Title

Machine learning for predicting antimicrobial efficacy of periodontal gel formulations in vitro biofilm models

Authors

Rohitkumar R Thakkar¹*, Nirma Yadav², Anand Kumar³, Shilpa Duseja⁴, Sunny Mavi⁵ & Udipta Sahoo⁶

Affiliation

¹Department of Periodontology, Siddhpur Dental College and Hospital, Siddhpur – 384151, Gujarat, India; ²Department of Dentistry, Maa Vindhyawasini Autonomous State Medical College, Mirzapur, Uttar Pradesh, India; ³Department of Dentistry, Moti Lal Nehru Medical College, Prayagraj, Uttar Pradesh, India; ⁴Department of Periodontology, Narsinhbhai Patel Dental College and Hospital, Sankalchand Patel University, Visnagar, India; ⁵Department of Periodontics, Sudha Rustagi College of Dental Sciences and Research, Faridabad, Haryana, India; ⁶Department of Periodontics, Kalinga Institute of Dental Sciences, KIIT (Deemed to be university), Patia, Bhubaneswar, Odisha, India; *Corresponding author

Email

Rohitkumar R Thakkar - E- mail: drrohitperio@gmail.com
Nirma Yadav - E- mail: nirmay90@gmail.com
Anand Kumar - E- mail: anandkmr901@gmail.com
Shilpa Duseja - E- mail: budhirajashilpa@gmail.com
Sunny Mavi - E- mail: snnymavi@gmail.com
Udipta Sahoo - E- mail: sahooudipta2000@gmail.com

Article Type

Research Article

Date

Received October 1, 2025; Revised October 31, 2025; Accepted October 31, 2025, Published October 31, 2025

Abstract

Periodontal disease caused by dysbiotic biofilms poses a major challenge and predicting the efficacy of topical antimicrobial gels is limited by biofilm resistance and resource-intensive in vitro testing. Therefore, it is of interest to develop machine learning (ML) models to predict antimicrobial efficacy of novel gel formulations against multi-species periodontal biofilms. Hence, a total of 120 formulations with varying polymers, agents, concentrations and enhancers were tested using the Calgary Biofilm Device and efficacy data were used to train Random Forest, SVM, Gradient Boosting and Neural Network models. Gradient Boosting achieved the best performance (accuracy 92.8%, AUC-ROC 0.96), with antimicrobial type, concentration and polymer viscosity as key predictors. ML, particularly Gradient Boosting, offers a reliable tool for predicting periodontal gel efficacy, enabling faster formulation optimization and reducing the need for extensive laboratory screening.

Keywords

Machine learning, periodontal gel, antimicrobial efficacy, biofilm, prediction model, drug formulation, chlorhexidine, chitosan.

Citation

Thakkar et al. Bioinformation 21(10): 3866-3870 (2025)

Edited by

Hiroj Bagde

ISSN

0973-2063

Publisher

Biomedical Informatics

License

This is an Open Access article which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. This is distributed under the terms of the Creative Commons Attribution License.