-

AIDD8124-Chemobioinformatics 

I am an Associate Professor at the Faculty of Applied Sciences (FCA) at Macao Polytechnic University (MPU) and the Group Leader of the Peking University-Health Science Center-Macao Polytechnic University Joint Research Laboratory in Artificial Intelligence Empowered Smart Healthy Ageing (PKU-MPU AIHA), operating under FCA. Concurrently, I am also leading the development of a new PhD program in AI-empowered Healthy Ageing, expected to launch in Fall 2026. Prior to joining MPU in 2023, I spent over 12 years as a faculty member at the University of California, San Diego (UCSD).

Our team's research is centered on AI-driven smart healthy aging and the innovative application of causal inference in medical big data. We address the core challenge of geriatric care—minimizing disability duration caused by aging and disease—by employing interdisciplinary approaches integrating artificial intelligence (AI), multi-omics analysis, and causal inference. This enables us to decode the complex interaction mechanisms and dynamic evolution patterns among physical-mental-brain comorbidities, aging trajectories, and disability progression. Ultimately, our goal is to develop evidence-based intelligent intervention strategies and products that effectively delay the progression of geriatric disability, thereby contributing to the realization of global healthy aging initiatives.

 To date, our team has published over 120 peer-reviewed scientific papers in high-impact journals including Nature Human Behaviour, World Psychiatry, PNAS, Advanced Science, and Analytical Chemistry. Supported by competitive funding from MPU, the Macao SAR Government, and national agencies, our group maintains state-of-the-art computational infrastructure and has established enduring collaborations with leading medical and healthy aging institutions across Macao, Mainland China, Southeast Asia, India, and the United States. Furthermore, we have established a multidisciplinary research team with PhD students whose backgrounds span computer science, big data analytics, public health, applied mathematics, and clinical medicine, providing a robust foundation for our cross-disciplinary research endeavors.

本團隊的研究領域聚焦於人工智能驅動的智慧康養與因果推斷在醫療大數據中的創新應用。養老照護的核心目標在於最大限度減少衰老與疾病導致的失能時間。我們團隊綜合運用人工智能、多組學分析及因果推斷等多學科交叉方法，開展多源動態異構醫療與康養大數據的深度挖掘，旨在揭示身-心-脑共病、衰老及失能之間的複雜交互機制與動態演變規律，進而開發智能化干預策略與產品，以有效延緩老年失能進程，助力健康老齡化戰略的實現。

課題組目前擁有充足的科研經費，正承擔著來自大學、澳門特區政府及國家層面的多項科研項目。團隊配備先進的計算資源，並與澳門、中國內地、東南亞、印度及美國等地區的多家醫療與康養機構建立了長期穩定的合作關係，保障數據資源的豐富獲取。同時，我們已構建起多學科交叉的研究團隊，成員背景涵蓋計算機科學、大數據分析、公共衛生、應用數學及臨床醫學等領域，為跨學科研究提供堅實支撐。

  • Current Employer/Organization

    Macao Polytechnic University

  • Current Position

    Associate Professor

    Macao Polytechnic University

  • Subjects Taught

    AIDD8124-Chemobioinformatics 

  • Education

    • PhD., Michigan Technological University, MI, USA
    • MSc., Michigan Technological University, MI, USA
    • MSc., Tianjin University, Tianjin, China
    • BSc.,  Tianjin University of Traditional Chinese Medicine, Tianjin, China

  • Research Interests

    • Algorithmic Foundations: AI-Causal Inference Algorithm Development & Medical Big Data Applications

    Designing interpretable causal inference frameworks (e.g., counterfactual learning, dynamic treatment regimes and causal decision trees.) for medical/healthcare data, with applications in quantifying treatment effects and mitigating confounding biases in aging-related interventions.

