PDXGEM: Patient-Derived Tumor Xenograft based Gene Expression Model for Predicting Clinical Response to Anticancer Therapy in Cancer Patients

摘要: Abstract Background Cancer is a highly heterogeneous disease and shows varying responses to anti-cancer drugs. Although several approaches have been attempted predict the drug by analyzing molecular profiling data of tumors from preclinical cancer models or patients, there still great need developing accurate prediction response drugs for clinical applications toward personalized medicine. Here, we present PDXGEM pipeline build predictive gene expression model (GEM) patients’ on basis activity in patient-derived xenograft (PDX) models. Results Drug sensitivity biomarkers were identified an association analysis between levels post-treatment tumor volume changes PDX Only with concordant co-expression patterns patient used random-forest algorithm model, so called PDXGEM. We applied cytotoxic chemotherapy as well targeted therapy agents that are treat breast cancer, pancreatic colorectal non-small cell lung cancer. Significantly predictions pathological survival outcomes observed through extensive validation analyses multiple independent datasets obtained retrospective observational study prospective trials. Conclusion Our results demonstrated strong potential utilizing profiles clinically translatable patients. web application publicly available at http://pdxgem.moffitt.org.