17th International Conference on Fundamental and Applied Aspects of Physical Chemistry (Proceedings, Volume II) (2024) [K-24-P, pp. 535-538]
AUTHOR(S) / АУТОР(И): Branislav Stanković 
and Filip Marinković
Download Full Pdf 
DOI: 10.46793/Phys.Chem24II.535S
ABSTRACT / САЖЕТАК:
Nitroaromatic compounds (NACs) are omnipresent and pervasive organic pollutants. Here, we aim to design transparent, interpretable, reproducible, and publicly available methodologies for deriving quantitative structure-activity relationship models and testing them by modeling the mutagenicity of NACs against the Salmonella typhimurium TA100 strain.
Selection of molecular descriptors are performed using a genetic, Boruta, Featurewiz, and ForwardSelector algorithm. Modelling utilizes the multiple linear regression method. The models are ranked by the Multi-Criteria Decision Making procedure. Our findings reveal that Featurewiz showing a slight advantage over Boruta and ForwardSelector and significantly outperforms genetic algorithm. Constructed models can serve as valuable tools for the quick and reliable prediction of NACs mutagenicity.
KEYWORDS / КЉУЧНЕ РЕЧИ:
ACKNOWLEDGEMENT / ПРОЈЕКАТ:
This work was supported by the Ministry of Education, Science and Technological Development of the Republic of Serbia (grants no No. 451-03-66/2024-03/200017 and 451-03-66/2024-03/ 200162).
REFERENCES / ЛИТЕРАТУРА:
- C. L. Zhang, Y. Y. Yu, Z. Fang, S. Naraginti, Y. H. Zhang, Y. C. Yong, Process. Biochem., 70 (2018) 129.
- J. Tiwari, P. Tarale, S. Sivanesan, A. Bafana, Environ. Sci. Pollut. Res., 26 (2019) 28650.
- P. Kovacic, R. Somanathan, J. Appl. Toxicol., 34 (2014) 810.
- Organization for Economic Co-Operation and Development – Guidance Document on the Validation of (Q)SAR Models (2007).