Machine Learning Meta-analysis of Large Metagenomic Datasets: Tools and Biological Insights
Open accessThe DOI matches its Crossref record; 70 of the 71 references it cites were found in a registry or an index.
Abstract
Shotgun metagenomic analysis of the human associated microbiome provides a rich set of microbial features for prediction and biomarker discovery in the context of human diseases and health conditions. However, the use of such high-resolution microbial features presents new challenges, and validated computational tools for learning tasks are lacking. Moreover, classification rules have scarcely been validated in independent studies, posing questions about the generality and generalization of disease-predictive models across cohorts. In this paper, we comprehensively assess approaches to metagenomics-based prediction tasks and for quantitative assessment of the strength of potential microbiome-phenotype associations. We develop a computational framework for prediction tasks using quantitative microbiome profiles, including species-level relative abundances and presence of strain-specific markers. A comprehensive meta-analysis, with particular emphasis on generalization across cohorts, was performed in a collection of 2424 publicly available metagenomic samples from eight large-scale studies. Cross-validation revealed good disease-prediction capabilities, which were in general improved by feature selection and use of strain-specific markers instead of species-level taxonomic abundance. In cross-study analysis, models transferred between studies were in some cases less accurate than models tested by within-study cross-validation. Interestingly, the addition of healthy (control) samples from other studies to training sets improved disease prediction capabilities. Some microbial species (most notably Streptococcus anginosus) seem to characterize general dysbiotic states of the microbiome rather than connections with a specific disease. Our results in modelling features of the "healthy" microbiome can be considered a first step toward defining general microbial dysbiosis. The software framework, microbiome profiles, and metadata for thousands of samples are publicly available at http://segatalab.cibio.unitn.it/tools/metaml.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures






![Fig 7 Cross-study analysis in multiple gut datasets for (a) T2D discrimination and (b) disease discrimination (independently from the type of disease). For (a), we included all the healthy (controls) and diabetes (cases) samples, whereas samples labelled as other diseases were not considered. For (b), we instead included all the samples where samples with one of the considered diseases were put together in the same "diseases" class. The * denotes cross-validation results (with the margin of error reported in parenthesis). In the other cases, the model was generated on all the datasets other than the dataset considered for testing, a “leave-one-dataset-out” cross-study validation [51]. For the testing datasets with only healthy samples, prediction accuracy was evaluated in terms of overall accuracy (OA). In bold we report the best value for each scenario and feature type (i.e., species abundance or marker presence), and circled are the absolute best value for each scenario.](https://figures.cochat.ai/paper-figures/5bb56b13e2b047c5a1c14f0db710b338/machine-learning-meta-analysis-of-large-metagenomic-datasets-tools-and-figure-7.jpg)
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“We chose to use RF as our classifier, given its, on average, superior performance using microbial feature sets in previous benchmarking studies 31 .”
From A gut microbial signature for combination immune checkpoint blockade across cancer types (2024) · cites this paper as [31]
In the citing paper
“As in previous studies (Pasolli et al., 2016; Thomas et al., 2019), RFs using functional features performed similarly (0.69 cross validation and 0.71 LODO ROC AUC on pathways relative abundance), indicating a tight link between strain-specific taxonomy and gene carriage in this setting.”
From Integrating taxonomic, functional, and strain-level profiling of diverse microbial communities with bioBakery 3 (2021) · cites this paper as Pasolli et al., 2016
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · cited 1×
“The classifiers were implemented using the scikit-learn python package [61].”
MethodCortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
Regression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482 · cited 13×
“Lasso is based on a multiple logistic regression trained with L1-norm penalized likelihood, while both L1 and L2 norms are penalized in ENet.”
BackgroundMethodInfluentialNeural Networks: A Comprehensive Foundation
Haykin, S. (1998) · Cited by 30,070
Wu, Y. (1999) · Technometrics · doi:10.1080/00401706.1999.10485951 · Cited by 27,221
The Elements of Statistical Learning
Hastie, T., Friedman, J., & Tibshirani, R. (2001) · Springer Series in Statistics · doi:10.1007/978-0-387-21606-5 · Cited by 24,162
Regularization and Variable Selection Via the Elastic Net
Zou, H., & Hastie, T. (2005) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2005.00503.x · Cited by 20,957
Classification and Regression Trees.
Ryzin, J. V., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1986) · Journal of the American Statistical Association · doi:10.2307/2288003 · Cited by 20,825
Metagenomic biomarker discovery and explanation
Segata, N., Izard, J., Waldron, L., Gevers, D., Miropolsky, L., Garrett, W. S., & Huttenhower, C. (2011) · Genome Biology · doi:10.1186/gb-2011-12-6-r60 · Cited by 16,192 · cited 1×
“The approach proposed here (RF with embedded feature selection) focuses on the set of features with the most discriminating power rather than on strictly statistical assessments [46] or statistical assessment coupled with effect size [47].”
