Evaluation of anti-EGFR-iRGD recombinant protein with GOLD nanoparticles: synergistic effect on antitumor efficiency using optimized deep neural networks

Abstract

The epidermal growth factor receptor, also known as EGFR, is a tyrosine kinase receptor commonly found in epithelial tumors. As part of the first target for cancer treatment, EGFR has been the subject of intense research for more than 20 years; as a result, there are a number of anti-EGFR agents currently available. More recently, with our basic understanding of mechanisms related to receptor activation and function, both the secondary and primary forms of EGFR somatic mutations have led to the discovery of new anti-EGFR agents aimed at providing new insights into the clinical targeting of this receptor and possibly acting as an ideal model for developing strategies to target other types of receptors. In this study, we use genomic pattern to prove that EGFR is most frequently altered in GBM, glioma and astrocytoma; and analysed the prognostic potentiality of EGFR in glioma, which is a major type of brain tumor. Further we proposed a new screening technique for EGFR inhibitors by employing an in silico optimized deep neural network approach. This method was applied to screen a nanoparticle (NP) library, and it was concluded that gold NPs (AuNPs) induced significant inhibition of EGFR compared with other selected NPs. These findings were further analyzed by molecular docking, systems biology, time course simulations and synthetic biology (biological circuits), revealing that anti-EGFR-iRGD and AuNP showed potential inhibition against tumors caused by EGFR.