    • Data Methodology: Dynamic Time-Series Analysis and Virtual Cell Modeling via Multi-Omics Fusion

    Developing virtual cell modeling and spatiotemporal analytics to decode longitudinal interactions between genomic, proteomic, clinical, and behavioral data in aging trajectories

    • Mechanistic Exploration: Dynamics of Physical-Mental-Brain Comorbidities in Aging and Disability

    Uncovering causal pathways linking multimorbidity patterns (e.g., depression-dementia-diabetes), biological aging clocks, and functional disability progression through longitudinal cohort studies and causal network analysis.

    • Translational Application: Intelligent Healthy Aging Ecosystems with Multi-Modal LLMs and Assistive Robotics

    Building multimodal AI agents (e.g., multimodal LLMs for personalized care planning) and robotic companions for real-time physiological monitoring, fall prevention, and cognitive rehabilitation in elderly care settings.

    • 算法基础：人工智能因果推斷算法開發及其在醫療康養大數據中的應用

    設計可解釋性因果推斷框架（如反事實學習、動態治療方案優化、因果決策樹等），應用於醫療數據中治療效應量化與衰老相關干預的混雜偏倚校正。

    • 数据方法：醫療康養多組學融合的動態時序分析與虛擬細胞建模

    開發多模態數據融合算法與時空分析技術，解碼基因組、蛋白組、臨床及行為數據在衰老軌跡中的縱向交互機制。

    • 机制探索：身心脑共病与衰老-失能动态演变机制研究

    通過隊列研究與因果網絡分析，揭示抑鬱-癡呆-糖尿病等共病模式、生物衰老時鐘與功能失能進展的因果路徑。

    • 产品落地：智能康養生態系統：多模態大模型與助老機器人開發

    構建多模態智能體（如個性化照護規劃大語言模型）及助老機器人，實現情感陪伴、實時生理監測、跌倒預防與認知康復等的智能干預。

  • Work Experience

    • 01/2023 - now,  Associate professor,  Faculty of Applied Sciences, Macao Polytechnic University, Macau SR
    • 07/2017 - 12/2022, Associate Professor, UC San Diego Medical Center, Hillcrest, USA
    • 07/2014 - 06/2017, Assistant Professor, UC San Diego Medical Center, Hillcrest, USA
    • 07/2012 - 06/2014, Postdoctoral Scientist, School of Medicine, University of California, San Diego, USA

  • Additional Experience

    • 11/2024 - 12/2026, Joint Research Funding Program between FDCT-GDST (0009/2024/AGJ), 90 K MOP, PI, ongoing.
    • 1/2024 - 12/2026,  FDCT（0033/2023/RIB), 2 million MOP，PI, ongoing.
    • 10/2025- 10/2028, FDCT-MOST,  1.73 million MOP, PI, ongoing.

  • Publications

    Below are the representative publications from each research area.  The full list of publications from our group can be found through the link https://scholar.google.com/citations?user=Vq8CpowAAAAJ&hl=en   or our group website  https://liomicslab.cn/


    • Causal inference algorithms and their medical big data applications (人工智能因果推斷算法開發及其在醫療康養大數據中的應用)

    [1] Xu W, Luo G, Meng W, Zhai X, Zheng K, Wu J, Li Y, Xing A, Li J, Li Z, Zheng K, Li K*. MRAgent: an LLM-based automated agent for causal knowledge discovery in disease via Mendelian randomization. Brief Bioinform. 2025, 26: bbaf140. (JCR Q1)

    [2] Xing A, Cai T, Du H, Li Z, Ng H, Li J, Jiang G, Chen L, Li K*. MRanalysis: a comprehensive online platform for integrated, multimethod Mendelian randomization and associated post-GWAS analyses. Gigascience. 2025, 14: giaf131. (JCR Q1)

    [3] Sha Y, Pan H, Xu W, Meng W, Luo G, Du X, Zhai X, Tong HHY, Shi C, Li K*. MDD-LLM: Towards accuracy large language models for major depressive disorder diagnosis. J Affect Disord. 2025, 388:119774. (JCR Q1)


