Application of artificial neural networks to prediction of new substances with antimicrobial activity againstEscherichia coli

Aims This article presents models of artificial neural networks (ANN) employed to predict the biological activity of chemical compounds based of their structure. Regression and classification models were designed to determine antimicrobial properties of quaternary ammonium salts againstEscherichia colistrain. Methods and Results The minimum inhibitory concentration microbial growthE. coliwas experimentally determined by the serial dilution method for a series of 140 imidazole derivatives. Then, three-dimensional models for imidazole chlorides were constructed with computational chemistry methods which allowed to calculate molecular descriptors. The transformation of chemical information into a useful number is a main result of this operation. The designed regression and classification ANN models were characterized by a high predictive ability (classification accuracy was 95%, regression model: learning setR = 0.87, testing setR = 0.91, validation setR = 0.89). Conclusions Artificial neural networks can be successfully used to find potential antimicrobial preparations. Significance and Impact of the Study The neural networks are a very elaborate modelling technique, which allows not only to optimize and minimize labour costs but also to increase food safety.

Automated summary

This study successfully used artificial neural networks to predict the biological activity of chemical compounds, with regression and classification models showing high predictive accuracy in determining antimicrobial properties. Three-dimensional models constructed with computational chemistry methods allowed the transformation of chemical information into useful numerical values, increasing experimental efficiency.