AI Insight
Researchers developed the first benchmark dataset and classification models for identifying nine native Bangladeshi fish species using protein sequences, comprising 2,845 high-quality sequences. They created a novel hybrid architecture (MotifCNN-Transformer+TA-PE) that achieved 79.80% accuracy, performing statistically similarly to the larger ProtBERT model (83.04% accuracy) while being 42 times smaller, 5 times faster, and capable of running without GPU requirements. The study systematically compared seven different architectural approaches and demonstrated how phylogenetic relationships affect sequence-based species identification.
Why it matters
This work enables practical fish species authentication in resource-constrained settings like rural Bangladesh, supporting food security, preventing fraud in fisheries, and aiding biodiversity conservation. The computationally efficient model can be deployed on standard hardware, making protein-based species identification accessible for fisheries management and food authentication in developing regions with protein-dependent economies.
arXiv:2606.18302v1 Announce Type: new
Abstract: Correct identification of fish species is highly significant for food security, economic development, and climate resilience in Bangladesh. Protein sequences directly reflect functional and evolutionary constraints which are important for species authentication and biodiversity monitoring. Yet there exists no benchmark for native Bangladeshi fish species identification from protein sequence. In this study, we addressed this gap by introducing the first curated dataset for nine native Bangladeshi fish species of 2845 high quality protein sequences. We also established the first protein sequence classification baseline for this domain through a systematic benchmarking of seven architectural paradigms. Moreover, we propose a realistic deployable novel hybrid architecture of MotifCNN and Transformer with Terminal-Aware Positional-Encoding (MotifCNN-Transformer+TA-PE). Our novel architecture achieves 79.80% accuracy with macro-F1 of 0.80. The highest 83.04% accuracy is achieved by finetuned protein language model ProtBERT that has 420M parameters and requires dual 16GB GPUs for inference. According to McNemar’s test, ProtBERT’s 3.24% accuracy gain over our MotifCNN-Transformer+TA-PE is statistically insignificant (p = 0.1120). Our novel architecture beats it among six of the nine classes in per class identification. Also our MotifCNN-Transformer+TA-PE is approximately 5x faster, 42x smaller, and supports 16x larger batch size than ProtBERT and has GPU free inference, making it more practical for deployment in resources constrained areas such as rural Bangladesh. Beyond this, our foundational work shows effects of phylogenetic relationships on sequence similarity and establishes pathways for fisheries management, food authentication and biodiversity conservation in South Asia’s protein dependent economy.