Imagem da capa

PCVR: a pre-trained contextualized visual representation for DNA sequence classification

Na minha lista:
Publicado no:BMC Bioinformatics vol. 26 (2025), p. 1
Autor principal: Zhou, Jiarui
Outros Autores: Wu, Hui, Du, Kang, Zhou, Wengang, Cong-Zhao, Zhou, Li, Houqiang
Publicado em:
Springer Nature B.V.
Assuntos:
Language
New species
Genetic analysis
Datasets
Deep learning
Classification
Bioinformatics
Unsupervised learning
Ablation
Image processing
Nucleotide sequence
Machine learning
Coders
Representations
Efficiency
Data analysis
Vision
Gene sequencing
Neural networks
Deoxyribonucleic acid > DNA
Databases
Natural language processing
Fc receptors
Environmental
Acesso em linha:Citation/Abstract
Full Text
Full Text - PDF
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
Resumo:BackgroundThe classification of DNA sequences is pivotal in bioinformatics, essentially for genetic information analysis. Traditional alignment-based tools tend to have slow speed and low recall. Machine learning methods learn implicit patterns from data with encoding techniques such as k-mer counting and ordinal encoding, which fail to handle long sequences or sacrifice structural and sequential information. Frequency chaos game representation (FCGR) converts DNA sequences of arbitrary lengths into fixed-size images, breaking free from the constraints of sequence length while preserving more sequential information than other representations. However, existing works merely consider local information, ignoring long-range dependencies and global contextual information within FCGR image.ResultsWe propose PCVR, a Pre-trained Contextualized Visual Representation for DNA sequence classification. PCVR encodes FCGR with a vision transformer into contextualized features containing more global information. To meet the substantial data requirements of the training of vision transformer and learn more robust features, we pre-train the encoder with a masked autoencoder. Pre-trained PCVR exhibits impressive performance on three datasets even with only unsupervised learning. After fine-tuning, PCVR outperforms existing methods on superkingdom and phylum levels. Additionally, our ablation studies confirm the contribution of the vision transformer encoder and masked autoencoder pre-training to performance improvement.ConclusionsPCVR significantly improves DNA sequence classification accuracy and shows strong potential for new species discovery due to its effective capture of global information and robustness. Codes for PCVR are available at https://github.com/jiaruizhou/PCVR.
ISSN:1471-2105
DOI:10.1186/s12859-025-06136-x
Fonte:Health & Medical Collection