Big data and computational biology strategy for personalized prognosis

Abstract

The era of big data and precision medicine has led to accumulation of massive datasets of gene expression data and clinical information of patients. For a new patient, we propose that identification of a highly similar reference patient from an existing patient database via similarity matching of both clinical and expression data could be useful for predicting the prognostic risk or therapeutic efficacy.Here, we propose a novel methodology to predict disease/treatment outcome via analysis of the similarity between any pair of patients who are each characterized by a certain set of pre-defined biological variables (biomarkers or clinical features) represented initially as a prognostic binary variable vector (PBVV) and subsequently transformed to a prognostic signature vector (PSV). Our analyses revealed that Euclidean distance rather correlation distance measure was effective in defining an unbiased similarity measure calculated between two PSVs.We implemented our methods to high-grade serous ovarian cancer (HGSC) based on a 36-mRNA predictor that was previously shown to stratify patients into 3 distinct prognostic subgroups. We studied and revealed that patient's age, when converted into binary variable, was positively correlated with the overall risk of succumbing to the disease. When applied to an independent testing dataset, the inclusion of age into the molecular predictor provided more robust personalized prognosis of overall survival correlated with the therapeutic response of HGSC and provided benefit for treatment targeting of the tumors in HGSC patients.Finally, our method can be generalized and implemented in many other diseases to accurately predict personalized patients’ outcomes.

Big genomics and clinical data analytics strategies for precision cancer prognosis

“…In a subsequent follow up study, we studied the effect of patients’ age on overall prognosis and due to its survival significance, we added this clinical risk factor into the original 36-gene combined mRNA prognostic signature to form a 37-variable hybrid mRNA/clinical data prognostic signature6.…”

“…The patients could be classified into different risk subgroups based on the values of the AWR. The procedures were implemented in a training cohort comprising 349 TCGA HGSC patients68.…”

“…Our results proposed that Euclidean distance measure of the prognostic signature vector (PSV) is an appropriate method of assessing the similarity between any patient pair6. A brief schema is outlined in Fig.…”

“…In our previous study, we proposed the following three-step strategy of personalized cancer patient’s prognosis6. In the first step, the method performs sensitive, specific and robust feature selection procedure to select the most discriminative and reproducible variables (genes, clinical characteristics, etc.)…”

“…In the second step, the method combines the binary variables into a multi-variable classifier of differential diagnosis, prognosis or prediction of treatment outcome8. In the third step, the method applies the multivariate weighted voting prognosis model to an independent patient/sample or independent dataset which were not used in the original training and attempt to classify a new patient into pre-defined classes of diagnosis, prognosis or outcome therapy risks6. Our method is termed Prognostic Signature Vector Matching (PSVM)6.…”