The Incipient Role of Computational Intelligence in Oncology: Drug Designing, Discovery, and Development

Abstract

AbstractComputational intelligence (CI) approaches are multi-layered neural networks having robust reasoning, logical, and self-regulating capability to learn that highly simulate the human cognitive process. CI technologies such as machine learning (ML), deep learning (DL), and artificial intelligence (AI) algorithms appeared to be the promising solution that overcome the obstacle and problems in designing and discovering drugs. Drug designing, discovery, and development are associated with certain hurdles and challenges such as off-target delivery, inappropriate dosage, less efficacy, production costs, and time consumption. Additionally, the complex and enormous data from proteomics, microarray, genomics data, and clinical trials impact the drug discovery pipeline. In oncology, the drug discovery process is more crucial as there are approximately three hundred variant forms of cancers that affect people of all age groups. Even though understanding disease pathogenesis and progress is in developing innovative small molecule drugs, successful discovery and development require 13–14 years and expensive investment. Therefore, the CI can envisage oncology drug discovery and development and further aid in addressing resistance in oncology drugs by learning and analyzing data. Oncology remains at the forefront to reap the profits of CI for the overall management of cancer, including identifying the target, hit identification, optimization of the lead compound, preclinical or clinical trials, and then regulatory approvals. This study described the current advancement of CI in the arena of oncology, with the simultaneous prospect of anticancer drug development and therapeutic approaches. CI tools and techniques such as machine and deep learning can profoundly augment the prevailing method of oncology drug research.KeywordsAnticancerComputational intelligenceDrug discoveryDrug developmentDeep learning