Hepatitis C virus (HCV) treatment is on the cutting edge of medicine. Due to the high rate of mutations and low fidelity of HCV replication, resistant strains quickly become dominant in a viral population under the selection pressure of a drug. In this paper, we examined the drug resistance mechanism in the NS5A region of genotype 1a HCV virus by comparing the sequence data from interferon-ribavirin treated and untreated patients. To find the drug resistance difference, we used innovative Bayesian probability models to detect mutation combinations and inferred detailed interaction structures of these mutations. We aim to provide reference to drug design and mutation mechanism understanding through our work.