    • Dynamic Time-Series Analysis and Multi-omics （醫療康養多組學數據分析）

    [1] Xu W, Guo R, Chen P, Li L, Gu M, Sun H, Hu L*, Wang Z*, Li K*. Cherry growth modeling based on Prior Distance Embedding contrastive learning: Pre-training, anomaly detection, semantic segmentation, and temporal modeling. Comput. Electron. Agr. 2024, 221:108973. (JCR Q1)

    [2] Sha Y, Meng W, Gang L, Zhai XB, Henry TT, Wang Y*, Li K*. MetDIT: Transforming and analyzing clinical metabolomics data with convolutional neural networks. Anal. Chem. 2024, 96:2949-2957. (JCR Q1)

    [3] Cui S, Li L, Zhang Y, Lu J, Wang X, Song X, Liu J*, Li K*. Machine learning identifies metabolic signatures that predict the risk of recurrent angina in remitted patients after percutaneous coronary intervention: A multicenter prospective cohort study. Adv. Sci. 2021, 8:2003893. (JCR Q1)


    • Mental Health and Physical-Mental-Brain Comorbidities (精神和身-心-腦共病與衰老)

    [1] Zhai X, Tong HHY, Lam CK, Xing A, Sha Y, Luo G, Meng W, Li J, Zhou M, Huang Y, Wong LS, Wang C*, Li K*. Association and causal mediation between marital status and depression in seven countries. Nat Hum Behav. 2024, 8:2392-2405. (JCR Q1)

    [2] Pan H, Sha Y, Zhai X, Luo G, Xu W, Meng W, Li K*. Bootstrap inference and machine learning reveal core differential plasma metabolic connectome signatures in major depressive disorder. J Affect Disord. 2025, 378:281-292. (JCR Q1) 

    [3] Luo G, Xu W, Sha Y, Zhao X, Pan H, Zhai X, Li Z, Meng W, Li J, Ji J, Yu L, Li K*. An interpretable machine learning model predicts the interactive and cumulative risks of different environmental chemical exposures on depression. Transl Psychiatry. 2025, 15:450. (JCR Q1)


    • Intelligent Healthy Aging Ecosystems（智能康養生態系統）

    [1] Xie C, Zhai X, Chi H, Li W, Li X, Sha Y, Li K*. A Novel Fusion Pruning-Processed Lightweight CNN for Local Object Recognition on Resource-Constrained Devices. IEEE Trans. Consum. Electron. 2024, 70: 6713 - 6724. (JCR Q1)

  • Description

    Our team's research is centered on AI-driven smart healthy aging and the innovative application of causal inference in medical big data. We address the core challenge of geriatric care—minimizing disability duration caused by aging and disease—by employing interdisciplinary approaches integrating artificial intelligence (AI), multi-omics analysis, and causal inference. This enables us to decode the complex interaction mechanisms and dynamic evolution patterns among physical-mental-brain comorbidities, aging trajectories, and disability progression. Ultimately, our goal is to develop evidence-based intelligent intervention strategies and products that effectively delay the progression of geriatric disability, thereby contributing to the realization of global healthy aging initiatives.


    本團隊的研究領域聚焦於人工智能驅動的智慧康養與因果推斷在醫療大數據中的創新應用。養老照護的核心目標在於最大限度減少衰老與疾病導致的失能時間。我們團隊綜合運用人工智能、多組學分析及因果推斷等多學科交叉方法，開展多源動態異構醫療與康養大數據的深度挖掘，旨在揭示身-心-脑共病、衰老及失能之間的複雜交互機制與動態演變規律，進而開發智能化干預策略與產品，以有效延緩老年失能進程，助力健康老齡化戰略的實現。

  • Journal papers

    Below are the representative publications from each research area.  The full list of publications from our group can be found through the link https://scholar.google.com/citations?user=Vq8CpowAAAAJ&hl=en   or our group website  https://liomicslab.cn/


    • Causal inference algorithms and their medical big data applications (人工智能因果推斷算法開發及其在醫療康養大數據中的應用)

