Machine Learning with Ensemble Feature Selections for Mass Spectrometry Data in Cancer Study

• Activity Number: 254 - Contributed Poster Presentations: Section on Statistical Learning and Data Science
• Type: Contributed
• Date/Time: Monday, July 30, 2018 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistical Learning and Data Science
• Author(s): Yulan Liang* and Amin Gharipour and Arpad Kelemen and Adam Kelemen and Hui Zhang
• Companies: University of Maryland Baltimore and Griffith University and University of Maryland Baltimore and University of Maryland College Park and Johns Hopkins Medical Institutions
• Keywords: Mass Spectrometry based proteomic technologies ; Ensemble Feature Selections ; Machine Learning ; Ovarian cancer ; reproducibility; prediction

Abstract

Identifications of disease signature or protein biomarkers have been crucial for medical diagnosis and prognosis, and drug target selection in complex diseases, such as cancer. Statistical models with single feature selection encompass the multi-testing burden with low power if with limited sample size. High correlations among the markers, along with small to moderate effects often lead to unstable selections, and cause reproducibility issues. Machine learning with ensemble feature selections (EFSs) has the advantage to alleviate and compensate those drawbacks. Mass spectrometry (MS) based proteomic technologies have enabled global expression profiling at the protein level to examine the linkages between protein, cancer subtypes and treatment heterogeneity. In this work we conducted and compared various EFS methods in machine learning models such as random forests, support vector machine, and neural network for predicting both binary and multiple class outcomes using MS proteomic ovarian cancer data. Despite the different prediction accuracies from various machine-learning models, EFSs identify the consistent and reproducible sets of proteins biomarkers linked to the outcomes.