Prediction and Prioritization of Rare Oncogenic Mutations in the Cancer Kinome Using Novel Features and Multiple Classifiers

Abstract

Cancer is a genetic disease that develops through a series of somatic mutations, a subset of which drive cancer progression. Although cancer genome sequencing studies are beginning to reveal the mutational patterns of genes in various cancers, identifying the small subset of “causative” mutations from the large subset of “non-causative” mutations, which accumulate as a consequence of the disease, is a challenge. In this article, we present an effective machine learning approach for identifying cancer-associated mutations in human protein kinases, a class of signaling proteins known to be frequently mutated in human cancers. We evaluate the performance of 11 well known supervised learners and show that a multiple-classifier approach, which combines the performances of individual learners, significantly improves the classification of known cancer-associated mutations. We introduce several novel features related specifically to structural and functional characteristics of protein kinases and find that the level of conservation of the mutated residue at specific evolutionary depths is an important predictor of oncogenic effect. We consolidate the novel features and the multiple-classifier approach to prioritize and experimentally test a set of rare unconfirmed mutations in the epidermal growth factor receptor tyrosine kinase (EGFR). Our studies identify T725M and L861R as rare cancer-associated mutations inasmuch as these mutations increase EGFR activity in the absence of the activating EGF ligand in cell-based assays.

Newly emergent acquired EGFR exon 18 G724S mutation after resistance of a T790M specific EGFR inhibitor osimertinib in non-small-cell lung cancer: a case report

“…29 It can be assumed that EGFR G724S mutation may be an extremely rare mutation induced by EGFR-TKIs, including different generations of TKIs. EGFR G724S may be assumed as an oncogenic mutation as it is also within the ATP binding-loop of the kinase,30 which confers drug resistance to TKIs by either changing the protein structure, or enhancing ATP affinity or stabilizing active mutation. Fassunke et al demonstrated that EGFR G724S limited the activities of third-generation EGFR TKI inhibitors both in vitro and in vivo.…”

Analysis of Circulating Cell-Free DNA Identifies Multiclonal Heterogeneity of BRCA2 Reversion Mutations Associated with Resistance to PARP Inhibitors

“…Functional annotation was performed in ANNOVAR version 2016Feb01 (19). Copy number calling of solid tumor exomes was performed using CNVkit version 0.8.1 (20). Genome coverage was calculated using bedtools version 2.26 (21).…”

Kinase Regulation by Hydrophobic Spine Assembly in Cancer

“…We also showed that replacement of the RS3 residue, Leu95, with Phe resulted in a constitutively active kinase; modeling suggested that the Phe could stabilize the active conformation of the R-spine (4). To determine whether such changes are important in disease, we used an ontology-based search tool, ProKinO (11,12), to query for mutations that introduce a Phe residue in the hydrophobic core (Fig. 1).…”

“…Figure 3A shows the residue numbers in BRAF, CRAF, and PKA that correspond to the R-spine residues. The corresponding residues in every kinase were designated in our earlier analysis of the R-spine residues (18) and in the ProKinO database (12).…”

“…To correlate the mutated sequence with structural motifs and secondary structure elements, we used the Protein Kinase Ontology (ProKinO) tool, which provides a conceptual representation of data, relating cancer mutations to conserved sequence and structural motifs associated with protein kinase regulation (11,12). We identified a C-spine residue, valine 57 (V57), which is mutated to a phenylalanine (V57F).…”