Abstract

The role of computational tools in the drug discovery and development process is becoming central, thanks to the possibility to analyze large amounts of data. The high throughput and affordability of current omics technologies, allowing quantitative measurements of many putative targets, has exponentially increased the volume of scientific data available. The quality of the data and the speed with which in silico predictions can be validated in vitro is instrumental in accelerating clinical laboratory medicine, significantly and substantially impacting Precision Medicine (PM). PM affords the basis to develop new drugs by providing a wide knowledge of the patient as an essential step towards individualized medicine. It is, therefore, essential to collect as much information and data as possible on each patient to identify the causes of the different responses to drugs from a pharmacogenomics perspective and to identify biological biomarkers capable of accurately describing the risk signals to develop specific diseases. Furthermore, the role of biomarkers in early drug discovery is increasing, as they can significantly reduce the time it takes to develop new drugs. This review article will discuss how Artificial Intelligence fits in the drug discovery pipeline, covering the benefits of an automated, integrated laboratory framework where the application of Machine Learning methodologies to interpret omics-based data can avail the future perspective of Translational Precision Medicine.

Keywords: f, dfsd, fsdf, sdf, sf, sd, fsd

Graphical Abstract