DNASimCLR: a contrastive learning-based deep learning approach for gene sequence data classification

• Published in: BMC bioinformatics 2024-10, Vol.25 (1), p.328-13, Article 328
• Main Authors: Yang, Minghao, Wang, Zehua, Yan, Zizhuo, Wang, Wenxiang, Zhu, Qian, Jin, Changlong
• Format: Article
• Language: English
• Subjects: Accuracy; Adaptability; Artificial neural networks; Bioinformatics; Biological models (mathematics); Biological sequence data; Classification; Computer vision; Contrastive learning; Convolutional neural networks; Data processing; Deep Learning; DNA sequencing; Electronic data processing; Feature extraction; Gene sequencing; Genomics; Infectious diseases; Machine learning; Mathematical functions; Metagenome - genetics; Methods; Microorganisms; Natural language processing; Neural networks; Neural Networks, Computer; Nucleotide sequencing; Pathogens; Representation learning; Robustness (mathematics); Sequence classification; SimCLR; Supervised learning; Task complexity; Taxonomy; Viruses
• ISSN: 1471-2105; 1471-2105
• DOI: 10.1186/s12859-024-05955-8

The rapid advancements in deep neural network models have significantly enhanced the ability to extract features from microbial sequence data, which is critical for addressing biological challenges. However, the scarcity and complexity of labeled microbial data pose substantial difficulties for supervised learning approaches. To address these issues, we propose DNASimCLR, an unsupervised framework designed for efficient gene sequence data feature extraction. DNASimCLR leverages convolutional neural networks and the SimCLR framework, based on contrastive learning, to extract intricate features from diverse microbial gene sequences. Pre-training was conducted on two classic large scale unlabelled datasets encompassing metagenomes and viral gene sequences. Subsequent classification tasks were performed by fine-tuning the pretrained model using the previously acquired model. Our experiments demonstrate that DNASimCLR is at least comparable to state-of-the-art techniques for gene sequence classification. For convolutional neural network-based approaches, DNASimCLR surpasses the latest existing methods, clearly establishing its superiority over the state-of-the-art CNN-based feature extraction techniques. Furthermore, the model exhibits superior performance across diverse tasks in analyzing biological sequence data, showcasing its robust adaptability. DNASimCLR represents a robust and database-agnostic solution for gene sequence classification. Its versatility allows it to perform well in scenarios involving novel or previously unseen gene sequences, making it a valuable tool for diverse applications in genomics.