The relationship between single nucleotide polymorphisms (SNPs) and phenotypes is noisy and cryptic due to the abundance of genetic factors and the influence of environmental factors on complex traits, which makes the idea of applying artificial neural networks (ANNs) as universal approximates of complex functions promising. In this study, we compared different ANN architectures and input parameters to predict the adult length of Pacific lampreys, which is the primary indicator of their total migratory distance. Feedforward and simple recurrent network architectures with a different range of input parameters and different sizes of hidden layers were compared. Results indicate that the highest performing ANN had an accuracy of 67.5% in discriminating between long and short specimens. Sensitivity and specificity were 62.16% and 70.73%, respectively. Our results imply that feedforward ANN architecture with a single hidden neuron is enough to solve the problem of specimen classification. Nonetheless, while ANNs are useful at approximating functions with unknown relationships in the case of SNP data, additional work needs to be performed to ensure that the chosen SNP markers are related to functional regions related to the examined trait, as the use of non-specific markers will result in the introduction of noise into the dataset.

abstract In a study of the Bosnian-Herzegovinian (B&H) population, Y-chromosome marker frequencies for 100 individuals, generated using the PowerPlex Y23 kit, were used to perform Y-chromosome haplogroup assignment via Whit Athey's Haplogroup Predictor. This algorithm determines Y-chromosome haplogroups from Y-chromosome short tandem repeat (Y-STR) data using a Bayesian probability-based approach. The most frequent haplogroup appeared to be I2a, with a prevalence of 49%, followed by R1a and E1b1b, each accounting for 17% of all haplogroups within the population. Remaining haplogroups were J2a (5%), I1 (4%), R1b (4%), J2b (2%), G2a (1%), and N (1%). These results confirm previously published preliminary B&H population data published over 10 years ago, especially the prediction about the B&H population being a part of the Western Balkan area, which served as the Last Glacial Maximum refuge for the Paleolithic human European population. Furthermore, the results corroborate the hypothesis that this area was a significant stopping point on the “Middle East—Europe highway” during the Neolithic farmer migrations. Finally, since these results are almost completely in accordance with previously published data on B&H and neighboring populations generated by Y-chromosome single nucleotide polymorphism analysis, it can be concluded that in silico analysis of Y-STRs is a reliable method for approximation of the Y-chromosome haplogroup diversity of an examined population.

Analysis of Y-chromosome haplogroup distribution is widely used when investigating geographical clustering of different populations, which is why it plays an important role in population genetics, human migration patterns and even in forensic investigations. Individual determination of these haplogroups is mostly based on the analysis of single nucleotide polymorphism (SNP) markers located in the non-recombining part of Y-chromosome (NRY). On the other hand, the number of forensic and anthropology studies investigating short tandem repeats on the Y-chromosome (Y-STRs) increases rapidly every year. During the last few years, these markers have been successfully used as haplogroup prediction methods, which is why they have been used in this study. Previously obtained Y-STR haplotypes (23 loci) from 100 unrelated Turkish males recently settled in Sarajevo were used for the determination of haplogroups via 'Whit Athey's Haplogroup Predictor' software. The Bayesian probability of 90 of the studied haplotypes is greater than 92.2% and ranges from 51.4% to 84.3% for the remaining 10 haplotypes. A distribution of 17 different haplogroups was found, with the Y- haplogroup J2a being most prevalent, having been found in 26% of all the samples, whereas R1b, G2a and R1a were less prevalent, covering a range of 10% to 15% of all the samples. Together, these four haplogroups account for 63% of all Y-chromosomes. Eleven haplogroups (E1b1b, G1, I1, I2a, I2b, J1, J2b, L, Q, R2, and T) range from 2% to 5%, while E1b1a and N are found in 1% of all samples. Obtained results indicate that a large majority of the Turkish paternal line belongs to West Asia, Europe Caucasus, Western Europe, Northeast Europe, Middle East, Russia, Anatolia, and Black Sea Y-chromosome lineages. As the distribution of Y-chromosome haplogroups is consistent with the previously published data for the Turkish population residing in Turkey, it was concluded that the analyzed population could also be recognized as a representative sample of the Turkish population residing in Turkey.