Unsupervised classification of environmental marine microbes using a Raman spectra-based deep learning framework

Fengyun LÜ; Yanmei ZHANG; Hongtao LIANG; Luyang SUN

doi:10.1007/s00343-025-5087-z

Your Location：

Home >

Browse articles >

Unsupervised classification of environmental marine microbes using a Raman spectra-based deep learning framework

Biology | Updated：2026-05-07

- Unsupervised classification of environmental marine microbes using a Raman spectra-based deep learning framework
- Journal of Oceanology and Limnology Vol. 44, Issue 2, Pages: 728-742(2026)
- Affiliations：
  
  1.School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266100, China
  2.Single-Cell Center, CAS Key Laboratory of Biofuels, Shandong Key Laboratory of Energy Genetics, Qingdao New Energy Shandong Laboratory, Shandong Energy Institute, Qingdao Institute of Bioenergy and Bioprocess Technology, Chinese Academy of Sciences, Qingdao 266101, China
  3.College of Life Science, University of Chinese Academy of Sciences, Beijing 101408, China
- Author bio：
  
  lht@qust.edu.cn
  sunly@qibebt.ac.cn
- Funds：
- DOI：10.1007/s00343-025-5087-z
  CLC：
- Received：24 March 2025，
  
  Accepted：22 April 2025，
  
  Online First：28 May 2025，
  
  Published：01 March 2026
- Accepted：
Scan QR Code
LÜ Fengyun,ZHANG Yanmei,LIANG Hongtao,et al.Unsupervised classification of environmental marine microbes using a Raman spectra-based deep learning framework[J].Journal of Oceanology and Limnology,2026,44(02):728-742.
DOI：

LÜ Fengyun,ZHANG Yanmei,LIANG Hongtao,et al.Unsupervised classification of environmental marine microbes using a Raman spectra-based deep learning framework[J].Journal of Oceanology and Limnology,2026,44(02):728-742. DOI： 10.1007/s00343-025-5087-z.

摘要

Abstract

The development of microfluidic-based Raman devices has enabled the acquisition of thousands of single-cell Raman spectra from complex microbial populations

offering new avenues for characterizing environmental bacteria. We proposed and validated the convolutional deep embedded clustering (CDEC) model

a clustering framework designed for the unsupervised classification of marine microbial Raman spectra. A four-stage analytical framework was employed to systematically assess the performance of the CDEC model

with increasing dataset complexity ranging from mock communities of pure bacterial cultures to natural microbial populations isolated from seawater. The CDEC algorithm consistently distinguished bacterial species across all stages

achieving an average accuracy of 97.27%

and surpassed the baseline methods in performance. In natural microbial communities

the model resolved eight distinct clusters with unique Raman spectral markers

revealing underlying metabolic heterogeneity. These results highlight the scalability and utility of the CDEC model for studying marine microbial diversity and characterizing microbial composition and metabolic traits at single-cell resolution.

关键词

Keywords

references

Avdiyuk K V , Ivanytsia V O , Varbanets L D et al . 2024 . Bacteria of deep-sea sediments of the black sea breaking down keratin . Mikrobiolohichnyi Zhurnal , 86 ( 3 ): 18 - 26 , https://doi.org/10.15407/microbiolj86.03.018 https://doi.org/10.15407/microbiolj86.03.018 .

Bendale A , Boult T E . 2016 . Towards open set deep networks . In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . IEEE , Las Vegas, USA . p. 1563 - 1572 , https://doi.org/10.1109/CVPR.2016.173 https://doi.org/10.1109/CVPR.2016.173 .

Blondel V D , Guillaume J L , Lambiotte R et al . 2008 . Fast unfolding of communities in large networks . Journal of Statistical Mechanics : Theory and Experiment , 2008 ( 1 ): P 10008 , https://doi.org/10.1088/1742-5468/2008/10/P10008 https://doi.org/10.1088/1742-5468/2008/10/P10008 .

Burke C , Steinberg P , Rusch D et al . 2011 . Bacterial community assembly based on functional genes rather than species . Proceedings of the National Academy of Sciences of the United States of America , 108 ( 34 ): 14288 - 14293 , https://doi.org/10.1073/pnas.1101591108 https://doi.org/10.1073/pnas.1101591108 .

Cui D Y , Kong L C , Wang Y et al . 2022 . In situ identification of environmental microorganisms with Raman spectroscopy. Environmental Science and Ecotechnology , 11 : 100187 , https://doi.org/10.1016/j.ese.2022.100187 https://doi.org/10.1016/j.ese.2022.100187 .

