MediaMatch : Prediction of Bacterial Growth on Different Culture Media Using the XGBoost Algorithm

2025/10/01 by Jianhan Liu, Guoshun Xu, W. Liu +9 · 1 voice
Biochemistry, Genetics and Molecular Biology · #Genomics and Phylogenetic Studies #Gene expression and cancer classification #Machine Learning in Bioinformatics

paper · pdf · doi:10.1111/1751-7915.70245

openalex publication_date 2025/10/01 · openalex created_date 2025/10/05 · openalex updated_date 2026/07/23

Abstract

Microorganism culturing is essential in microbiological research, with the selection of suitable culture media being critical for successful microbial growth. Traditionally, this selection has relied on empirical knowledge or trial and error, often resulting in inefficiency. In this study, we analysed nutrient compositions from the MediaDive database to construct a dataset of 2369 media types. Leveraging this dataset and microbial 16S rRNA sequences, we developed 45 binary classification models using the XGBoost algorithm. These models demonstrated strong predictive performance, achieving accuracies ranging from 76% to 99.3%, with the top-performing models for J386, J50 and J66 media reaching 99.3%, 98.9% and 98.8%, respectively. The models effectively predicted growth conditions for various human gut microbes, confirming their practical utility. This research improves the efficiency of microbial cultivation and highlights the potential of machine learning to optimise culture media selection and advance microbiological studies.

Citations

• Nearest neighbor pattern classification
• 16S rRNA Gene Sequencing for Bacterial Identification in the Diagnostic Laboratory: Pluses, Perils, and Pitfalls
• Present and Future of Culturing Bacteria
• The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation
• Machine Learning Testing: Survey, Landscapes and Horizons

Discussions

• #MicroSky: Using 2,369 media types and microbial 16S rRNA sequences, Liu et al built 45 XGBoost-based binary classification models with accuracies from 76% to 99.3%. These models reliably predict grow [bsky, 3 points, 1 comments]

Related

• Applications of machine Learning to improve the efficiency and range of microbial biosynthesis: a review of state-of-art techniques
• A toolbox of machine learning software to support microbiome analysis
• Transformer-based Prediction of Microbial Growth Rates from Genomic Data
• Advancing microbiome research with machine learning: key findings from the ML4Microbiome COST action
• Machine Learning Reveals Quantitative Amino Acid Preferences in Bifidobacterium longum Growth