A Hopfield neural network based algorithm for haplotype assembly from low-quality data

Abstract

The objective of the haplotype assembly problem is to conclude a pair of haplotypes from a set of aligned single nucleotide polymorphism (SNP) fragments from a single individual. Errors in the SNP fragments, which are inevitable in the real-world application, severely increase the difficulty of the problem. As a result, most methods could not get accurate haplotypes on the data with high error rate. In this paper, we introduce a Hopfield neural network based method, named HNHap, to solve the haplotype assembly problem. Hopfield neural network is a very promising and effective approach to solve the combinatorial optimization problem. The stochastic optimal competitive Hopfield network model that has the mechanism to escape from the local optimum is a great improvement for the original model. Thus we map the haplotype assembly problem onto the stochastic optimal competitive Hopfield network model, in which a group of neurons correspond to an SNP fragment and the states of neurons denote the classification of the fragment. We also design a proper energy function based on the minimum error correction model for the haplotype assembly problem. We compare HNHap with other algorithms and the experiment results show that HNHap is an effective method to solve the haplotype assembly problem, especially on data with high error rate.