Abstract: The prediction of phenotypic traits from genomic information is an ongoing challenge in computational biology. Although the fundamental principles of information encoding in genomes have been studied since decades and allowed first directed modifications, the expression of phenotypic traits is often the result of complex interactions. Predictive approaches in bioinformatics therefore focus on machine learning from labeled genomic data.

During the last years, we have focused on the computational prediction of microbial phenotypic traits from metagenomic data. These data have been collected on large scale, to explore the diversity and composition of microbial communities and to correlate them with environmental factors (e.g. human health and disease). The prediction of traits for these millions of genomes, based on neural networks that use protein families as features, goes one step further and can be used in first applications.

About the speaker: Professor Thomas Rattei is a chemist by training. He is Professor for “In silico genomics” at the University of Vienna since 2010.

Thomas Rattei’s work covers a wide spectrum of topics from bioinformatics, genome and metagenome analysis and systems biology. He has long-standing expertise in developing and applying computational methods for the interpretation of large-scale sequence information. The international reputation of his research group triggered their involvement in numerous international (meta-) genome sequencing and analysis consortia.

Thomas’ research activities not only cover individual, project-specific questions but also general problems in bioinformatics, computational infrastructure, and large-scale biological databases. Furthermore, his group develops novel, genome-based computational approaches for studying molecular inter-species interactions, such as between hosts and pathogens, between symbionts, or in microbial ecosystems.

Thomas and his team maintain and develop internationally relevant resources in computational biology, such as the web portals phendb.org, vogdb.org and effectivedb.org for microbial trait prediction, virus orthologous groups and protein families, and bacterial secreted proteins and secretion systems.