We have developed a method for learning tree ansambles for hierarchical multi-label clasification. We have used it for gene function prediction in three different organisms: S. cerevisiae, A. thaliana and M. musculus. The results show that our method is as accurate as state-of-the-art methods for amutomatic gene function prediction, but has a much lower time complexity.
F.02 Acquisition of new scientific knowledge
COBISS.SI-ID: 23480359The project team organized the Third Workshop on Machine Learning in Systems Biology (MLSB-09) in Ljubljana in September 2009. This is a highly reputed workshop with high quality invited speakers and reviewed contributions that attracted more than 60 participants. S. Džeroski co-chaired the program committee of the event. The proceedings of the workshop are published and contain the abstracts of 6 invited talks, 12 full papers and 22 abstracts of poster presentations.
B.02 Presiding over the programming board of a conference
COBISS.SI-ID: 22827559