MOLECULAR DESCRIPTOR-BASED ASSESSMENT OF CANDIDATE SIRTUIN6 INHIBITORS
Deprecated: htmlspecialchars(): Passing null to parameter #1 ($string) of type string is deprecated in /var/www/html/lib/pkp/lib/vendor/smarty/smarty/libs/plugins/modifier.escape.php on line 36
DOI:
https://doi.org/10.53555/b.v1i2.2599Keywords:
Sirtuin6, Molecular descriptors, Machine learning, Bioinformatics, Drug discoveryAbstract
Sirtuin6 (SIRT6) is an important nicotinamide adenine dinucleotide (NAD⁺)-dependent enzyme involved in regulating DNA repair, metabolism, inflammation, and aging, making it an attractive therapeutic target for drug discovery. This study aimed to assess candidate Sirtuin6 inhibitors using molecular descriptor analysis and supervised machine-learning techniques. A publicly available dataset comprising 100 candidate compounds described by six molecular descriptors and classified into High_BFE and Low_BFE binding free-energy groups was analyzed. Data preprocessing confirmed the absence of missing values and a balanced class distribution. Exploratory statistical analysis, correlation assessment, and comparative descriptor evaluation were performed before developing multiple classification models, including logistic regression, support vector machine, random forest, k-nearest neighbours, and gradient boosting. Model performance was evaluated using five-fold cross-validation with accuracy, precision, recall, F1-score, and receiver operating characteristic area under the curve (ROC-AUC). The results demonstrated that molecular descriptors effectively differentiated candidate compounds, while all machine-learning models achieved satisfactory predictive performance. Gradient boosting produced the highest ROC-AUC, indicating superior classification capability for identifying candidate inhibitors. Overall, the findings demonstrate that molecular descriptor-based computational assessment provides an efficient and reproducible strategy for prioritizing potential Sirtuin6 inhibitors and supports bioinformatics-driven drug discovery and early-stage lead optimization.
References
Tardu, M., Rahim, F., Halil Kavakli, I., & Turkay, M. (2016). Milp-hyperbox classification for structure-based drug design in the discovery of small molecule inhibitors of sirtuin6. RAIRO-Operations Research, 50(2), 387-400.
Parenti, M. D., Grozio, A., Bauer, I., Galeno, L., Damonte, P., Millo, E., ... & Nencioni, A. (2014). Discovery of novel and selective SIRT6 inhibitors. Journal of medicinal chemistry, 57(11), 4796-4804.
Zhang, Q., Chen, Y., Ni, D., Huang, Z., Wei, J., Feng, L., ... & Zhang, J. (2022). Targeting a cryptic allosteric site of SIRT6 with small-molecule inhibitors that inhibit the migration of pancreatic cancer cells. Acta Pharmaceutica Sinica B, 12(2), 876-889.
Liu, J., & Zheng, W. (2016). Cyclic peptide-based potent human SIRT6 inhibitors. Organic & Biomolecular Chemistry, 14(25), 5928-5935.
Sociali, G., Liessi, N., Grozio, A., Caffa, I., Parenti, M. D., Ravera, S., ... & Bruzzone, S. (2020). Differential modulation of SIRT6 deacetylase and deacylase activities by lysine-based small molecules. Molecular diversity, 24(3), 655-671.
Li, Y., You, L., Huang, W., Liu, J., Zhu, H., & He, B. (2015). A FRET-based assay for screening SIRT6 modulators. European Journal of Medicinal Chemistry, 96, 245-249.
Rahnasto-Rilla, M., Tyni, J., Huovinen, M., Jarho, E., Kulikowicz, T., Ravichandran, S., ... & Moaddel, R. (2018). Natural polyphenols as sirtuin 6 modulators. Scientific reports, 8(1), 4163.
You, W., Zheng, W., Weiss, S., Chua, K. F., & Steegborn, C. (2019). Structural basis for the activation and inhibition of Sirtuin 6 by quercetin and its derivatives. Scientific Reports, 9(1), 19176.
