Cephalopod species identification using integrated analysis of machine learning and deep learning approaches

Background Despite the high commercial fisheries value and ecological importance as prey item for higher marine predators, very limited taxonomic work has been done on cephalopods in Malaysia. Due to the soft-bodied nature of cephalopods, the identification of cephalopod species based on the beak hard parts can be more reliable and useful than conventional body morphology. Since the traditional method for species classification was time-consuming, this study aimed to develop an automated identification model that can identify cephalopod species based on beak images. Methods A total of 174 samples of seven cephalopod species were collected from the west coast of Peninsular Malaysia. Both upper and lower beaks were extracted from the samples and the left lateral views of upper and lower beak images were acquired. Three types of traditional morphometric features were extracted namely grey histogram of oriented gradient (HOG), colour HOG, and morphological shape descriptor (MSD). In addition, deep features were extracted by using three pre-trained convolutional neural networks (CNN) models which are VGG19, InceptionV3, and Resnet50. Eight machine learning approaches were used in the classification step and compared for model performance. Results The results showed that the Artificial Neural Network (ANN) model achieved the best testing accuracy of 91.14%, using the deep features extracted from the VGG19 model from lower beak images. The results indicated that the deep features were more accurate than the traditional features in highlighting morphometric differences from the beak images of cephalopod species. In addition, the use of lower beaks of cephalopod species provided better results compared to the upper beaks, suggesting that the lower beaks possess more significant morphological differences between the studied cephalopod species. Future works should include more cephalopod species and sample size to enhance the identification accuracy and comprehensiveness of the developed model.

Cephalopoda (Mollusca) of the Colombian Caribbean Sea

The cephalopod fauna in Colombian Caribbean waters is poorly known. This work gives an overview of the species found in the area. For elaborating this list, the most relevant natural history collections where the material of the area’s is material is deposited were consulted, identifications were verified compared with type material and original descriptions and redescriptions. In the Colombian Caribbean Sea 48 cephalopod species are present in different environments, represented in 17 families and 33 genera. There is one Spirula, seven sepiolids, 21 squids, and 19 octopod species. Most animals are from shallow coastal waters.

Cerebrotypes in Cephalopods: Brain Diversity and Its Correlation With Species Habits, Life History, and Physiological Adaptations

Here we analyze existing quantitative data available for cephalopod brains based on classical contributions by J.Z. Young and colleagues, to cite some. We relate the relative brain size of selected regions (area and/or lobe), with behavior, life history, ecology and distribution of several cephalopod species here considered. After hierarchical clustering we identify and describe ten clusters grouping 52 cephalopod species. This allows us to describe cerebrotypes, i.e., differences of brain composition in different species, as a sign of their adaptation to specific niches and/or clades in cephalopod molluscs for the first time. Similarity reflecting niche type has been found in vertebrates, and it is reasonable to assume that it could also occur in Cephalopoda. We also attempted a phylogenetic PCA using data by Lindgren et al. (2012) as input tree. However, due to the limited overlap in species considered, the final analysis was carried out on <30 species, thus reducing the impact of this approach. Nevertheless, our analysis suggests that the phylogenetic signal alone cannot be a justification for the grouping of species, although biased by the limited set of data available to us. Based on these preliminary findings, we can only hypothesize that brains evolved in cephalopods on the basis of different factors including phylogeny, possible development, and the third factor, i.e., life-style adaptations. Our results support the working hypothesis that the taxon evolved different sensorial and computational strategies to cope with the various environments (niches) occupied in the oceans. This study is novel for invertebrates, to the best of our knowledge.

