Pharma Data Analytics (Pharma Intelligence): Opportunities and Challenges in the Multi-Omics Era of Drug Discovery and Development

Although the advent of “Omics” technologies (genomics, transcriptome, proteome and metabolome) has allowed overcoming the challenges imposed by the traditional empirical drug development models, facilitating drug discovery and development, these technologies have contributed to the generation of a large volume of data (pharma big data). Due to the complex nature of the (bio) pharmaceutical data, which count on structured and non-structured data, conventional statistic techniques are not sufficient to efficiently explore these datasets, which could lead to noise accumulation or spurious correlation. In this context, data analytics offers a set of appropriate statistical techniques that, combined with Artificial Intelligence (AI) have allowed overcoming the challenges imposed by the Pharmaceutical Big Data Era. The applications of these techniques in the (bio) pharmaceutical sector have allowed for a selection of features of interest, revealing unexpected correlations among multi-Omics, preclinical and clinical data, reducing the time and cost for drug discovery. Based on this, this review aims to summarize the most useful applications of pharma data analytics (pharma intelligence), discussing the opportunities and challenges offered by this new field of investigation.