MethodSelf-citation
Research works printed but not linked: 1
- J Qin, 2012, A metagenome-wide association study of gut microbiota in type 2 diabetes, Nature, 490, 55, 10.1038/nature11450 · DOI · Paper page
Cited by
Items 201–300 of 666
Graph Embedding Deep Learning Guides Microbial Biomarkers' Identification
Zhu, Q., Jiang, X., Zhu, Q., Pan, M., & He, T. (2019) · Frontiers in Genetics · doi:10.3389/fgene.2019.01182 · Cited by 35
“Traditional classification methods such as Random Forest has been shown to be the best performers in omics data classification tasks and the results show that Random Forest has achieved the best performance on microbial classification (Pasolli et al., 2016).”
BackgroundMethodLevade, I., Saber, M. M., Midani, F. S., Chowdhury, F., Khan, A. I., Begum, Y. A., Ryan, E. T., David, L. A., Calderwood, S. B., Harris, J. B., et al. (2020) · The Journal of Infectious Diseases · doi:10.1093/infdis/jiaa358 · Cited by 35
Seed tuber microbiome can predict growth potential of potato varieties
Song, Y., Atza, E., Sánchez-Gil, J. J., Akkermans, D., de Jonge, R., de Rooij, P. G. H., Kakembo, D., Bakker, P. A. H. M., Pieterse, C. M. J., Budko, N. V., et al. (2024) · Nature Microbiology · doi:10.1038/s41564-024-01872-x · Cited by 37
“RF has been widely used in microbiome– host trait predictions in clinical studies, where it often outperforms other models 37,49 .”
A Phylogeny-Regularized Sparse Regression Model for Predictive Modeling of Microbial Community Data
Xiao, J. Y., Chen, L., Yu, Y., Zhang, X., & Chen, J. (2018) · Frontiers in Microbiology · doi:10.3389/fmicb.2018.03112 · Cited by 35
“Besides those sparse regression models, we also compared SICS to a representative machine learning method, Random Forest (RF), which has been demonstrated good prediction performance on microbiome data (Pasolli et al., 2016).”
MethodEmerging use of artificial intelligence in inflammatory bowel disease
Kohli, A., Holzwanger, E. A., & Levy, A. N. (2020) · World Journal of Gastroenterology · doi:10.3748/wjg.v26.i44.6923 · Cited by 34
Tonelli, M., Signori, C. N., Bendia, A. G., Neiva, J., Ferrero, B., Pellizari, V. H., & Wainer, I. E. K. C. (2021) · Frontiers in Marine Science · doi:10.3389/fmars.2021.636226 · Cited by 36
“ML algorithms like random forest (RF) and neural networks were reported to be one of the most effective tools for analyzing microbiome data, with high accuracy in a range of 16S rRNA sequencing data (Liu et al., 2011; Larsen et al., 2012; Statnikov et al., 2013; Pasolli et al., 2016).”
MethodHuman host status inference from temporal microbiome changes via recurrent neural networks
Chen, X., Liu, L., Zhang, W., Yang, J., & Wong, K. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbab223 · Cited by 35
Human disease prediction from microbiome data by multiple feature fusion and deep learning
Chen, X., Zhu, Z., Zhang, W., Wang, Y., Wang, F., Yang, J., & Wong, K. (2022) · iScience · doi:10.1016/j.isci.2022.104081 · Cited by 34
“…related studies in the past several years, most existing methods are tailored for focused studies; when applied to other datasets, they can suffer from underfitting for different reasons (e.g., small data size adaptation issue, noisy features, lack of data processing, etc.) (Pasolli et al., 2016).”
MethodInfluentialAyoub, C., Arroyo, L. G., MacNicol, J. L., Renaud, D. L., Weese, J. S., & Gómez, D. E. (2022) · Journal of Veterinary Internal Medicine · doi:10.1111/jvim.16562 · Cited by 36
“42 Initially, all sequences were grouped at genus level and zero and near-zero variance predictors were removed from downstream analysis.”
Byndloss, M. X., Devkota, S., Duca, F. A., Niess, J. H., Nieuwdorp, M., Orho‐Melander, M., Sanz, Y., Tremaroli, V., & Zhao, L. (2024) · Diabetes Care · doi:10.2337/dci24-0052 · Cited by 50
“…lifestyle, and other demographic characteristics, it will be important to perform studies in large populations and to include healthy individuals/control participants from different studies as references; these approaches have been shown to increase disease prediction accuracy (5,6).”
BackgroundGastrointestinal microbiota and inflammasomes interplay in health and disease: a gut feeling
Luca, R. D., Arrè, V., Nardone, S., Incerpi, S., Giannelli, G., Trivedi, P., Anastasiadou, E., & Negro, R. (2025) · Gut · doi:10.1136/gutjnl-2025-334938 · Cited by 37
“155 ML algorithms can determine the most effective probiotic combination 156 and personalise nutrition plans for IBS-affected patients.”
