Prediction of KRASG12C inhibitors using conjoint fingerprint and machine learning-based QSAR models

Tarapong Srisongkram; Patcharapa Khamtang; Natthida Weerapreeyakul

doi:10.1016/j.jmgm.2023.108466

Prediction of KRAS^G12C inhibitors using conjoint fingerprint and machine learning-based QSAR models

J Mol Graph Model. 2023 Jul:122:108466. doi: 10.1016/j.jmgm.2023.108466. Epub 2023 Apr 7.

Authors

Tarapong Srisongkram¹, Patcharapa Khamtang², Natthida Weerapreeyakul³

Affiliations

¹ Division of Pharmaceutical Chemistry, Faculty of Pharmaceutical Sciences, Khon Kaen University, 40002, Thailand. Electronic address: tarasri@kku.ac.th.
² Faculty of Pharmaceutical Sciences, Khon Kaen University, 40002, Thailand.
³ Division of Pharmaceutical Chemistry, Faculty of Pharmaceutical Sciences, Khon Kaen University, 40002, Thailand.

PMID: 37058997
DOI: 10.1016/j.jmgm.2023.108466

Abstract

Kirsten rat sarcoma virus G12C (KRAS^G12C) is the major protein mutation associated with non-small cell lung cancer (NSCLC) severity. Inhibiting KRAS^G12C is therefore one of the key therapeutic strategies for NSCLC patients. In this paper, a cost-effective data driven drug design employing machine learning-based quantitative structure-activity relationship (QSAR) analysis was built for predicting ligand affinities against KRAS^G12C protein. A curated and non-redundant dataset of 1033 compounds with KRAS^G12C inhibitory activity (pIC₅₀) was used to build and test the models. The PubChem fingerprint, Substructure fingerprint, Substructure fingerprint count, and the conjoint fingerprint-a combination of PubChem fingerprint and Substructure fingerprint count-were used to train the models. Using comprehensive validation methods and various machine learning algorithms, the results clearly showed that the XGBoost regression (XGBoost) achieved the highest performance in term of goodness of fit, predictivity, generalizability and model robustness (R² = 0.81, Q²_CV = 0.60, Q²_Ext = 0.62, R² - Q²_Ext = 0.19, R²_Y-Random = 0.31 ± 0.03, Q²_Y-Random = -0.09 ± 0.04). The top 13 molecular fingerprints that correlated with the predicted pIC₅₀ values were SubFPC274 (aromatic atoms), SubFPC307 (number of chiral-centers), PubChemFP37 (≥1 Chlorine), SubFPC18 (Number of alkylarylethers), SubFPC1 (number of primary carbons), SubFPC300 (number of 1,3-tautomerizables), PubChemFP621 (N-C:C:C:N structure), PubChemFP23 (≥1 Fluorine), SubFPC2 (number of secondary carbons), SubFPC295 (number of C-ONS bonds), PubChemFP199 (≥4 6-membered rings), PubChemFP180 (≥1 nitrogen-containing 6-membered ring), and SubFPC180 (number of tertiary amine). These molecular fingerprints were virtualized and validated using molecular docking experiments. In conclusion, this conjoint fingerprint and XGBoost-QSAR model demonstrated to be useful as a high-throughput screening tool for KRAS^G12C inhibitor identification and drug design.

Keywords: Deep neural network; Drug design; KRAS; Machine learning; QSAR; Random forest; Support vector regression; XGBoost.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Carcinoma, Non-Small-Cell Lung* / drug therapy
Humans
Lung Neoplasms* / drug therapy
Lung Neoplasms* / genetics
Machine Learning
Molecular Docking Simulation
Mutation
Proto-Oncogene Proteins p21(ras)
Quantitative Structure-Activity Relationship

Substances

Proto-Oncogene Proteins p21(ras)
KRAS protein, human