The field of pharmacogenomics investigates how genomics may modulate pathological trends using information on both genotype and phenotype, with the aim of designing personalised healthcare. Homoeostasis is partially regulated through the expression of core protein groups whose functionality is determined at gene level and modulated by environmental factors. Harmful changes in physiology may promote several dis-functionalities. In prior work gene expression was used as a biomarker to assess both pathological propensity and disease progression. A growing body of pharmacogenomics research has developed new compounds, on one hand, and on the other, it has proposed novel therapeutic applications for the existing ones. Over the past decades, collective efforts have significantly increased the number of omics information available. However, efficient and deterministic in silico mechanisms that efficiently analyse and detect trends on the basis of often unknown and limited physiological information responding to challenging clinical questions are still lacking. In this context, computational automation via artificial intelligence methodologies has proven to be accurate, robust to noise, cost efficient, and dynamic dealing with massive databases and forecasting on the basis of the available information. Moreover, this set of computational techniques, based on well-established mathematical models, provide efficient ways of determining trends based on both a priori knowledge and dynamically acquired information, working successfully on incomplete datasets. Therefore, in this chapter we assess developmental similarities between two major causes of worldwide death: glioblastoma and chronic arterial inflammation; and discuss the potential applicability of two artificial intelligence approaches for drug discovery and repositioning. According to the World Health Organization (WHO) a glioblastoma multiform is the most malignant glial-type tumour (graded level IV in the WHO scale); and inflammatory diseases affecting the cardiovascular network are the cause of high mortality. As suggested, these two pathologies have several developmental similarities and share common genetic variants. Therefore, we additionally seek to discuss the main promoters presented in the current literature, aiming at benefiting from their similarities in drug discovery and repositioning, via automatic artificial intelligence pattern recognition, forecasting, and computational design.
CITATION STYLE
Pereira, G. C. (2017). Genomics and artificial intelligence working together in drug discovery and repositioning: The advent of adaptive pharmacogenomics in glioblastoma and chronic arterial inflammation therapies. In Biotechnology and Production of Anti-Cancer Compounds (pp. 253–281). Springer International Publishing. https://doi.org/10.1007/978-3-319-53880-8_11
Mendeley helps you to discover research relevant for your work.