Quality assessment of Mycobacterium tuberculosis genotyping in a large laboratory network

Abstract

Quality assessment exercises were conducted to evaluate the reproducibility of IS6110 DNA fingerprinting performed by eight laboratories in the National Tuberculosis Genotyping and Surveillance Network. Three panels, each with 8 to 16 isolates, were typed at all laboratories, resulting in 280 images. When the pattern obtained by the majority for each isolate was used as the standard, exact matches were obtained for 73% of patterns; 90% and 97% of patterns matched within one- and two-band differences, respectively. A second approach involved retyping of randomly selected isolates at the Centers for Disease Control and Prevention. Retyping was done for 8-19 isolates per laboratory (76 total). Paired images matched exactly for 54% of isolates and within one and two band differences, 78% and 93%, respectively. We evaluated reasons for mismatching. We also evaluated the reproducibility of spoligotyping using a test panel of 13 isolates; a discrepancy of 1 in 91 results was noted.

Figure 1

Quality assessment panel match results shown by number of bands in patterns.

Figure 2

A) Computer-derived IS6110 restriction fragment length polymorphism patterns from eight laboratories for one isolate. Addition or omission of bands is demonstrated. B) Autoradiogram images demonstrating the addition of IS6110 band in restriction fragment length polymorphism pattern in one subpopulation of Mycobacterium tuberculosis isolates used in the quality assessment exercise.

Figure 3

Computer-derived IS6110 restriction fragment length polymorphism patterns from seven laboratories for one isolate. Misidentified doublet and shifted patterns are demonstrated.

Figure 4

Quality assessment retyping match results by number of bands in the IS6110 restriction fragment length polymorphism patterns.