Machine Learning for Genomic Data

TL;DR

This paper investigates the use of advanced machine learning clustering methods, including Hidden Markov Models and Bayesian Networks, to analyze short time-series gene expression data, addressing the limitations of standard algorithms.

Contribution

It introduces the application of model-based clustering techniques, particularly Hidden Markov Models and Bayesian Networks, tailored for short time-series genomic data analysis.

Findings

Hidden Markov Models effectively capture temporal gene expression patterns.

Bayesian Networks provide insights into gene regulatory relationships.

Model-based clustering outperforms standard methods on short time-series data.

Abstract

This report explores the application of machine learning techniques on short timeseries gene expression data. Although standard machine learning algorithms work well on longer time-series', they often fail to find meaningful insights from fewer timepoints. In this report, we explore model-based clustering techniques. We combine popular unsupervised learning techniques like K-Means, Gaussian Mixture Models, Bayesian Networks, Hidden Markov Models with the well-known Expectation Maximization algorithm. K-Means and Gaussian Mixture Models are fairly standard, while Hidden Markov Model and Bayesian Networks clustering are more novel ideas that suit time-series gene expression data.