Sinha, R., Ahsan, H., Blaser, M. J., Caporaso, J. G., Carmical, J. R., Chan, A. T., Fodor, A. A., Gail, M. H., Harris, C. C., Helzlsouer, K. J., et al. (2018) · Microbiome · doi:10.1186/s40168-018-0596-z · Cited by 34
Machine Learning Analysis of Inflammatory Bowel Disease-Associated Metagenomics Dataset
Hacılar, H., Nalbantoğlu, Ö. U., & Bakır-Güngör, B. (2018) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk.2018.8566487 · Cited by 31
Microbial source tracking using metagenomics and other new technologies
Raza, S., Kim, J., Sadowsky, M. J., & Unno, T. (2021) · The Journal of Microbiology · doi:10.1007/s12275-021-0668-9 · Cited by 35
EnsDeepDP: An Ensemble Deep Learning Approach for Disease Prediction Through Metagenomics
Shen, Y., Zhu, J., Deng, Z., Lu, W., & Wang, H. (2022) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2022.3201295 · Cited by 34
“A total of 1156 human intestinal meta-genomic samples are collected from all six datasets, all from the MetAML library[12].”
BackgroundEngineering the Microbiome to Prevent Adverse Events: Challenges and Opportunities
Khan, S. M., Hauptman, R., & Kelly, L. (2020) · The Annual Review of Pharmacology and Toxicology · doi:10.1146/annurev-pharmtox-031620-031509 · Cited by 31
Microbiome Preprocessing Machine Learning Pipeline
Jasner, Y. Y., Belogolovski, A., Izhak, M. B., Koren, O., & Louzoun, Y. (2021) · Frontiers in Immunology · doi:10.3389/fimmu.2021.677870 · Cited by 30
“MetAML performs microbiota or full metagenomic classi fi cation, which incorporates embedded feature selection methods, including Lasso and ENet, with RF and SVM classi fi ers.”
MethodIt takes guts to learn: machine learning techniques for disease detection from the gut microbiome
Curry, K. D., Nute, M., & Treangen, T. J. (2021) · Emerging Topics in Life Sciences · doi:10.1042/etls20210213 · Cited by 35
Mathematical-based microbiome analytics for clinical translation
Narayana, J. K., Aogáin, M. M., Goh, W. W. B., Xia, K., Tsaneva-Atanasova, K. T., & Chotirmall, S. H. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.11.029 · Cited by 32
Giuffrè, M., Moretti, R., & Tiribelli, C. (2023) · International Journal of Molecular Sciences · doi:10.3390/ijms24065229 · Cited by 34
“Fortunately, recent developments in data repositories [29–33], reporting guidelines [34], and frameworks [35,36] have improved the accessibility and transparency of the data analysis process, making it more efficient and reliable.”
BackgroundWater and soil contaminated by arsenic: the use of microorganisms and plants in bioremediation
Bertin, P. N., Crognale, S., Plewniak, F., Battaglia‐Brunet, F., Rossetti, S., & Mench, M. J. (2021) · Environmental Science and Pollution Research · doi:10.1007/s11356-021-17817-4 · Cited by 36
“Finally, storing, exchanging and analysing the massive data amounts generated by high-throughput sequencing methods require the implementation of robust new computing methods, much more complex than those required by conventional statistical analyses (Pasolli et al. 2016; Li et al. 2017).”
MethodBiomarker discovery in inflammatory bowel diseases using network-based feature selection
Abbas, M. M., Matta, J., Le, T., Bensmail, H., Obafemi-Ajayi, T., Honavar, V., & EL‐Manzalawy, Y. (2019) · PLoS ONE · doi:10.1371/journal.pone.0225382 · Cited by 29
“Results in Table 1 demonstrate the superior performance of RF feature importance for identifying a small subset of discriminative features from metagenomics data which is widely acknowledged in the literature [42, 43].”
BackgroundByndloss, M. X., Devkota, S., Duca, F. A., Niess, J. H., Nieuwdorp, M., Orho‐Melander, M., Sanz, Y., Tremaroli, V., & Zhao, L. (2024) · Diabetes · doi:10.2337/dbi24-0028 · Cited by 35
Towards multi-label classification: Next step of machine learning for microbiome research
Wu, S., Chen, Y., Li, Z., Li, J., Zhao, F., & Su, X. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.04.054 · Cited by 34
“Both RF and GBDT are not only superior to individual ML methods in precision, but can also evaluate the elucidate the contribution of each microbial feature for classification [22,23].”
BackgroundMethodThe oral microbiome in relation to pancreatic cancer risk in African Americans
Petrick, J. L., Wilkinson, J. E., Michaud, D. S., Cai, Q., Gerlovin, H., Signorello, L. B., Wolpin, B. M., Ruiz-Narváez, E., Long, J., Yang, Y., et al. (2021) · British Journal of Cancer · doi:10.1038/s41416-021-01578-5 · Cited by 29
The forecasting power of the microbiome
Correa‐García, S., Constant, P., & Yergeau, É. (2022) · Trends in Microbiology · doi:10.1016/j.tim.2022.11.013 · Cited by 29
Goallec, A. L., Tierney, B. T., Luber, J. M., Cofer, E. M., Kostic, A. D., & Patel, C. J. (2020) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1007895 · Cited by 30
“[2,12] That being said, though, a potential downside of de novo assembled data types is that gene-level variation may be so subject-specific that predictors of host phenotype in one cohort may not reproduce well in other cohorts.”
Smart Microbiomes: How AI Is Revolutionizing Personalized Medicine
Alexandrescu, L., Tofolean, I. T., Condur, L., Tofolean, D. E., Nicoara, A. D., Șerbănescu, L., Rusu, E. E., Twakor, A. N., Dumitru, E., Dumitru, A., et al. (2025) · Bioengineering · doi:10.3390/bioengineering12090944 · Cited by 30
“More recently, deep-learning approaches, including convolutional neural networks, have been utilized for biomarker discovery and improved disease prediction [92,94].”
