Along with the completion of human genome project, major interest in human genetics is to distinguish mutations that are functionally neutral from those that contribute to disease. The central focus of cancer genetics is the study of mutations that are causally implicated in tumorigenesis. The identification of such causal mutations not only provides insight into cancer biology but also presents anticancer therapeutic targets and diagnostic markers. Understanding the human genetic variation through Single Nucleotide Polymorphisms (SNPs) is currently believed to reveal the cause of individual susceptibility to disease and the large variation observed in response to treatment. The aim of our study reported here is to determine the deleterious SNPs that can alter the expression and function of the ARNT gene in causing acute myeloblastic leukemia through computational methods. Our approach will present the application of computational tools in understanding functional variation from the perspective of structure, expression, evolution and phenotype. Based on the SIFT (evolutionary basedapproach) and PolyPhen (structure based-approach) scores, structure analysis was carried out with the major mutation that occurred in the native protein (1X0O) coded by ARNT gene, which are at the amino acid position F363L and R430Q. The amino acid residues in the native and mutant modeled protein were further analyzed for solvent accessibility, and secondary structure to check the stability of the proteins. The models built in this work would be applicable for predicting the deleterious nsSNPs which would be helpful for further genotype-phenotype research as well as pharmacogenetics studies.