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
Opportunities and obstacles for deep learning in biology and medicine
Ching, T., Himmelstein, D. S., Beaulieu-Jones, B. K., Kalinin, A. A., Do, B. T., Way, G. P., Ferrero, E., Agapow, P.-M., Zietz, M., Hoffman, M. M., et al. (2018) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0387 · Cited by 2,310
“Also, researchers have looked into how feature selection can improve classification [237,239], and techniques have been proposed that are classifier-independent [240,241].”
BackgroundBeghini, F., McIver, L. J., Blanco-Míguez, A., Dubois, L., Asnicar, F., Maharjan, S., Mailyan, A., Manghi, P., Scholz, M., Thomas, A. M., et al. (2021) · eLife · doi:10.7554/elife.65088 · Cited by 2,303
Self-citationShotgun metagenomics, from sampling to analysis
Quince, C., Walker, A. W., Simpson, J. T., Loman, N. J., & Segata, N. (2017) · Nature Biotechnology · doi:10.1038/nbt.3935 · Cited by 2,202
Self-citationExtensive impact of non-antibiotic drugs on human gut bacteria
Maier, L., Pruteanu, M., Kuhn, M., Zeller, G., Telzerow, A., Anderson, E. E., Brochado, A. R., Fernandez, K. C., Dose, H., Mori, H., et al. (2018) · Nature · doi:10.1038/nature25979 · Cited by 1,905
“This suggests that human-targeted drugs have an even larger impact to the gut microbiome with key species related to healthy status 15, such as major butyrate-(E. rectale, R. intestinalis, Coprococcus comes) and propionate-producers (B. vulgatus, Prevotella copri, Blautia obeum) 16, and enterotype…”
Species-level functional profiling of metagenomes and metatranscriptomes
Franzosa, E. A., McIver, L. J., Rahnavard, G., Thompson, L. R., Schirmer, M., Weingart, G., Lipson, K. S., Knight, R., Caporaso, J. G., Segata, N., et al. (2018) · Nature Methods · doi:10.1038/s41592-018-0176-y · Cited by 1,693
Self-citationWirbel, J., Pyl, P. T., Kartal, E., Zych, K., Kashani, A., Milanese, A., Fleck, J. S., Voigt, A. Y., Palleja, A., Ponnudurai, R., et al. (2019) · Nature Medicine · doi:10.1038/s41591-019-0406-6 · Cited by 1,373
Self-citationThomas, A. M., Manghi, P., Asnicar, F., Pasolli, E., Armanini, F., Zolfo, M., Beghini, F., Manara, S., Karcher, N., Pozzi, C., et al. (2019) · Nature Medicine · doi:10.1038/s41591-019-0405-7 · Cited by 1,030
Self-citationAsnicar, F., Berry, S. E., Valdes, A. M., Nguyen, L. H., Piccinno, G., Drew, D. A., Leeming, E., Gibson, R., Le Roy, C., Khatib, H. A., et al. (2021) · Nature Medicine · doi:10.1038/s41591-020-01183-8 · Cited by 995
Self-citationMeta-analysis of gut microbiome studies identifies disease-specific and shared responses
(2017) · doi:10.1038/s41467-017-01973-8 · Cited by 986
The Human Gut Microbiome: From Association to Modulation
Schmidt, T. S. B., Raes, J., & Bork, P. (2018) · Cell · doi:10.1016/j.cell.2018.02.044 · Cited by 845
“Two recent meta-analyses of microbiome-disease association studies found that between-study variation required explicit or implicit batch effect correction (Duvallet et al., 2017; Pasolli et al., 2016).”
