Michel-Mata Sebastian, Wang Xu-Wen, Liu Yang-Yu, Angulo Marco Tulio
Center for Applied Physics and Advanced Technology, Universidad Nacional Autónoma de México, Juriquilla 76230, México.
Department of Ecology and Evolutionary Biology, Princeton University, Princeton, NJ 08544, USA.
Imeta. 2022 Mar;1(1). doi: 10.1002/imt2.3. Epub 2022 Mar 1.
Microbes can form complex communities that perform critical functions in maintaining the integrity of their environment or their hosts' well-being. Rationally managing these microbial communities requires improving our ability to predict how different species assemblages affect the final species composition of the community. However, making such a prediction remains challenging because of our limited knowledge of the diverse physical, biochemical, and ecological processes governing microbial dynamics. To overcome this challenge, we present a deep learning framework that automatically learns the map between species assemblages and community compositions from training data only, without knowing any of the above processes. First, we systematically validate our framework using synthetic data generated by classical population dynamics models. Then, we apply our framework to data from and microbial communities, including ocean and soil microbiota, gut microbiota, and human gut and oral microbiota. We find that our framework learns to perform accurate out-of-sample predictions of complex community compositions from a small number of training samples. Our results demonstrate how deep learning can enable us to understand better and potentially manage complex microbial communities.
微生物能够形成复杂的群落，这些群落在维持其生存环境的完整性或宿主的健康方面发挥着关键作用。合理管理这些微生物群落需要提高我们预测不同物种组合如何影响群落最终物种组成的能力。然而，由于我们对控制微生物动态的各种物理、生化和生态过程的了解有限，做出这样的预测仍然具有挑战性。为了克服这一挑战，我们提出了一个深度学习框架，该框架仅从训练数据中自动学习物种组合与群落组成之间的映射关系，而无需了解上述任何过程。首先，我们使用经典种群动态模型生成的合成数据系统地验证了我们的框架。然后，我们将我们的框架应用于来自海洋和土壤微生物群、肠道微生物群以及人类肠道和口腔微生物群等微生物群落的数据。我们发现，我们的框架能够从少量训练样本中学习，对复杂的群落组成进行准确的样本外预测。我们的结果证明了深度学习如何使我们能够更好地理解并有可能管理复杂的微生物群落。
