Adaptive Locality-Effective Kernel Machine for protein phosphorylation site prediction

In this study, we propose a new machine learning model namely, Adaptive Locality-Effective Kernel Machine (Adaptive-LEKM) for protein phosphorylation site prediction. Adaptive-LEKM proves to be more accurate and exhibits a much stable predictive performance over the existing machine learning models. Adaptive-LEKM is trained using Position Specific Scoring Matrix (PSSM) to detect possible protein phosphorylation sites for a target sequence. The performance of the proposed model was compared to seven existing different machine learning models on newly proposed PS-Benchmark_1 dataset in terms of accuracy, sensitivity, specificity and correlation coefficient. Adaptive-LEKM showed better predictive performance with 82.3% accuracy, 80.1% sensitivity, 84.5% specificity and 0.65 correlationcoefficient than contemporary machine learning models.

• Type: Conference
• Year: 2008
• Where: IPPS
• Authors: Paul D. Yoo, Yung Shwen Ho, Bing Bing Zhou, Albert Y. Zomaya
• Keywords: Distributed And Parallel Computing, IPPS 2008, Machine Learning Models, Predictive Performance, Protein Phosphorylation Sites