Drug discovery entails novel drug development based on knowledge about existing biological targets. The goal is to create pharmaceuticals that demonstrate efficacy, reduced adverse reactions, and optimized therapeutic advantages in the most cost-efficient way. In the realm of drug design and exploration, bioinformatics plays a pivotal role by employing computational methodologies to scrutinize biological information and address intricate challenges within the field of pharmaceutical investigation such as identifying targets, conducting drug screenings, refining compounds, characterizing side effects, and predicting resistance. Computer-aided drug design strategies harness computerized algorithms, modeling approaches, and informatics resources to streamline the unearthing and enhancement of novel pharmaceutical substances. Specific tools for QSAR-based pharmacophore modelling and optimization have helped to optimize interactions between drug target and ligands. Artificial intelligence-based tools are the newest upgrades in drug discovery pipelines. Machine learning and deep learning techniques are constantly evolving, aimed at improving the existing computational pipelines and to reduce the number of required experiments. A few techniques address issues such as lead optimizations, while a few others aim at virtual screening. Specific objectives have also been targeted by these techniques. However, there are still limitations that exist due to data quality and algorithm wise. Nevertheless, with respect to preclinical studies, computational tools and techniques have greatly contributed toward saving time and money. This book chapter discusses the newest techniques used in drug discovery and development, while discussing its limitations.