Online Program

Return to main conference page
Monday, January 6
Mon, Jan 6, 5:30 PM - 6:30 PM
Pacific D
Welcome Reception & Poster Session I

Classification Algorithm for High Dimensional Protein Markers in Time-course Data (307791)

*SOUVIK BANERJEE, Indian Institute of Technology(ISM) Dhanbad 
Atanu Bhattacharjee, ACTREC, Tata Memorial Center 
Gajendra Kumar Vishwakarma, Indian Institute of Technology(ISM) Dhanbad 

Keywords: Classification, Frailty, Joint Modeling, Auto-regressive, Bayesian.

Identification of biomarkers is an emerging area in Oncology. In this article, we develop an efficient statistical procedure for classification of protein markers according to their effect on cancer progression. A high-dimensional time-course dataset of protein markers for 80 patients motivates us for developing the algorithm. We obtain the optimal threshold values for markers using Cox proportional hazard model. The optimal threshold value is defined as a level of a marker having maximum impact on cancer progression. The classification was validated by comparing random components using accelerated failure time frailty model. The study elucidates the application of two separate joint modeling techniques using auto regressive-type model and mixed effect model for time-course data and proportional hazard model for survival data with proper utilization of Bayesian methodology. Also, a prognostic scoring system based on contributing biomarkers is developed to readily identify the survival status of a patient. The complete analysis is performed by R programming code. This study facilitates to identify relevant biomarkers from a high dimensional set of markers.