Multilabel classification of drug-like molecules via max-margin conditional random fields

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


We present a multilabel learning approach for molecular classification, an important task in drug discovery. We use a conditional random field to model the dependencies between drug targets and discriminative training to separate correct multilabels from incorrect ones with a large margin. Efficient training of the model is ensured by conditional gradient optimization on the marginal dual polytope, using loopy belief propagation to find the steepest feasible ascent directions. In our experiments, the MMCRF method outperformed the support vector machine with state-of-the-art graph kernels on a dataset comprising of cancer inhibition potential of drug-like molecules against a large number cancer cell lines.
Original languageEnglish
Title of host publicationProceedings of The Fifth European Workshop on Probabilistic Graphical Models (PGM-2010)
Subtitle of host publication13-15 September, 2010, Helsinki, Finland
EditorsPetri Myllymäki, Teemu Roos, Tommi Jaakkola
ISBN (Electronic)978-952-60-3314-3
Publication statusPublished - 2010
MoE publication typeA4 Article in a conference publication
EventEuropean Workshop on Probabilistic Graphical Models - Helsinki, Finland
Duration: 13 Sep 201015 Sep 2010
Conference number: 5

Publication series

NameHIIT Publications
PublisherHelsinki Institute for Information Technology HIIT
ISSN (Electronic)1458-946X


WorkshopEuropean Workshop on Probabilistic Graphical Models
Abbreviated titlePGM

Fingerprint Dive into the research topics of 'Multilabel classification of drug-like molecules via max-margin conditional random fields'. Together they form a unique fingerprint.

Cite this