# GeSubNet: Gene Interaction Inference for Disease Subtype Network Generation

arXiv: https://arxiv.org/abs/2410.13178 · HTML: https://mlsanity.com/paper/2410.13178/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 62 references that are in the map.
- First posted on arXiv 17 Oct 2024.

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

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction](https://mlsanity.com/paper/2206.04216/) (2022)
- [DELTACON: A Principled Massive-Graph Similarity Function](https://mlsanity.com/paper/1304.4657/) (2013)
- [XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data](https://mlsanity.com/paper/2105.12807/) (2021)
- [wTO: an R package for computing weighted topological overlap and consensus networks with an integrated visualization tool](https://mlsanity.com/paper/1711.04702/) (2017)
- [Automated Cancer Subtyping via Vector Quantization Mutual Information Maximization](https://mlsanity.com/paper/2206.10801/) (2022)
- [MoCLIM: Towards Accurate Cancer Subtyping via Multi-Omics Contrastive Learning with Omics-Inference Modeling](https://mlsanity.com/paper/2308.09725/) (2023)

## Built on by (most cited first, 1 of 1)

- [ExPath: Targeted Pathway Inference for Biological Knowledge Bases via Graph Learning and Explanation](https://mlsanity.com/paper/2502.18026/) (2025)

## Abstract (arXiv)

Retrieving gene functional networks from knowledge databases presents a challenge due to the mismatch between disease networks and subtype-specific variations. Current solutions, including statistical and deep learning methods, often fail to effectively integrate gene interaction knowledge from databases or explicitly learn subtype-specific interactions. To address this mismatch, we propose GeSubNet, which learns a unified representation capable of predicting gene interactions while distinguishing between different disease subtypes. Graphs generated by such representations can be considered subtype-specific networks. GeSubNet is a multi-step representation learning framework with three modules: First, a deep generative model learns distinct disease subtypes from patient gene expression profiles. Second, a graph neural network captures representations of prior gene networks from knowledge databases, ensuring accurate physical gene interactions. Finally, we integrate these two representations using an inference loss that leverages graph generation capabilities, conditioned on the patient separation loss, to refine subtype-specific information in the learned representation. GeSubNet consistently outperforms traditional methods, with average improvements of 30.6%, 21.0%, 20.1%, and 56.6% across four graph evaluation metrics, averaged over four cancer datasets. Particularly, we conduct a biological simulation experiment to assess how the behavior of selected genes from over 11,000 candidates affects subtypes or patient distributions. The results show that the generated network has the potential to identify subtype-specific genes with an 83% likelihood of impacting patient distribution shifts.