• TUCS Publication Series
• How to Publish in TUCS Series
• Publication Search
• Publication Graph
• Publication Input
• Publication Input Guide
• JuFo Browser

Learning Monadic and Dyadic Relations: Three Case Studies in Systems Biology

Michiel Stock, Tapio Pahikkala, Antti Airola, Tapio Salakoski, Bernard De Baets, Willem Waegeman, Learning Monadic and Dyadic Relations: Three Case Studies in Systems Biology. In: Oliver Ray, Katsumi Inoue (Eds.), Proceedings of the ECML/PKDD 2012 Workshop on Learning and Discovery in Symbolic Systems Biology, 74–84, ECML/PKDD 2012 Workshop on Learning and Discovery in Symbolic Systems Biology, 2012.

Abstract:

In molecular biology and other subfields of biology one can encounter many machine learning problems where the goal consists of predicting relations or interactions between pairs of objects. In this article we elaborate on three applications that represent such a learning scenario: predicting functional relationships between enzymes in bioinformatics, predicting protein-ligand interactions in computational drug design and predicting heterotroph-methanotroph interactions in microbial ecology. All three case studies are analyzed using an extension of a general kernel-based framework that we proposed recently. From a mathematical perspective, we both consider monadic and dyadic relations, and we use Kronecker product feature mappings to couple feature representations of paired objects, which correspond to vertices in a graph.

Files:

Full publication in PDF-format

BibTeX entry:

@INPROCEEDINGS{inpStPaAiSaDeWa12a,
  title = {Learning Monadic and Dyadic Relations: Three Case Studies in Systems Biology},
  booktitle = {Proceedings of the ECML/PKDD 2012 Workshop on Learning and Discovery in Symbolic Systems Biology},
  author = {Stock, Michiel and Pahikkala, Tapio and Airola, Antti and Salakoski, Tapio and De Baets, Bernard and Waegeman, Willem},
  editor = {Ray, Oliver and Inoue, Katsumi},
  publisher = {ECML/PKDD 2012 Workshop on Learning and Discovery in Symbolic Systems Biology},
  pages = {74–84},
  year = {2012},
  keywords = {Machine learning, Learning relations, computational drug design, microbial ecology, ranking},
}

Belongs to TUCS Research Unit(s): Algorithmics and Computational Intelligence Group (ACI), Turku BioNLP Group

Edit publication