Privacy Preserving Calculation of Fisher Criterion Score for Informative Gene Selection

Informative gene selection is an important topic in the field of bioinformatics which has attracted intensive interest in recent years. It aims to identify the genes which are differentially expressed in different groups, and thus are informative for the classification between the groups. For this purpose, many micro array experiments have been conducted by various medical institutes on their own sets of patients and test subjects. For those institutes who have conducted experiments regarding the same type of disease, it would be beneficial to all of them if they learn on the union of their data to find the informative genes instead of learn just on their own datasets, since the amount of data each institute holds is very limited. However, in many cases, the institutes are not allowed to share their data with others because micro array datasets contain private information about the patients and test subjects. In this paper, we focus on this problem and propose a privacy preserving algorithm that allows multiple parties to perform the widely used informative gene selection method, the Fisher criterion, on the union of their data, without revealing each party's data to others. Basically, we utilize the homomorphic cryptographic system to protect the data during the calculations. Experimental results on real world datasets show the effectiveness of the proposed method.