MoKCa database--mutations of kinases in cancer

Abstract

Members of the protein kinase family are amongst the most commonly mutated genes in human cancer, and both mutated and activated protein kinases have proved to be tractable targets for the development of new anticancer therapies The MoKCa database (Mutations of Kinases in Cancer, http://strubiol.icr.ac.uk/extra/mokca) has been developed to structurally and functionally annotate, and where possible predict, the phenotypic consequences of mutations in protein kinases implicated in cancer. Somatic mutation data from tumours and tumour cell lines have been mapped onto the crystal structures of the affected protein domains. Positions of the mutated amino-acids are highlighted on a sequence-based domain pictogram, as well as a 3D-image of the protein structure, and in a molecular graphics package, integrated for interactive viewing. The data associated with each mutation is presented in the Web interface, along with expert annotation of the detailed molecular functional implications of the mutation. Proteins are linked to functional annotation resources and are annotated with structural and functional features such as domains and phosphorylation sites. MoKCa aims to provide assessments available from multiple sources and algorithms for each potential cancer-associated mutation, and present these together in a consistent and coherent fashion to facilitate authoritative annotation by cancer biologists and structural biologists, directly involved in the generation and analysis of new mutational data.

Figure 1.

MoKCa kinase gene list. Genes encoding protein kinases are shown listed by ranking of their probability of containing one or more cancer-driving mutation (11). Gene names are additionally annotated with number of mutations found in the Cancer Genome Project analysis (9), the calculated selection pressure on that gene, and indicators showing the cancer types in which the gene was found mutated. The list can also be sorted alphabetically or by selective pressure. Gene names hyperlink to gene-level pages.

Figure 2.

Mapping mutations to domains. The spectrum of mutations identified for each gene is shown on its gene-level page mapped on to a schematic representation of the domain structure of the encoded protein. (a) The domain structure of each encoded protein (defined by Pfam definitions) is shown as a pictogram, with the positions of mutations annotated with icons specific to the type of mutation—silent, missense, nonsense (stop), deletion (frameshift or in-frame) or insertion (frameshift or in-frame). Functionally important sequence features, such as documented phosphorylation sites from Phospho.ELM (23) are also shown. Annotation of features such as active sites and ATP-binding motifs (from Prosite) will be added in future versions. (b) Example domain pictogram for TGFBR2, showing missense mutations distributed in the extra-cellular and kinase domains, a frameshift (probably truncating) deletion mutation in the extra-cellular domain, and a truncating nonsense mutation in the C-terminal lobe of the kinase domain. Automated assessment by CanPredict identifies a lung-cancer associated H328Y mutation as a cancer driver. (c) Domain pictogram for BRAF, identified as a strongly selected mutated gene in melanoma and a range of other cancers, showing the cluster of activating missense mutations in the activation segment.

Figure 3.

Mutations, mechanisms and pathways. (a) Gene-level pages (illustrated for BRAF) provide links to data for the gene in a range of primary and other databases including COSMIC, UNIPROT and KinBase. Additional links are provided to GO functional annotations, Pfam definitions for domains of the encoded protein, and Prosite motifs matched in the encoded protein sequence. A hyperlink to the ROCK Online Cancer Knowledge base (Zvelebil et al., unpublished), provides view of the protein–protein interactions [see (c)]. A hyperlinked list of mutations, annotated with tumour sample registry numbers, and indicators for tumour type and CanPredict assessment of driver probability, points out to individual mutation-level pages [see (b)]. (b) Mutation-level pages give specific domain assignments and CanPredict assessments for the individual mutation, as well as hyperlinks to a homology-ranked list of protein structures homologous to the affected domain. A 3D-graphic overview of the domain is provided with the mutated residue highlighted, and a Jmol session allowing interaction with the protein can be launched. ‘Expert’ users are able to enter a description of the mechanistic implications of the particular mutation, if any, and evidence for that opinion. Future developments will include bibliographic hyperlinks to relevant publications. (c) ROCK provides a graphical view (with optional Cytoscape viewer) of the documented protein–protein interactions for the affected gene (highlighted red). For other kinases appearing in the interaction network, the selective pressure for cancer-associated mutations is used to colour the node. In the BRAF example shown, the two ERK kinases (MAP2K1/2) downstream of BRAF display no selective pressure, whereas RAF1 (aka C-RAF) which co-operates in parallel with BRAF, displays a selective pressure for cancer driver mutations. The displayed network can be interactively expanded or contracted, and interrogated, as required. A full description of ROCK will be presented elsewhere.