Machine learning approaches to assess microendemicity and conservation risk in cave-dwelling arachnofauna

The biota of cave habitats faces heightened conservation risks, due to geographic isolation and high levels of endemism. Molecular datasets, in tandem with ecological surveys, have the potential to delimit precisely the nature of cave endemism and identify conservation priorities for microendemic species. Here, we sequenced ultraconserved elements of Tegenaria within, and at the entrances of, 25 cave sites to test phylogenetic relationships, combined with an unsupervised machine learning approach to delimit species. Our data identified clear species limits, as well as the incidence of previously unidentified, potential cryptic species. We employed the R package canaper and Categorical Analysis of Neo- and Paleo-Endemism (CANAPE) to generate conservation metrics that are informative for future policy, in tandem with conservation assessments for the troglobitic Israeli species of this genus.