ML-assisted rapid detection of pathogens using nanopore sequencing

Short description of the project

Modern proteomics methods enable large-scale studies of proteins produced in an organism, system, or biological context, and are also becoming increasingly powerful for identifying biological threats, potential disease mechanisms and disease biomarkers. Nanopore-based analyzers provide a high-throughput, low-cost and portable alternative to mass spectrometry. Hence, the application of nanopore technology for protein sequencing at the single molecule level represents a new innovative approach. Due to the significantly higher complexity of proteins compared to DNA, the complexity of resulting nanopore raw signals also increases. Therefore, adapted Machine learning - based methods are needed to convert these signals into reliable peptide identifications.

The project addresses the following “Essential Public Health Functions” (EPHS):

• #1: Assess and monitor population health status, factors that influence health, and community needs and assets.
  Nanopore peptide sequencing is an innovative technology, that could be used to quantify specific pathogens in metagenomic samples.
• #2: Investigate, diagnose, and address health problems and hazards affecting the population.
  Nanopore peptide sequencing could help to detect emerging health threats by rapidly identifying specific biomarkers and pathogens.
• #9: Improve and innovate public health functions through ongoing evaluation, research, and continuous quality improvement.
  Nanopore peptide sequencing has the potential to revolutionize the field of proteomics. The establishment of a reliable experimental protocol and ML methods to interpret the nanopore signals would make this approach directly applicable to public health problems.

to the top