# Predicting Cellular Responses with Variational Causal Inference and Refined Relational Information

arXiv: https://arxiv.org/abs/2210.00116 · HTML: https://mlsanity.com/paper/2210.00116/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 43 references that are in the map.
- First posted on arXiv 30 Sep 2022.

## Builds on (most cited first, 7 of 7)

- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [Causal Effect Inference with Deep Latent-Variable Models](https://mlsanity.com/paper/1705.08821/) (2017)
- [Graph-based Molecular Representation Learning](https://mlsanity.com/paper/2207.04869/) (2022)
- [Tutorial: Deriving The Efficient Influence Curve for Large Models](https://mlsanity.com/paper/1903.01706/) (2019)
- [Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery](https://mlsanity.com/paper/2106.02190/) (2021)
- [Variational Causal Inference](https://mlsanity.com/paper/2209.05935/) (2022)
- [Supervised, semi-supervised and unsupervised inference of gene regulatory networks](https://mlsanity.com/paper/1301.1083/) (2013)

## Built on by (most cited first, 11 of 11)

- [Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality](https://mlsanity.com/paper/2410.04780/) (2024)
- [Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model](https://mlsanity.com/paper/2306.01424/) (2023)
- [Learning Identifiable Factorized Causal Representations of Cellular Responses](https://mlsanity.com/paper/2410.22472/) (2024)
- [In-silico biological discovery with large perturbation models](https://mlsanity.com/paper/2503.23535/) (2025)
- [Doloris: Dual Conditional Diffusion Implicit Bridges with Sparsity Masking Strategy for Unpaired Single-Cell Perturbation Estimation](https://mlsanity.com/paper/2506.21107/) (2025)
- [STRAND: Sequence-Conditioned Transport for Single-Cell Perturbations](https://mlsanity.com/paper/2602.10156/) (2026)
- [GRAPE: Heterogeneous Graph Representation Learning for Genetic Perturbation with Coding and Non-Coding Biotype](https://mlsanity.com/paper/2505.03853/) (2025)
- [CRADLE-VAE: Enhancing Single-Cell Gene Perturbation Modeling with Counterfactual Reasoning-based Artifact Disentanglement](https://mlsanity.com/paper/2409.05484/) (2024)
- [PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimation](https://mlsanity.com/paper/2510.07964/) (2025)
- [Identifying biological perturbation targets through causal differential networks](https://mlsanity.com/paper/2410.03380/) (2024)
- [DRIFT: Disentangled Responsive-Invariant Flow Transport for Single-Cell Perturbation Prediction](https://mlsanity.com/paper/2609.35106/) (2026)

## Abstract (arXiv)

Predicting the responses of a cell under perturbations may bring important benefits to drug discovery and personalized therapeutics. In this work, we propose a novel graph variational Bayesian causal inference framework to predict a cell's gene expressions under counterfactual perturbations (perturbations that this cell did not factually receive), leveraging information representing biological knowledge in the form of gene regulatory networks (GRNs) to aid individualized cellular response predictions. Aiming at a data-adaptive GRN, we also developed an adjacency matrix updating technique for graph convolutional networks and used it to refine GRNs during pre-training, which generated more insights on gene relations and enhanced model performance. Additionally, we propose a robust estimator within our framework for the asymptotically efficient estimation of marginal perturbation effect, which is yet to be carried out in previous works. With extensive experiments, we exhibited the advantage of our approach over state-of-the-art deep learning models for individual response prediction.