Analisis Komputasi Inhibitor DGAT dengan Model QSAR Menggunakan Deskriptor RDKit dan XGBoost

Algafari Bakti Manggara, Ratna Juwita, Atmira Sariwati

Abstract


Diacylglycerol acyltransferase (DGAT) is a key therapeutic target for metabolic diseases. This study aims to develop a robust Quantitative Structure-Activity Relationship (QSAR) model to predict the activity of DGAT inhibitors using a computational approach. A dataset of 197 DGAT inhibitors with pIC50 values was curated from the ChEMBL database. Molecular descriptors were calculated using RDKit, followed by feature selection through the elimination of zero-variance descriptors and correlation analysis (threshold r > 0.80), resulting in 41 representative descriptors for modeling. A predictive model was built using the Extreme Gradient Boosting (XGBoost) algorithm. Model evaluation demonstrated excellent performance with a coefficient of determination (R²) of 0.885 on training data and 0.758 on test data, alongside low RMSE and MAE values. Feature importance analysis revealed that NOCount and MaxPartialCharge descriptors were the most significant contributors to inhibitory activity, providing valuable insights for rational drug design. Although the model showed high predictive accuracy, a negative Q² from cross-validation indicates a need for further optimization. In conclusion, this study successfully demonstrates that the integration of RDKit descriptors and the XGBoost algorithm can yield an accurate and interpretable QSAR model to accelerate the insilico discovery of DGAT inhibitors.

Keywords


DGAT; QSAR; RDKit;XGBoost

Full Text:

