Enhancing drug-food interaction prediction with precision representations through multilevel self-supervised learning

被引:7
|
作者
Wei, Jinhang [1 ]
Li, Zhen [2 ]
Zhuo, Linlin [1 ]
Fu, Xiangzheng [3 ]
Wang, Mingjing [1 ]
Li, Keqin [3 ,4 ]
Chen, Chengshui [5 ,6 ]
机构
[1] Wenzhou Univ Technol, Wenzhou 325000, Peoples R China
[2] Guangzhou Univ, Inst Computat Sci & Technol, Guangzhou 510006, Peoples R China
[3] Hunan Univ, Coll Comp Sci & Elect Engn, Changsha 410006, Peoples R China
[4] SUNY, Dept Comp Sci, New York, NY 12561 USA
[5] Wenzhou Med Univ, Quzhou Affiliated Hosp, Quzhou Peoples Hosp, Dept Pulm & Crit Care Med, Quzhou 324000, Peoples R China
[6] Wenzhou Med Univ, Affiliated Hosp 1, Dept Pulm & Crit Care Med, Key Lab Intervent Pulmonol Zhejiang Prov, Wenzhou 325000, Peoples R China
关键词
Drug-food interaction; Self-supervised learning; Enhanced representations quality; Feature alignment; Domain separation;
D O I
10.1016/j.compbiomed.2024.108104
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
Drug-food interactions (DFIs) crucially impact patient safety and drug efficacy by modifying absorption, distribution, metabolism, and excretion. The application of deep learning for predicting DFIs is promising, yet the development of computational models remains in its early stages. This is mainly due to the complexity of food compounds, challenging dataset developers in acquiring comprehensive ingredient data, often resulting in incomplete or vague food component descriptions. DFI-MS tackles this issue by employing an accurate feature representation method alongside a refined computational model. It innovatively achieves a more precise characterization of food features, a previously daunting task in DFI research. This is accomplished through modules designed for perturbation interactions, feature alignment and domain separation, and inference feedback. These modules extract essential information from features, using a perturbation module and a feature interaction encoder to establish robust representations. The feature alignment and domain separation modules are particularly effective in managing data with diverse frequencies and characteristics. DFI-MS stands out as the first in its field to combine data augmentation, feature alignment, domain separation, and contrastive learning. The flexibility of the inference feedback module allows its application in various downstream tasks. Demonstrating exceptional performance across multiple datasets, DFI-MS represents a significant advancement in food presentations technology. Our code and data are available at https://github.com/kkkayle/DFI-MS.
引用
收藏
页数:12
相关论文
共 50 条
  • [41] Enhancing Self-Supervised Learning through Explainable Artificial Intelligence Mechanisms: A Computational Analysis
    Neghawi, Elie
    Liu, Yan
    BIG DATA AND COGNITIVE COMPUTING, 2024, 8 (06)
  • [42] Bridging vision and touch: advancing robotic interaction prediction with self-supervised multimodal learning
    Li, Luchen
    Thuruthel, Thomas George
    FRONTIERS IN ROBOTICS AND AI, 2024, 11
  • [43] Self-supervised generative learning for sequential data prediction
    Xu, Ke
    Zhong, Guoqiang
    Deng, Zhaoyang
    Zhang, Kang
    Huang, Kaizhu
    APPLIED INTELLIGENCE, 2023, 53 (18) : 20675 - 20689
  • [44] Co-contrastive Self-supervised Learning for Drug-Disease Association Prediction
    Gao, Zihao
    Ma, Huifang
    Zhang, Xiaohui
    Wu, Zheyu
    Li, Zhixin
    PRICAI 2022: TRENDS IN ARTIFICIAL INTELLIGENCE, PT I, 2022, 13629 : 327 - 338
  • [45] IMAGE ENHANCED ROTATION PREDICTION FOR SELF-SUPERVISED LEARNING
    Yamaguchi, Shinya
    Kanai, Sekitoshi
    Shioda, Tetsuya
    Takeda, Shoichiro
    2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 489 - 493
  • [46] Self-supervised generative learning for sequential data prediction
    Ke Xu
    Guoqiang Zhong
    Zhaoyang Deng
    Kang Zhang
    Kaizhu Huang
    Applied Intelligence, 2023, 53 : 20675 - 20689
  • [47] Self-Supervised Learning of Action Affordances as Interaction Modes!
    Wang, Liquan
    Dvornik, Nikita
    Dubeau, Rafael
    Mittal, Mayank
    Garg, Animesh
    2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2023), 2023, : 7279 - 7286
  • [48] Self-supervised learning with automatic data augmentation for enhancing representation
    Park, Chanjong
    Kim, Eunwoo
    PATTERN RECOGNITION LETTERS, 2024, 184 : 133 - 139
  • [49] Enhancing robust VQA via contrastive and self-supervised learning
    Cao, Runlin
    Li, Zhixin
    Tang, Zhenjun
    Zhang, Canlong
    Ma, Huifang
    PATTERN RECOGNITION, 2025, 159
  • [50] Self-supervised Learning Through Colorization for Microscopy Images
    Pandey, Vaidehi
    Brune, Christoph
    Strisciuglio, Nicola
    IMAGE ANALYSIS AND PROCESSING, ICIAP 2022, PT II, 2022, 13232 : 621 - 632