A prediction model for the drug efficacy of interferon in CHC patients based on SNPs

In the studies of pharmacogenomics, genetic predisposition information, such as single nucleotide polymorphisms (SNPs), can be used to understand the relationship between genetic variations (or population variations) and drug efficacy. In this paper, a prediction model is resulted from analyzing chronic hepatitis C (CHC) patient's SNPs, comparing to control groups, to predict the responsiveness of interferon (IFN) combination treatment. We have developed an advanced methodology with the combination of artificial neural network (ANN) and other algorithms to achieve a prediction with high accuracy among the patients. Filtering through thousands of SNPs of 150 genes, we found nearly 30 SNPs relevant to the responsiveness of IFN. With a statistical analysis of sensitivity (SEN), specificity (SPE), positive prediction value (PPV), and negative prediction value (NPV), our model achieves a higher successful rate of prediction, i.e., > 90% accuracy. This model allows patients and doctors to make more informed decisions based on SNP genotyping data. The data was generated in the high-throughput genomics lab of Vita Genomics, Inc.