Plant Microbe Interaction-Predicting the Pathogen Internalization Through Stomata Using Computational Neural Network...

Area of Science:

• Plant pathology and food safety
• Computational biology and bioinformatics
• Environmental microbiology

Background:

• Foodborne diseases pose significant public health challenges.
• Plant-pathogen interactions, particularly pathogen entry via stomata, are influenced by environmental factors like humidity and temperature.
• Understanding these interactions is key to preventing foodborne hazards.

Purpose of the Study:

• To develop a computational model using neural networks to predict pathogen internalization via plant stomata.
• To quantitatively assess the influence of environmental factors (humidity, temperature) on pathogen internalization.
• To provide a novel approach for understanding plant-microbe interactions in the context of food safety.

Main Methods:

• Utilized computational modeling with neural networks to simulate and predict pathogen internalization.
• Assessed internalization likelihood and duration for bacterial pathogens, specifically Salmonella enterica (S. enterica).
• Analyzed the impact of varying humidity levels (50% and 100%) on internalization parameters.

Main Results:

• Pathogen internalization likelihood ranged from 0.6200 to 0.8820.
• Internalization time varied between 4000 s and 5080 s.
• A 100% humidity level resulted in approximately 1042.73 s shorter internalization time and a 26.2% increase in internalization likelihood compared to 50% humidity.

Conclusions:

• The developed neural network model effectively predicts pathogen internalization via stomata.
• Environmental conditions, especially humidity, significantly impact the rate and likelihood of pathogen entry into plants.
• This research offers a technologically advanced strategy for understanding and mitigating foodborne illness risks.