InfluentialLongitudinal profiling of the burn patient cutaneous and gastrointestinal microbiota: a pilot study
Lima, K. M., Davis, R. R., Liu, S. Y., Greenhalgh, D. G., & Tran, N. K. (2021) · Scientific Reports · doi:10.1038/s41598-021-89822-z · Cited by 30
Louca, P., Meijnikman, A. S., Nogal, A., Asnicar, F., Attaye, I., Vijay, A., Kouraki, A., Visconti, A., Wong, K. E., Berry, S. E., et al. (2023) · Cell Reports Medicine · doi:10.1016/j.xcrm.2023.100993 · Cited by 28
Self-citationManghi, P., Antonello, G., Schiffer, L., Golzato, D., Wokaty, A., Beghini, F., Mirzayi, C. A., Long, K., Gravel-Pucillo, K., Piccinno, G., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-66888-1 · Cited by 34
“We used the Random Forest Algorithm 80 as implemented in the MetAML Python software 60 to discriminate between males and females, and to predict disease status in patients.”
Self-citationZhang, W., Chen, X., & Wong, K. (2021) · Journal of Gastroenterology and Hepatology · doi:10.1111/jgh.15500 · Cited by 26
“SVM method was adopted to both 16S rRNA amplicon sequencing datasets 26,32 and metagenomic sequencing datasets 35 for intestinal disease diagnosis based on microbiome pro fi ling.”
MethodWang, B., Sun, F., & Luan, Y. (2024) · Scientific Reports · doi:10.1038/s41598-024-57670-2 · Cited by 31
“We performed prediction of disease status using random forest, which has been shown to outperform other learning tools for most microbiome data 65 .”
MethodA Comprehensive Study on Predicting Functional Role of Metagenomes Using Machine Learning Methods
Wassan, J. T., Wang, H., Browne, F., & Zheng, H. (2018) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2018.2858808 · Cited by 27
“[32] proposed a computational tool for functional meta-analysis using SVM, RF, Least Absolute Shrinkage and Selection Operator (Lasso), and ENet as ML models.”
BackgroundMethodEnvironmental metagenome classification for constructing a microbiome fingerprint
Kawulok, J., Kawulok, M., & Deorowicz, S. (2019) · Biology Direct · doi:10.1186/s13062-019-0251-z · Cited by 25
Optimizing Microbiota Profiles for Athletes
Mancin, L., Rollo, I., Mota, J. F., Piccini, F., Carletti, M., Susto, G. A., Valle, G., & Paoli, A. (2020) · Exercise and Sport Sciences Reviews · doi:10.1249/jes.0000000000000236 · Cited by 30
“To date, ML tools have been broadly used in biomedical research and life science to diagnose or predict the risk of cancer, CVDs, and genetic disorders and, more generally, to produce health outcome predictions (62).”
Topçuoğlu, B. D., Lesniak, N. A., Ruffin, M. T., Wiens, J., & Schloss, P. D. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/816090 · Cited by 28
Ayoola, M. B., Pillai, N., Nanduri, B., Rothrock, M. J., & Ramkumar, M. (2023) · Animal Microbiome · doi:10.1186/s42523-023-00260-w · Cited by 24
“Traditional machine learning algorithms, such as support vector machine, random forest and logistic regression, have been used to identify available micro-biome features like relative abundance that is linked to obesity and diabetes [22].”
BackgroundMethodResultInfluentialBi, C., Xiao, G., Liu, C., Yan, J., Chen, J., Si, W., Zhang, J., & Liu, Z. (2021) · Frontiers in Cell and Developmental Biology · doi:10.3389/fcell.2021.702414 · Cited by 29
Han, Z., Hu, Y., Lin, X., Cheng, H., Dong, B., Liu, X., Wu, B., & Xu, Z. Z. (2025) · mSystems · doi:10.1128/msystems.01247-24 · Cited by 27
Barone, M., D’Amico, F., Fabbrini, M., Rampelli, S., Brigidi, P., & Turroni, S. (2021) · World Journal of Gastroenterology · doi:10.3748/wjg.v27.i41.7041 · Cited by 24
Identification and validation of microbial biomarkers from cross-cohort datasets using xMarkerFinder
Gao, W., Lin, W., Li, Q., Chen, W., Yin, W., Zhu, X., Gao, S., Liu, L., Li, W., Wu, D., et al. (2024) · Nature Protocols · doi:10.1038/s41596-024-00999-9 · Cited by 25
Bifidobacteriaceae diversity in the human microbiome from a large-scale genome-wide analysis
Pasolli, E., Mauriello, I. E., Avagliano, M., Cavaliere, S., De Filippis, F., & Ercolini, D. (2024) · Cell Reports · doi:10.1016/j.celrep.2024.115027 · Cited by 22
Self-citationRoadmap for the integration of environmental microbiomes in risk assessments under EFSA's remit
Debode, F., Caulier, S., Demeter, S., Dubois, B., Gelhay, V., Hulin, J., Muhovski, Y., Ninane, V., Rousseau, G., & Bragard, C. (2024) · EFSA Supporting Publications · doi:10.2903/sp.efsa.2024.en-8602 · Cited by 24
Meta‐analysis generates and prioritizes hypotheses for translational microbiome research
Duvallet, C. (2018) · Microbial Biotechnology · doi:10.1111/1751-7915.13047 · Cited by 22
Robust biomarker discovery for microbiome-wide association studies
Zhu, Q., Li, B., He, T., Li, G., & Jiang, X. (2019) · Methods · doi:10.1016/j.ymeth.2019.06.012 · Cited by 27
Pooled analysis of oral microbiome profiles defines robust signatures associated with periodontitis
Soueidan, A., Idiri, K., Bechina, C., Esparbès, P., Legrand, A., Bastard, Q. L., & Montassier, E. (2024) · mSystems · doi:10.1128/msystems.00930-24 · Cited by 25
“We used a Lasso-based machine learning framework to estimate the prediction ability of the combination of taxonomic and functional features of the microbiome to segregate periodontitis (cross-validation setting with nested cross-validation for feature selection) (18, 19).”