Cui Y , Cui Y W , Huang J L . 2021 . A novel halophilic Exiguobacterium mexicanum strain removes nitrogen from saline wastewater via heterotrophic nitrification and aerobic denitrification. Bioresource Technology , 333 : 125189 , https://doi.org/10.1016/j.biortech.2021.125189 https://doi.org/10.1016/j.biortech.2021.125189 .

Falkowski P G , Fenchel T , Delong E F . 2008 . The microbial engines that drive Earth’s biogeochemical cycles . Science , 320 ( 5879 ): 1034 - 1039 , https://doi.org/10.1126/science.1153213 https://doi.org/10.1126/science.1153213 .

Frempong S B , Salbreiter M , Mostafapour S et al . 2024 . Illuminating the tiny world: a navigation guide for proper Raman studies on microorganisms . Molecules , 29 ( 5 ): 1077 , https://doi.org/10.3390/molecules29051077 https://doi.org/10.3390/molecules29051077 .

Genicot S M , Groisillier A , Rogniaux H et al . 2014 . Discovery of a novel iota carrageenan sulfatase isolated from the marine bacterium Pseudoalteromonas carrageenovora . Frontiers in Chemistry , 2 : 67 , https://doi.org/10.3389/fchem.2014.00067 https://doi.org/10.3389/fchem.2014.00067 .

Glaeser S P , Dott W , Busse H J et al . 2013 . Fictibacillus phosphorivorans gen. nov., sp. nov. and proposal to reclassify Bacillus arsenicus , Bacillus barbaricus , Bacillus macauensis , Bacillus nanhaiensis , Bacillus rigui , Bacillus solisalsi and Bacillus gelatini in the genus Fictibacillus . International Journal of Systematic and Evolutionary Microbiology , 63 ( Pt 8 ): 2934 - 2944 , https://doi.org/10.1099/ijs.0.049171-0 https://doi.org/10.1099/ijs.0.049171-0 .

Gracia Moisés A , Vitoria Pascual I , Imas González J J et al . 2023 . Data augmentation techniques for machine learning applied to optical spectroscopy datasets in agrifood applications: a comprehensive review . Sensors , 23 ( 20 ): 8562 , https://doi.org/10.3390/s23208562 https://doi.org/10.3390/s23208562 .

Guo S X , Heinke R , Stöckel S et al . 2018a . Model transfer for Raman-spectroscopy-based bacterial classification . Journal of Raman Spectroscopy , 49 ( 4 ): 627 - 637 , https://doi.org/10.1002/jrs.5343 https://doi.org/10.1002/jrs.5343 .

Guo S X , Kohler A , Zimmermann B et al . 2018b . Extended multiplicative signal correction based model transfer for raman spectroscopy in biological applications . Analytical Chemistry , 90 ( 16 ): 9787 - 9795 , https://doi.org/10.1021/acs.analchem.8b01536 https://doi.org/10.1021/acs.analchem.8b01536 .

Guo Y X , Jin W Q , Wang W L et al . 2022 . Unsupervised convolutional variational autoencoder deep embedding clustering for Raman spectra . Analytical Methods , 14 ( 39 ): 3898 - 3910 , https://doi.org/10.1039/d2ay01184k https://doi.org/10.1039/d2ay01184k .

Ho C S , Jean N , Hogan C A et al . 2019 . Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning . Nature Communications , 10 ( 1 ): 4927 , https://doi.org/10.1038/s41467-019-12898-9 https://doi.org/10.1038/s41467-019-12898-9 .

Hong J K , Kim S B , Lyou E S et al . 2021 . Microbial phenomics linking the phenotype to function: the potential of Raman spectroscopy . Journal of Microbiology , 59 ( 3 ): 249 - 258 , https://doi.org/10.1007/s12275-021-0590-1 https://doi.org/10.1007/s12275-021-0590-1 .

Jonker R , Volgenant T . 1986 . Improving the Hungarian assignment algorithm . Operations Research Letters , 5 ( 4 ): 171 - 175 , https://doi.org/10.1016/0167-6377(86)90073-8 https://doi.org/10.1016/0167-6377(86)90073-8 .

Kobayashi-Kirschvink K J , Comiter C S , Gaddam S et al . 2024 . Prediction of single-cell RNA expression profiles in live cells by Raman microscopy with Raman2RNA . Nature Biotechnology , 42 ( 11 ): 1726 - 1734 , https://doi.org/10.1038/s41587-023-02082-2 https://doi.org/10.1038/s41587-023-02082-2 .

