Skip to content

Paper analyzing the accuracy and predictor importance of various machine/deep learning models predicting estrogen receptor status using breast cancer metabolomics data

Notifications You must be signed in to change notification settings

roshinib3/breast-cancer-metabolomics

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Comparative Study of Machine Learning Algorithms for Estrogen Receptor Status Prediction Using Breast Cancer Metabolomics Data

Full study available here

Abstract

Metabolomics, the comprehensive analysis of metabolites in a biological sample, is emerging as an important tool for detecting altered cellular processes in diseased individuals. In this study, metabolomics data (n=271) are used to test the accuracy of various machine and deep learning models on an estrogen receptor status classification task. The Deep Learning framework was the optimal model in terms of area under the receiver-operating characteristic (AUC), with support vector machines and random forests performing as a close second and third, respectively. Further analysis of predictor importance reveals the biological significance of these approaches and areas for future investigation.

Results

(Left) Predictive Accuracy Measured by Average AUC     (Right) Biaprtite Network for Predictor Importance

About

Paper analyzing the accuracy and predictor importance of various machine/deep learning models predicting estrogen receptor status using breast cancer metabolomics data

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages