Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

AI analysis of Next Generation Sequencing data to identify infectious agents and their properties

Reference number
Coordinator Statens Veterinärmedicinska Anstalt
Funding from Vinnova SEK 364 158
Project duration December 2020 - December 2021
Status Completed
Venture AI - Competence, ability and application
Call Start your AI-journey for public organizations - autumn 2020

Important results from the project

The project has made an evaluation to determine whether methods based on AI / machine learning have the potential to become part of SVA´s set of method for identification and characterization of microbiological infectious agents in data generated with the analysis method "Next generation sequencing" (NGS). Both data from whole genome sequencing of isolated infectious agents and sequencing of complex samples with unknown infectious agents has been used. The project has built knowledge at SVA about AI analysis of NGS data and has compared AI methods with traditional analysis methods.

Expected long term effects

The project has resulted in that AI-based methods now are available at SVA to find genetic markers of pathogenicity (capacity to induce disease) in NGS data. The methods have been evaluated by testing them with large amounts of data relevant to SVA´s issues. An understanding of the methods´ strengths and weaknesses has been built up. This forms a good basis for creating future AI methods tailored to SVA´s needs.

Approach and implementation

A literature review was followed by tests of selected methods that were relevant to SVA´s work. Data sets from internal sequencing as well as relevant data from the international database archives have been used to test the methods and in parallel compare with traditional non-AI based sequence comparisons. The ability of the methods to generalize to new data types was evaluated by including data from organisms that were not included in the training of the AI models. Internal knowledge transfer / competence development has also been carried out in the form of seminars.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 3 March 2022

Reference number 2020-04048