Prediction of lipid-interacting amino acid residues from sequence features.

Proteins and lipids are integral components of cell membranes, and play important roles in cell signalling. Alterations of normal protein-lipid recognition may cause various diseases. However, molecular mechanisms underlying protein-lipid recognition are still poorly understood. In this study, we have developed a support vector machine-based approach for predicting lipid-interacting residues from amino acid sequence features. To the best of our knowledge, this is the first study that applies machine learning to sequence-based prediction of lipid-interacting residues in proteins. Our study provides useful information for understanding protein-lipid interactions, and may lead to advances in drug discovery.