Missing-Modality-Aware Graph Neural Network for Cancer Classification

TL;DR

MAGNET is a novel graph neural network that effectively handles missing modalities in multimodal biological data, improving cancer classification accuracy with scalable, adaptive fusion strategies.

Contribution

Introduces MAGNET, a missing-modality-aware GNN with dynamic attention and patient graph construction, addressing scalability and flexibility issues in multimodal data fusion.

Findings

MAGNET outperforms state-of-the-art methods on three multiomics datasets.

The model's complexity scales linearly with the number of modalities.

MAGNET effectively handles real-world missingness in multimodal data.

Abstract

A key challenge in learning from multimodal biological data is missing modalities, where data from one or more modalities are absent for some patients. Existing approaches either exclude patients with missing modalities, impute missing modalities, or make predictions directly with partial modalities. However, most of these methods rely on inflexible, patient-agnostic fusion strategies and do not scale computationally to the combinatorial growth of missing-modality patterns as the number of modalities increases. To address these limitations, we propose MAGNET (Missing-modality-Aware Graph neural NETwork) to enhance multimodal prediction with partial modalities, featuring a dynamic patient-modality multi-head attention mechanism to fuse lower-dimensional modality embeddings based on their contribution and missingness. MAGNET fusion's complexity increases linearly with the number of modalities while adapting to missing-pattern variability. To generate predictions, MAGNET further constructs a patient graph with fused multimodal embeddings as node features and connectivity determined by the modality missingness, followed by a graph neural network. Experiments on three public multiomics datasets for cancer classification, with real-world missingness, show that MAGNET outperforms state-of-the-art fusion methods. The data and code are available at https://github.com/SinaTabakhi/MAGNET.