You, W., Rotili, D., Li, T. M., Kambach, C., Meleshin, M., Schutkowski, M., ... & Steegborn, C. (2017). Structural basis of sirtuin 6 activation by synthetic small molecules. Angewandte Chemie International Edition, 56(4), 1007-1011.
Huang, Z., Zhao, J., Deng, W., Chen, Y., Shang, J., Song, K., ... & Zhang, J. (2018). Identification of a cellularly active SIRT6 allosteric activator. Nature chemical biology, 14(12), 1118-1126.
Klein, M. A., Liu, C., Kuznetsov, V. I., Feltenberger, J. B., Tang, W., & Denu, J. M. (2020). Mechanism of activation for the sirtuin 6 protein deacylase. Journal of Biological Chemistry, 295(5), 1385-1399.
Lu, S., Chen, Y., Wei, J., Zhao, M., Ni, D., He, X., & Zhang, J. (2021). Mechanism of allosteric activation of SIRT6 revealed by the action of rationally designed activators. Acta Pharmaceutica Sinica B, 11(5), 1355-1361.
Pan, P. W., Feldman, J. L., Devries, M. K., Dong, A., Edwards, A. M., & Denu, J. M. (2011). Structure and biochemical functions of SIRT6. Journal of Biological Chemistry, 286(16), 14575-14587.
He, T., Shang, J., Gao, C., Guan, X., Chen, Y., Zhu, L., ... & Pang, T. (2021). A novel SIRT6 activator ameliorates neuroinflammation and ischemic brain injury via EZH2/FOXC1 axis. Acta Pharmaceutica Sinica B, 11(3), 708-726.
Zhang, Z., Sun, W., Zhang, G., Fang, Z., Chen, X., & Li, L. (2023). Design, synthesis, and biological screening of a series of pyrazolo [1, 5-a] quina-zoline derivatives as SIRT6 activators. European Journal of Pharmaceutical Sciences, 185, 106424.
Kokkonen, P., Rahnasto-Rilla, M., Mellini, P., Jarho, E., Lahtela-Kakkonen, M., & Kokkola, T. (2014). Studying SIRT6 regulation using H3K56 based substrate and small molecules. European Journal of Pharmaceutical Sciences, 63, 71-76.
Yap, C. W. (2011). PaDEL‐descriptor: An open source software to calculate molecular descriptors and fingerprints. Journal of computational chemistry, 32(7), 1466-1474.
Moriwaki, H., Tian, Y. S., Kawashita, N., & Takagi, T. (2018). Mordred: a molecular descriptor calculator. Journal of cheminformatics, 10(1), 4.
Vyas, R., Bapat, S., Jain, E., S. Tambe, S., Karthikeyan, M., & D. Kulkarni, B. (2015). A study of applications of machine learning based classification methods for virtual screening of lead molecules. Combinatorial Chemistry & High Throughput Screening, 18(7), 658-672.
Ahamed, T. S., Rajan, V. K., Sabira, K., & Muraleedharan, K. (2018). QSAR classification-based virtual screening followed by molecular docking studies for identification of potential inhibitors of 5-lipoxygenase. Computational Biology and Chemistry, 77, 154-166.
Fang, X., Bagui, S., & Bagui, S. (2017). Improving virtual screening predictive accuracy of Human kallikrein 5 inhibitors using machine learning models. Computational Biology and Chemistry, 69, 110-119.
Grimm, M., Liu, Y., Yang, X., Bu, C., Xiao, Z., & Cao, Y. (2020). LigMate: a multifeature integration algorithm for ligand-similarity-based virtual screening. Journal of Chemical Information and Modeling, 60(12), 6044-6053.
Bonanno, E., & Ebejer, J. P. (2020). Applying machine learning to ultrafast shape recognition in ligand-based virtual screening. Frontiers in pharmacology, 10, 1675.
Chang, H., Zhang, Z., Tian, J., Bai, T., Xiao, Z., Wang, D., ... & Li, C. (2024). Machine learning-based virtual screening and identification of the fourth-generation EGFR inhibitors. ACS omega, 9(2), 2314.