PDF

References


Zubair M., Tong X., Ashraf A., Li H., Li G., Xin A., Chen J., Wang Y., Li Z., Huang J., and Cheng Y., "Genetic regulation and breeding application of medium-chain fatty acids metabolism in rice," Biology, vol. 14, no. 12, p. 1674, Nov. 2025, doi: 10.3390/biology14121674.
[2] Longo M., Paolini E., Di Benedetto P., Tomassini E., Meroni M., and Dongiovanni P., "DGAT1 and DGAT2 inhibitors for metabolic dysfunction-associated steatotic liver disease (MASLD) management: Benefits for their single or combined application," Int. J. Mol. Sci., vol. 25, no. 16, p. 9074, Aug. 2024, doi:10.3390/ijms25169074.
[3] Guerra J. V., Dias M. M., Brilhante A. J., Terra M. F., Garcia-Arevalo M., and Figueira A. C., "Multifactorial basis and therapeutic strategies in metabolism-related diseases," Nutrients, vol. 13, no. 8, p. 2830, Aug. 2021, doi: 10.3390/nu13082830.
[4] Zhang Y., Liu C., Liu M., Liu T., Lin H., Huang C. B., and Ning L., "Attention is all you need: Utilizing attention in AI-enabled drug discovery," Brief. Bioinform., vol. 25, no. 1, p. bbad467, Jan. 2024, doi: 10.1093/bib/bbad467.
[5] Saadiq M., Uddin G., Latif A., Ali M., Akbar N., Ammara, Ali S., Ahmad M., Zahoor M., Khan A., and Al- Harrasi A., "Synthesis, bioactivity assessment, and molecular docking of non-sulfonamide benzimidazole- derived N-acylhydrazone scaffolds as carbonic anhydrase-II inhibitors," ACS Omega, vol. 7, no. 1, pp. 705-715, Dec. 2021, doi: 10.1021/acsomega.1c05041.
[6] Zhang H., Shen C., Zhang H. R., Chen W. X., Luo Q. Q., and Ding L., "Discovery of novel DGAT1 inhibitors by combination of machine learning methods, pharmacophore model and 3D-QSAR model," Mol. Diversity,vol. 25, no. 3, pp. 1481-1495, Aug. 2021, doi: 10.1007/s11030-021-10239-0
[7] Kumar P., Kumar A., and Sindhu J., "In silico design of diacylglycerol acyltransferase-1 (DGAT1) inhibitors based on SMILES descriptors using Monte-Carlo method," SAR QSAR Environ. Res., vol. 30, no. 8, pp. 525-541, Aug. 2019, doi: 10.1080/1062936X.2019.1685788.
[8] Zhang S., Xu Y., Zeng X., Ran J., Chen Y., Kuai L., Li K., Xu P., Yan F., and Wang D., "QSAR-based physiologically based pharmacokinetic (PBPK) modeling for 34 fentanyl analogs: Model validation, human pharmacokinetic prediction and abuse risk insights," Front. Pharmacol., vol. 16, p. 1692293, Oct. 2025, doi: 10.3389/fphar.2025.1692293.
[9] Deng L., Liu Y., Mi N., Ding F., Zhang S., Wu L., and Tong H., "Combined structure-based virtual screening and machine learning approach for the identification of potential dual inhibitors of ACC and DGAT2," Int. J. Biol. Macromol., vol. 278, p. 134363, Oct. 2024, doi: 10.1016/j.ijbiomac.2024.134363.
[10] Landrum G., "RDKit: Open-source cheminformatics," 2006. [Online]. Available: https://www.rdkit.org
[11] Chen T. and Guestrin C., "XGBoost: A scalable tree boosting system," in Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, pp. 785-794, 2016, doi: 10.1145/2939672.2939785.
[12] Leong G. K., Yunpeng L., Kelin X., and Jie W. J., "XGBoost, Mordred and RDKit for the prediction of glass transition temperature of polymers," in Proc. URECA@NTU, vol. 21, 2020. [Online]. Available: https://hdl.handle.net/10356/155298.
[13] Nael M. A., Alakonda L. M., and Elokely K. M., "Defining the data set defines the QSAR claim," J. Chem. Inf. Model., Feb. 2026, doi: 10.1021/acs.jcim.6c00514.
[14] Aljaafreh M. J., Sumrra S. H., and Noreen S., "A machine learning quest to design molecular graph fingerprints of organic chromophores for adjusting photoluminescent quantum yields," ACS Omega, Feb. 2026, doi: 10.1021/acsomega.5c08921.
[15] Manggara A. B. and Sugimoto M., "Extended regression modeling of the toxicity of phenol derivatives toTetrahymena pyriformis using the electronic-structure informatics descriptor," J. Comput. Aided Chem., vol. 22, pp. 17-22, 2021, doi: 10.2751/jcac.22.17.
[16] Nalluri M., Pentela M., and Eluri N. R., "A scalable tree boosting system: XG boost," Int. J. Res. Stud. Sci. Eng. Technol., vol. 7, no. 12, pp. 36-51, Oct. 2020, doi: 10.22259/2349-476X.0712005.
[17] Bento A. P., Hersey A., Félix E., Landrum G., Gaulton A., Atkinson F., Bellis L. J., De Veij M., and Leach A. R., "An open source chemical structure curation pipeline using RDKit," J. Cheminformatics, vol. 12, no. 1, p. 51, Sep. 2020, doi: 10.1186/s13321-020-00456-1.
