Involving Machine Learning in genetics has been a very significant approach in the field of Biosciences or biological sciences as it helps us to subdue the complexities involved in understanding the human genetic structure. By collecting large scale data at different levels of granularity and by introducing sophisticated machine learning algorithms, we are able to pinpoint genetic markers that impact drug response and side effects with remarkable accuracy.
Additionally, machine learning is essential for finding new therapeutic targets and ranking them according to their safety and efficacy profiles [1]. This strategy guarantees that we reduce the possibility of negative effects while simultaneously developing medications that work. This paper focuses on discussing supervised, unsupervised and deep learning models in drug discovery studies to optimize side effects based on human genetics.