Kruse L , Loeschcke A , de Witt J et al . 2024 . Halopseudomonas species: cultivation and molecular genetic tools . Microbial Biotechnology , 17 ( 1 ): e 14369 , https://doi.org/10.1111/1751-7915.14369 https://doi.org/10.1111/1751-7915.14369 .

Langille M G I , Zaneveld J , Caporaso J G et al . 2013 . Predictive functional profiling of microbial communities using 16S rRNA marker gene sequences . Nature Biotechnology , 31 ( 9 ): 814 - 821 , https://doi.org/10.1038/nbt.2676 https://doi.org/10.1038/nbt.2676 .

Le Reste P J , Pilalis E , Aubry M et al . 2021 . Integration of Raman spectra with transcriptome data in glioblastoma multiforme defines tumour subtypes and predicts patient outcome . Journal of Cellular and Molecular Medicine , 25 ( 23 ): 10846 - 10856 , https://doi.org/10.1111/jcmm.16902 https://doi.org/10.1111/jcmm.16902 .

Li X J , Wang K , Lyu Y et al . 2020 . Deep learning enables accurate clustering with batch effect removal in single-cell RNA-seq analysis . Nature Communications , 11 ( 1 ): 2338 , https://doi.org/10.1038/s41467-020-15851-3 https://doi.org/10.1038/s41467-020-15851-3 .

MacQueen J . 1967 . Some methods for classification and analysis of multivariate observations . In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability . Statistical Laboratory of the University, Be rkeley, USA. p. 281 - 297 .

Martiny J B H , Jones S E , Lennon J T et al . 2015 . Microbiomes in light of traits: a phylogenetic perspective . Science , 350 ( 6261 ): aac 9323 , https://doi.org/10.1126/science.aac9323 https://doi.org/10.1126/science.aac9323 .

Moradi M , Song Z L , Tao X . 2015 . Introducing a novel bacterium, Vibrio neocaledonicus sp., with the highest corrosion inhibition efficiency . Electrochemistry Communications , 51 : 64 - 68 , https://doi.org/10.1016/j.elecom.2014.12.007 https://doi.org/10.1016/j.elecom.2014.12.007 .

Parks D H , Chuvochina M , Chaumeil P A et al . 2020 . A complete domain-to-species taxonomy for Bacteria and Archaea . Nature Biotechnology , 38 ( 9 ): 1079 - 1086 , https://doi.org/10.1038/s41587-020-0501-8 https://doi.org/10.1038/s41587-020-0501-8 .

Qin L , Zhang G Y , Zhang S Q et al . 2024 . Deep batch integration and Denoise of single-cell RNA-Seq data . Advanced Science , 11 ( 29 ): e 2308934 , https://doi.org/10.1002/advs.202308934 https://doi.org/10.1002/advs.202308934 .

Sun Z J , Wang Z , & Jiang M Q . 2024 . RamanCluster: a deep clustering-based framework for unsupervised Raman spectral identification of pathogenic bacteria. Talanta , 275 : 126076 , https://doi.org/10.1016/j.talanta.2024.126076 https://doi.org/10.1016/j.talanta.2024.126076 .

Tang J W , Liu Q H , Yin X C et al . 2021 . Comparative analysis of machine learning algorithms on surface enhanced Raman spectra of clinical Staphylococcus species. Frontiers in Microbiology , 12 : 696921 , https://doi.org/10.3389/fmicb.2021.696921 https://doi.org/10.3389/fmicb.2021.696921 .

Taş N , de Jong A E E , Li Y M et al . 2021 . Metagenomic tools in microbial ecology research . Current Opinion in Biotechnology , 67 : 184 - 191 , https://doi.org/10.1016/j.copbio.2021.01.019 https://doi.org/10.1016/j.copbio.2021.01.019 .

Terzin M , Robbins S J , Bell S C et al . 2025 . Gene content of seawater microbes is a strong predictor of water chemistry across the great barrier reef . Microbiome , 13 ( 1 ): 11 , https://doi.org/10.1186/s40168-024-01972-0 https://doi.org/10.1186/s40168-024-01972-0 .

Thrift W J , Ronaghi S , Samad M et al . 2020 . Deep learning analysis of vibrational spectra of bacterial lysate for rapid antimicrobial susceptibility testing . ACS Nano , 14 ( 11 ): 15336 - 15348 , https://doi.org/10.1021/acsnano.0c05693 https://doi.org/10.1021/acsnano.0c05693 .