Artificial intelligence and human microbiome: A brief narrative review
Fonseca, D. C., Fernandes, G. D. R., & Waitzberg, D. L. (2025) · Clinical Nutrition Open Science · doi:10.1016/j.nutos.2024.12.009 · Cited by 28
Chen, Y., Wu, T., Lu, W., Yuan, W., Pan, M., Lee, Y. K., Zhao, J., Zhang, H., Chen, W., Zhu, J., et al. (2021) · Microorganisms · doi:10.3390/microorganisms9102149 · Cited by 25
“The robustness of microbiome–disease associations can be assessed by a meta-analysis of data integrated from all relevant investigations [13].”
BackgroundShen, W. X., Liang, S. R., Jiang, Y., & Chen, Y. (2022) · Patterns · doi:10.1016/j.patter.2022.100658 · Cited by 23
“5 They learn unordered 1D vectors of taxa or microbe abundances.”
BackgroundChoudhury, N., Sahu, T. K., Rao, A. R., Rout, A. K., & Behera, B. K. (2023) · Genes · doi:10.3390/genes14051082 · Cited by 22
“All these methods are rule-based and require higher computational resources such as memory and execution time, whereas MegaR [14] and MetAML [15] are recently developed machine learning-based approaches which can classify the metagenome data efficiently.”
MethodSharma, D., Lou, W. Y. W., & Xu, W. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae161 · Cited by 23
“Recently, machine learning (ML) models have been advocated for a data-driven approach for the prediction of the host phenotypes (Pasolli et al. 2016, LaPierre et al. 2019, Sharma et al. 2020, McCoubrey et al. 2021, Sharma and Xu 2021).”
BackgroundHuman Intestinal Microbiota and Colorectal Cancer: Moving Beyond Associative Studies
Jobin, C. (2017) · Gastroenterology · doi:10.1053/j.gastro.2017.10.030 · Cited by 24
“For example, intestinal bacterial communities have been associated with pathologic conditions such as inflammatory bowel diseases, colorectal cancer, obesity, and liver cirrhosis by 16S rRNA gene or whole genome metagenomic sequencing analysis.(1) An important concept emerging from these correlative studies is that a…”
Identifying Group-Specific Sequences for Microbial Communities Using Long k-mer Sequence Signatures
Wang, Y., Fu, L., Ren, J., Yu, Z., Chen, T., & Sun, F. (2018) · Frontiers in Microbiology · doi:10.3389/fmicb.2018.00872 · Cited by 23
“An example of subgroups for disease is the AR-type (marked akinesia and rigidity) and T-type (predominant resting tremor) in Parkinson’s disease (Paulus and Jellinger, 1991).”
BackgroundWassan, J. T., Wang, H., Browne, F., & Zheng, H. (2019) · IEEE Transactions on NanoBioscience · doi:10.1109/tnb.2019.2912824 · Cited by 21
“Uncovering the function of the microbial genome from its structure forms an important problem in the ML domain [14-17].”
BackgroundMethodSi, H., Sun, C., Chen, B., Shi, L., & Qiao, H. (2019) · IEEE Access · doi:10.1109/access.2019.2923052 · Cited by 21
Microbiome modeling: a beginner's guide
Lange, E., Kranert, L., Krüger, J., Benndorf, D., & Heyer, R. (2024) · Frontiers in Microbiology · doi:10.3389/fmicb.2024.1368377 · Cited by 21
Arabameri, A., Asemani, D., & Teymourpour, P. (2018) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2018.2870124 · Cited by 20
“To address these problems, Pasolli et al. [27] developed a computational framework for prediction tasks using quantitative micro-biome profiles, and a comprehensive meta-analysis, with particular emphasis on generalization through cohorts, was performed.”
MethodWang, W., & Fu, P. (2023) · Microorganisms · doi:10.3390/microorganisms11020291 · Cited by 24
“The AUROC metric summarizes the true-positive rate (TPR) and false-positive rate (FPR) for the unequal proportions of each outcome [63].”
