To address the critical global challenge of microplastic pollution and the limitations of alignment-dependent genomic tools in analyzing fragmented environmental data, this study introduces an alignment-free computational framework for identifying microbial bioremediation potential. We established a standardized, multi-domain dataset encompassing Bacteria, Protists, Archaea, and Fungi, integrating metadata on polymer interactions to fill existing data gaps. Utilizing tetranucleotide frequency patterns (k=4), we developed a novel analysis method to isolate predictive genomic signatures, identifying C-rich motifs such as ‘CCCC’ as primary indicators of degradation capability.A statistical scoring model was subsequently implemented to rank candidate taxa, effectively prioritizing high-value organisms from complex metagenomes derived from plastic-associated microbial assemblages. Our approach demonstrates significantly reduced computational time and more sensitive than the older methods, identifying potential degraders that alignment techniques often miss. It connects the theoretical side of detecting functional genes with real-world environmental checks, creating a flexible tool to speed up finding new microbes for tackling plastic waste and restoring ecosystems.
U. Luke, Emem Okon Abang, Etimbuk Daniel Akpan et al.· E3S Web of Conferences· 0 citations
This paper presents a comprehensive multi-modal artificial intelligence framework for the prediction of disease from electronic health records that integrates ClinicalBERT natural language processing with graph neural networks, temporal modeling and explainability analysis. Using Synthea synthetic EHR dat with SNOMED CT codes from 1,171 patients, our approach combines semantic understanding of clinical narratives with structural modeling of patient-disease-treatment relationships. The system achieves predictive performance with macro-averaged F1 score of 0.4512 and AUC of 0.9071 across six chronic conditions, demonstrating outstanding results for diabetes (F1=0.900) and hypertension (F1=0.949). Novel contributions include temporal progression forecasting over 12-month periods using LSTM-Transformer hybrid architecture and comprehensive explainability framework providing gradient-based feature importance analysis and automated clinical reasoning generation. The frameworks successfully validates synthetic EHR data utility for privacy-preserving healthcare AI development while addressing critical requirements necessary for clinical decision support system.
U. Luke, P. Asuquo, Victor Anaga et al.· E3S Web of Conferences· 0 citations