Accurate prediction of error in Haplotype Inference methods through neural networks

Haplotype information has a central role in the understanding and diagnosis of certain illnesses, and also for the evolution studies. Since that type of information is hard to obtain directly, computational methods to infer haplotype from genotype data have received great attention from the computational biology community. Unfortunately, this is a very hard computational problem, and the existing methods can only partially identify correct solutions. In this paper we present neural network models that use different properties of the data to predict when a method is more prone to make errors. We construct models for three different Haplotype Inference approaches and we show that our models are accurate and statistically relevant. The results of our experiments offer valuable insights on the performance of those methods, opening opportunity for a combination of strategies or improvement of individual approaches.