A novel metabarcoding primer pair for environmental DNA analysis of Cephalopoda (Mollusca) targeting the nuclear 18S rRNA region

Cephalopods are pivotal components of marine food webs, but biodiversity studies are hampered by challenges to sample these agile marine molluscs. Metabarcoding of environmental DNA (eDNA) is a potentially powerful technique to study oceanic cephalopod biodiversity and distribution but has not been applied thus far. We present a novel universal primer pair for metabarcoding cephalopods from eDNA, Ceph18S (Forward: 5′-CGC GGC GCT ACA TAT TAG AC-3′, Reverse: 5′-GCA CTT AAC CGA CCG TCG AC-3′). The primer pair targets the hypervariable region V2 of the nuclear 18S rRNA gene and amplifies a relatively short target sequence of approximately 200 bp in order to allow the amplification of degraded DNA. In silico tests on a reference database and empirical tests on DNA extracts from cephalopod tissue estimate that 44–66% of cephalopod species, corresponding to about 310–460 species, can be amplified and identified with this primer pair. A multi-marker approach with the novel Ceph18S and two previously published cephalopod mitochondrial 16S rRNA primer sets targeting the same region (Jarman et al . 2006 Mol. Ecol. Notes. 6 , 268–271; Peters et al . 2015 Mar. Ecol. 36 , 1428–1439) is estimated to amplify and identify 89% of all cephalopod species, of which an estimated 19% can only be identified by Ceph18S . All sequences obtained with Ceph18S were submitted to GenBank, resulting in new 18S rRNA sequences for 13 cephalopod taxa.

Ege University Faculty of Fisheries Museum (ESFM) cephalopod inventory

In this study, cephalopod individuals exemplified in scientific studies from 1988 to 2015 were registered and listed in the Ege University Faculty of Fisheries Museum (ESFM). Cephalopod species examined in the museum were obtained from the Marmara Sea, the Aegean Sea, the Mediterranean and Northern Cyprus waters. In this study, cephalopod individuals exemplified in scientific studies from 1988 to 2015 were registered and listed in the Ege University Faculty of Fisheries Museum (ESFM). These studies showed that Turkey seas surrounding the 46 species of sepiida orders from 58 pieces, the orders in Sepiolida 230, Teuthida orders of 106 pieces and order Octopoda total 146 storage in a jar. As a result of this study surrounding Turkey seas it has been identified 46 species of cephalopods. The cephalopod types found in the museum were first cleaned and fixed to the jars using the formalin fixation method, which is the most suitable of the 4 known fixation methods, and then the necessary information regarding the sampling was labeled on the jars and the ESFM museum registration was performed.

A Rapid Colorimetric Assay for On-Site Authentication of Cephalopod Species

A colorimetric assay, exploiting the combination of loop-mediated isothermal amplification (LAMP) with DNA barcoding, was developed to address the authentication of some cephalopod species, a relevant group in the context of seafood traceability, due to the intensive processing from the fishing sites to the shelf. The discriminating strategy relies on accurate design of species-specific LAMP primers within the conventional 5’ end of the mitochondrial COI DNA barcode region and allows for the identification of Loligo vulgaris among two closely related and less valuable species. The assay, coupled to rapid genomic DNA extraction, is suitable for large-scale screenings and on-site applications due to its easy procedures, with fast (30 min) and visual readout.

Cuttlefish use stereopsis to strike at prey

The camera-type eyes of vertebrates and cephalopods exhibit remarkable convergence, but it is currently unknown whether the mechanisms for visual information processing in these brains, which exhibit wildly disparate architecture, are also shared. To investigate stereopsis in a cephalopod species, we affixed “anaglyph” glasses to cuttlefish and used a three-dimensional perception paradigm. We show that (i) cuttlefish have also evolved stereopsis (i.e., the ability to extract depth information from the disparity between left and right visual fields); (ii) when stereopsis information is intact, the time and distance covered before striking at a target are shorter; (iii) stereopsis in cuttlefish works differently to vertebrates, as cuttlefish can extract stereopsis cues from anticorrelated stimuli. These findings demonstrate that although there is convergent evolution in depth computation, cuttlefish stereopsis is likely afforded by a different algorithm than in humans, and not just a different implementation.