| Rational Design and Computational Evaluation of Next-Generation EGFR Inhibitors Using Machine Learning and Molecular Simulations |
| کد مقاله : 1223-ICOC |
| نویسندگان |
|
علیرضا باوفاطرقبه *1، محمد حسین حورزاد2، مهدی ریحانی3 1. 2دانشجو دانشگاه تربیت مدرس 3دانشجوی صنعتی شریف |
| چکیده مقاله |
| EGFR (Epidermal Growth Factor Receptor) is a key oncogenic driver whose dysregulation promotes tumor progression, particularly in non-small cell lung cancer (NSCLC).[1] This study focused on designing a novel scaffold to selectively inhibit the ATP-binding pocket of EGFR, incorporating amino acids and nucleobases to improve stability and reduce off-target effects. Early-stage molecular selection employed machine-learning models that identified 312 candidate molecules with high predicted inhibitory potential. Due to experimental limitations, computational analyses were performed using Gefitinib, a clinically validated EGFR inhibitor,[2] as the reference compound, followed by molecular docking and molecular dynamics simulations. Among the shortlisted compounds, ligand E-204 demonstrated superior binding affinity and conformational stability—especially within the hinge region—surpassing Gefitinib across multiple computational metrics and highlighting its potential as a next-generation EGFR inhibitor.[3] |
| کلیدواژه ها |
| 1- Drug design 2- Molecular docking 3- Machine learning 4- Molecular dynamics 5- Cancer |
| وضعیت: پذیرفته شده |