摘要：AbstractDue to the significance of accurate genetic determination of sex of birds, the aim of this study was to assess comparatively the performance of the methods of Griffiths et al. (1998) and Fridolfsson and Ellegren (1999), and to clarify the specifications that could improve their reliable application in practice. The reference material consisted of samples (n = 354) of whole blood, oral swabs and feathers, collected from 118 individuals of known sex and 15 avian species, including several that have not been tested before. The investigation was conducted with respect to ISO17025, including assessment of DNA quality and investigation for PCR inhibitors, use of controls for all the stages of the analysis, and the assessment of method accordance.The determination of sex using the PCR assay developed by Griffiths et al. produced the expected results for 100 of the individuals and all the samples (n = 300) that were collected from them. The respective values recorded for the assay developed by Fridolfsson and Ellegren were 98 and 294. Method accordance was 100% for both assays under study. Overall relative specificity of the method of Griffiths et al. was 97.1 ± 3.25%, corresponding to 94.2 ± 6.34% and 100% respectively, for male and female individuals. Relative specificity of the method of Fridolfsson and Ellegren was 83.1 ± 6.78%, corresponding to 100% and 65.5 ± 12.23%, respectively, for male and female individuals. Despite the fact that the birds studied were of known sex, in terms of phenotype and reproductive record, inconsistent results were recorded with both methods in some species examined. The difference between the relative specificities was statistically significance in connection with the biological samples in general (p < 0.01) and with the female individuals (p < 0.01). In conclusion, the method of Griffiths et al. proved in most cases, more reliable for the determination of sex of birds. However when testing for the first time a species of birds, a preliminary study that would include method calibration and application on control samples is highly recommended before selecting the method of choice.
