9th International Conference on ICT for Sustainable Development

Authors - Ayush P. Gadkari, Mansvi Daigavhane, Anushka Arghode, Prateek Verma, Swapnil Gundewar
Abstract - In the realm of drug discovery process, Machine Learning (ML) is essential for enhancing decision-making in biological or pharmaceutical databases. ML has applications in several phases of the drug development process, such as target validation, predictive biomarker identification, and digital pathology data interpretation in clinical trials. Utilizing ML in drug discovery can increase success rates and expedite the identification of promising new therapeutic targets. The goal of drug discovery is to find new drug candidates by analyzing enormous amounts of biological or medicinal data using computational algorithms. A drug development process faces a number of difficulties, including insufficient data, model transferability, sparse and heterogeneous data, repeatability and validation, and feature representation and selection. In the area of drug discovery, virtual screening and predictive modelling are the two main uses of ML. By effectively screening huge chemical libraries, supporting target identification and optimizing, and easing drug repurposing initiatives, virtual screening significantly speeds up the drug development process and eventually results in the identification of novel therapeutic agents. In the realm of drug development, the current study reviews the role of virtual screening and predictive modelling to analyze large amounts of data and forecast treatment outcomes for cancer and other diseases.