/) (2023)

## Built on by (most cited first, 4 of 4)

- [PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling](https://mlsanity.com/paper/2607.23447/) (2026)
- [Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects](https://mlsanity.com/paper/2605.31522/) (2026)
- [Artificial Intelligence Virtual Cells: From Measurements to Decisions across Modality, Scale, Dynamics, and Evaluation](https://mlsanity.com/paper/2510.12498/) (2025)
- [Bison: Cross-Dataset Learning for Unseen-Compound Perturbation Prediction](https://mlsanity.com/paper/2609.32467/) (2026)

## Abstract (arXiv)

Data generated in perturbation experiments link perturbations to the changes they elicit and therefore contain information relevant to numerous biological discovery tasks -- from understanding the relationships between biological entities to developing therapeutics. However, these data encompass diverse perturbations and readouts, and the complex dependence of experimental outcomes on their biological context makes it challenging to integrate insights across experiments. Here, we present the Large Perturbation Model (LPM), a deep-learning model that integrates multiple, heterogeneous perturbation experiments by representing perturbation, readout, and context as disentangled dimensions. LPM outperforms existing methods across multiple biological discovery tasks, including in predicting post-perturbation transcriptomes of unseen experiments, identifying shared molecular mechanisms of action between chemical and genetic perturbations, and facilitating the inference of gene-gene interaction networks.