BackgroundFung, D. L. X., Li, X., Leung, C. K.-S., & Hu, P. (2023) · Bioinformatics Advances · doi:10.1093/bioadv/vbad059 · Cited by 22
Zulfiqar, M., Singh, V. P., Steinbeck, C., & Sorokina, M. (2024) · Critical Reviews in Microbiology · doi:10.1080/1040841x.2024.2306465 · Cited by 25
“Machine learning approaches, such as random forests and neural networks, have gained increasing attention in microbial ecology for their ability to accurately classify new, unclassified sequences based on patterns and relationships learned from reference databases (Pasolli et al. 2016).”
Macintyre, P. D., van Niekerk, A., Dobrowolski, M. P., Tsakalos, J. L., & Mucina, L. (2018) · Ecology and Evolution · doi:10.1002/ece3.4176 · Cited by 21
“While ML has been applied to examine a diverse range of problems (e.g. Pasolli, Truong, Malik, Waldron, & Segata, 2016; Shipp et al., 2002; Tango & Botta, 2013), there has been a recent increase in its use within the geospatial and ecological sciences.”
BackgroundEnhancing Metagenome-based Disease Prediction by Unsupervised Binning Approaches
Nguyen, T. H., & Zucker, J. (2019) · International Conference on Knowledge and Systems Engineering/Proceedings · doi:10.1109/kse.2019.8919295 · Cited by 20
“in [6] introduced MetAML, a computational framework to predict”
BackgroundMethodInfluentialGawlik, A., Salonen, A., Jian, C., Yanover, C., Antosz, A., Shmoish, M., Wasniewska, M. G., Bereket, A., Wudy, S. A., Hartmann, M. F., et al. (2021) · Pediatric Obesity · doi:10.1111/ijpo.12835 · Cited by 20
“Machine learning (Table 1/Glossary) methods, commonly used in healthcare research, have proven successful for example, in revealing disease prediction features from pooled metagenomics data sets from adults.(78) Further conceptual and methodological developments of these tools are needed for the integration of various…”
MethodChe, T.-H., Qiu, G., Yu, H., & Wang, Q. (2024) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2024.177076 · Cited by 21
Linking Inflammatory Bowel Disease Symptoms to Changes in the Gut Microbiome Structure and Function
Hassouneh, S. A.-D., Loftus, M. G., & Yooseph, S. (2021) · Frontiers in Microbiology · doi:10.3389/fmicb.2021.673632 · Cited by 22
Guo, S., Zhang, H., Chu, Y., Jiang, Q., & Ma, Y. (2022) · iMeta · doi:10.1002/imt2.20 · Cited by 20
Loganathan, T., & Doss, C. G. P. (2022) · Life Sciences · doi:10.1016/j.lfs.2022.121118 · Cited by 22
Salim, F., Mizutani, S., Zolfo, M., & Yamada, T. (2023) · Current Opinion in Biotechnology · doi:10.1016/j.copbio.2022.102884 · Cited by 21
Yi, X., He, Y., Gao, S., & Li, M. (2024) · Diabetes & Metabolic Syndrome Clinical Research & Reviews · doi:10.1016/j.dsx.2024.103000 · Cited by 20
MetaGen: reference-free learning with multiple metagenomic samples
Xing, X., Liu, J. S., & Zhong, W. (2017) · Genome biology · doi:10.1186/s13059-017-1323-y · Cited by 27
“Among the 13 contigs, Based on large-scale metagenomic data sets, predictive models using machine-learning tools have revealed predictive capabilities for different phenotypes, such as disease state [38], plant productivity [39], and environmental factors [40].”
BackgroundHumans adapt their anticipatory eye movements to the volatility of visual motion properties
Pasturel, C., Montagnini, A., & Perrinet, L. (2020) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1007438 · Cited by 21
Murthy, H. S., Gharaibeh, R. Z., Al‐Mansour, Z., Kozlov, A., Trikha, G., Newsome, R. C., Gauthier, J., Farhadfar, N., Wang, Y., Kelly, D. L., et al. (2020) · Transplantation and Cellular Therapy · doi:10.1016/j.bbmt.2020.07.023 · Cited by 22
Proffitt, C., Bidkhori, G., Moyes, D. L., & Shoaie, S. (2020) · Microorganisms · doi:10.3390/microorganisms8091381 · Cited by 24
Iqbal, S., Begum, F., Ullah, I., Jalal, N., & Shaw, P. M. (2024) · Critical Reviews in Microbiology · doi:10.1080/1040841x.2024.2319669 · Cited by 27
“Among the Ml methods, random forest, support vector machine (SvM), and linear regression models are widely used to analyze microbiome data (Pasolli et al. 2016).”
