Machine learning is an essential tool for predicting systems' behavior. Many
machine learning algorithms have recently been used to predict the system's changing
behavioral pattern. Phase transition is an exciting phenomenon in physics, observed in
many molecules and systems, where a sharp structural change occurs with a minor
change in an environment like pressure or temperature. It is a significant process to
understand the structure of a molecule. The Bayesian algorithm has diverse
applications, and in this chapter, its usage is incorporated with the approach of oneclass classification to predict the phase transition in biopolymers. In this study, the
algorithm proposed predicts the phase transition of L-alanine polypeptide. This
algorithm corroborates the detection of transition parameters or changepoints in
temperature-dependent significant frequencies with experimental results. The observed
variation of Amide frequencies of the polypeptide is used to confirm the occurrence of
a phase transition that causes structural change with the effect of temperature change.
Keywords: Amide frequencies, Change-point, Infrared spectroscopy, Machine learning, Naïve Bayes, One-class classification, Phase transition, Probability, Temperature variability.
