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.

Integrative descriptions of two new Macrobiotus species (Tardigrada, Eutardigrada, Macrobiotidae) from Mississippi (USA) and Crete (Greece)

In this paper, we describe two new Macrobiotus species from Mississippi (USA) and Crete (Greece) by means of integrative taxonomy. Detailed morphological data from light and scanning electron microscopy, as well as molecular data (sequences of four genetic markers: 18S rRNA, 28S rRNA, ITS-2 and COI), are provided in support of the descriptions of the new species. Macrobiotus annewintersaesp. nov. from Mississippi belongs to the Macrobiotus persimilis complex (Macrobiotus clade B) and exhibits a unique egg processes morphology, similar only to Macrobiotus anemone Meyer, Domingue & Hinton, 2014, but mainly differs from that species by the presence of eyes, granulation on all legs, dentate lunulae on legs IV, and of bubble-like structures within the tentacular arms that are present on the distal portion of the egg processes. Macrobiotus rybakisp. nov. from Crete belongs to the Macrobiotus clade A and is most similar to Macrobiotus dariae Pilato & Bertolani, 2004, Macrobiotus noemiae Roszkowska & Kaczmarek, 2019, Macrobiotus santoroi Pilato & D’Urso, 1976, and Macrobiotus serratus Bertolani, Guidi & Rebecchi, 1996, but differs from them mainly in the morphological details of its egg processes and chorion reticulation, but also by a number of morphometric characters. In light of the specific morphology of the egg processes of Macrobiotus annewintersaesp. nov. and Macrobiotus anemone, that are equipped with tentacular arms instead of proper terminal disc, we also provide an updated definition of the Macrobiotus persimilis complex.

Milnesium (Tardigrada: Apochela) in Japan: The First Confirmed Record of Milnesium tardigradum s.s. and Description of Milnesium pacificum sp. nov

Presently, more than 40 species of the genus Milnesium Doyère, 1840 (Tardigrada: Eutardigrada: Apochela: Milnesiidae) have been described. In Japan, however, almost all records of milnesiid tardigrades should be re-examined with the current criteria on the taxonomy of this genus, except for one species, the recently described Milnesium inceptum Morek, Suzuki, Schill, Georgiev, Yankova, Marley, and Michalczyk, 2019. In this study, we found two species, Milnesium pacificum sp. nov. and Milnesium tardigradum Doyère, 1840, from three southern islands and two cold regions in Japan, respectively. Milnesium pacificum sp. nov., having dorsal sculpturing, exhibits an early positive change in claw configuration. On the other hand, M. tardigradum s.s. from Japan has an early negative claw configuration change, as has been reported in a recent study on the neotype population of this species. We performed DNA barcoding for both species, which indicated that M. pacificum sp. nov. has a close affinity with an undescribed Milnesium species collected from Brazil, and that M. tardigradum from Japan represents the recently described subclade that contains specimens from Poland, Hungary, and Russia. The chromosome numbers were 2n = 14 in M. pacificum sp. nov. and 2n = 10 in M. tardigradum. We detected at least three species of the genus Milnesium present in Japan. Our results advance the investigation of the relationship between phylogenetic position and characteristic morphology as well as expand the known geographic range of M. tardigradum.

Novel integrative data for two Milnesium Doyère, 1840 (Tardigrada: Apochela) species from Central Asia

Tardigrada are a phylum of microscopic animals inhabiting a variety of ecosystems, both aquatic and terrestrial, being recognised for their remarkable abilities to withstand tough environmental conditions. The order Apochela groups exclusively carnivorous species, with the vast majority representing the genus Milnesium Doyère, 1840. Representatives of this genus are characterised by simplified morphology, therefore possessing an extremely limited set of taxonomically meaningful morphological traits. Nevertheless, the taxonomy of Milnesium is mostly based on classical data: observations and measurements in light microscopy with the majority of descriptions lacking integrative data, most importantly DNA barcodes, but also scanning electron microscopy photographs and developmental variability analysis. Hence, re-descriptions that include novel integrative data are urgently needed. In this contribution, we provide new taxonomic data for two species described from Central Asia, Milnesium almatyense (a single population) and Milnesium reductum Tumanov, 2006 (five populations): morphometrics, DNA barcodes, SEM observations and description of developmental variability. As a result, we amend the description of both species and reveal phylogenetic relationships of those species and other sequenced congeners. The integrative data confirm the validity of the two species and include them in the growing set of Milnesium species associated with DNA sequences.