Cai, C., Shi, Q., Li, J., Jiao, Y., Xu, A., Zhou, Y., Wang, X., Peng, C., Zhang, X., Cui, X., et al. (2024) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2024.105648 · Cited by 20
Han, J., Zhang, H., & Ning, K. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf015 · Cited by 24
Nguyen, T. H., Prifti, E., Sokolovska, N., & Zucker, J. (2019) · RIVF International Conference on Computing and Communication Technologies (RIVF) · doi:10.1109/rivf.2019.8713670 · Cited by 18
Deep Learning for Metagenomic Data: using 2D Embeddings and Convolutional Neural NetworksPreprint
Hải, N. T., Chevaleyre, Y., Prifti, E., Sokolovska, N., & Zucker, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.00244 · Cited by 20
“We evaluated our method with each of the different representations in the six datasets, which include bacterial species related to various disease, namely: liver cirrhosis (CIR), colorectal cancer (COL), obesity (OBE), inflammatory bowel diseases (IBD) and Type 2 Diabetes (T2D) [6, 21, 29, 15, 20, 19, 11], with CIR (n=…”
InfluentialThe Gut Microbiome Controls Liver Tumors via the Vagus NervePreprint
Bauer, K. C., Trehan, R., Ruf, B., Myojin, Y., Benmebarek, M.-R., Ma, C., Seifert, M., Nur, A., Qi, J., Huang, P., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.01.23.576951 · Cited by 20
Next-Generation Sequencing for the Detection of Microbial Agents in Avian Clinical Samples
Afonso, C. L., & Afonso, A. M. (2023) · Veterinary Sciences · doi:10.3390/vetsci10120690 · Cited by 23
“…applications to aid in bioinformatics, analysis of biological network analysis of microbiomes, taxonomic and functional annotations, and clinical diagnosis, are already being explored, including one study that assesses the risk of Salmonella contamination in poultry samples [80,83,134–137].”
BackgroundLiao, H., Shang, J., & Sun, Y. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad747 · Cited by 19
“While MetAML demonstrated competitive performance, its effectiveness on the IBD datasets in the cross-study experiment was unsatisfactory.”
InfluentialOn the Role of Bioinformatics and Data Science in Industrial Microbiome Applications
van den Bogert, B., Boekhorst, J., Pirovano, W., & May, A. (2019) · Frontiers in Genetics · doi:10.3389/fgene.2019.00721 · Cited by 21
“This led to studies with higher statistical power, and consequently to the transition of OTU tables and functional profiles from end-goal deliverables into starting material for downstream analyses such as machine learning (ML) applications (Pasolli et al., 2016).”
BackgroundWang, J., Li, X., Wu, X., Wang, Z., Wu, X., Jin, G., Wang, D., & Yan, T. (2021) · Infection and Drug Resistance · doi:10.2147/idr.s308308 · Cited by 18
“Currently, clinical trials have also been performed to detect the efficacy of FMT for the treatment of other diseases such as ulcerative colitis (UC)[3, 4], irritable bowel syndrome (IBS)[5], constipation[6], and metabolic syndrome[7, 8].”
BackgroundZhu, C., Wang, X., Li, J., Jiang, R., Chen, H., Chen, T., & Yang, Y. (2022) · BMC Microbiology · doi:10.1186/s12866-021-02414-9 · Cited by 18
The Phylogenetic Tree based Deep Forest for Metagenomic Data Classification
Zhu, Q., Zhu, Q., Pan, M., Jiang, X., Hu, X. T., & He, T. (2018) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2018.8621463 · Cited by 17
“In this experiment we use three public datasets of the MetAML package [12] cirrhosis, type 2 diabetes (T2D), obesity.”
BackgroundMethodLee, S., Park, H.-T., Park, S., Lee, J. H., Kim, D., Yoo, H. S., & Kim, D. (2023) · Microbiology Spectrum · doi:10.1128/spectrum.03134-22 · Cited by 20
“For example, ML-based diagnostic models for general dysbiosis states (20) or diseases such as Crohn’s disease (CD) (21) have succeeded in classifying abnormal states with high accuracy.”
BackgroundBakır-Güngör, B., Temiz, M., Jabeer, A., Wu, D., & Yousef, M. (2023) · Frontiers in Microbiology · doi:10.3389/fmicb.2023.1264941 · Cited by 16
“Pasolli et al. (2016) investigated the utility of microbiomes in disease prediction using metagenomic datasets for five different diseases: liver cirrhosis, CRC, IBD, obesity, and T2D.”
BackgroundHuang, K. D., Amend, L., Gálvez, E. J. C., Lesker, T.-R., de Oliveira, R., Bielecka, A., Blanco‐Míguez, A., Valles‐Colomer, M., Ruf, I., Pasolli, E., et al. (2024) · Cell Reports Medicine · doi:10.1016/j.xcrm.2024.101426 · Cited by 18
“87,88 We created a learning model using 1,000 estimator trees and Shannon entropy to evaluate the quality for each node splitting of a tree.”
MethodSelf-citationExploring and exploiting the rice phytobiome to tackle climate change challenges
Khatibi, S. M. H., Dimaano, N. G., Veliz, E., Sundaresan, V., & Ali, J. (2024) · Plant Communications · doi:10.1016/j.xplc.2024.101078 · Cited by 19
“For microbiome data, support vector machines, random forests (RFs), and linear regression models perform well among the standard ML techniques (Statnikov et al., 2013; Pasolli et al., 2016).”
