Fish Classification Using DNA Barcode Sequences through Deep Learning Method

• Published in: Symmetry (Basel) Vol. 13; no. 9; p. 1599
• Main Authors: Jin, Lina, Yu, Jiong, Yuan, Xiaoqian, Du, Xusheng
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2021
• Subjects: Bar codes; Biodiversity; Biology; Classification; COI gene; Datasets; Deep learning; Deoxyribonucleic acid; DNA; DNA barcode; Fish; fish classification; Fisheries; Gene sequencing; Kernel Density Estimation; Machine learning; Morphology; Resource management; Stacked Autoencoder; Taxonomy
• ISSN: 2073-8994; 2073-8994
• DOI: 10.3390/sym13091599

Fish is one of the most extensive distributed organisms in the world. Fish taxonomy is an important component of biodiversity and the basis of fishery resources management. The DNA barcode based on a short sequence fragment is a valuable molecular tool for fish classification. However, the high dimensionality of DNA barcode sequences and the limitation of the number of fish species make it difficult to reasonably analyze the DNA sequences and correctly classify fish from different families. In this paper, we propose a novel deep learning method that fuses Elastic Net-Stacked Autoencoder (EN-SAE) with Kernel Density Estimation (KDE), named ESK model. In stage one, the ESK preprocesses original data from DNA barcode sequences. In stage two, EN-SAE is used to learn the deep features and obtain the outgroup score of each fish. In stage three, KDE is used to select a threshold based on the outgroup scores and classify fish from different families. The effectiveness and superiority of ESK have been validated by experiments on three datasets, with the accuracy, recall, F1-Score reaching 97.57%, 97.43%, and 98.96% on average. Those findings confirm that ESK can accurately classify fish from different families based on DNA barcode sequences.