BackgroundMicrobial strain-level population structure and genetic diversity from metagenomes
Truong, D. T., Tett, A., Pasolli, E., Huttenhower, C., & Segata, N. (2017) · Genome Research · doi:10.1101/gr.216242.116 · Cited by 839
Self-citationThe gut microbiome as a modulator of healthy ageing
Ghosh, T. S., Shanahan, F., & O’Toole, P. W. (2022) · Nature Reviews Gastroenterology & Hepatology · doi:10.1038/s41575-022-00605-x · Cited by 817
Meslier, V., Laiola, M., Roager, H. M., De Filippis, F., Roume, H., Quinquis, B., Giacco, R., Mennella, I., Ferracane, R., Pons, N., et al. (2020) · Gut · doi:10.1136/gutjnl-2019-320438 · Cited by 583
Self-citationEstaki, M., Jiang, L., Bokulich, N. A., McDonald, D., González, A., Kosciolek, T., Martino, C., Zhu, Q., Birmingham, A., Vázquez‐Baeza, Y., et al. (2020) · Current Protocols in Bioinformatics · doi:10.1002/cpbi.100 · Cited by 565
“…(GSC) has created the “Minimum Information about any (x) Sequence” (MIxS) and “Minimum Information about a MARKer gene Sequence” (MIMARKS) specifications (Yilmaz et al., 2011) as well as 15 “environmental packages” that extend and refine these standards for samples from environments ranging from…”
BackgroundAnalysis of Gut Microbiota in Patients with Parkinson’s Disease
Petrov, V. A., Saltykova, I. V., Zhukova, I. A., Alifirova, V. M., Zhukova, N. G., Dorofeeva, Y. B., Tyakht, A. V., Kovarsky, B. A., Alekseev, D. G., Kostryukova, E. S., et al. (2017) · Bulletin of Experimental Biology and Medicine · doi:10.1007/s10517-017-3700-7 · Cited by 487
Accessible, curated metagenomic data through ExperimentHub
Pasolli, E., Schiffer, L., Manghi, P., Renson, A., Obenchain, V., Truong, D. T., Beghini, F., Malik, F., Ramos, M., Dowd, J. B., et al. (2017) · Nature Methods · doi:10.1038/nmeth.4468 · Cited by 514
Self-citationThe Human Oral Microbiome in Health and Disease: From Sequences to Ecosystems
Willis, J. R., & Gabaldón, T. (2020) · Microorganisms · doi:10.3390/microorganisms8020308 · Cited by 468
“One machine learning-based study, which collected 2424 publicly available metagenomes from eight studies, showed that the performance of disease predictions was improved when using strain-level features (not feasible with 16S sequencing), and suggested that disease phenotypes are linked to “non-core” microbial genes/f…”
BackgroundLee, K. A., Thomas, A. M., Bolte, L. A., Björk, J. R., de Ruijter, L. K., Armanini, F., Asnicar, F., Blanco-Miguez, A., Board, R., Calbet-Llopart, N., et al. (2022) · Nature Medicine · doi:10.1038/s41591-022-01695-5 · Cited by 464
Self-citationForbes, J. D., Chen, C.-Y., Knox, N. C., Marrie, R.-A., El-Gabalawy, H., de Kievit, T., Alfa, M., Bernstein, C. N., & Van Domselaar, G. (2018) · Microbiome · doi:10.1186/s40168-018-0603-4 · Cited by 450
Marcos-Zambrano, L. J., Karaduzovic-Hadziabdic, K., Loncar Turukalo, T., Przymus, P., Trajkovik, V., Aasmets, O., Berland, M., Gruca, A., Hasic, J., Hron, K., et al. (2021) · Frontiers in Microbiology · doi:10.3389/fmicb.2021.634511 · Cited by 416
“Pasolli et al. (2016) used the SVM, RF classifiers, LASSO and elastic net regularized multiple logistic regression, Neural Networks and Bayesian logistic regression, and assessed the prediction power of metagenomic data in linking the gut microbiome with disease states (Pasolli et al., 2016).”
MethodGut microbiome in HCC – Mechanisms, diagnosis and therapy
Schwabe, R. F., & Greten, T. F. (2020) · Journal of Hepatology · doi:10.1016/j.jhep.2019.08.016 · Cited by 363
Machine learning and deep learning applications in microbiome research
Hernández Medina, R., Kutuzova, S., Nielsen, K. N., Johansen, J., Hansen, L. H., Nielsen, M., & Rasmussen, S. (2022) · ISME Communications · doi:10.1038/s43705-022-00182-9 · Cited by 341
“Among the classical ML methods, linear regression models, random forests (RFs), and support vector machines (SVMs) have been found to perform well on microbiome data [38, 39].”
