Protein Classification using Hidden Markov Models and Random Forests

Abstract—Since the introduction of next generation sequencing there is a demand for sophisticated methods to classify proteins based on sequence data. The approaches for this task typically involve the alignment among raw sequences and the extraction of discrete high level feature from the protein sequences for recognition. In this paper, we employ two different machine learning methods to perform the task, i.e. Hidden Markov Model and Random Forests. Profile Hidden Markov Models are built from multiple alignment of raw sequence data and amino acid emission and transition parameters are estimated for a given alignment and effectively harness the power of aligning a test protein to a model built form many proteins. Random Forests on the other hand are used to discriminate between two sets of proteins based on features such as functional amino acid groups and physiochemical properties extracted from the raw sequences. The strengths and limitations of each method are presented and discussed, focusing on the individual merits and how they could work possibly compliment each other rather than just being compared by their classification accuracy. I