The Kirsten rat sarcoma viral G12C (KRASG12C) protein is one of the most common mutations in non-small-cell lung cancer (NSCLC). KRASG12C inhibitors are promising for NSCLC treatment, but their weaker activity in resistant tumors is their drawback. This study aims to identify new KRASG12C inhibitors from among the FDA-approved covalent drugs by taking advantage of artificial intelligence. The machine learning models were constructed using an extreme gradient boosting (XGBoost) algorithm. The models can predict KRASG12C inhibitors well, with an accuracy score of validation = 0.85 and Q2Ext = 0.76. From 67 FDA-covalent drugs, afatinib, dacomitinib, acalabrutinib, neratinib, zanubrutinib, dutasteride, and finasteride were predicted to be active inhibitors. Afatinib obtained the highest predictive log-inhibitory concentration at 50% (pIC50) value against KRASG12C protein close to the KRASG12C inhibitors. Only afatinib, neratinib, and zanubrutinib covalently bond at the active site like the KRASG12C inhibitors in the KRASG12C protein (PDB ID: 6OIM). Moreover, afatinib, neratinib, and zanubrutinib exhibited a distance deviation between the KRASG2C protein-ligand complex similar to the KRASG12C inhibitors. Therefore, afatinib, neratinib, and zanubrutinib could be used as drug candidates against the KRASG12C protein. This finding unfolds the benefit of artificial intelligence in drug repurposing against KRASG12C protein.
Keywords: NSCLC; QSAR; XGBoost; adagrasib; afatinib; artificial intelligence; covalent drugs; drug repositioning; drug repurposing; extreme gradient boosting; sotorasib.