Van Rossum T , Ferretti P , Maistrenko O M et al . 2020 . Diversity within species: interpreting strains in microbiomes . Nature Reviews Microbiology , 18 ( 9 ): 491 - 506 , https://doi.org/10.1038/s41579-020-0368-1 https://doi.org/10.1038/s41579-020-0368-1 .

Wang X X , Ren L H , Diao Z D et al . 2023 . Robust spontaneous Raman flow Cytometry for single-cell metabolic Phenome profiling via pDEP-DLD-RFC . Advanced Science , 10 ( 16 ): 2207497 , https://doi.org/10.1002/advs.202207497 https://doi.org/10.1002/advs.202207497 .

Xie J Y , Girshick R B , Farhadi A . 2016 . Unsupervised deep embedding for clustering analysis . In: Proceedings of the 33rd International Conference on Machine Learning . ICML, New York, USA . p. 478 - 487 . https://do 10.1007/978-3-319-46493-0_51 http://dx.doi.org/10.1007/978-3-319-46493-0_51

Yu S X , Li H F , Li X et al . 2020 . Classification of pathogens by Raman spectroscopy combined with generative adversarial networks. Science of the Total Environment , 726 : 138477 , https://doi.org/10.1016/j.scitotenv.2020.138477 https://doi.org/10.1016/j.scitotenv.2020.138477 .

Yu S X , Li X , Lu W L et al . 2021 . Analysis of Raman spectra by using deep learning methods in the identification of marine pathogens . Analytical Chemistry , 93 ( 32 ): 11089 - 11098 , https://doi.org/10.1021/acs.analchem.1c00431 https://doi.org/10.1021/acs.analchem.1c00431 .

Zhang Y M , Jing G C , Chen R Z et al . 2025 . RamEx: an R package for high-throughput microbial ramanome analyses with accurate quality assessment . bioRxiv , https://doi.org/10.1101/2025.03.10.642505 https://doi.org/10.1101/2025.03.10.642505 .

Zhu D C , Zhang P P , Niu L L et al . 2016 . Bacillus ectoiniformans sp. nov., a halotolerant bacterium isolated from deep-sea sediments . International Journal of Systematic and Evolutionary Microbiology , 66 ( 2 ): 616 - 622 , https://doi.org/10.1099/ijsem.0.000763 https://doi.org/10.1099/ijsem.0.000763 .

Zhu L J , Yang Y N , Xu F et al . 2025 . Open-set deep learning–enabled single-cell Raman spectroscopy for rapid identification of airborne pathogens in real-world environments . Science Advances , 11 ( 2 ): eadp 7991 , https://doi.org/10.1126/sciadv.adp7991 https://doi.org/10.1126/sciadv.adp7991 .

Zhu Y B , Qiao C C , Li H B et al . 2018 . Improvement thermostability of Pseudoalteromonas carrageenovora arylsulfatase by rational design . International Journal of Biological Macromolecules , 108 : 953 - 959 , https://doi.org/10.1016/j.ijbiomac.2017.11.014 https://doi.org/10.1016/j.ijbiomac.2017.11.014 .

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Application of confocal laser Raman spectroscopy on marine sediment microplastics

Comparative study of stock status and sustainable management of Pomadasys olivaceus fishery along Pakistan coast

Vertical change of living siliceous radiolarians and their responses to water masses in the tropical Southeast Indian Ocean in spring

From light to nutrient limitation: attributing cyanobacterial bloom transitions in Taihu Lake (2007–2023) through a limiting factor perspective

Alternative splicing genes/events play important role in adaptation of mud crab Scylla paramamosain to low salinity

Related Author

Xin ZHANG

Jun YAN

Lei CAO

Bing WANG

Shichuan XI

Lianfu LI

Zhendong LUAN

Zengfeng DU

Related Institution

Key Laboratory of Marine Geology and Environment&Center of Deep Sea Research, Institute of Oceanology, Chinese Academy of Sciences

Laboratory for Marine Geology, Pilot National Laboratory for Marine Science and Technology (Qingdao)

University of Chinese Academy of Sciences

Center for Ocean Mega-Science, Chinese Academy of Sciences

Address：Editorial Office of JOL, 88 Haijun Rd. Qingdao, 266000, China
Tel：+86-532-82898754 Email：jol@qdio.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