Login / Signup

Machine Learning Application Identifies Germline Markers of Hypertension in Ovarian Cancer Patients Treated with Carboplatin, Taxane and Bevacizumab.

Maurizio PolanoLuca BedonMichele Dal BoRoberto SorioMichele BartolettiElena De MattiaErika CecchinCarmela PisanoDomenica LorussoAndrea Alberto LissoniAndrea De CensiSabrina Chiara CecerePaolo ScolloSergio MarchiniLaura ArenareUgo De GiorgiDaniela CalifanoElena BiagioliPaolo ChiodiniFrancesco PerroneSandro PignataGiuseppe Toffoli
Published in: Clinical pharmacology and therapeutics (2023)
Pharmacogenomics studies how genes influence a person's response to treatment. When complex phenotypes are influenced by multiple genetic variations with little effect, a single piece of genetic information is often insufficient to explain this variability. The application of machine learning (ML) in pharmacogenomics holds great potential; namely, it can be used to unravel complicated genetic relationships that could explain response to therapy. In this study, ML techniques were used to investigate the relationship between genetic variations affecting more than 60 candidate genes and carboplatin-, taxane-, and bevacizumab-induced toxicities in 171 patients with ovarian cancer enrolled in the MITO-16A/MaNGO-OV2A trial. Single nucleotide polymorphism (SNP) profiles were examined using ML to find and prioritise those associated with drug-induced toxicities, specifically hypertension, hematological toxicity, non-hematological toxicity, and proteinuria. The Boruta algorithm was used in cross-validation to determine the significance of SNPs in predicting toxicities. Important SNPs were then used to train eXtreme gradient boosting models. During cross-validation, the models achieved reliable performance with a Matthews correlation coefficient ranging from 0.375 to 0.410. A total of 43 SNPs critical for predicting toxicity were identified. For each toxicity, key SNPs were used to create a polygenic toxicity risk score that effectively divided individuals into high-risk and low-risk categories. In particular, compared with low-risk individuals, high-risk patients were 28- fold more likely to develop hypertension. The proposed method provided insightful data to improve precision medicine for ovarian cancer patients, which may be useful for reducing toxicities and improving toxicity management.
Keyphrases