EUVIMEDEUVIMED entdecken
Übersichtsarbeit

Machine Learning Applications in Predicting Microbial Interactions

Md Jasim Uddin, Samiha Binte Sadiq, Nayla Nuren Snigdha, Redea Sultana Sinthea, Jubaida Yeasmin Suchi, Israt Jahan Anamika

Advances in Experimental Medicine and Biology · 2026 · 169-212

DOI: 10.1007/978-981-92-0010-8_7 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Advances in Experimental Medicine and Biology, online erschienen am 02.07.2026. Verfasst von Md Jasim Uddin und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmaceutical Technology, Faculty of Pharmacy, Universiti Malaya, Kuala Lumpur, Malaysia. j.uddin@um.edu.my. Hauptthemen laut MEDLINE: Machine Learning, Microbial Interactions, Microbiota, Bacteria. Die Arbeit nennt 126 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Health, the course of disease and treatment results are all significantly impacted by microbial interactions. However, it is challenging to examine the behaviour of microbial communities using conventional methods due to their complexity and diversity. A strong framework for identifying patterns in sizable and intricate biological datasets is provided by machine learning (ML). The use of machine learning (ML) to forecast microbial activity and comprehend how microbial populations react to drugs and other external factors is examined in this chapter. Microbiological data analysis has made extensive use of popular machine learning techniques like support vector machines, random forests and neural networks. These methods enable prediction of interspecies interactions, identification of metabolic interdependencies and classification of microbial taxa. ML models may also identify minute differences in microbial responses that affect treatment results by combining genomic, transcriptomic and metabolomic datasets. For instance, multi-omics integration can enhance predictions of microbial behaviour under stress through linking changes in gene expression with metabolite profiles. The chapter also covers how drug-induced dysbiosis, a disruption of the microbial balance brought on by medications, can be predicted using machine learning. ML techniques can identify possible changes in the composition of the microbiome and evaluate susceptibility to dysbiosis. The creation of therapeutic and preventative measures can be influenced by these forecasts. Together, these applications show how machine learning (ML) enhances drug-microbe interaction predictions, expands our knowledge of microbial dynamics and promotes precision medicine in microbiome and pharmaceutical research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningMicrobial InteractionsMicrobiotaBacteriaHumansPredictive Learning ModelsMultiomicsRandom ForestPrediction AlgorithmsDysbiosisSupport Vector MachineAnimalsSoft ComputingClassification Algorithms

Stichwörter der Autor:innen

Artificial IntelligenceDrug-microbe interaction predictionGenomicsMachine LearningMetabolomicsMicrobial interactionsTranscriptomics

Autor:innen und Institutionen

  • Department of Pharmaceutical Technology, Faculty of Pharmacy, Universiti Malaya, Kuala Lumpur, Malaysia. j.uddin@um.edu.my.
  • Drug Delivery & Therapeutics Lab, Dhaka, Bangladesh.

Zitieren

APA

Uddin, M. J., Sadiq, S. B., Snigdha, N. N., Sinthea, R. S., Suchi, J. Y., & Anamika, I. J. (2026). Machine Learning Applications in Predicting Microbial Interactions. Advances in Experimental Medicine and Biology, 169-212. https://doi.org/10.1007/978-981-92-0010-8_7

Vancouver

Uddin MJ, Sadiq SB, Snigdha NN, Sinthea RS, Suchi JY, Anamika IJ. Machine Learning Applications in Predicting Microbial Interactions. Advances in Experimental Medicine and Biology. 2026:169-212. doi:10.1007/978-981-92-0010-8_7

BibTeX
@article{Uddin2026,
  author = {Uddin, Md Jasim and Sadiq, Samiha Binte and Snigdha, Nayla Nuren and Sinthea, Redea Sultana and Suchi, Jubaida Yeasmin and Anamika, Israt Jahan},
  title = {Machine Learning Applications in Predicting Microbial Interactions},
  journal = {Advances in Experimental Medicine and Biology},
  year = {2026},
  pages = {169--212},
  doi = {10.1007/978-981-92-0010-8_7}
}
Kostenlos starten →