PANOPLY: A computational method for identification of promising drugs for a patient based on multidimensional data
PurposeThe majority of cancer patients receive treatments that are minimally informed by omics data. We propose a precision medicine computational framework (PANOPLY: Precision cancer genomic report: single sample inventory) to identify and prioritize drug targets and cancer therapy regimens.\n\nMethodsThe PANOPLY approach integrates clinical data with germline and somatic features obtained from multi-omics platforms, and apply machine learning, and network analysis approaches in the context of the individual patient and matched controls. The PANOPLY workflow employs four steps (i) selection of matched controls to the case of interest (ii) identification of case-specific genomic events (iii) identification of suitable drugs using the driver-gene network and random forest analyses and (iv) provide an integrated multi-omics case report of the patient with prioritization of anti-cancer drugs.\n\nResultsThe PANOPLY workflow can be executed on a stand-alone virtual machine and is also available for download as an R package. We applied the method to an institutional breast cancer neoadjuvant chemotherapy study which collected clinical and genomic data as well as patient-derived xenografts (PDXs) to investigate the prioritization offered by PANOPLY. In a chemotherapy-resistant PDX model, we found that that the prioritized drug, olaparib, was more effective than placebo in treating the tumor (P < 0.05). We also applied PANOPLY to in-house and publicly accessible multi-omics tumor datasets with therapeutic response or survival data available.\n\nConclusionPANOPLY shows promise as a means to prioritize drugs based on clinical and multi-omics data for an individual cancer patient. Additional studies are needed to confirm this approach.