HA Nagarajaram
Laboratory of Computational Biology, Centre for DNA Fingerprinting & Diagnostics (CDFD), Gruhakalpa, Nampally, Hyderabad 500 00, Andhra Pradesh, India.

ABSTRACT

Phenotypic effects (“disease” and “neutral”) of a large number of missence mutations caused by nsSNPs as well as rare mutations have not been characterized. It is therefore perceived as highly important to develop methods for accurate prediction of the phenotypic effects of missense mutations. We recently developed a SVM-based method named as Hansa which uses a novel set of discriminatory features to classify missense mutations into disease and neutral types. Hansa was evaluated by performing a five-fold cross validation on a benchmark dataset comprising of well characterized known disease and neutral mutations. Further validation studies were also conducted using an independent dataset of known cancer missense mutations. These studies unequivocally showed that Hansa achieves better prediction accuracies as compared to the other known methods. Read More …