An eigen-binding site based method for the analysis of anti-EGFR drug resistance in lung cancer treatment
We explore the drug resistance mechanism in non-small cell lung cancer treatment by characterizing the drug-binding site of a protein mutant based on local surface and energy features. These features are transformed to an eigen-binding site space and used for drug resistance level prediction and analysis.
Keywords: Epidermal growth factor receptor, non-small-cell lung carcinoma, tyrosine kinase inhibitor, gefitinib, binding free energy, binding site, alpha shape modeling
Figure 1. Distributions of mutant samples described with the first several (k) PCs. (A) Projection of the mutant features to the first two PCs (k = 2). Here blue, red, green and dark circles represent mutant groups that correspond to drug response levels from 1 to 4 respectively, and ’*’ stands for the centroid of each group. (B) Mutant features projected to the first three PCs, with the data set condensed to Response (blue circles) and No-response (magenta circles) groups. (C) and (D) show the feature trends of the two groups of mutants.
Table 1. Performance of each of the 15 features in drug response level prediction.
Table 2. The result of SVM slassification.
Table 2. The result of SVM slassification.[Back]