Autoencoder neural networks enable low dimensional structure analyses of microbial growth dynamics

The ability to effectively represent microbiome dynamics is a crucial challenge in their quantitative analysis and engineering. By using autoencoder neural networks, we show that microbial growth dynamics can be compressed into low-dimensional representations and reconstructed with high fidelity. These low-dimensional embeddings are just as effective, if not better, than raw data for tasks such as identifying bacterial strains, predicting traits like antibiotic resistance, and predicting community dynamics. Additionally, we demonstrate that essential dynamical information of these systems can be captured using far fewer variables than traditional mechanistic models. Our work suggests that machine learning can enable the creation of concise representations of high-dimensional microbiome dynamics to facilitate data analysis and gain new biological insights.

• Publication year

  2023

• Venue

  Nature Communications

• Publication date

  2023-12-01

• Fields of study

  Biology, Medicine, Computer Science, Environmental Science

• Identifiers
  DOI 10.1038/s41467-023-43455-0PMID 38049401PMCID 10696002
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Autoencoder neural networks enable low dimensional structure analyses of microbial growth dynamics

  2023cited by this paper
• Toward predictive engineering of gene circuits.

  2022cited by this paper
• Vertical and horizontal gene transfer tradeoffs direct plasmid fitness

  2022cited by this paper
• Mapping single‐cell responses to population‐level dynamics during antibiotic treatment

  2022cited by this paper
• Deep model predictive control of gene expression in thousands of single cells

  2022cited by this paper
• Machine learning-assisted discovery of growth decision elements by relating bacterial population dynamics to environmental diversity

  2022cited by this paper
• Population-level integration of single-cell datasets enables multi-scale analysis across samples

  2022cited by this paper
• Predicting microbial growth dynamics in response to nutrient availability

  2021cited by this paper
• A new analysis method for evaluating bacterial growth with microplate readers.

  2021cited by this paper
• Towards a deeper understanding of microbial communities: integrating experimental data with dynamic models.

  2021cited by this paper
• Fast and precise single-cell data analysis using a hierarchical autoencoder

  2021cited by this paper
• Modulation of microbial community dynamics by spatial partitioning

  2021cited by this paper
• An efficient and scalable top-down method for predicting structures of microbial communities

  2021cited by this paper
• VEGA is an interpretable generative model for inferring biological network activity in single-cell transcriptomics

  2021cited by this paper
• Control engineering and synthetic biology: working in synergy for the analysis and control of microbial systems.

  2021cited by this paper
• Design of synthetic human gut microbiome assembly and butyrate production

  2021cited by this paper
• The persistence potential of transferable plasmids

  2020cited by this paper
• Delineating the evolutionary dynamics of cancer from theory to reality

  2020cited by this paper
• Temporal encoding of bacterial identity and traits in growth dynamics

  2020cited by this paper
• Deep learning enables accurate clustering with batch effect removal in single-cell RNA-seq analysis

  2020cited by this paper
• Deep reinforcement learning for the control of microbial co-cultures in bioreactors

  2020cited by this paper
• Environmental and genetic determinants of plasmid mobility in pathogenic Escherichia coli

  2020cited by this paper
• Predicting microbial growth in a mixed culture from growth curve data

  2019cited by this paper
• A unifying framework for interpreting and predicting mutualistic systems

  2019cited by this paper
• A theoretical framework for controlling complex microbial communities

  2019cited by this paper
• An Introduction to Variational Autoencoders

  2019cited by this paper
• Rock-paper-scissors: Engineered population dynamics increase genetic stability

  2019cited by this paper
• Common principles and best practices for engineering microbiomes

  2019cited by this paper
• Single-cell RNA-seq denoising using a deep count autoencoder

  2018cited by this paper
• Inter-species population dynamics enhance microbial horizontal gene transfer and spread of antibiotic resistance

  2017cited by this paper
• Genomic Analysis of Multidrug-Resistant Escherichia coli from North Carolina Community Hospitals: Ongoing Circulation of CTX-M-Producing ST131-H30Rx and ST131-H30R1 Strains

  2017cited by this paper
• Coupling spatial segregation with synthetic circuits to control bacterial survival

  2016cited by this paper
• Challenges in microbial ecology: building predictive understanding of community function and dynamics

  2016cited by this paper
• Gazing into the crystal ball : predicting the behavior of microbial consortia

  2016cited by this paper
• Community structure follows simple assembly rules in microbial microcosms

  2016cited by this paper
• Growth dynamics of gut microbiota in health and disease inferred from single metagenomic samples

  2015cited by this paper
• Marine microbial community dynamics and their ecological interpretation

  2015cited by this paper
• Song, H.-S., et al. Mathematical Modeling of Microbial Community Dynamics: A Methodological Review. Processes 2014, 2, 711–752

  2015cited by this paper
• Sloppiness and Emergent Theories in Physics, Biology, and Beyond

  2015cited by this paper
• The ecology of the microbiome: Networks, competition, and stability

  2015cited by this paper
• Phenotypic Signatures Arising from Unbalanced Bacterial Growth

  2014cited by this paper
• Cancer Evolution: Mathematical Models and Computational Inference

  2014cited by this paper
• Long-term model predictive control of gene expression at the population and single-cell levels

  2012cited by this paper
• Microbial population and community dynamics on plant roots and their feedbacks on plant communities.

