MoCLIM: Towards Accurate Cancer Subtyping via Multi-Omics Contrastive Learning with Omics-Inference Modeling

被引:1
作者
Yang, Ziwei [1 ]
Chen, Zheng [2 ]
Matsubara, Yasuko [2 ]
Sakurai, Yasushi [2 ]
机构
[1] Kyoto Univ, Bioinformat Ctr, Kyoto, Japan
[2] Osaka Univ, SANKEN, Suita, Osaka, Japan
来源
PROCEEDINGS OF THE 32ND ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2023 | 2023年
关键词
Cancer subtypes; Multi-omics data; Contrastive learning; EPIGENOMICS; EXPRESSION; NETWORK;
D O I
10.1145/3583780.3614970
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Precision medicine fundamentally aims to establish causality between dysregulated biochemical mechanisms and cancer subtypes. Omics-based cancer subtyping has emerged as a revolutionary approach, as different level of omics records the biochemical products of multistep processes in cancers. This paper focuses on fully exploiting the potential of multi-omics data to improve cancer subtyping outcomes, and hence developed MoCLIM, a representation learning framework. MoCLIM independently extracts the informative features from distinct omics modalities. Using a unified representation informed by contrastive learning of different omics modalities, we can well-cluster the subtypes, given cancer, into a lower latent space. This contrast can be interpreted as a projection of inter-omics inference observed in biological networks. Experimental results on six cancer datasets demonstrate that our approach significantly improves data fit and subtyping performance in fewer high-dimensional cancer instances. Moreover, our framework incorporates various medical evaluations as the final component, providing high interpretability in medical analysis.
引用
收藏
页码:2895 / 2905
页数:11
相关论文
共 76 条
[21]  
Dilokthanakul Nat., 2016, P 5 INT C LEARNING R
[22]  
Fan J, 2020, EXP MOL MED, V52, P1452
[23]   Personalizing the treatment of women with early breast cancer: highlights of the St Gallen International Expert Consensus on the Primary Therapy of Early Breast Cancer 2013 [J].
Goldhirsch, A. ;
Winer, E. P. ;
Coates, A. S. ;
Gelber, R. D. ;
Piccart-Gebhart, M. ;
Thuerlimann, B. ;
Senn, H. -J. .
ANNALS OF ONCOLOGY, 2013, 24 (09) :2206-2223
[24]   Toward a Shared Vision for Cancer Genomic Data [J].
Grossman, Robert L. ;
Heath, Allison P. ;
Ferretti, Vincent ;
Varmus, Harold E. ;
Lowy, Douglas R. ;
Kibbe, Warren A. ;
Staudt, Louis M. .
NEW ENGLAND JOURNAL OF MEDICINE, 2016, 375 (12) :1109-1112
[25]  
Gu Yichen, 2022, PR MACH LEARN RES
[26]   Hallmarks of Cancer: New Dimensions [J].
Hanahan, Douglas .
CANCER DISCOVERY, 2022, 12 (01) :31-46
[27]   Multi-omics approaches to disease [J].
Hasin, Yehudit ;
Seldin, Marcus ;
Lusis, Aldons .
GENOME BIOLOGY, 2017, 18
[28]   Inferring Interaction Networks From Multi-Omics Data [J].
Hawe, Johann S. ;
Theis, Fabian J. ;
Heinig, Matthias .
FRONTIERS IN GENETICS, 2019, 10
[29]  
Henaff OJ, 2020, PR MACH LEARN RES, V119
[30]   Dynamic modeling of gene expression data [J].
Holter, NS ;
Maritan, A ;
Cieplak, M ;
Fedoroff, NV ;
Banavar, JR .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2001, 98 (04) :1693-1698