# Gene Regulatory Network Inference in the Presence of Dropouts: a Causal View

arXiv: https://arxiv.org/abs/2403.15500 · HTML: https://mlsanity.com/paper/2403.15500/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 84 references that are in the map.
- First posted on arXiv 21 Mar 2024.

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

- [Causal-learn: Causal Discovery in Python](https://mlsanity.com/paper/2307.16405/) (2023)
- [Permutation-based Causal Inference Algorithms with Interventions](https://mlsanity.com/paper/1705.10220/) (2017)
- [Causal Discovery in the Presence of Missing Data](https://mlsanity.com/paper/1807.04010/) (2018)
- [High-dimensional consistency in score-based and hybrid structure learning](https://mlsanity.com/paper/1507.02608/) (2015)
- [Active Learning for Optimal Intervention Design in Causal Models](https://mlsanity.com/paper/2209.04744/) (2022)
- [Fast Causal Inference with Non-Random Missingness by Test-Wise Deletion](https://mlsanity.com/paper/1705.09031/) (2017)
- [MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models](https://mlsanity.com/paper/2205.13869/) (2022)
- [Matching a Desired Causal State via Shift Interventions](https://mlsanity.com/paper/2107.01850/) (2021)
- [Independence Testing-Based Approach to Causal Discovery under Measurement Error and Linear Non-Gaussian Models](https://mlsanity.com/paper/2210.11021/) (2022)
- [Anchored Causal Inference in the Presence of Measurement Error](https://mlsanity.com/paper/1906.00928/) (2019)
- [High Dimensional Semiparametric Latent Graphical Model for Mixed Data](https://mlsanity.com/paper/1404.7236/) (2014)
- [Directed Graphical Models and Causal Discovery for Zero-Inflated Data](https://mlsanity.com/paper/2004.04150/) (2020)
- [Sparse semiparametric canonical correlation analysis for data of mixed types](https://mlsanity.com/paper/1807.05274/) (2018)
- [Reframed GES with a Neural Conditional Dependence Measure](https://mlsanity.com/paper/2206.08531/) (2022)
- [Sparse semiparametric discriminant analysis for high-dimensional zero-inflated data](https://mlsanity.com/paper/2208.03734/) (2022)

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

- [The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications](https://mlsanity.com/paper/2412.01953/) (2024)
- [scDFM: Distributional Flow Matching Model for Robust Single-Cell Perturbation Prediction](https://mlsanity.com/paper/2602.07103/) (2026)
- [Amortized Active Causal Induction with Deep Reinforcement Learning](https://mlsanity.com/paper/2405.16718/) (2024)
- [When Selection Meets Intervention: Additional Complexities in Causal Discovery](https://mlsanity.com/paper/2503.07302/) (2025)
- [Conditional Diffusion Models Based Conditional Independence Testing](https://mlsanity.com/paper/2412.11744/) (2024)
- [Latent Variable Causal Discovery under Selection Bias](https://mlsanity.com/paper/2512.11219/) (2025)
- [Learning to refine domain knowledge for biological network inference](https://mlsanity.com/paper/2410.14436/) (2024)
- [InfoSEM: A Deep Generative Model with Informative Priors for Gene Regulatory Network Inference](https://mlsanity.com/paper/2503.04483/) (2025)
- [Zero Inflation as a Missing Data Problem: a Proxy-based Approach](https://mlsanity.com/paper/2406.00549/) (2024)
- [Causal Modeling of Selection in Evolution](https://mlsanity.com/paper/2606.05689/) (2026)
- [Causal ASCEND: Scalable Two-tier Causal Discovery on High Dimensional Multi-omics Data](https://mlsanity.com/paper/2607.04527/) (2026)

## Abstract (arXiv)

Gene regulatory network inference (GRNI) is a challenging problem, particularly owing to the presence of zeros in single-cell RNA sequencing data: some are biological zeros representing no gene expression, while some others are technical zeros arising from the sequencing procedure (aka dropouts), which may bias GRNI by distorting the joint distribution of the measured gene expressions. Existing approaches typically handle dropout error via imputation, which may introduce spurious relations as the true joint distribution is generally unidentifiable. To tackle this issue, we introduce a causal graphical model to characterize the dropout mechanism, namely, Causal Dropout Model. We provide a simple yet effective theoretical result: interestingly, the conditional independence (CI) relations in the data with dropouts, after deleting the samples with zero values (regardless if technical or not) for the conditioned variables, are asymptotically identical to the CI relations in the original data without dropouts. This particular test-wise deletion procedure, in which we perform CI tests on the samples without zeros for the conditioned variables, can be seamlessly integrated with existing structure learning approaches including constraint-based and greedy score-based methods, thus giving rise to a principled framework for GRNI in the presence of dropouts. We further show that the causal dropout model can be validated from data, and many existing statistical models to handle dropouts fit into our model as specific parametric instances. Empirical evaluation on synthetic, curated, and real-world experimental transcriptomic data comprehensively demonstrate the efficacy of our method.