MethodMeta-Analysis Reveals Reproducible Gut Microbiome Alterations in Response to a High-Fat Diet
Bisanz, J. E., Upadhyay, V., Turnbaugh, J. A., Ly, K., & Turnbaugh, P. J. (2019) · Cell Host & Microbe · doi:10.1016/j.chom.2019.06.013 · Cited by 333
“As a first pass, we conducted a leave-one-dataset-out analysis (Pasolli et al., 2016) in which each study using conventionally-colonized mice was systematically excluded from training and then subsequently predicted using the model (Figure S2C) demonstrating excellent reproducibility with a median area under the recei…”
MethodGut microbiome, big data and machine learning to promote precision medicine for cancer
Cammarota, G., Ianiro, G., Ahern, A., Carbone, C., Temko, A., Claesson, M. J., Gasbarrini, A., & Tortora, G. (2020) · Nature Reviews Gastroenterology & Hepatology · doi:10.1038/s41575-020-0327-3 · Cited by 324
Ghannam, R. B., & Techtmann, S. M. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.01.028 · Cited by 278
Topçuoğlu, B. D., Lesniak, N. A., Ruffin, M. T., Wiens, J., & Schloss, P. D. (2020) · mBio · doi:10.1128/mbio.00434-20 · Cited by 266
Wirbel, J., Zych, K., Essex, M., Karcher, N., Kartal, E., Salazar, G., Bork, P., Sunagawa, S., & Zeller, G. (2021) · Genome Biology · doi:10.1186/s13059-021-02306-1 · Cited by 269
Machine learning for microbiologists
Asnicar, F., Thomas, A. M., Passerini, A., Waldron, L., & Segata, N. (2024) · Nature Reviews Microbiology · doi:10.1038/s41579-023-00984-1 · Cited by 256
“This approach was proposed for transcriptomic 114 and microbiome studies 28 .”
Self-citationAdjusting for age improves identification of gut microbiome alterations in multiple diseases
Ghosh, T. S., Das, M., Jeffery, I. B., & O'Toole, P. W. (2020) · eLife · doi:10.7554/elife.50240 · Cited by 233
“Alterations in the gut microbiome have been reported for many diseases (Duvallet et al., 2017; Pasolli et al., 2016).”
BackgroundMethodResultInfluentialBig data in IBD: big progress for clinical practice
Seyed Tabib, N. S., Madgwick, M., Sudhakar, P., Verstockt, B., Korcsmaros, T., & Vermeire, S. (2020) · Gut · doi:10.1136/gutjnl-2019-320065 · Cited by 223
“Multiple machine learning-based microbiome frameworks have been established such as Multivariate Association with Linear Models (MaAsLin), 68 Metagenomic prediction Analysis based on Machine Learning 69 and phylogenetic convolutional neural networks 70 which incorporate patient clinical data, knowledge of microbial st…”
MethodAltered microbiome composition in individuals with fibromyalgia
Minerbi, A., Gonzalez, E., Brereton, N. J. B., Anjarkouchian, A., Dewar, K., Fitzcharles, M.-A., Chevalier, S., & Shir, Y. (2019) · Pain · doi:10.1097/j.pain.0000000000001640 · Cited by 220
“Having established that gut microbiome is altered in FM patients, LASSO machine-learning algorithm showed high prediction accuracy of patients from controls, based only on individual microbiome features.(67) Further study, including larger cohorts, greater ethnic sampling, and cross-cohort assessment, is required befo…”
Result(2020) · Progress in Molecular Biology and Translational Science · doi:10.1016/bs.pmbts.2020.04.003 · Cited by 212
Artificial Intelligence (AI)-Based Systems Biology Approaches in Multi-Omics Data Analysis of Cancer
Biswas, N., & Chakrabarti, S. (2020) · Frontiers in Oncology · doi:10.3389/fonc.2020.588221 · Cited by 209
De Filippis, F., Paparo, L., Nocerino, R., Della Gatta, G., Carucci, L., Russo, R., Pasolli, E., Ercolini, D., & Berni Canani, R. (2021) · Nature Communications · doi:10.1038/s41467-021-26266-z · Cited by 206
Self-citationPredicting measures of soil health using the microbiome and supervised machine learning
Wilhelm, R. C., van Es, H. M., & Buckley, D. H. (2022) · Soil Biology and Biochemistry · doi:10.1016/j.soilbio.2021.108472 · Cited by 203
“There are methods to address these challenges, such as regularization (Pasolli et al., 2016; Topçuoğlu et al., 2020) or aggregating features by broader classes (Statnikov et al.”
