Microbial communities are constantly exposed to the invasion of exogenous species, which can significantly modify their composition and function. The capacity of a microbial community to resist invasion is regarded as an emergent property emerging from the complex interactions among its constituent species.

The ability to predict and modify the colonization outcomes (i.e., prevent the engraftment of pathogens and promote the engraftment of probiotics) is crucial for personalized microbiota-based interventions in nutrition and medicine.

Despite the accumulating empirical studies, predicting the colonization outcomes in complex communities, remains a fundamental challenge due to limited knowledge of interspecies interactions.

Recently, a research team led by Prof. DAI Lei from the Shenzhen Institute of Advanced Technology (SIAT) of the Chinese Academy of Sciences, together with collaborators, developed a data-driven approach that is independent of any dynamics model to predict colonization outcomes of exogenous species, for complex microbial communities without detailed knowledge of the underlying ecological and biochemical process.

The study was published in Nature Communications on Mar. 16.

In this study, the researchers systematically evaluated the proposed data-driven approach by employing synthetic data generated from classical ecological dynamical models and in vitro human stool-derived microbial communities. They found that, given a sufficient sample size in training data (on the order of ~O(N)), the colonization outcomes (i.e., whether an exogenous species can establish and what its abundance would be if it can establish) can be predicted through machine learning models.

Subsequently, the researchers generated large-scale datasets with in vitro experimental outcomes of two representative species colonizing human stool-derived microbial communities. They validated that machine-learning models can also predict colonization outcomes in experiments (AUROC > 0.8).

Furthermore, the researchers employed machine learning models to infer species with significant colonization impacts and empirically demonstrated that the introduction of highly interacting species can substantially modify colonization outcomes.

“Our results show that the colonization outcome of complex microbial communities can be predicted via data-driven approaches and tunable,” said Prof. DAI.  

“Data-driven methodologies are powerful tools for biologists. In conjunction with advancements in predicting the characteristics of complex biomolecules, I anticipate that this approach will precipitate a paradigm shift in studying the stability and function of intricate ecological systems and facilitate significant applications in healthcare and agriculture,” DAI added.

Data-driven prediction of colonization outcomes for complex microbial communities (Image by SIAT)

Media Contact: LU Qun

Email: qun.lu@siat.ac.cn

Download the attachment：

Data-driven prediction of colonization outcomes for complex microbial communities