Abstract
Background: Interpreting short tandem repeat (STR) profiles from low-template DNA (LT-DNA) requires consideration of the stochastic phenomena that can affect the reliability of genotypes. Although several probabilistic genotyping tools have been developed to model such uncertainties, most have only been used for direct comparisons between persons of interest and crime scene samples. Their application to kinship testing involving LT-DNA has received comparatively little attention. Methods: We evaluated the performance of two PGS, EuroForMix (EFM) and EFMrep, which support alternative hypotheses with relatedness, by comparing them with a standard paternity testing software (Familias) in 33 paternity cases involving LT-DNA samples categorised as 'mildly' (MD) or 'highly' (HD) degraded based on the quality of the STR profiles. The samples included formalin-fixed paraffin-embedded tissues, bone specimens, and stains collected from personal items. Pedigrees with ('trio') and without ('duo') maternal information were considered. Results: In MD and HD duos, the likelihood ratios (LRs) obtained with EFMrep were significantly higher compared to other software. In trios, Familias produced significantly higher LRs than PGS for MD samples, whereas the three software performed comparably for HD samples. Notably, in HD trios, EFMrep was the software most likely to maximise LR values, which were above 10,000 in 60% of the cases, compared to 50% of EFM and 40% of Familias. Conclusions: These findings provide preliminary evidence of the potential and limitations of using PGS for kinship assessments involving LT-DNA specimens.