Relier, S., Amalric, A., Attina, A., Koumare, I. B., Rigau, V., Burel‐Vandenbos, F., Fontaine, D., Baroncini, M., Hugnot, J., Duffau, H., et al. (2022) · Analytical Chemistry · doi:10.1021/acs.analchem.2c01526 · Cited by 16
Ghensi, P., Heidrich, V., Bazzani, D., Asnicar, F., Armanini, F., Bertelle, A., Dell'Acqua, F., Dellasega, E., Waldner, R., Vicentini, D., et al. (2025) · Journal Of Clinical Periodontology · doi:10.1111/jcpe.14121 · Cited by 18
“Alpha-diversity, beta-diversity and multidimensional scaling (MDS) ordination were performed via custom python scripts based on Scipy (version 1.7.3) and Scikit-learn (version 1.0.2) (Pasolli et al. 2016; Varoquaux et al. 2015).”
InfluentialSelf-citationHarnessing vaginal inflammation and microbiome: a machine learning model for predicting IVF success
Bar, O., Vagios, S., Barkai, O., Elshirbini, J., Souter, I. C., Xu, J., James, K. E., Bormann, C. L., Mitsunami, M., Chavarro, J. E., et al. (2025) · npj Biofilms and Microbiomes · doi:10.1038/s41522-025-00732-8 · Cited by 16
“Using Support Vector Machine (SVM) supervised machine learning model, we demonstrate that vaginal micro-biome data alone — or combined with in fl ammatory markers — can effectively predict pregnancy potential with high performance 13,14 .”
Transformer Models, Graph Networks, and Generative AI in Gut Microbiome Research: A Narrative Review
Zhu, Y., Tang, Y., Qi, X., & Zhu, X. (2026) · Bioengineering · doi:10.3390/bioengineering13020144 · Cited by 18
“Gut microbiome composition is highly sensitive to external influences such as diet, medication use, geography, age, lifestyle, and host genetics [18,107].”
Supervised learning and model analysis with compositional data
Huang, S., Ailer, E., Kilbertus, N., & Pfister, N. (2023) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1011240 · Cited by 22
Liu, Z., Sun, Y., Li, Y., Ma, A., Willaims, N. F., Jahanbahkshi, S., Hoyd, R., Wang, X., Zhang, S., Zhu, J., et al. (2024) · Advanced Science · doi:10.1002/advs.202403393 · Cited by 19
Data and Statistical Methods To Analyze the Human Microbiome
Waldron, L. (2018) · mSystems · doi:10.1128/msystems.00194-17 · Cited by 18
“We have also shown the value of these approaches for metagenomic prediction problems (17).”
BackgroundSelf-citationPredicting Host Phenotype Based on Gut Microbiome Using a Convolutional Neural Network Approach
Reiman, D. J., Farhat, A. M., & Dai, Y. D. (2020) · Methods in molecular biology · doi:10.1007/978-1-0716-0826-5_12 · Cited by 15
Child type 1 diabetes associated with mother vaginal bacteriome and mycobiome
Ruotsalainen, A. L., Tejesvi, M. V., Vänni, P., Suokas, M., Tossavainen, P. H., Pirttilä, A. M., Talvensaari‐Mattila, A., & Nissi, R. (2022) · Medical Microbiology and Immunology · doi:10.1007/s00430-022-00741-w · Cited by 17
Statistical Data Analysis of Microbiomes and Metabolomics
Xia, Y., & Sun, J. (2021) · ACS in focus · doi:10.1021/acsinfocus.7e5035 · Cited by 15
Metadata
- Authors
- Pasolli, E., Truong, D. T., Malik, F., Waldron, L., & Segata, N.
- Affiliations
- University of Trento (IT)
- City University of New York (US)
- Corresponding author
- Segata, Nicola
- Venue
- PLOS Computational Biology
- Publisher
- Public Library of Science (PLoS)
- Published
- 2016-07-11
- Volume
- 12
- Issue
- 7
- Pages
- e1004977
- ISSN
- 1553-734X (ISSN-L)
- 1553-7358
- PMC
- PMC4939962
- OpenAlex
- W2473355215
- Cited by
- 659
- References
- 71
- Citations by year
- 2026: 81 · 2025: 66 · 2024: 83 · 2023: 64 · 2022: 84 · 2021: 93 · 2020: 80 · 2019: 44 · 2018: 38 · 2017: 24 · 2016: 1
- FWCI
- 3.23
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- PLoS Computational Biology (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Iris (University of Trento) (submittedVersion, cc-by)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Figshare (submittedVersion, cc-by)
- Funders
- Ministero dell’Istruzione, dell’Università e della Ricerca (RBFR13EWWI)
- Seventh Framework Programme (BE) (PCIG13-618833)
- Fondazione Caritro (Rif.Int.2013.0239)
- Terme di Comano
- National Science Foundation (CNS-958379, CNS-0855217, ACI-1126113)
- City University of New York High Performance Computing Center
- National Institute of Allergy and Infectious Diseases (1R21AI121784-01)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gut microbiota and health
- Health Sciences › Dentistry › Periodontics › Oral microbiology and periodontitis research
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
- Keywords
- metagenomics, human microbiome, disease prediction, biomarker discovery, strain-specific markers, dysbiosis, Streptococcus anginosus, feature selection, cross-validation
- MeSH terms
- Gastrointestinal Microbiome, Machine Learning, Humans, Obesity, Software, Colorectal Neoplasms, Inflammatory Bowel Diseases, Computational Biology, Metagenome, Metagenomics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.