Prediction of the functional class of lipid binding proteins from sequence-derived properties irrespective of sequence similarity

Abstract

Lipid binding proteins play important roles in signaling, regulation, membrane trafficking, immune response, lipid metabolism, and transport. Because of their functional and sequence diversity, it is desirable to explore additional methods for predicting lipid binding proteins irrespective of sequence similarity. This work explores the use of support vector machines (SVMs) as such a method. SVM prediction systems are developed using 14,776 lipid binding and 133,441 nonlipid binding proteins and are evaluated by an independent set of 6,768 lipid binding and 64,761 nonlipid binding proteins. The computed prediction accuracy is 78.9, 79.5, 82.2, 79.5, 84.4, 76.6, 90.6, 79.0, and 89.9% for lipid degradation, lipid metabolism, lipid synthesis, lipid transport, lipid binding, lipopolysaccharide biosynthesis, lipoprotein, lipoyl, and all lipid binding proteins, respectively. The accuracy for the nonmember proteins of each class is 99.9, 99.2, 99.6, 99.8, 99.9, 99.8, 98.5, 99.9, and 97.0%, respectively. Comparable accuracies are obtained when homologous proteins are considered as one, or by using a different SVM kernel function. Our method predicts 86.8% of the 76 lipid binding proteins nonhomologous to any protein in the Swiss-Prot database and 89.0% of the 73 known lipid binding domains as lipid binding. These findings suggest the usefulness of SVMs for facilitating the prediction of lipid binding proteins. Our software can be accessed at the SVMProt server

The interplay of descriptor-based computational analysis with pharmacophore modeling builds the basis for a novel classification scheme for feruloyl esterases

“…patterns of a particular physicochemical property along the protein sequence. T hese descriptors, developed by Dubchak et al (1995), have been successfully used for functional classification of proteins from their primary sequence (Cai et al, 2003b), predicting functional family of enzymes Lin et al, 2006) and for prediction of protein folding class (Dubchak et al, 1999). CT D descriptors comprise attributes of seven structural or physicochemical properties and each attribute is further divided into three groups as shown in T able 3.…”

Predicting Protein-Protein Interactions Based on PPI Networks

“…2. The comparison for ROC curve of the network and other method, the red one is our method and blue one is method [18] VI. CONCLUSION…”

“…Table 1 shows the seven classes clustered by the dipole [11]. We apply three descriptors composition (C), transition (T) and distribution (D) [18]. C represents the frequency over a certain attribution among seven clusters in a protein sequence.…”

Global approaches for the elucidation of phosphoinositide-binding proteins

“…Also reported in 2006, Lin and co-workers developed and applied an SVM prediction system to search a large number of proteins from the Swiss-Prot database for proteins involved in lipid degradation, lipid metabolism, lipid synthesis, lipid transport, lipid binding, lipopolysaccharide biosynthesis, and protein lipidation (Lin et al, 2006). This SVM was developed using 14,776 lipid-binding and 133,441 non-lipid binding proteins and evaluated using an independent set of 6768 binding and 64,761 non-bonding proteins.…”