Taha Bakr Ahmed, Abdulrahm Zahraa Mustafa, Addie Ali J, Haider Adawiya J, Alkawaz Ali Najem, Yaqoob Isam Ahmed M, Arsad Norhana
Photonics Technology Lab, Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, UKM, Bangi, 43600, Malaysia; Alimam University College, Balad, Iraq.
Aliraqia University, Collage of Media, Department Relations Public, Iraq.
Talanta. 2025 May 15;287:127693. doi: 10.1016/j.talanta.2025.127693. Epub 2025 Feb 4.
Multi-omics profiling integrates genomic, epigenomic, transcriptomic, and proteomic data, essential for understanding complex health and disease pathways. This review highlights the transformative potential of combining optical nanosensors with artificial intelligence (AI). It is possible to identify disease-specific biomarkers using real-time and sensitive molecular interactions. These technologies are precious for genetic, epigenetic, and proteomic changes critical to disease progression and treatment response. AI improves multi-omics profiling by analyzing large, diverse data sets and common patterns traditional methods overlook. Machine learning tools Biomarkers Discovery is revolutionizing, drug resistance is being understood, and medicine is being personalized as the combination of AI and nanosensors has advanced the detection of DNA methylation and proteomic signatures and improved our understanding of cancer, cardiovascular disease and vascular disease. Despite these advances, challenges still exist. Difficulties in integrating data sets, retaining sensors, and building scalable computing tools are the biggest obstacles. It also examines various solutions with advanced AI algorithms and innovations, including fabrication in nanosensor design. Moreover, it highlights the potential of nanosensor-assisted, AI-driven multi-omics profiling to revolutionize disease diagnosis and treatment. As technology advances, these tools pave the way for faster diagnosis, more accurate treatment and improved patient outcomes, offering new hope for personalized medicine.
多组学分析整合了基因组、表观基因组、转录组和蛋白质组数据，这对于理解复杂的健康和疾病通路至关重要。本综述强调了将光学纳米传感器与人工智能（AI）相结合的变革潜力。利用实时且灵敏的分子相互作用来识别疾病特异性生物标志物是可行的。这些技术对于疾病进展和治疗反应至关重要的遗传、表观遗传和蛋白质组学变化而言十分珍贵。人工智能通过分析传统方法忽视的大量多样数据集和共同模式来改进多组学分析。机器学习工具生物标志物发现正在发生变革，随着人工智能与纳米传感器的结合推动了DNA甲基化和蛋白质组学特征的检测并增进了我们对癌症、心血管疾病和血管疾病的理解，耐药性正在被了解，医学也正在走向个性化。尽管取得了这些进展，但挑战依然存在。整合数据集、保留传感器以及构建可扩展计算工具方面的困难是最大的障碍。它还研究了采用先进人工智能算法和创新的各种解决方案，包括纳米传感器设计中的制造。此外，它强调了纳米传感器辅助、人工智能驱动的多组学分析在革新疾病诊断和治疗方面的潜力。随着技术的进步，这些工具为更快的诊断、更精确的治疗和改善患者预后铺平了道路，为个性化医疗带来了新希望。
