Inferring Protein Interactions from Sequence using Support Vector Machine

Data of protein-protein interactions derived from High-throughput technologies are often incomplete and fairly noisy. Therefore, it is very important to develop computational methods for predicting protein-protein interactions. A sequence-based method is proposed by combining support vector machine and a new feature representation using Geary autocorrelation. SVM model trained with Geary autocorrelation of amino acid sequence yielded the best performance with a high accuracy of 82.9% using gold standard positives (GSPs) PRS and gold standard negatives (GSNs) RRS datasets. Meanwhile, the SVM model has been successfully employed to predict the single core PPI network.