    [1] Xu W, Luo G, Meng W, Zhai X, Zheng K, Wu J, Li Y, Xing A, Li J, Li Z, Zheng K, Li K*. MRAgent: an LLM-based automated agent for causal knowledge discovery in disease via Mendelian randomization. Brief Bioinform. 2025, 26: bbaf140. (JCR Q1)

    [2] Xing A, Cai T, Du H, Li Z, Ng H, Li J, Jiang G, Chen L, Li K*. MRanalysis: a comprehensive online platform for integrated, multimethod Mendelian randomization and associated post-GWAS analyses. Gigascience. 2025, 14: giaf131. (JCR Q1)

    [3] Sha Y, Pan H, Xu W, Meng W, Luo G, Du X, Zhai X, Tong HHY, Shi C, Li K*. MDD-LLM: Towards accuracy large language models for major depressive disorder diagnosis. J Affect Disord. 2025, 388:119774. (JCR Q1)


    • Dynamic Time-Series Analysis and Multi-omics （醫療康養多組學數據分析）

    [1] Xu W, Guo R, Chen P, Li L, Gu M, Sun H, Hu L*, Wang Z*, Li K*. Cherry growth modeling based on Prior Distance Embedding contrastive learning: Pre-training, anomaly detection, semantic segmentation, and temporal modeling. Comput. Electron. Agr. 2024, 221:108973. (JCR Q1)

    [2] Sha Y, Meng W, Gang L, Zhai XB, Henry TT, Wang Y*, Li K*. MetDIT: Transforming and analyzing clinical metabolomics data with convolutional neural networks. Anal. Chem. 2024, 96:2949-2957. (JCR Q1)

    [3] Cui S, Li L, Zhang Y, Lu J, Wang X, Song X, Liu J*, Li K*. Machine learning identifies metabolic signatures that predict the risk of recurrent angina in remitted patients after percutaneous coronary intervention: A multicenter prospective cohort study. Adv. Sci. 2021, 8:2003893. (JCR Q1)


    • Mental Health and Physical-Mental-Brain Comorbidities (精神和身-心-腦共病與衰老)

    [1] Zhai X, Tong HHY, Lam CK, Xing A, Sha Y, Luo G, Meng W, Li J, Zhou M, Huang Y, Wong LS, Wang C*, Li K*. Association and causal mediation between marital status and depression in seven countries. Nat Hum Behav. 2024, 8:2392-2405. (JCR Q1)

    [2] Pan H, Sha Y, Zhai X, Luo G, Xu W, Meng W, Li K*. Bootstrap inference and machine learning reveal core differential plasma metabolic connectome signatures in major depressive disorder. J Affect Disord. 2025, 378:281-292. (JCR Q1) 

    [3] Luo G, Xu W, Sha Y, Zhao X, Pan H, Zhai X, Li Z, Meng W, Li J, Ji J, Yu L, Li K*. An interpretable machine learning model predicts the interactive and cumulative risks of different environmental chemical exposures on depression. Transl Psychiatry. 2025, 15:450. (JCR Q1)


    • Intelligent Healthy Aging Ecosystems（智能康養生態系統）

    [1] Xie C, Zhai X, Chi H, Li W, Li X, Sha Y, Li K*. A Novel Fusion Pruning-Processed Lightweight CNN for Local Object Recognition on Resource-Constrained Devices. IEEE Trans. Consum. Electron. 2024, 70: 6713 - 6724. (JCR Q1)

  • Conference Papers

    • Y. Sha, H. Pan, W Meng, Li K*. Contrastive knowledge-guided large language models for medical report generation. MICCAI-2025. [CCF-B]

  • Professional Membership:

    • Council Member, Macau Association for the Promotion of Industry-Academia-Research Collaboration
    • Committee Member, Macau Society of Digital Medicine and Artificial Intelligence
    • Youth Editorial Board Member, Military Medical Research
    • Grant reviewer: EPA, NIH, NSFC, and National Medical Research Council, Singapore