Revolutionizing microbial classification: leveraging machine learning for enhanced classification with feature-based data.
Saved in:
| Title: | Revolutionizing microbial classification: leveraging machine learning for enhanced classification with feature-based data. |
|---|---|
| Authors: | Bekhet, Saddam1 (AUTHOR) saddam.bekhet@svu.edu.eg, Alsheref, Fahad K.2 (AUTHOR) drfahad@fcis.bsu.edu.eg, AbdelAziz, Amr M.2 (AUTHOR) amraziz@fcis.bsu.edu.eg, Alshazly, Hammam3 (AUTHOR) ha.alshazly@svu.edu.eg |
| Source: | Multimedia Tools & Applications. Nov2025, Vol. 84 Issue 36, p45041-45060. 20p. |
| Subjects: | Machine learning, Bacteria classification, Model validation, Quantitative research, Software frameworks, Medical technology, Data quality, Biotechnology |
| Abstract: | This paper presents a comprehensive machine learning (ML)-based framework for microbial classification, addressing the growing need for scalable, accurate, and low-resource alternatives to traditional manual methods. Given the critical role of microbes across domains such as environmental monitoring, biotechnology, and healthcare, efficient classification methods are essential for advancing both scientific understanding and practical applications. Traditional manual microbial classification methods are labor-intensive, time-consuming, and hinder scalability. In response, this research proposes a comprehensive and systematic comparative framework evaluating large number of ML algorithms to identify their relative strengths and weaknesses in microbial classification tasks. The framework leverages a large-scale, feature-based dataset comprising over 21k samples, avoiding the high computational costs associated with image-based data acquisition and processing. Extensive hyperparameter tuning, model validation, and rigorous statistical assessments were conducted to ensure robustness and prevent over-fitting. Notably, more than five different classifiers achieved accuracy exceeding 90%, with the best-performing reaching 97.4% accuracy. Furthermore, by prioritizing biologically meaningful features, this work provides a scalable and effective computational approach to microbial trait analysis. To the best of our knowledge, this is the first study to conduct such a broad and rigorous evaluation of ML models for microbial classification, offering valuable insights for both computer science and microbiology communities, and paving the way for more efficient, data-driven approaches in microbial research and medicinal development. [ABSTRACT FROM AUTHOR] |
| Copyright of Multimedia Tools & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | This paper presents a comprehensive machine learning (ML)-based framework for microbial classification, addressing the growing need for scalable, accurate, and low-resource alternatives to traditional manual methods. Given the critical role of microbes across domains such as environmental monitoring, biotechnology, and healthcare, efficient classification methods are essential for advancing both scientific understanding and practical applications. Traditional manual microbial classification methods are labor-intensive, time-consuming, and hinder scalability. In response, this research proposes a comprehensive and systematic comparative framework evaluating large number of ML algorithms to identify their relative strengths and weaknesses in microbial classification tasks. The framework leverages a large-scale, feature-based dataset comprising over 21k samples, avoiding the high computational costs associated with image-based data acquisition and processing. Extensive hyperparameter tuning, model validation, and rigorous statistical assessments were conducted to ensure robustness and prevent over-fitting. Notably, more than five different classifiers achieved accuracy exceeding 90%, with the best-performing reaching 97.4% accuracy. Furthermore, by prioritizing biologically meaningful features, this work provides a scalable and effective computational approach to microbial trait analysis. To the best of our knowledge, this is the first study to conduct such a broad and rigorous evaluation of ML models for microbial classification, offering valuable insights for both computer science and microbiology communities, and paving the way for more efficient, data-driven approaches in microbial research and medicinal development. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 13807501 |
| DOI: | 10.1007/s11042-025-20933-9 |
