Email updates

Keep up to date with the latest news and content from BMC Bioinformatics and BioMed Central.

Open Access 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

Author Affiliations

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

2 Care Advantage, NJ 08850, USA

3 Ariadne Genomics Inc, Rockville, MD 20850, USA

4 New Jersey Department of Health, Trenton, NJ USA

5 Center for Translational Medicine, Philadelphia, PA USA

6 Beckman Coulter Inc., Princeton, NJ USA

7 Johnson & Johnson, NJ 08850 USA

8 Vonage Inc., Edison, NJ, 08817 USA

9 BD Preanalytical Systems, Franklin Lakes, NJ USA

10 University of Maryland, Baltimore, MD 21201, USA

For all author emails, please log on.

BMC Bioinformatics 2004, 5:36  doi: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.