Description: Conference Template
Next-generation sequencing (NGS) technologies are getting cheaper and cheaper, making it possible to sequence massive panels of microbial genomes. Accordingly, NGS is becoming a key technological pillar to understand and fight microbial infections. This was exemplified in the context of the on-going COVID-19 pandemic, where NGS technologies offered the possibility to identify novel variants of the SARS-CoV2 virus, and to monitor in real-time their worldwide evolution. Likewise, they are increasingly used to
The improvement and increasing accessibility of NGS data call for innovative data analysis strategies to extract meaningful and actionable information. Machine learning approaches are more and more popular in this context, offering alternative and complementary tools beyond bioinformatics to analyze genomic data. Our objective is to gather a community of researchers working at the interface of machine learning and computational biology to study microbial genomic data.
Typical problems of interest include: Improving microbial genome-wide association studies (GWAS), e.g. by proposing more relevant representations of genetic variation, novel testing procedures or better ways to deal with the strong population structure encountered in typical bacterial panels. Predicting a phenotype of interest (e.g. AMR, hypervirulence) from a microbial genome. Inferring multiple aspects of a population’s evolutionary history from a set of microbial genomes, e.g. the presence of selective s