Learning with multiple pairwise kernels for drug bioactivity prediction

Simple item page
dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorCichonska, Annaen_US
dc.contributor.authorPahikkala, Tapioen_US
dc.contributor.authorSzedmak, Sandoren_US
dc.contributor.authorJulkunen, Helien_US
dc.contributor.authorAirola, Anttien_US
dc.contributor.authorHeinonen, Markusen_US
dc.contributor.authorAittokallio, Teroen_US
dc.contributor.authorRousu, Juhoen_US
dc.contributor.departmentDepartment of Computer Scienceen
dc.contributor.groupauthorProfessorship Rousu Juhoen
dc.contributor.groupauthorHelsinki Institute for Information Technology (HIIT)en
dc.contributor.groupauthorProfessorship Lähdesmäki Harrien
dc.contributor.groupauthorCentre of Excellence in Molecular Systems Immunology and Physiology Research Group, SyMMysen
dc.contributor.organizationUniversity of Turkuen_US
dc.contributor.organizationAalto Universityen_US
dc.date.accessioned2018-08-21T13:48:14Z
dc.date.available2018-08-21T13:48:14Z
dc.date.issued2018-07-01en_US
dc.description.abstractMotivation: Many inference problems in bioinformatics, including drug bioactivity prediction, can be formulated as pairwise learning problems, in which one is interested in making predictions for pairs of objects, e.g. drugs and their targets. Kernel-based approaches have emerged as powerful tools for solving problems of that kind, and especially multiple kernel learning (MKL) offers promising benefits as it enables integrating various types of complex biomedical information sources in the form of kernels, along with learning their importance for the prediction task. However, the immense size of pairwise kernel spaces remains a major bottleneck, making the existing MKL algorithms computationally infeasible even for small number of input pairs. Results: We introduce pairwiseMKL, the first method for time- and memory-efficient learning with multiple pairwise kernels. pairwiseMKL first determines the mixture weights of the input pairwise kernels, and then learns the pairwise prediction function. Both steps are performed efficiently without explicit computation of the massive pairwise matrices, therefore making the method applicable to solving large pairwise learning problems. We demonstrate the performance of pairwiseMKL in two related tasks of quantitative drug bioactivity prediction using up to 167 995 bioactivity measurements and 3120 pairwise kernels: (i) prediction of anticancer efficacy of drug compounds across a large panel of cancer cell lines; and (ii) prediction of target profiles of anticancer compounds across their kinome-wide target spaces. We show that pairwiseMKL provides accurate predictions using sparse solutions in terms of selected kernels, and therefore it automatically identifies also data sources relevant for the prediction problem.en
dc.description.versionPeer revieweden
dc.format.extenti509-i518
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationCichonska, A, Pahikkala, T, Szedmak, S, Julkunen, H, Airola, A, Heinonen, M, Aittokallio, T & Rousu, J 2018, ' Learning with multiple pairwise kernels for drug bioactivity prediction ', Bioinformatics, vol. 34, no. 13, pp. i509-i518 . https://doi.org/10.1093/bioinformatics/bty277en
dc.identifier.doi10.1093/bioinformatics/bty277en_US
dc.identifier.issn1367-4803
dc.identifier.issn1460-2059
dc.identifier.otherPURE UUID: e5385311-2528-4460-818f-4f98fbe1ffceen_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/e5385311-2528-4460-818f-4f98fbe1ffceen_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85050821710&partnerID=8YFLogxKen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/27134633/bty277.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/33571
dc.identifier.urnURN:NBN:fi:aalto-201808214704
dc.language.isoenen
dc.relation.ispartofseriesBioinformaticsen
dc.relation.ispartofseriesVolume 34, issue 13en
dc.rightsopenAccessen
dc.titleLearning with multiple pairwise kernels for drug bioactivity predictionen
dc.typeA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessäfi
dc.type.versionpublishedVersion
Files
Collections
[article-cris] Perustieteiden korkeakoulu / SCI