Skip to main content
Fig. 6 | BMC Bioinformatics

Fig. 6

From: Prediction of sensitivity to gefitinib/erlotinib for EGFR mutations in NSCLC based on structural interaction fingerprints and multilinear principal component analysis

Fig. 6

Interaction fingerprint. a Seven bits that represent seven different interactions for each residue. In the diagram, 1 means the interaction exists while 0 means the interaction does not exist. b Example of WT EGFR-erlotinib interactions (PDB: 1M17). The 3D figure was generated using Molsoft MolBrowser 3.8–5 (http://www.molsoft.com/). c For each frame in the MD trajectory, we can combine the 7-bit IFP of all residues to obtain its IFP vector. d For all frames in the MD trajectory of each complex we can produce an IFP matrix. This IFP matrix can be considered as the binding mode of this EGFR mutant with the specific TKI. e Combining these IFP matrices of multiple EGFR mutant-TKI complexes, we can obtain a third order IFP tensor

Back to article page