Machine learning-based approach for efficient prediction of toxicity of chemical gases using feature selection

• Published in: Journal of hazardous materials Vol. 455; p. 131616
• Main Authors: Erturan, Ahmet Murat, Karaduman, Gül, Durmaz, Habibe
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 05-08-2023
• Subjects: Algorithms; Amides; Bayes Theorem; Chemical Agents; Gases - toxicity; Machine Learning; Organophosphates (OPs); QSAR; Toxic gases; United States; United States; Toxic gases; QSAR; Machine Learning; Chemical Agents; Organophosphates (OPs)
• ISSN: 0304-3894; 1873-3336
• DOI: 10.1016/j.jhazmat.2023.131616

Toxic gases can be fatal as they damage many living tissues, especially the nervous and respiratory systems. They can cause permanent damage for many years by harming environmental tissue and living organisms. They can also cause mass deaths when used as chemical weapons. These chemical agents consist of organophosphates, namely ester, amide, or thiol derivatives of phosphorus, phosphonic or phosphinic acids, or can be synthesized independently. In this study, machine learning models were used to predict the toxicity of chemical gases. Toxic and non-toxic gases, consisting of 144 gases, were identified according to the United States Environmental Protection Agency, Occupational Safety and Health Administration, and the Centers for Disease Control and Prevention. Six machine-learning models were used to predict the toxicity of these chemical gases. The performance of the models was verified through internal and external validation. The results showed that the model's internal validation accuracy was 86.96% with the Relief-J48 algorithm. The accuracy value of the model was 89.65% with the Bayes Net algorithm for external validation. Our results reveal that identifying the toxicity of existing and potential chemicals is essential for the early detection of these chemicals in nature.
[Display omitted]
•The structure-activity relationship of the compounds consisting of 144 chemical gases was investigated.•Six optimum binary classification models were developed.•The models created for classifying and predicting chemical gases have shown promising results.•With these models, toxic gases will be detected without any safety and health problems.