BACRNA · Integrative Machine Learning Approaches for Bacterial sRNA Genome Annotation

Lines connect the coordinator with its partners.

Project objective

This project addresses the critical challenge of accurate, genome-wide annotation of bacterial small regulatory RNAs (sRNAs), which are key regulators of microbial adaptation and gene expression. Despite advances in sequencing technologies, many sRNAs remain undetected due to their diverse sequence conservation, complex secondary structures, and variable genomic contexts. The researcher will compile and curate a large and diverse dataset of bacterial genomes with experimentally validated and computationally annotated sRNAs. Novel machine learning models will be developed to improve sRNA prediction accuracy, and these models will be integrated into an open-source annotation pipeline. Rigorous benchmarking will validate model performance, and all algorithms, datasets, and results will be released openly to enhance reproducibility and foster community impact. This fellowship will significantly expand the researcher’s expertise in bioinformatics and bacterial genomics, advancing their independent research career. Concurrently, the host organization will benefit from enhanced research capacity. The project is positioned to advance sRNA annotation methodologies, enable novel biological discoveries, and contribute to leadership in this emerging field.

Original text from CORDIS.

Participants

• UNIVERSITA TA MALTA · MSIDACoordinatorMalta

Links

• View on CORDIS
• DOI: 10.3030/101283050