  2012cited by this paper
• Oscillations by Minimal Bacterial Suicide Circuits Reveal Hidden Facets of Host-Circuit Physiology

  2010cited by this paper
• Plant-Animal Mutualistic Networks: The Architecture of Biodiversity

  2007cited by this paper
• Universally Sloppy Parameter Sensitivities in Systems Biology Models

  2007cited by this paper
• Statistical mechanical approaches to models with many poorly known parameters.

  2003cited by this paper
• Growth Kinetics of Suspended Microbial Cells: From Single-Substrate-Controlled Growth to Mixed-Substrate Kinetics

  1998cited by this paper
• Strange attractors in volterra equations for species in competition

  1982cited by this paper
• More is different.

  1972cited by this paper

• Generalized EPICS (gEPICS): Handling species extinctions in predicting microbial community structures using effective pairwise interactions

  2026cites this paper
• Artificial intelligence for microbiology and microbiome research.

  2026cites this paper
• Machine Learning-Powered Multi-Omics for Food Microbiology and Smarter Food Safety

  2025cites this paper
• Data-driven discovery of dynamical models in biology

  2025cites this paper
• The human microbiome in clinical translation: from bench to bedside

  2025cites this paper
• Harnessing machine learning for metagenomic data analysis: trends and applications

  2025cites this paper
• Generative design of synthetic gene circuits for functional and evolutionary properties

  2025cites this paper
• μGrowthDB: querying, visualizing, and sharing microbial growth curve data

  2025cites this paper
• Artificial intelligence empowers gut microbiota research in neurodegenerative diseases molecular mechanisms and precision therapy

  2025cites this paper
• An Ecologically-Informed Deep Learning Framework for Interpretable and Validatable Habitat Mapping

  2025influential citation
• Bridging VAE-Derived Latent Gene Representations and Graph Neural Networks for Improved Drug Response Prediction

  2025cites this paper
• A foundation model for microbial growth dynamics

  2025influential citation
• Simulation-templated photorealistic prediction of bacterial patterns

  2025cites this paper
• Biomaterial-based strategies to overcome antibiotic resistance: Mechanisms, technologies, and applications in bacterial infection control

  2025cites this paper
• Dynamics of an algae–bacteria microcosm: Photosynthesis, chemotaxis, and expulsion in inhomogeneous active matter

  2025cites this paper
• Four Principles for Physically Interpretable World Models

  2025cites this paper
• Towards synthetic ecology: strategies for the optimization of microbial community functions

  2025cites this paper
• Assessing Flood and Waterlogging Vulnerability and Community Governance in Urban Villages in the Context of Climate Change: A Case Study of 89 Urban Villages in Shanghai

  2025cites this paper
• Bistable States of Microbial Communities Driven by Nutrient Loading in the Hyporheic Zone of Effluent-Dominated Rivers: Predicting Taxonomic Composition and Metabolic Functions

  2025cites this paper
• Linear scaling reveals low-dimensional structure in observable microbial dynamics

  2025cites this paper
• An Improved Autoencoder Conjugacy Network to Learn Chaotic Maps

  2025cites this paper
• Learning disentangled latent representations facilitates discovery and design of functional materials

  2025cites this paper
• Predicting population dynamics of antimicrobial resistance using mechanistic modeling and machine learning.

  2025cites this paper
• Smart Microbiomes: How AI Is Revolutionizing Personalized Medicine

  2025cites this paper
• Pretrained Large Models in Telecommunications: A Survey of Technologies and Applications

  2024cites this paper
• Ocular Surface Microbiome: Influences of Physiological, Environmental, and Lifestyle Factors

  2024cites this paper
• Pathogenesis‐Guided Engineering: pH‐Responsive Imprinted Polymer Co‐Delivering Folate for Inflammation‐Resolving as Immunotherapy in Implant‐Related Infections

  2024cites this paper
• Discovery of interpretable patterning rules by integrating mechanistic modeling and deep learning

  2024cites this paper
• Private benefit of β-lactamase dictates selection dynamics of combination antibiotic treatment

  2024cites this paper
• Linking spatial drug heterogeneity to microbial growth dynamics in theory and experiment

  2024cites this paper
• Data-driven discovery of the interplay between genetic and environmental factors in bacterial growth

  2024cites this paper
• Autoencoder neural networks enable low dimensional structure analyses of microbial growth dynamics

  2023cites this paper
• Anti-Diffusion in an Algae-Bacteria Microcosm: Photosynthesis, Chemotaxis, and Expulsion

  2023cites this paper
• Why should autoencoders work?

  2023cites this paper
• A quantitative approach to easily characterize and predict cell death and escape to β-lactam treatments

  2021cites this paper