Timezone: »
Poster
MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data
Tianyu Liu · Yuge Wang · Rex Ying · Hongyu Zhao
Event URL: https://github.com/HelloWorldLTY/MuSe-GNN »
Discovering genes with similar functions across diverse biomedical contexts poses a significant challenge in gene representation learning due to data heterogeneity. In this study, we resolve this problem by introducing a novel model called Multimodal Similarity Learning Graph Neural Network, which combines Multimodal Machine Learning and Deep Graph Neural Networks to learn gene representations from single-cell sequencing and spatial transcriptomic data. Leveraging 82 training datasets from 10 tissues, three sequencing techniques, and three species, we create informative graph structures for model training and gene representations generation, while incorporating regularization with weighted similarity learning and contrastive learning to learn cross-data gene-gene relationships. This novel design ensures that we can offer gene representations containing functional similarity across different contexts in a joint space. Comprehensive benchmarking analysis shows our model's capacity to effectively capture gene function similarity across multiple modalities, outperforming state-of-the-art methods in gene representation learning by up to $\textbf{100.4}$%. Moreover, we employ bioinformatics tools in conjunction with gene representations to uncover pathway enrichment, regulation causal networks, and functions of disease-associated genes. Therefore, our model efficiently produces unified gene representations for the analysis of gene functions, tissue functions, diseases, and species evolution.
Discovering genes with similar functions across diverse biomedical contexts poses a significant challenge in gene representation learning due to data heterogeneity. In this study, we resolve this problem by introducing a novel model called Multimodal Similarity Learning Graph Neural Network, which combines Multimodal Machine Learning and Deep Graph Neural Networks to learn gene representations from single-cell sequencing and spatial transcriptomic data. Leveraging 82 training datasets from 10 tissues, three sequencing techniques, and three species, we create informative graph structures for model training and gene representations generation, while incorporating regularization with weighted similarity learning and contrastive learning to learn cross-data gene-gene relationships. This novel design ensures that we can offer gene representations containing functional similarity across different contexts in a joint space. Comprehensive benchmarking analysis shows our model's capacity to effectively capture gene function similarity across multiple modalities, outperforming state-of-the-art methods in gene representation learning by up to $\textbf{100.4}$%. Moreover, we employ bioinformatics tools in conjunction with gene representations to uncover pathway enrichment, regulation causal networks, and functions of disease-associated genes. Therefore, our model efficiently produces unified gene representations for the analysis of gene functions, tissue functions, diseases, and species evolution.
Author Information
Tianyu Liu (Yale University)
Yuge Wang (Yale University)
Rex Ying (Yale University)
Hongyu Zhao (Yale University)
More from the Same Authors
-
2022 : GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks »
Kenza Amara · Rex Ying · Ce Zhang -
2022 : Learning Efficient Hybrid Particle-continuum Representations of Non-equilibrium N-body Systems »
Tailin Wu · Michael Sun · Hsuan-Gu Chou · Pranay Reddy Samala · Sithipont Cholsaipant · Sophia Kivelson · Jacqueline Yau · Rex Ying · E. Paulo Alves · Jure Leskovec · Frederico Fiuza -
2022 : How Powerful is Implicit Denoising in Graph Neural Networks »
Songtao Liu · Rex Ying · Hanze Dong · Lu Lin · Jinghui Chen · Dinghao Wu -
2022 : Efficient Automatic Machine Learning via Design Graphs »
Shirley Wu · Jiaxuan You · Jure Leskovec · Rex Ying -
2022 : GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks »
Kenza Amara · Rex Ying · Zitao Zhang · Zhihao Han · Yinan Shan · Ulrik Brandes · Sebastian Schemm -
2023 : GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Network Explanations »
Kenza Amara · Mennatallah El-Assady · Rex Ying -
2023 : FAFormer: Frame Averaging Transformer for Predicting Nucleic Acid-Protein Interactions »
Tinglin Huang · Zhenqiao Song · Rex Ying · Wengong Jin -
2023 Workshop: New Frontiers in Graph Learning (GLFrontiers) »
Jiaxuan You · Rex Ying · Hanjun Dai · Ge Liu · Azalia Mirhoseini · Smita Krishnaswamy -
2023 Poster: Static and Sequential Malicious Attacks in the Context of Selective Forgetting »
Chenxu Zhao · Wei Qian · Rex Ying · Mengdi Huai -
2023 Poster: Learning to Group Auxiliary Datasets for Molecule »
Tinglin Huang · Ziniu Hu · Rex Ying -
2023 Poster: D4Explainer: In-distribution Explanations of Graph Neural Network via Discrete Denoising Diffusion »
Jialin Chen · Shirley Wu · Abhijit Gupta · Rex Ying -
2023 Poster: TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery »
Jialin Chen · Rex Ying -
2022 Workshop: New Frontiers in Graph Learning »
Jiaxuan You · Marinka Zitnik · Rex Ying · Yizhou Sun · Hanjun Dai · Stefanie Jegelka -
2022 : Invited Talk »
Rex Ying