Analysis of Machine Learning techniques for identification of post translation modification in protein sequencing: A Review

Bioinformatics is the study of computational and statistical techniques used in biological science. It plays an important role in the detection, prediction and treatment of a wide range of biological diseases. Protein is the main component of human tissues made up of amino acids. Post Translation Modification (PTM) is any modification that occurs in amino acids that are making protein. These changes may be done by adding some groups with the amino acids or decomposing a group of amino acids. A proteome is the complete set of proteins that are expressed by the human organism. As PTM refers to the modification in the proteins so it is very important to understand it for a complete understanding of proteins and the diseases that refers to it. Acetylation, Phosphorylation, Hydroxylation, Methylation, AMPylation, Lipidation, Ubiquitination, Proteolysis, and Deamidation are some PTMs. This study describes machine learning techniques used for the detection of Post Translation Modification. These machine learning techniques include Artificial Neural Network (ANN), Random Forest (RF), Logical Regression (LR) Pseudo-amino acid composition (PseAAC) using Deep Neural Network, 10-fold cross validation test, Jackknife validation, Independent set testing. These techniques with their results are discussed in this paper.