[18] Sieg J., Feldmann C. W., Hemmerich J., Stork C., Sandfort F., Eiden P., and Mathea M., "MolPipeline: A python package for processing molecules with RDKit in scikit-learn," J. Chem. Inf. Model., vol. 64, no. 24, pp. 9027-9033, Sep. 2024, doi: 10.1021/acs.jcim.4c00987.
[19] Sugimoto M., Manggara A. B., Yoshida K., Inoue T., and Ideo T., "An electronic-structure informatics study on the toxicity of alkylphenols to Tetrahymena pyriformis," Mol. Inf., vol. 39, no. 1-2, p. 1900121, Jan. 2020, doi: 10.1002/minf.201900121.
[20] Ardhana V. Y., Lonang S., Kumoro D. T., and Mulyodiputro M. D., "Benchmarking model machine learning untuk prediksi data berdasarkan akurasi dan error," SainsTech Innovation J., vol. 8, no. 2, pp. 568-577, Nov. 2025, doi: 10.37824/sij.v8i2.2025.1141.
[21] Hajjo R., Sabbah D. A., Sweidan K., and Shattat G., "Structure-guided target prioritization of heterocyclic carboxamides for hyperlipidemia and obesity via cheminformatics, network biology, and docking studies,"Lett. Drug Des. Discovery, p. 100166, Nov. 2025, doi: 10.1016/j.ldd.2025.100166.
[22] Graffelman J. and De Leeuw J., "Improved approximation and visualization of the correlation matrix," Amer.Statistician, vol. 77, no. 4, pp. 432-442, Oct. 2023, doi: 10.1080/00031305.2023.2187654.
[23] Manggara A. B., Ohkawa K., and Sugimoto M., "Classifying modes of toxic action of molecules with electronic-structure informatics. Application to imbalanced toxicity data of phenol derivatives to Tetrahymena pyriformis," Chem. Lett., vol. 50, no. 11, pp. 1887-1891, Nov. 2021, doi: 10.1246/cl.210624.
[24] Yates L. A., Aandahl Z., Richards S. A., and Brook B. W., "Cross validation for model selection: A review with exampdoiles from ecology," Ecol. Monogr., vol. 93, no. 1, p. e1557, Feb. 2023, doi: 10.1002/ecm.1557.
[25] Isah J. J., Uzairu A., Uba S., and Ibrahim M. T., "Machine learning-driven discovery and optimization of PI3Kδ inhibitors for diffuse large B-cell lymphoma," Sci. African, p. e03206, Jan. 2026, doi: 10.1016/j.sciaf.2026.e03206.
[26] Masand V. H., Al-Hussain S., Alzahrani A. Y., Al-Mutairi A. A., Sultan Alqahtani A., Samad A., Alafeefy A. M., Jawarkar R. D., and Zaki M. E., "Unveiling dynamics of nitrogen content and selected nitrogen heterocycles in thrombin inhibitors: A ceteris paribus approach," Expert Opin. Drug Discovery, vol. 19, no. 8, pp. 991-1009, Aug. 2024, doi: 10.1080/17460441.2024.2368743.
[27] Chung Y. K., Lee S. J., Lee J., Cho H., Kim S. J., and Huh J., "Prediction of intrinsic solubility for drug-like organic compounds using automated network optimizer (ANO) for physicochemical feature and hyperparameter optimization," ChemRxiv, Nov. 2024, doi: 10.26434/chemrxiv-2024-mp291.
[28] Sui X., Wang K., Song K., Xu C., Song J., Lee C. W., Liao M., Farese R. V. Jr., and Walther T. C., "Mechanism of action for small-molecule inhibitors of triacylglycerol synthesis," Nat. Commun., vol. 14, no. 1, p. 3100, May 2023, doi: 10.1038/s41467-023-39123-0.
[29] Suresh C. H. and Anila S., "Molecular electrostatic potential topology analysis of noncovalent interactions," Acc. Chem. Res., vol. 56, no. 13, pp. 1884-1895, Jun. 2023, doi: 10.1021/acs.accounts.3c00012.
[30] Miclot T. and Timr S., "Beyond contacts: The important role of the support region in protein complex assembly," Protein Sci., vol. 35, no. 2, p. e70470, Feb. 2026, doi: 10.1002/pro.70470.
[31] Filipski K. J., Edmonds D. J., Garnsey M. R., Smaltz D. J., Coffman K., Futatsugi K., et al., "Design of next- generation DGAT2 inhibitor PF-07202954 with longer predicted half-life," ACS Med. Chem. Lett., vol. 14, no. 10, pp. 1427-1433, 2023, doi: 10.1021/acsmedchemlett.3c00330.
[32] Cao J. and Liu Y., "Multi-objective QSAR prediction of ERα antagonists via SHAP-based interpretation," PLoS ONE, vol. 21, no. 1, p. e0338080, Jan. 2026, doi: 10.1371/journal.pone.0338080.
[33] Singh S., Baker Q. B., and Singh D. B., "Molecular docking and molecular dynamics simulation," in Bioinformatics, Academic Press, 2022, pp. 291-304, doi: 10.1016/B978-0-323-89775-4.00014-6.




DOI: https://doi.org/10.18860/al.v14i1.40626

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Algafari Bakti Manggara

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Kirim NME Creative Commons

This work is licensed under NME Creative Commons Atribusi-NonKomersial-BerbagiSerupa 4.0 Internasional.
ALCHEMY is managed by  http://kimia.uin-malang.ac.id/
© All rights reserved 2016. Alchemy, Journal of Chemistry, eISSN 2460-6871

 

View My Stats