MethodUnexplored diversity and strain-level structure of the skin microbiome associated with psoriasis
Tett, A., Pasolli, E., Farina, S., Truong, D. T., Asnicar, F., Zolfo, M., Beghini, F., Armanini, F., Jousson, O., De Sanctis, V., et al. (2017) · npj Biofilms and Microbiomes · doi:10.1038/s41522-017-0022-5 · Cited by 209
Self-citationLarge-scale comparative metagenomics of Blastocystis, a common member of the human gut microbiome
Beghini, F., Pasolli, E., Truong, T. D., Putignani, L., Cacciò, S. M., & Segata, N. (2017) · The ISME Journal · doi:10.1038/ismej.2017.139 · Cited by 201
“Our previous work on such machine learning signatures (Pasolli et al., 2016) showed that all the diseases considered here can be associated, with a variable degree of accuracy, with their microbiome structures.”
MethodInfluentialSelf-citationAutonomous biomedical research with an artificial intelligence agent
Huang, K., Zhang, S., Wang, H., Qu, Y., Lu, Y., Li, R., Roohani, Y., Qiu, L., Cao, S., Li, G. L., et al. (2026) · Science · doi:10.1126/science.adz4351 · Cited by 349
q2-sample-classifier: machine-learning tools for microbiome classification and regression
Bokulich, N., Dillon, M., Bolyen, E., Kaehler, B., Huttley, G., & Caporaso, J. (2018) · Journal of Open Source Software · doi:10.21105/joss.00934 · Cited by 206
A Review and Tutorial of Machine Learning Methods for Microbiome Host Trait Prediction
Zhou, Y.-H., & Gallins, P. (2019) · Frontiers in Genetics · doi:10.3389/fgene.2019.00579 · Cited by 192
“Prediction models have sometimes been difficult to generalize across studies (Pasolli et al., 2016).”
BackgroundMethodInfluentialExperimental design and quantitative analysis of microbial community multiomics
Mallick, H., Ma, S., Franzosa, E. A., Vatanen, T., Morgan, X. C., & Huttenhower, C. (2017) · Genome Biology · doi:10.1186/s13059-017-1359-z · Cited by 192
“Meta-analysis [91] is, in general, the quantitative integration of findings from multiple studies, and it is crucial in any molecular 'omics field for verifying true, biological associations and improving power.”
BackgroundMethodInfluentialDeepMicro: Deep representation learning for disease prediction based on microbiome data
Oh, M., & Zhang, L. (2020) · Scientific Reports · doi:10.1038/s41598-020-63159-5 · Cited by 190
Correcting for batch effects in case-control microbiome studies
Gibbons, S. M., Duvallet, C., & Alm, E. J. (2018) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1006102 · Cited by 162
“Consequently, pooling non-normalized data from different batches has been 508 common practice in the microbiome field [27, 29, 35, 47-55].”
MethodA gut microbial signature for combination immune checkpoint blockade across cancer types
Gunjur, A., Shao, Y., Rozday, T., Klein, O., Mu, A., Haak, B. W., Markman, B., Kee, D., Carlino, M. S., Underhill, C., et al. (2024) · Nature Medicine · doi:10.1038/s41591-024-02823-z · Cited by 165
“We chose to use RF as our classifier, given its, on average, superior performance using microbial feature sets in previous benchmarking studies 31 .”
