✅ Secondment from UVSQ to FIISC (06/2026 – 08/2026)
This secondment brought together artificial intelligence and long-read genomics to address the challenge of extracting reliable and biologically meaningful information from complex genomic data. It provided an opportunity to bridge advanced machine learning techniques with cutting-edge Nanopore sequencing technologies in a clinically relevant research environment.
The focus of the secondment was the development of efficient, robust, and interpretable machine learning methods for genomic data analysis, carried out in close collaboration with the research team at the Research Unit of the Hospital Universitario N.S. de Candelaria in Santa Cruz de Tenerife. By combining expertise in machine learning with Nanopore long-read 16S rRNA sequencing, the work explored an end-to-end approach capable of transforming raw sequencing reads into meaningful taxonomic information. This collaboration led to the development of an end-to-end deep learning architecture integrating read processing, denoising, clustering, and taxonomic profiling within a unified framework. Beyond improving the efficiency of genomic data analysis, the work aimed to enhance the interpretability and reliability of the resulting profiles, paving the way for more scalable and trustworthy AI-driven approaches to microbiome and genomic research.
