Multi-Modal Multi-Kernel Graph Learning for Autism Prediction and Biomarker Discovery

TY - JOUR

T1 - Multi-Modal Multi-Kernel Graph Learning for Autism Prediction and Biomarker Discovery

AU - Liu, Jin

AU - Mao, Junbin

AU - Lin, Hanhe

AU - Kuang, Hulin

AU - Pan, Shirui

AU - Wu, Xusheng

AU - Xie, Shan

AU - Liu, Fei

AU - Pan, Yi

N1 - Publisher Copyright: © 2025 IEEE.

PY - 2025/2/6

Y1 - 2025/2/6

N2 - Graph learning-based multi-modal integration and classification is one of the most challenging tasks for disease prediction. To effectively offset the negative impact among modalities in the process of multi-modal integration and heterogeneous information extractions from graphs, we propose a novel method called Multi-modal Multi-Kernel Graph Learning (MMKGL). To solve the problem of negative impact among modalities, we propose a multi-modal graph embedding module to construct a multi-modal graph. Different from conventional methods that manually construct static graphs for all modalities, each modality generates a separate graph by adaptive learning, where a function graph and a supervision graph are introduced for optimization during the multi-graph fusion embedding process. We then propose a multi-kernel graph learning module to extract heterogeneous information from the multi-modal graph. The information in the multi-modal graph at different levels is aggregated by convolutional kernels with different receptive field sizes, followed by generating a cross-kernel discovery tensor for disease prediction. Our method is evaluated on the benchmark Autism Brain Imaging Data Exchange (ABIDE) dataset and outperforms the state-of-the-art methods. In addition, discriminative brain regions associated with autism are identified by our model, providing guidance for the study of autism pathology.

AB - Graph learning-based multi-modal integration and classification is one of the most challenging tasks for disease prediction. To effectively offset the negative impact among modalities in the process of multi-modal integration and heterogeneous information extractions from graphs, we propose a novel method called Multi-modal Multi-Kernel Graph Learning (MMKGL). To solve the problem of negative impact among modalities, we propose a multi-modal graph embedding module to construct a multi-modal graph. Different from conventional methods that manually construct static graphs for all modalities, each modality generates a separate graph by adaptive learning, where a function graph and a supervision graph are introduced for optimization during the multi-graph fusion embedding process. We then propose a multi-kernel graph learning module to extract heterogeneous information from the multi-modal graph. The information in the multi-modal graph at different levels is aggregated by convolutional kernels with different receptive field sizes, followed by generating a cross-kernel discovery tensor for disease prediction. Our method is evaluated on the benchmark Autism Brain Imaging Data Exchange (ABIDE) dataset and outperforms the state-of-the-art methods. In addition, discriminative brain regions associated with autism are identified by our model, providing guidance for the study of autism pathology.

KW - autism prediction

KW - biomarker discovery

KW - graph learning

KW - multi-kernel learning

KW - Multi-modal integration

UR - https://www.scopus.com/pages/publications/105017145253

U2 - 10.1109/TCBBIO.2025.3539744

DO - 10.1109/TCBBIO.2025.3539744

M3 - Article

C2 - 40811387

AN - SCOPUS:105017145253

VL - 22

SP - 842

EP - 854

JO - IEEE Transactions on Computational Biology and Bioinformatics

JF - IEEE Transactions on Computational Biology and Bioinformatics

IS - 2

ER -