Matrix Completion with Weighted Constraint for Haplotype Estimation

TL;DR

This paper introduces HapWeC, a novel matrix completion method with weighted constraints for haplotype estimation, demonstrating improved accuracy over recent algorithms through simulations.

Contribution

It proposes a new optimization approach for matrix completion with weighted measurements specifically for haplotype reconstruction.

Findings

HapWeC outperforms recent algorithms in normalized reconstruction error

HapWeC achieves higher reconstruction rates in simulations

The method provides a new error bound for weighted matrix completion

Abstract

A new optimization design is proposed for matrix completion by weighting the measurements and deriving the corresponding error bound. Accordingly, the Haplotype reconstruction using nuclear norm minimization with Weighted Constraint (HapWeC) is devised for haplotype estimation. Computer simulations show the outperformance of the HapWeC compared to some recent algorithms in terms of the normalized reconstruction error and reconstruction rate.