Prediction of Protein – Peptide Binding Residues Using Classification Algorithms

EasyChair Preprint 4083

Abstract

Peptide-binding proteins prediction is important in understanding biological Interaction, protein performance analysis, cellular processes, drug design, and even cancer prediction, so using experimental and laboratory predictive methods, despite their operational capabilities, has limitations such as: cost and time, differences between unrecognized protein structures and sequences, and design and development of computational systems for maintenance, Optimization models for representing biological knowledge, management and the analysis of huge biological data is so strong that the authors used machine learning-based techniques such as: SVM,RF,DT(C4.5),DT(ID3),Gradient Boosting classifiers, which evaluated experimental results to optimize the Support vector machine strap (with RBF core) with significant evaluation parameters such as : ACC is equal to 0.7401 and 0.7599 for Independent test set and 10 Fold Cross Validation and also SPE is equal to 0.7966 and 0.8088 for 10 Fold Cross Validation and Independent test set (respectively) and using various Structure- Based and Sequence-Based

Keyphrases: Binding Residue, Protein-Peptide, classification algorithms, machine learning

@booklet{EasyChair:4083,
  author    = {Shima Shafiee and Abdolhossein Fathi and Fardin Abdali Mohammadi},
  title     = {Prediction of Protein – Peptide Binding Residues Using Classification Algorithms},
  howpublished = {EasyChair Preprint 4083},
  year      = {EasyChair, 2020}}