Tags

Type your tag names separated by a space and hit enter

Kinact: a computational approach for predicting activating missense mutations in protein kinases.
Nucleic Acids Res. 2018 07 02; 46(W1):W127-W132.NA

Abstract

Protein phosphorylation is tightly regulated due to its vital role in many cellular processes. While gain of function mutations leading to constitutive activation of protein kinases are known to be driver events of many cancers, the identification of these mutations has proven challenging. Here we present Kinact, a novel machine learning approach for predicting kinase activating missense mutations using information from sequence and structure. By adapting our graph-based signatures, Kinact represents both structural and sequence information, which are used as evidence to train predictive models. We show the combination of structural and sequence features significantly improved the overall accuracy compared to considering either primary or tertiary structure alone, highlighting their complementarity. Kinact achieved a precision of 87% and 94% and Area Under ROC Curve of 0.89 and 0.92 on 10-fold cross-validation, and on blind tests, respectively, outperforming well established tools (P < 0.01). We further show that Kinact performs equally well on homology models built using templates with sequence identity as low as 33%. Kinact is freely available as a user-friendly web server at http://biosig.unimelb.edu.au/kinact/.

Authors+Show Affiliations

Department of Biochemistry and Molecular Biology, Bio21 Institute, University of Melbourne.Department of Biochemistry and Molecular Biology, Bio21 Institute, University of Melbourne. Department of Biochemistry, University of Cambridge. Instituto René Rachou, Fundação Oswaldo Cruz.Instituto René Rachou, Fundação Oswaldo Cruz.

Pub Type(s)

Journal Article
Research Support, Non-U.S. Gov't
Validation Study

Language

eng

PubMed ID

29788456

Citation

Rodrigues, Carlos Hm, et al. "Kinact: a Computational Approach for Predicting Activating Missense Mutations in Protein Kinases." Nucleic Acids Research, vol. 46, no. W1, 2018, pp. W127-W132.
Rodrigues CH, Ascher DB, Pires DE. Kinact: a computational approach for predicting activating missense mutations in protein kinases. Nucleic Acids Res. 2018;46(W1):W127-W132.
Rodrigues, C. H., Ascher, D. B., & Pires, D. E. (2018). Kinact: a computational approach for predicting activating missense mutations in protein kinases. Nucleic Acids Research, 46(W1), W127-W132. https://doi.org/10.1093/nar/gky375
Rodrigues CH, Ascher DB, Pires DE. Kinact: a Computational Approach for Predicting Activating Missense Mutations in Protein Kinases. Nucleic Acids Res. 2018 07 2;46(W1):W127-W132. PubMed PMID: 29788456.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Kinact: a computational approach for predicting activating missense mutations in protein kinases. AU - Rodrigues,Carlos Hm, AU - Ascher,David B, AU - Pires,Douglas Ev, PY - 2018/01/31/received PY - 2018/04/28/accepted PY - 2018/5/23/pubmed PY - 2019/8/14/medline PY - 2018/5/23/entrez SP - W127 EP - W132 JF - Nucleic acids research JO - Nucleic Acids Res. VL - 46 IS - W1 N2 - Protein phosphorylation is tightly regulated due to its vital role in many cellular processes. While gain of function mutations leading to constitutive activation of protein kinases are known to be driver events of many cancers, the identification of these mutations has proven challenging. Here we present Kinact, a novel machine learning approach for predicting kinase activating missense mutations using information from sequence and structure. By adapting our graph-based signatures, Kinact represents both structural and sequence information, which are used as evidence to train predictive models. We show the combination of structural and sequence features significantly improved the overall accuracy compared to considering either primary or tertiary structure alone, highlighting their complementarity. Kinact achieved a precision of 87% and 94% and Area Under ROC Curve of 0.89 and 0.92 on 10-fold cross-validation, and on blind tests, respectively, outperforming well established tools (P < 0.01). We further show that Kinact performs equally well on homology models built using templates with sequence identity as low as 33%. Kinact is freely available as a user-friendly web server at http://biosig.unimelb.edu.au/kinact/. SN - 1362-4962 UR - https://www.unboundmedicine.com/medline/citation/29788456/Kinact:_a_computational_approach_for_predicting_activating_missense_mutations_in_protein_kinases_ L2 - https://academic.oup.com/nar/article-lookup/doi/10.1093/nar/gky375 DB - PRIME DP - Unbound Medicine ER -