Alghamdi Mashael A
Department of Chemistry, College of Science, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi Arabia.
Pharmaceuticals (Basel). 2025 Jul 14;18(7):1041. doi: 10.3390/ph18071041.
The discovery of effective therapeutics against Alzheimer's disease (AD) and other neurological disorders remains a significant challenge. Artificial intelligence (AI) tools are of considerable interest in modern drug discovery processes and, by exploiting machine learning (ML) algorithms and deep learning (DL) tools, as well as data analytics, can expedite the identification of new drug targets and potential lead molecules. The current study was aimed at assessing the role of AI-based tools in the discovery of new drug targets against AD and other related neurodegenerative diseases and their efficacy in the discovery of new drugs against these diseases. AD represents a multifactorial neurological disease with limited therapeutics available for management and limited efficacy. The discovery of more effective medications is limited by the complicated pathophysiology of the disease, involving amyloid beta (Aβ), neurofibrillary tangles (NFTs), oxidative stress, and inflammation-induced damage in the brain. The integration of AI tools into the traditional drug discovery process against AD can help to find more effective, safe, highly potent compounds, identify new targets of the disease, and help in the optimization of lead molecules. A detailed literature review was performed to gather evidence regarding the most recent AI tools for drug discovery against AD, Parkinson's disease (PD), multiple sclerosis (MLS), and epilepsy, focusing on biological markers, early diagnoses, and drug discovery using various databases like PubMed, Web of Science, Google Scholar, Scopus, and ScienceDirect to collect relevant literature. We evaluated the role of AI in analyzing multifaceted biological data and the properties of potential drug candidates and in streamlining the design of clinical trials. By exploring the intersection of AI and neuroscience, this review focused on providing insights into the future of AD treatment and the potential of AI to revolutionize the field of drug discovery. Our findings conclude that AI-based tools are not only cost-effective, but the success rate is extremely high compared to traditional drug discovery methods in identifying new therapeutic targets and in the screening of the majority of molecules for clinical trial purposes.
发现针对阿尔茨海默病（AD）和其他神经疾病的有效治疗方法仍然是一项重大挑战。人工智能（AI）工具在现代药物发现过程中备受关注，通过利用机器学习（ML）算法、深度学习（DL）工具以及数据分析，可以加快新药物靶点和潜在先导分子的识别。当前的研究旨在评估基于AI的工具在发现针对AD和其他相关神经退行性疾病的新药物靶点中的作用，以及它们在发现针对这些疾病的新药物方面的功效。AD是一种多因素神经疾病，可用于管理的治疗方法有限且疗效不佳。更有效药物的发现受到该疾病复杂病理生理学的限制，包括淀粉样β蛋白（Aβ）、神经纤维缠结（NFTs）、氧化应激以及大脑中的炎症诱导损伤。将AI工具整合到针对AD的传统药物发现过程中，有助于找到更有效、安全、高效的化合物，识别该疾病的新靶点，并有助于优化先导分子。进行了详细的文献综述，以收集有关针对AD、帕金森病（PD）、多发性硬化症（MLS）和癫痫的最新药物发现AI工具的证据，重点关注生物标志物、早期诊断以及使用PubMed、科学网、谷歌学术、Scopus和ScienceDirect等各种数据库进行药物发现，以收集相关文献。我们评估了AI在分析多方面生物数据和潜在药物候选物特性以及简化临床试验设计中的作用。通过探索AI与神经科学的交叉点，本综述重点在于深入了解AD治疗的未来以及AI彻底改变药物发现领域的潜力。我们的研究结果表明，基于AI的工具不仅具有成本效益，而且与传统药物发现方法相比，在识别新的治疗靶点以及筛选用于临床试验的大多数分子方面成功率极高。
