Geometric morphometrics and machine learning as tools for the identification of sibling mosquito species of the Maculipennis complex (Anopheles)

Bellin, Nicolò; Calzolari, Mattia; Callegari, Emanuele; Bonilauri, Paolo; Grisendi, Annalisa; Dottori, M.; Rossi, Valeria

doi:10.1016/j.meegid.2021.105034

Cited by 12 publications

(8 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A species-specific machine learning approach to setting homologous landmarks automatically along the outline of a specific plant organ would be desirable. Attempts to combine GM and ML have been recently made in anthropology [ 193 ] and zoology [ 194 , 195 , 196 ]. However, similar to automatic plant identification, features extracted from ANNs [ 197 ] can be used for morphometric analysis of plant organs.…”

Section: Discussionmentioning

confidence: 99%

Geometric Morphometric Versus Genomic Patterns in a Large Polyploid Plant Species Complex

Hodač

Karbstein

Tomasello

et al. 2023

Biology

View full text Add to dashboard Cite

Plant species complexes represent a particularly interesting example of taxonomically complex groups (TCGs), linking hybridization, apomixis, and polyploidy with complex morphological patterns. In such TCGs, mosaic-like character combinations and conflicts of morphological data with molecular phylogenies present a major problem for species classification. Here, we used the large polyploid apomictic European Ranunculus auricomus complex to study relationships among five diploid sexual progenitor species and 75 polyploid apomictic derivate taxa, based on geometric morphometrics using 11,690 landmarked objects (basal and stem leaves, receptacles), genomic data (97,312 RAD-Seq loci, 48 phased target enrichment genes, 71 plastid regions) from 220 populations. We showed that (1) observed genomic clusters correspond to morphological groupings based on basal leaves and concatenated traits, and morphological groups were best resolved with RAD-Seq data; (2) described apomictic taxa usually overlap within trait morphospace except for those taxa at the space edges; (3) apomictic phenotypes are highly influenced by parental subgenome composition and to a lesser extent by climatic factors; and (4) allopolyploid apomictic taxa, compared to their sexual progenitor, resemble a mosaic of ecological and morphological intermediate to transgressive biotypes. The joint evaluation of phylogenomic, phenotypic, reproductive, and ecological data supports a revision of purely descriptive, subjective traditional morphological classifications.

show abstract

Section: Discussionmentioning

confidence: 99%

Geometric Morphometric Versus Genomic Patterns in a Large Polyploid Plant Species Complex

Hodač

Karbstein

Tomasello

et al. 2023

Biology

View full text Add to dashboard Cite

show abstract

“…However, image‐based morphological methods have become increasingly popular (Hoenle et al, 2020 ). Furthermore, unprecedented technological advances in digitization and steadily expanding open‐access databases with mass sources of phenotypic information [e.g., AntWeb ( www.antweb.org ); FaceBase ( https://www.facebase.org/ ); MosquitoLab ‐ Wingbank ( www.wingbank.butantan.gov.br )] yield new opportunities in science (Bellin et al, 2021 ; Hoenle et al, 2020 ; McQuin et al, 2018 ; Psenner, 2018 ; Samuels et al, 2020 ; Virginio et al, 2021 ; Wang et al, 2020 ). These methods have opened new ways for scientists to study virtual specimens (Hsiang et al, 2018 ), but their use usually requires high‐quality digital data sources (Davies et al, 2017 ; Lürig et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

Comparing ant morphology measurements from microscope and online AntWeb.org 2D z‐stacked images

Csősz

Báthori

Rádai

et al. 2023

Ecology and Evolution

View full text Add to dashboard Cite

show abstract

“…There are several methods which are used to make classifications in morphology studies 34 . Thus, we fitted four different classification models with scores of all PC1-11, and chose the best one based on a classification performance 35 . The four models are: (1) linear discriminant analysis (LDA, or discriminant function analysis), (2) linear support vector machine (SVM) without hyperparameter tuning, (3) linear SVM with hyperparameter tuning, and (4) non-linear SVM (with Radial Basis Function kernel) with hyperparameter tuning.…”

Section: Methodsmentioning

confidence: 99%

Revisiting the baby schema by a geometric morphometric analysis of infant facial characteristics across great apes

Kawaguchi

Nakamura²,

Tajima³

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Infants across species are thought to exhibit specific facial features (termed the “baby schema”, such as a relatively bigger forehead and eyes, and protruding cheeks), with an adaptive function to induce caretaking behaviour from adults. There is abundant empirical evidence for this in humans, but, surprisingly, the existence of a baby schema in non-human animals has not been scientifically demonstrated. We investigated which facial characteristics are shared across infants in five species of great apes: humans, chimpanzees, bonobos, mountain gorillas, and Bornean orangutans. We analysed eight adult and infant faces for each species (80 images in total) using geometric morphometric analysis and machine learning. We found two principal components characterizing infant faces consistently observed across species. These included (1) relatively bigger eyes located lower in the face, (2) a rounder and vertically shorter face shape, and (3) an inverted triangular face shape. While these features are shared, human infant faces are unique in that the second characteristic (round face shape) is more pronounced, whereas the third (inverted triangular face shape) is less pronounced than other species. We also found some infantile features only found in some species. We discuss future directions to investigate the baby schema using an evolutionary approach.

show abstract

Geometric morphometrics and machine learning as tools for the identification of sibling mosquito species of the Maculipennis complex (Anopheles)

Cited by 12 publications

References 53 publications

Geometric Morphometric Versus Genomic Patterns in a Large Polyploid Plant Species Complex

Geometric Morphometric Versus Genomic Patterns in a Large Polyploid Plant Species Complex

Comparing ant morphology measurements from microscope and online AntWeb.org 2D z‐stacked images

Revisiting the baby schema by a geometric morphometric analysis of infant facial characteristics across great apes

Contact Info

Product

Resources

About