Deep learning of causal structures in high dimensions under data limitations

Journal article

The aging process is a complex and multifaceted phenomenon affecting all living organisms. It involves a gradual deterioration of tissue and cellular function, leading to a higher risk of developing various age-related diseases (ARDs), including cancer, neurodegenerative, and cardiovascular diseases. The gene regulatory networks (GRNs) and their respective niches are crucial in determining the aging rate. Unveiling these GRNs holds promise for developing novel therapies and diagnostic tools to enhance healthspan and longevity. This review examines GRN modeling approaches in aging, encompassing differential equations, Boolean/fuzzy logic decision trees, Bayesian networks, mutual information, and regression clustering. These approaches provide nuanced insights into the intricate gene-protein interactions in aging, unveiling potential therapeutic targets and ARD biomarkers. Nevertheless, outstanding challenges persist, demanding more comprehensive datasets and advanced algorithms to comprehend and predict GRN behavior accurately. Despite these hurdles, identifying GRNs associated with aging bears immense potential and is poised to transform our comprehension of human health and aging. This review aspires to stimulate further research in aging, fostering the innovation of computational approaches for promoting healthspan and longevity

Authors: Lagemann, K; Lagemann, C; Taschler, B; Mukherjee, S

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Nature Research
• Journal: Nature Machine Intelligence
• Volume: 5
• Issue: 11
• Pages: 1306-1316
• Publication date: 2023-10-26
• DOI: 10.1038/s42256-023-00744-z
• EISSN: 2522-5839
• ISSN: 2522-5839
• Language: English
• Keywords: Artificial neural network; Machine learning; Causal model; Curse of dimensionality; Deep learning; Key (lock); Computer science; Convolutional neural network; Data science; Artificial intelligence; Mathematics