ML-QSAR and Fragment Selectivity for the Identification of Fourth-Generation EGFRL858R/T790M/C797S Inhibitors
- 1Jiangxi Province Key Laboratory of Drug Target Discovery and Validation, School of Pharmaceutical Science, Jiangxi Medical College, Nanchang University, Nanchang 330006, China
Abstract
This study aimed to establish an integrative workflow that couples QSAR modeling based on ML-QSAR, fragment-level selectivity analysis, large-library virtual screening, and MD simulations to identify fourth-generation inhibitors of the EGFRL858R/T790M/C797S mutant. Independent XGBoost models were trained on curated ChEMBL bioactivity data for mutant and wild-type EGFR, yielding strong predictive accuracy (R2 = 0.74–0.81; RMSE = 0.53–0.56) together with interpretable SHAP feature attributions. Fragment analysis highlighted structural motifs that were subsequently used to screen the ZINC database, from which 22 compounds with selectivity scores above 1.9 were retained. Docking and MD analyses identified three hits with strong selectivity, favorable binding energies (−25.3 to −36.4 kJ/mol) and interaction patterns consistent with known EGFRL858R/T790M/C797S inhibitors. The pipeline can be transferred to other targets and provides a scalable template for rational, next-generation drug exploratory in precision oncology.
Related
- Fragment-Based Discovery of KLK6 and KLK7 Inhibitors
- Fragment‐Linked Purine Derivatives as Inhibitors of (p)ppGpp Synthetases: Design, Synthesis, and Structure‐Activity Relationships
- RAF isoform selectivity of MEK inhibitors and rational design of a covalent ARAF-MEK inhibitor
- Integrated hierarchical fusion of GRU and meta-features for enhanced identification and interpretation of calcium ion inhibitors
- Recombinant SIRT1 expression and SIRT1 METTL3 interaction analysis with computational identification of phytochemical SIRT1 activators and inhibitors
BibTeX
@article{tu2026mlqsar,
title = {{ML-QSAR and Fragment Selectivity for the Identification of Fourth-Generation EGFRL858R/T790M/C797S Inhibitors}},
author = {Guo-Gang Tu},
journal = {International Journal of Molecular Sciences},
year = {2026},
month = oct,
doi = {10.3390/ijms27219796},
url = {https://www.mdpi.com/1422-0067/27/21/9796},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - ML-QSAR and Fragment Selectivity for the Identification of Fourth-Generation EGFRL858R/T790M/C797S Inhibitors
AU - Guo-Gang Tu
PY - 2026
DA - 2026/10/31
JO - International Journal of Molecular Sciences
DO - 10.3390/ijms27219796
UR - https://www.mdpi.com/1422-0067/27/21/9796
AB - This study aimed to establish an integrative workflow that couples QSAR modeling based on ML-QSAR, fragment-level selectivity analysis, large-library virtual screening, and MD simulations to identify fourth-generation inhibitors of the EGFRL858R/T790M/C797S mutant. Independent XGBoost models were trained on curated ChEMBL bioactivity data for mutant and wild-type EGFR, yielding strong predictive accuracy (R2 = 0.74–0.81; RMSE = 0.53–0.56) together with interpretable SHAP feature attributions. Fragment analysis highlighted structural motifs that were subsequently used to screen the ZINC database, from which 22 compounds with selectivity scores above 1.9 were retained. Docking and MD analyses identified three hits with strong selectivity, favorable binding energies (−25.3 to −36.4 kJ/mol) and interaction patterns consistent with known EGFRL858R/T790M/C797S inhibitors. The pipeline can be transferred to other targets and provides a scalable template for rational, next-generation drug exploratory in precision oncology.
SN - 1422-0067
ER -