Weighted averaging clustering algorithm for Haplotype Reconstruction Problem

The high cost and lack of accuracy in haplotypes sampling has caused it's reconstruction problem enters the field of computer science as a laboratory genetic science case. Deducing haplotypes from SNP fragments which may have deficient and incorrect information, decreases laboratory costs. In this regard, various models have been presented as a NPHard problem such as MEC and MEC/GI. The MEC model used in this paper is basically a clustering problem and there are some solutions in this area. Here we have tried to decrease the data complexity, using fuzzy method of weighted averaging then the K-Means clustering method has been applied. As a result, the proficiency of the model has been proven by applying it in two real datasets.