Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Identifying keystone species in microbial communities using deep learning

Nature Ecology & Evolution volume 8, pages 22–31 (2024)Cite this article

Subjects

Abstract

Previous studies suggested that microbial communities can harbour keystone species whose removal can cause a dramatic shift in microbiome structure and functioning. Yet, an efficient method to systematically identify keystone species in microbial communities is still lacking. Here we propose a data-driven keystone species identification (DKI) framework based on deep learning to resolve this challenge. Our key idea is to implicitly learn the assembly rules of microbial communities from a particular habitat by training a deep-learning model using microbiome samples collected from this habitat. The well-trained deep-learning model enables us to quantify the community-specific keystoneness of each species in any microbiome sample from this habitat by conducting a thought experiment on species removal. We systematically validated this DKI framework using synthetic data and applied DKI to analyse real data. We found that those taxa with high median keystoneness across different communities display strong community specificity. The presented DKI framework demonstrates the power of machine learning in tackling a fundamental problem in community ecology, paving the way for the data-driven management of complex microbial communities.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Workflow of the DKI framework.
Fig. 2: In silico validation of the DKI framework.
Fig. 3: Traditional topological indices calculated from the undirected correlation network do not correlate with structural keystoneness.
Fig. 4: In vitro validation of cNODE in keystoneness prediction.
Fig. 5: Keystone species in the human gut microbiome.

Similar content being viewed by others

Data availability

Gut microbiome data were collected from the curatedMetagenomicData32 database. Oral microbiome data are available at the CNGB Sequence Archive (CNSA) of the China National GeneBank DataBase (CNGBdb) (CNSA CNP0000687 for the 4D-SZ cohort and CNP0001221 for the Yunnan cohort). Coral and soil microbiome data were collected from Qiita40 (IDs 10895 and 2104). Data supporting our findings are provided at https://github.com/spxuw/DKI.

Code availability

The code used in this work is available at https://github.com/spxuw/DKI.

References

  1. Paine, R. T. A note on trophic complexity and community stability. Am. Nat. 103, 91–93 (1969).

    Article  Google Scholar 

  2. Paine, R. T. Food web complexity and species diversity. Am. Nat. 100, 65–75 (1966).

    Article  Google Scholar 

  3. Cottee-Jones, H. E. W. & Whittaker, R. J. The keystone species concept: a critical appraisal. Front Biogeogr. 4, 117–127 (2012).

    Article  Google Scholar 

  4. Power, M. E. et al. Challenges in the quest for keystones: identifying keystone species is difficult—but essential to understanding how loss of species will affect ecosystems. BioScience 46, 609–620 (1996).

    Article  Google Scholar 

  5. Ze, X., Duncan, S. H., Louis, P. & Flint, H. J. Ruminococcus bromii is a keystone species for the degradation of resistant starch in the human colon. ISME J. 6, 1535–1543 (2012).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Banerjee, S. et al. Network analysis reveals functional redundancy and keystone taxa amongst bacterial and fungal communities during organic matter decomposition in an arable soil. Soil Biol. Biochem. 97, 188–198 (2016).

    Article  CAS  Google Scholar 

  7. Trosvik, P. & de Muinck, E. J. Ecology of bacteria in the human gastrointestinal tract—identification of keystone and foundation taxa. Microbiome 3, 44 (2015).

    Article  PubMed  PubMed Central  Google Scholar 

  8. Xun, W. et al. Specialized metabolic functions of keystone taxa sustain soil microbiome stability. Microbiome 9, 35 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  9. LeBlanc, N. & Crouch, J. A. Prokaryotic taxa play keystone roles in the soil microbiome associated with woody perennial plants in the genus Buxus. Ecol. Evol. 9, 11102–11111 (2019).

    Article  PubMed  PubMed Central  Google Scholar 

  10. The Human Microbiome Project Consortium Structure, function and diversity of the healthy human microbiome. Nature 486, 207–214 (2012).

    Article  PubMed Central  Google Scholar 

  11. Franzosa, E. A. et al. Identifying personal microbiomes using metagenomic codes. Proc. Natl Acad. Sci. USA 112, E2930–E2938 (2015).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  12. Vujkovic-Cvijin, I. et al. Host variables confound gut microbiota studies of human disease. Nature 587, 448–454 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Stein, R. R. et al. Ecological modeling from time-series inference: insight into dynamics and stability of intestinal microbiota. PLoS Comput. Biol. 9, e1003388 (2013).