Ma, S., Shungin, D., Mallick, H., Schirmer, M., Nguyen, L. H., Kolde, R., Franzosa, E., Vlamakis, H., Xavier, R., & Huttenhower, C. (2022) · Genome biology · doi:10.1186/s13059-022-02753-4 · Cited by 164
“Of note, two meta-analysis studies included IBD as one of several phenotypes [24, 25].”
Chang, H.-X., Haudenshield, J. S., Bowen, C. R., & Hartman, G. L. (2017) · Frontiers in Microbiology · doi:10.3389/fmicb.2017.00519 · Cited by 159
“While the prediction model with a small training set resulted in lower accuracy compare to machine learning prediction in human diseases (generally included 100–300 samples; Pasolli et al., 2016), we expect the accuracy would be improved with a larger sample size.”
ResultGlasl, B., Webster, N. S., & Bourne, D. G. (2017) · Marine Biology · doi:10.1007/s00227-017-3097-x · Cited by 163
“Machine learning is a powerful tool and a current state-ofthe-art approach to identify dysbiosis of the human microbiome and to predict human diseases (Pasolli et al. 2016).”
BackgroundMicrobiome Tools for Forensic Science
Metcalf, J. L., Xu, Z. Z., Bouslimani, A., Dorrestein, P., Carter, D. O., & Knight, R. (2017) · Trends in Biotechnology · doi:10.1016/j.tibtech.2017.03.006 · Cited by 160
Armour, C. R., Nayfach, S., Pollard, K. S., & Sharpton, T. J. (2019) · mSystems · doi:10.1128/msystems.00332-18 · Cited by 160
“diseases finding that integrating multiple datasets improved prediction capabilities[15].”
BackgroundSocioeconomic Status and the Gut Microbiome: A TwinsUK Cohort Study
Bowyer, R. C. E., Jackson, M. A., Le Roy, C. I., Ni Lochlainn, M., Spector, T. D., Dowd, J. B., & Steves, C. J. (2019) · Microorganisms · doi:10.3390/microorganisms7010017 · Cited by 150
“For example, lower levels of deprivation correlate with key health-associated bacteria such as Faecalibacterium prausnitzii and Akkermansia muciniphila, both proposed to reduce host inflammation [52,53], whereas higher levels of deprivation were associated with Streptococcus anginosus, which has been identified as a m…”
BackgroundMachine learning for data integration in human gut microbiome
Li, P., Luo, H., Ji, B., & Nielsen, J. (2022) · Microbial Cell Factories · doi:10.1186/s12934-022-01973-4 · Cited by 140
Ghensi, P., Manghi, P., Zolfo, M., Armanini, F., Pasolli, E., Bolzan, M., Bertelle, A., Dell’Acqua, F., Dellasega, E., Waldner, R., et al. (2020) · npj Biofilms and Microbiomes · doi:10.1038/s41522-020-00155-7 · Cited by 150
Self-citationUnexplored microbial diversity from 2,500 food metagenomes and links with the human microbiome.
Carlino, N., Blanco-Míguez, A., Punčochář, M., Mengoni, C., Pinto, F., Tatti, A., Manghi, P., Armanini, F., Avagliano, M., Barcenilla, C., et al. (2024) · Cell · doi:10.1016/j.cell.2024.07.039 · Cited by 146
Niazi, S. K. (2023) · Drug Design Development and Therapy · doi:10.2147/dddt.s424991 · Cited by 184
“Help analyze the complex data from microbiome studies, potentially leading to new strategies for personalized drug therapy.(92)”
MethodMicrobiota and cancer immunotherapy: in search of microbial signals
Gharaibeh, R. Z., & Jobin, C. (2019) · Gut · doi:10.1136/gutjnl-2018-317220 · Cited by 144
Carcinogenesis and therapeutics: the microbiota perspective
Tsilimigras, M. C. B., Fodor, A., & Jobin, C. (2017) · Nature Microbiology · doi:10.1038/nmicrobiol.2017.8 · Cited by 144
Fackelmann, G., Manghi, P., Carlino, N., Heidrich, V., Piccinno, G., Ricci, L., Piperni, E., Arrè, A., Bakker, E., Creedon, A. C., et al. (2025) · Nature Microbiology · doi:10.1038/s41564-024-01870-z · Cited by 142
“In addition, diet patterns were highly distinguishable based on quantitative gut microbial profiles when using machine learning classifiers 17 .”
