uu.seUppsala University Publications
Change search
ReferencesLink to record
Permanent link

Direct link
Kinome-wide interaction modelling using alignment-based and alignment-independent approaches for kinase description and linear and non-linear data analysis techniques
Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Pharmacy, Department of Pharmaceutical Biosciences.
Uppsala University, Disciplinary Domain of Medicine and Pharmacy, Faculty of Pharmacy, Department of Pharmaceutical Biosciences.
2010 (English)In: BMC Bioinformatics, ISSN 1471-2105, Vol. 11, 339- p.Article in journal (Refereed) Published
Abstract [en]


Protein kinases play crucial roles in cell growth, differentiation, and apoptosis. Abnormal function of protein kinases can lead to many serious diseases, such as cancer. Kinase inhibitors have potential for treatment of these diseases. However, current inhibitors interact with a broad variety of kinases and interfere with multiple vital cellular processes, which causes toxic effects. Bioinformatics approaches that can predict inhibitor-kinase interactions from the chemical properties of the inhibitors and the kinase macromolecules might aid in design of more selective therapeutic agents, that show better efficacy and lower toxicity.


We applied proteochemometric modelling to correlate the properties of 317 wild-type and mutated kinases and 38 inhibitors (12,046 inhibitor-kinase combinations) to the respective combination's interaction dissociation constant (K-d). We compared six approaches for description of protein kinases and several linear and non-linear correlation methods. The best performing models encoded kinase sequences with amino acid physico-chemical z-scale descriptors and used support vector machines or partial least-squares projections to latent structures for the correlations. Modelling performance was estimated by double cross-validation. The best models showed high predictive ability; the squared correlation coefficient for new kinase-inhibitor pairs ranging P-2 = 0.67-0.73; for new kinases it ranged P-kin(2) = 0.65-0.70. Models could also separate interacting from non-interacting inhibitor-kinase pairs with high sensitivity and specificity; the areas under the ROC curves ranging AUC = 0.92-0.93. We also investigated the relationship between the number of protein kinases in the dataset and the modelling results. Using only 10% of all data still a valid model was obtained with P-2 = 0.47, P-kin(2) = 0.42 and AUC = 0.83.


Our results strongly support the applicability of proteochemometrics for kinome-wide interaction modelling. Proteochemometrics might be used to speed-up identification and optimization of protein kinase targeted and multi-targeted inhibitors.

Place, publisher, year, edition, pages
2010. Vol. 11, 339- p.
National Category
Pharmaceutical Sciences
URN: urn:nbn:se:uu:diva-135959DOI: 10.1186/1471-2105-11-339ISI: 000280332500002PubMedID: 20569422OAI: oai:DiVA.org:uu-135959DiVA: diva2:375903
Available from: 2010-12-09 Created: 2010-12-09 Last updated: 2013-12-12Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textPubMed

Search in DiVA

By author/editor
Lapins, MarisWikberg, Jarl E. S.
By organisation
Department of Pharmaceutical Biosciences
In the same journal
BMC Bioinformatics
Pharmaceutical Sciences

Search outside of DiVA

GoogleGoogle Scholar

Altmetric score

Total: 286 hits
ReferencesLink to record
Permanent link

Direct link