Machine learning algorithms accurately identify free-living marine nematode species

Background

Identifying species, particularly small metazoans, remains a daunting challenge and the phylum Nematoda is no exception. Typically, nematode species are differentiated based on morphometry and the presence or absence of certain characters. However, recent advances in artificial intelligence, particularly machine learning (ML) algorithms, offer promising solutions for automating species identification, mostly in taxonomically complex groups. By training ML models with extensive datasets of accurately identified specimens, the models can learn to recognize patterns in nematodes' morphological and morphometric features. This enables them to make precise identifications of newly encountered individuals. Implementing ML algorithms can improve the speed and accuracy of species identification and allow researchers to efficiently process vast amounts of data. Furthermore, it empowers non-taxonomists to make reliable identifications. The objective of this study is to evaluate the performance of ML algorithms in identifying species of free-living marine nematodes, focusing on two well-known genera: Acantholaimus Allgén, 1933 and Sabatieria Rouville, 1903.

Methods

A total of 40 species of Acantholaimus and 60 species of Sabatieria were considered. The measurements and identifications were obtained from the original publications of species for both genera, this compilation included information regarding the presence or absence of specific characters, as well as morphometric data. To assess the performance of the species identification four ML algorithms were employed: Random Forest (RF), Stochastic Gradient Boosting (SGBoost), Support Vector Machine (SVM) with both linear and radial kernels, and K-nearest neighbor (KNN) algorithms.

Results

For both genera, the random forest (RF) algorithm demonstrated the highest accuracy in correctly classifying specimens into their respective species, achieving an accuracy rate of 93% for Acantholaimus and 100% for Sabatieria, only a single individual from Acantholaimus of the test data was misclassified.

Conclusion

These results highlight the overall effectiveness of ML algorithms in species identification. Moreover, it demonstrates that the identification of marine nematodes can be automated, optimizing biodiversity and ecological studies, as well as turning species identification more accessible, efficient, and scalable. Ultimately it will contribute to our understanding and conservation of biodiversity.

Echiniscidae in the Mascarenes: the wonders of Mauritius

Many regions of the world remain unexplored in terms of the tardigrade diversity, and the islands of the Indian Ocean are no exception. In this work, we report four species of the family Echiniscidae representing three genera from Mauritius, the second largest island in the Mascarene Archipelago. Two species belong in the genus Echiniscus: Echiniscus perarmatus Murray, 1907, a pantropical species, and one new species: Echiniscus insularissp. nov., one of the smallest members of the spinulosus group and the entire genus, being particularly interesting due to the presence of males and supernumerary teeth-like spicules along the margins of the dorsal plates. The new species most closely resembles Echiniscus tropicalis Binda & Pilato, 1995, for which we present extensive multipopulation data and greatly extend its distribution eastwards towards islands of Southeast Asia. Pseudechiniscus (Meridioniscus) mascarenensissp. nov. is a typical member of the subgenus with elongated (dactyloid) cephalic papillae and the pseudosegmental plate IV’ with reduced posterior projections in males. Finally, a Bryodelphax specimen is also recorded. The assemblage of both presumably endemic and widely distributed tardigrade species in Mauritius fits the recent emerging biogeographic patterns for this group of micrometazoans.

Pseudechiniscus in Japan: re-description of Pseudechiniscus asper Abe et al., 1998 and description of Pseudechiniscus shintai sp. nov

The classification and identification of species within the genus Pseudechiniscus Thulin, 1911 has been considered almost a Sisyphean work due to an extremely high homogeneity of its members. Only recently have several contributions made progress in the taxonomy feasible through their detailed analyses of morphology and, crucially, by the re-description of the ancient, nominal species P. suillus (Ehrenberg, 1853). Herein, we focus on the Japanese representatives of this genus: P. asper, a rare species originally described from Hokkaido, and a new species P. shintai. Both taxa belong to the widespread suillus-facettalis complex. Detailed descriptions entailing DNA barcoding of four markers and illustrations of the ventral pillar patterns are indispensable for an accurate delineation of species within this genus.

Revised Cornechiniscus (Heterotardigrada) and new phylogenetic analyses negate echiniscid subfamilies and tribes

Echiniscidae are undoubtedly the most thoroughly studied lineage of the class Heterotardigrada. Recently, new subfamilies and tribes grouping echiniscid genera based on traditionally recognized morphological clues have been proposed. Here, by integrative analyses of morphology and DNA sequences of numerous populations of a rare genus Cornechiniscus, we show that this hypothesized classification is artificial. Specifically, we demonstrate that Echiniscinae are diphyletic, as Bryodelphax forms a distinct phyletic lineage within Echiniscidae, and Pseudechiniscinae are polyphyletic, with Mopsechiniscus being indirectly related to Pseudechiniscus, which is closer to the Echiniscus-like genera than to other genera with pseudosegmental plates. Consequently, the subfamilies and tribes are considered as unsupported from the phylogenetic and morphological point of view. The genus Cornechiniscus is revised, and the phenotypic diagnoses of several species are updated thanks to new rich material from Africa, Asia and Europe. Cornechiniscus imperfectus sp. nov. is described from mountains of Kyrgyzstan, being the second appendaged species within the genus and the third known to exhibit dioecy. A taxonomic key to the genus is provided. Systematic positions of Acanthechiniscus and Multipseudechiniscus are also discussed. Acanthechiniscus goedeni is confirmed to be a member of the genus Acanthechiniscus.