    Article  PubMed  PubMed Central  Google Scholar 

  14. Fisher, C. K. & Mehta, P. Identifying keystone species in the human gut microbiome from metagenomic timeseries using sparse linear regression. PLoS ONE 9, e102451 (2014).

    Article  PubMed  PubMed Central  Google Scholar 

  15. Bucci, V. et al. MDSINE: Microbial Dynamical Systems INference Engine for microbiome time-series analyses. Genome Biol. 17, 121 (2016).

    Article  PubMed  PubMed Central  Google Scholar 

  16. Berry, D. & Widder, S. Deciphering microbial interactions and detecting keystone species with co-occurrence networks. Front. Microbiol. 5, 219 (2014).

    Article  PubMed  PubMed Central  Google Scholar 

  17. Banerjee, S., Schlaeppi, K. & van der Heijden, M. G. A. Keystone taxa as drivers of microbiome structure and functioning. Nat. Rev. Microbiol. 16, 567–576 (2018).

    Article  CAS  PubMed  Google Scholar 

  18. Garrett, W. S. et al. Enterobacteriaceae act in concert with the gut microbiota to induce spontaneous and maternally transmitted colitis. Cell Host Microbe 8, 292–300 (2010).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  19. Hajishengallis, G. et al. Low-abundance biofilm species orchestrates inflammatory periodontal disease through the commensal microbiota and complement. Cell Host Microbe 10, 497–506 (2011).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  20. Agler, M. T. et al. Microbial hub taxa link host and abiotic factors to plant microbiome variation. PLoS Biol. 14, e1002352 (2016).

    Article  PubMed  PubMed Central  Google Scholar 

  21. Banerjee, S., Schlaeppi, K. & van der Heijden, M. G. Reply to ‘Can we predict microbial keystones?’. Nat. Rev. Microbiol. 17, 194–194 (2019).

    Article  CAS  PubMed  Google Scholar 

  22. Röttjers, L. & Faust, K. Can we predict keystones? Nat. Rev. Microbiol. 17, 193 (2019).

    Article  PubMed  Google Scholar 

  23. Amit, G. & Bashan, A. Top-down identification of keystone taxa in the microbiome. Nat. Commun. 14, 3951 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  24. Valls, A., Coll, M. & Christensen, V. Keystone species: toward an operational concept for marine biodiversity conservation. Ecol. Monogr. 85, 29–47 (2015).

    Article  Google Scholar 

  25. Tian, L. et al. Deciphering functional redundancy in the human microbiome. Nat. Commun. 11, 6217 (2020).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  26. Gouveia, C., Móréh, Á. & Jordán, F. Combining centrality indices: maximizing the predictability of keystone species in food webs. Ecol. Indic. 126, 107617 (2021).

    Article  Google Scholar 

  27. Kruse, R., Borgelt, C., Braune, C., Mostaghim, S. & Steinbrecher, M. Computational Intelligence: A Methodological Introduction (Springer, 2022).

  28. He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proc. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 770–778 (IEEE, 2016).

  29. Michel-Mata, S., Wang, X.-W., Liu, Y.-Y. & Angulo, M. T. Predicting microbiome compositions from species assemblages through deep learning. Imeta 1, e3 (2022).

    Article  PubMed  PubMed Central  Google Scholar 

  30. Almeida-Neto, M., Guimaraes, P., Guimaraes, P. R. Jr, Loyola, R. D. & Ulrich, W. A consistent metric for nestedness analysis in ecological systems: reconciling concept and measurement. Oikos 117, 1227–1239 (2008).

    Article  Google Scholar 

  31. Friedman, J., Higgins, L. M. & Gore, J. Community structure follows simple assembly rules in microbial microcosms. Nat. Ecol. Evol. 1, 0109 (2017).

    Article  Google Scholar 

  32. Pasolli, E. et al. Accessible, curated metagenomic data through ExperimentHub. Nat. Methods 14, 1023–1024 (2017).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  33. Tudela, H., Claus, S. P. & Saleh, M. Next generation microbiome research: identification of keystone species in the metabolic regulation of host–gut microbiota interplay. Front. Cell Dev. Biol. 9, 719072 (2021).

    Article  PubMed  PubMed Central  Google Scholar 

  34. Alessandri, G., van Sinderen, D. & Ventura, M. The genus Bifidobacterium: from genomics to functionality of an important component of the mammalian gut microbiota. Comput. Struct. Biotechnol. J. 19, 1472–1487 (2021).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  35. Zhang, Z. et al. Spatial heterogeneity and co-occurrence patterns of human mucosal-associated intestinal microbiota. ISME J. 8, 881–893 (2014).

