Machine Learning-Based Software for Predicting <i>Pseudomonas</i> spp. Growth Dynamics in Culture Media

In predictive microbiology, both primary and secondary models are widely used to estimate microbial growth, often applied through two-step or one-step modelling approaches. This study focused on developing a tool to predict the growth of <i>Pseudomonas</i> spp., a prominent bacterial gen...

Full description

Saved in:
Bibliographic Details
Main Author: Fatih Tarlak
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Life
Subjects:
Online Access:https://www.mdpi.com/2075-1729/14/11/1490
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850226835013500928
author Fatih Tarlak
author_facet Fatih Tarlak
author_sort Fatih Tarlak
collection DOAJ
description In predictive microbiology, both primary and secondary models are widely used to estimate microbial growth, often applied through two-step or one-step modelling approaches. This study focused on developing a tool to predict the growth of <i>Pseudomonas</i> spp., a prominent bacterial genus in food spoilage, by applying machine learning regression models, including Support Vector Regression (SVR), Random Forest Regression (RFR) and Gaussian Process Regression (GPR). The key environmental factors—temperature, water activity, and pH—served as predictor variables to model the growth of <i>Pseudomonas</i> spp. in culture media. To assess model performance, these machine learning approaches were compared with traditional models, namely the Gompertz, Logistic, Baranyi, and Huang models, using statistical indicators such as the adjusted coefficient of determination (R<sup>2</sup><sub>adj</sub>) and root mean square error (RMSE). Machine learning models provided superior accuracy over traditional approaches, with R<sup>2</sup><sub>adj</sub> values from 0.834 to 0.959 and RMSE values between 0.005 and 0.010, showcasing their ability to handle complex growth patterns more effectively. GPR emerged as the most accurate model for both training and testing datasets. In external validation, additional statistical indices (bias factor, <i>B</i><sub>f</sub>: 0.998 to 1.047; accuracy factor, <i>A</i><sub>f</sub>: 1.100 to 1.167) further supported GPR as a reliable alternative for microbial growth prediction. This machine learning-driven approach bypasses the need for the secondary modelling step required in traditional methods, highlighting its potential as a robust tool in predictive microbiology.
format Article
id doaj-art-3418a75baf164a4aa35c521659973d65
institution OA Journals
issn 2075-1729
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Life
spelling doaj-art-3418a75baf164a4aa35c521659973d652025-08-20T02:04:58ZengMDPI AGLife2075-17292024-11-011411149010.3390/life14111490Machine Learning-Based Software for Predicting <i>Pseudomonas</i> spp. Growth Dynamics in Culture MediaFatih Tarlak0Department of Bioengineering, Gebze Technical University, Gebze 41400, Kocaeli, TurkeyIn predictive microbiology, both primary and secondary models are widely used to estimate microbial growth, often applied through two-step or one-step modelling approaches. This study focused on developing a tool to predict the growth of <i>Pseudomonas</i> spp., a prominent bacterial genus in food spoilage, by applying machine learning regression models, including Support Vector Regression (SVR), Random Forest Regression (RFR) and Gaussian Process Regression (GPR). The key environmental factors—temperature, water activity, and pH—served as predictor variables to model the growth of <i>Pseudomonas</i> spp. in culture media. To assess model performance, these machine learning approaches were compared with traditional models, namely the Gompertz, Logistic, Baranyi, and Huang models, using statistical indicators such as the adjusted coefficient of determination (R<sup>2</sup><sub>adj</sub>) and root mean square error (RMSE). Machine learning models provided superior accuracy over traditional approaches, with R<sup>2</sup><sub>adj</sub> values from 0.834 to 0.959 and RMSE values between 0.005 and 0.010, showcasing their ability to handle complex growth patterns more effectively. GPR emerged as the most accurate model for both training and testing datasets. In external validation, additional statistical indices (bias factor, <i>B</i><sub>f</sub>: 0.998 to 1.047; accuracy factor, <i>A</i><sub>f</sub>: 1.100 to 1.167) further supported GPR as a reliable alternative for microbial growth prediction. This machine learning-driven approach bypasses the need for the secondary modelling step required in traditional methods, highlighting its potential as a robust tool in predictive microbiology.https://www.mdpi.com/2075-1729/14/11/1490software development<i>Pseudomonas</i> spp.machine learningtraditional modelling
spellingShingle Fatih Tarlak
Machine Learning-Based Software for Predicting <i>Pseudomonas</i> spp. Growth Dynamics in Culture Media
Life
software development
<i>Pseudomonas</i> spp.
machine learning
traditional modelling
title Machine Learning-Based Software for Predicting <i>Pseudomonas</i> spp. Growth Dynamics in Culture Media
title_full Machine Learning-Based Software for Predicting <i>Pseudomonas</i> spp. Growth Dynamics in Culture Media
title_fullStr Machine Learning-Based Software for Predicting <i>Pseudomonas</i> spp. Growth Dynamics in Culture Media
title_full_unstemmed Machine Learning-Based Software for Predicting <i>Pseudomonas</i> spp. Growth Dynamics in Culture Media
title_short Machine Learning-Based Software for Predicting <i>Pseudomonas</i> spp. Growth Dynamics in Culture Media
title_sort machine learning based software for predicting i pseudomonas i spp growth dynamics in culture media
topic software development
<i>Pseudomonas</i> spp.
machine learning
traditional modelling
url https://www.mdpi.com/2075-1729/14/11/1490
work_keys_str_mv AT fatihtarlak machinelearningbasedsoftwareforpredictingipseudomonasisppgrowthdynamicsinculturemedia