Hybrid Classification of Gene Sequences Using Graph Convolution Networks

• Published in: Moratuwa Engineering Research Conference pp. 175 - 180
• Main Authors: Jayaweera, Hasitha, Nanayakkara, Pahan, Wijekoon, Pamudu, Perera, Indika
• Format: Conference Proceeding
• Language: English
• Published: IEEE 08.08.2024
• Subjects: Bioinformatics; Codes; Convolution; Digestive system; Distance measurement; Graph Convolution Networks; Long reads; Machine learning; Marine ecosystems; Metagenomic hybrid classification; Metagenomics; Organisms; Read overlap graph; Taxonomic Levels
• ISSN: 2691-364X
• DOI: 10.1109/MERCon63886.2024.10688642

Diverse communities of organisms inhabit environments ranging from the human digestive system to marine ecosystems, significantly impacting both human health and the environment. Metagenomic classification, a crucial concept in bioinformatics, can be performed at various taxonomic levels. In this research, we introduce a hybrid classification approach. By leveraging results obtained from reference database approaches, where classification is available up to the species level, we identify patterns to enhance the taxonomic depth of partially classified sequences. Our proposed solution integrates the composition and coverage information of gene sequences. Graph-based machine learning techniques show superior performance over traditional methods in hybrid sequence classification, as demonstrated by our experimental results.