    Article  PubMed  Google Scholar 

  36. Leylabadlo, H. E. et al. The critical role of Faecalibacterium prausnitzii in human health: an overview. Microb. Pathog. 149, 104344 (2020).

    Article  CAS  PubMed  Google Scholar 

  37. Gotoh, A., Ojima, M. N. & Katayama, T. Minority species influences microbiota formation: the role of Bifidobacterium with extracellular glycosidases in bifidus flora formation in breastfed infant guts. Microb. Biotechnol. 12, 259–264 (2019).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  38. Bui, T. P. N. et al. Intestinimonas-like bacteria are important butyrate producers that utilize Nε-fructosyllysine and lysine in formula-fed infants and adults. J. Funct. Foods 70, 103974 (2020).

    Article  CAS  Google Scholar 

  39. Li, L. et al. Revealing proteome-level functional redundancy in the human gut microbiome using ultra-deep metaproteomics. Nat. Commun. 14, 3428 (2023).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  40. Gonzalez, A. et al. Qiita: rapid, web-enabled microbiome meta-analysis. Nat. Methods 15, 796–798 (2018).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  41. Friedman, J. & Alm, E. J. Inferring correlation networks from genomic survey data. PLoS Comput. Biol. 8, e1002687 (2012).

    Article  CAS  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

Y.-Y.L. acknowledges funding support from the National Institutes of Health (R01AI141529, R01HD093761, RF1AG067744, UH3OD023268, U19AI095219 and U01HL089856) as well as the Office of the Assistant Secretary of Defense for Health Affairs, through the Traumatic Brain Injury and Psychological Health Research Program (Focused Program Award) under award no. W81XWH-22-S-TBIPH2, endorsed by the Department of Defense. X.-W.W. acknowledges funding support from the National Institutes of Health (K25HL166208). Z.S. acknowledges funding support from the National Institutes of Health (K99HL163519). M.T.A. acknowledges the financial support provided by CONACyT grant No. A1-S-13909 and PAPIIT 104915.

Author information

Authors and Affiliations

  1. Channing Division of Network Medicine, Department of Medicine, Brigham and Women’s Hospital and Harvard Medical School, Boston, MA, USA

    Xu-Wen Wang, Zheng Sun, Scott T. Weiss & Yang-Yu Liu

  2. School of Life Sciences, Fudan University, Shanghai, China

    Huijue Jia

  3. Institute of Precision Medicine–Greater Bay Area (Guangzhou), Fudan University, Guangzhou, China

    Huijue Jia

  4. Department of Ecology and Evolutionary Biology, Princeton University, Princeton, NJ, USA

    Sebastian Michel-Mata

  5. Institute of Mathematics, Universidad Nacional Autónoma de México, Juriquilla, Mexico

    Marco Tulio Angulo

  6. CAS Key Laboratory of Quantitative Engineering Biology, Shenzhen Institute of Synthetic Biology, Shenzhen Institute of Advanced Technology, Shenzhen, China

    Lei Dai

  7. University of Chinese Academy of Sciences, Beijing, China

    Lei Dai

  8. Department of Microbiology, The Forsyth Institute, Cambridge, MA, USA

    Xuesong He

  9. Department of Oral Medicine, Infection and Immunity, Harvard School of Dental Medicine, Boston, MA, USA

    Xuesong He

  10. Center for Artificial Intelligence and Modeling, The Carl R. Woese Institute for Genomic Biology, University of Illinois at Urbana-Champaign, Champaign, IL, USA

    Yang-Yu Liu

Authors
  1. Xu-Wen Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zheng Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Huijue Jia
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sebastian Michel-Mata
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Marco Tulio Angulo
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Lei Dai
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Xuesong He
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Scott T. Weiss
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Yang-Yu Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Y.-Y.L. conceived and designed the project. X.-W.W. performed all the numerical calculations. X.-W.W. and Z.S. analysed real data. X.-W.W. and Y.-Y.L. wrote the manuscript. H.J., S.M.-M., M.T.A., L.D., X.H. and S.T.W. edited the manuscript. All authors approved the manuscript.

Corresponding author

Correspondence to Yang-Yu Liu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Ecology & Evolution thanks the anonymous reviewers for their contribution to the peer review of this work. Peer reviewer reports are available.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Supplementary Discussions 1–8 and Figs. 1–14.

Reporting Summary

Peer Review File

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, XW., Sun, Z., Jia, H. et al. Identifying keystone species in microbial communities using deep learning. Nat Ecol Evol 8, 22–31 (2024). https://doi.org/10.1038/s41559-023-02250-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41559-023-02250-2

This article is cited by

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing