Improved feature-based prediction of SNPs in human cytochrome P450 enzymes

Single nucleotide polymorphisms (SNPs) make up the most common form of mutations in human cytochrome P450 enzymes family, and have the potential to bring with different drug responses or specific diseases in individual patients. Here, based on machine learning technology, we aim to explore an effective set of sequence-based features for improving prediction of SNPs by using support vector machine algorithms. The features are derived from the target residues and flanking protein sequences, such as amino acid types, sequences composition, physicochemical properties, position-specific scoring matrix, phylogenetic entropy and the number of possible codons of target residues. In order to deal with the imbalance data with a majority of non-SNPs and a minority of SNPs, a preprocessing strategy based on fuzzy set theory was applied to the datasets. Our final model achieves the performance of 93.8% in sensitivity, 88.8% in specificity, 91.3% in accuracy and 0.971 of AUC value, which is significantly higher than the previous DNA sequence-based or protein sequence-based methods. Furthermore, our study also suggested the roles of individual features for prediction of SNPs. The most important features consist of the amino acid type, the number of available codons, position-specific scoring matrix and phylogenetic entropy. The improved model will be a promising tool for SNP predictions, and assist in the research of genome mutation and personalized prescriptions.