IDENTIFICATION OF POTENTIAL DNMT1INHIBITORS IN ALZHEIMER'S THERAPEUTICS: A DRUG REPURPOSING AND MACHINE LEARNING APPROACH

Abstract

The first part of the thesis examines the use of technology such as big data, artificial intelligence (AI) as well as machine learning (ML) in cognitive healthcare, with a focus on personalized medicine for neurodegenerative diseases and drug discovery and development. Healthcare systems throughout the world face considerable problems from neurological illnesses including Parkinson's disease, Alzheimer's disease, Amyotrophic Lateral Sclerosis, and Huntington's disease. As a result, novel methods of medication development, diagnosis, and treatment are required. The first part of the thesis analyzes the state of neurological healthcare today and the shortcomings of conventional approaches to treating the complexity and variety of neurodegenerative illnesses. It then explores how utilizing enormous amounts of data from sources including genomes, proteomics, imaging, and medical records might change drug development and precision medicine. Intending to identify disease causes and enhance therapeutic approaches, it investigates the incorporation of multi-omics data along with the creation of computer models. The thesis also addresses the difficulties and moral issues related to the application of AI and ML in brain-related treatment in its literature review section. It speaks to the necessity for open and strong validation frameworks as well as data confidentiality, unfairness, and interpretability challenges. This thesis illustrates the promise of AI and ML in improving neurological healthcare through a thorough examination of research, case studies, and computer experiments. It emphasizes how important it is for researchers, physicians, as well as business stakeholders to work together to fully utilize AI and ML for individualized and successful therapies in neurodegenerative illnesses. ix In the second part of the thesis, drug discovery and development, which is a segment of the literature review has been considered for the research work for the thesis. Using machine learning algorithms, I predicted drugs to stop the progression of Alzheimer’s disease by inhibiting the DNMT1 protein. Out of the drugs mentioned in the predicted list, I have retrieved the best-binding drugs which limit the disease continuation. This work was performed using multiple computational biology tools like virtual screening and molecular docking, which also work on machine learning algorithms. The resulting drugs can be studied in experimental labs to bring the results from the bench to the bedside. Finally, this research establishes the groundwork for future developments in novel drug discovery and personalized medicine for neurodegenerative illnesses, notably Alzheimer's Disease, and adds to the corpus of understanding in the discipline of AI and ML in brain healthcare.