Methodology article

Auto-validation of fluorescent primer extension genotyping assay using signal clustering and neural networks

Ching Yu Austin Huang¹ , Joel Studebaker² , Anton Yuryev³ , Jianping Huang⁴ , Kathryn E Scott⁵ , Jennifer Kuebler⁶ , Shobha Varde⁷ , Steven Alfisi⁸ , Craig A Gelfand⁹ , Mark Pohl¹⁰ and Michael T Boyce-Jacino⁶

¹Center for Pharmacogenomics and Complex Disease Research, Newark, NJ 07101, USA

²Care Advantage, NJ 08850, USA

³Ariadne Genomics Inc, Rockville, MD 20850, USA

⁴New Jersey Department of Health, Trenton, NJ USA

⁵Center for Translational Medicine, Philadelphia, PA USA

⁶Beckman Coulter Inc., Princeton, NJ USA

⁷Johnson & Johnson, NJ 08850 USA

⁸Vonage Inc., Edison, NJ, 08817 USA

⁹BD Preanalytical Systems, Franklin Lakes, NJ USA

¹⁰University of Maryland, Baltimore, MD 21201, USA

author email corresponding author email

BMC Bioinformatics 2004, 5:36doi:10.1186/1471-2105-5-36

Published:	2 April 2004

Abstract

Background

SNP genotyping typically incorporates a review step to ensure that the genotype calls for a particular SNP are correct. For high-throughput genotyping, such as that provided by the GenomeLab SNPstream^® instrument from Beckman Coulter, Inc., the manual review used for low-volume genotyping becomes a major bottleneck. The work reported here describes the application of a neural network to automate the review of results.

Results

We describe an approach to reviewing the quality of primer extension 2-color fluorescent reactions by clustering optical signals obtained from multiple samples and a single reaction set-up. The method evaluates the quality of the signal clusters from the genotyping results. We developed 64 scores to measure the geometry and position of the signal clusters. The expected signal distribution was represented by a distribution of a 64-component parametric vector obtained by training the two-layer neural network onto a set of 10,968 manually reviewed 2D plots containing the signal clusters.

Conclusion

The neural network approach described in this paper may be used with results from the GenomeLab SNPstream instrument for high-throughput SNP genotyping. The overall correlation with manual revision was 0.844. The approach can be applied to a quality review of results from other high-throughput fluorescent-based biochemical assays in a high-throughput mode.