Gradient boosted regression as a tool to reveal key drivers of temporal dynamics in a synthetic yeast community

• DOI: 10.1093/femsec/fiae080
• Publication Date: 2024-05-23T01:52:43Z
• Authors: Cleo Gertrud Cona...; Bruce William Watson; Florian Franz Bauer
• Keywords: Torulaspora delbrueckii; Dynamics; Community

Microbial communities are vital to our lives, yet their ecological functioning and dynamics remain poorly understood. This understanding is crucial for assessing threats these systems leveraging biotechnological applications. Given that temporal linked community functioning, this study investigated the drivers of succession in wine yeast community. We experimentally generated population data used it create an interpretable model with a gradient boosted regression tree approach. The was trained on viable species populations various combinations, including pairs, triplets, quadruplets, evaluated predictive accuracy input feature importance. Key findings revealed inoculation dosage non-Saccharomyces significantly influences performance mixed cultures, while Saccharomyces cerevisiae consistently dominates regardless initial abundance. Additionally, we observed multispecies interactions where Wickerhamomyces anomalus were influenced by Torulaspora delbrueckii pairwise but interaction altered inclusion S. cerevisiae. provides insights into offers valuable machine learning-based analysis techniques applicable other microbial communities, opening new avenues harnessing communities.