NpPred: Prediction of Nuclear Proteins Using SVM and HMM Models

NpPred: Prediction of Nuclear Proteins Using SVM and HMM Models Overview NpPred is a computational method developed for predicting nuclear proteins using Support Vector Machine (SVM) and Hidden Markov Model (HMM) techniques. The system combines sequence composition analysis and Pfam domain information to accurately distinguish nuclear proteins from non-nuclear proteins. Research Paper Title: Prediction of nuclear proteins using SVM and HMM models Authors:Manish Kumar and Gajendra P. S. Raghava Journal: BMC Bioinformatics (2009) DOI: https://doi.org/10.1186/1471-2105-10-22 https://github.com/Piyushh1104/NpPred.git Background Nuclear proteins are involved in: Chromosomal maintenance Gene regulation RNA processing Nuclear transport Cellular homeostasis Accurate prediction of nuclear proteins is important for: Functional annotation Proteome analysis Subcellular localization studies Computational biology Dataset Information The study used a non-redundant dataset containing: 2710 nuclear proteins 7662 non-nuclear proteins The dataset was extracted from Swiss-Prot release 40.41.