Self-citationThompson, J., Johansen, R., Dunbar, J., & Munsky, B. (2019) · PLOS ONE · doi:10.1371/journal.pone.0215502 · Cited by 144
Fermented food products in the era of globalization: tradition meets biotechnology innovations
Galimberti, A., Bruno, A., Agostinetto, G., Casiraghi, M., Guzzetti, L., & Labra, M. (2020) · Current Opinion in Biotechnology · doi:10.1016/j.copbio.2020.10.006 · Cited by 149
Faecal microbiome-based machine learning for multi-class disease diagnosis
Su, Q., Liu, Q., Lau, R. I., Zhang, J., Xu, Z., Yeoh, Y. K., Leung, T. W. H., Tang, W., Zhang, L., Liang, J. Q. Y., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-34405-3 · Cited by 133
Gupta, R., Kumari, S., Senapati, A., Ambasta, R. K., & Kumar, P. (2023) · Ageing Research Reviews · doi:10.1016/j.arr.2023.102013 · Cited by 134
Precision medicine using microbiota
Jobin, C. (2018) · Science · doi:10.1126/science.aar2946 · Cited by 133
Piccinno (2025) · doi:10.1038/s41591-025-03693-9 · Cited by 133
“For the ML analysis, we used the random forest classifier as implemented in the metaml tool (https://github.com/SegataLab/metaml) 29 .”
Multi-omic integration of microbiome data for identifying disease-associated modules
Muller, E., Shiryan, I., & Borenstein, E. (2024) · Nature Communications · doi:10.1038/s41467-024-46888-3 · Cited by 119
Campbell, T. P., Sun, X., Patel, V. H., Sanz, C., Morgan, D., & Dantas, G. (2020) · The ISME Journal · doi:10.1038/s41396-020-0634-2 · Cited by 130
Reiman, D. J., Metwally, A. A., Sun, J., & Dai, Y. D. (2020) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.2993761 · Cited by 145
“In the MetAML study [13], the OTUs for each dataset were assigned by MetaPhlAn2, which selects OTUs based on the read coverage of clade-specific markers and then estimates their relative abundance [30].”
BackgroundMethodToward an improved definition of a healthy microbiome for healthy aging
Ghosh, T. S., Shanahan, F., & O’Toole, P. W. (2022) · Nature Aging · doi:10.1038/s43587-022-00306-9 · Cited by 139
Mei, Z., Wang, F., Bhosle, A., Dong, D., Mehta, R. S., Ghazi, A. R., Zhang, Y., Liu, Y., Rinott, E., Ma, S., et al. (2024) · Nature Medicine · doi:10.1038/s41591-024-03067-7 · Cited by 142
“To examine whether the inclusion of gut microbial features improved the classification between T2D and controls, we used the MetAML package 74 , with the random forest algorithm implemented in Scikit-Learn v.0.19.0.”
InfluentialNishijima, S., Stankevič, E., Aasmets, O., Schmidt, T., Nagata, N., Keller, M. I., Ferretti, P., Juel, H. B., Fullam, A., Robbani, S. M., et al. (2024) · Cell · doi:10.1016/j.cell.2024.10.022 · Cited by 147
Biomni: A general-purpose biomedical ai agent
Huang, K., Zhang, S., Wang, H., Qu, Y., Lu, Y., Roohani, Y., Li, R., Qiu, L., Li, G., Zhang, J., et al. (2025) · doi:10.1101/2025.05.30.656746 · Cited by 125
“Dataset 3, developed by Pasolli et al. 37 , combines eight human metagenomic studies with species-level features processed using MetaPhlAn2 37 .”
The potential of tailoring the gut microbiome to prevent and treat cardiometabolic disease
Chakaroun, R., Olsson, L. M., & Bäckhed, F. (2022) · Nature Reviews Cardiology · doi:10.1038/s41569-022-00771-0 · Cited by 139
Large-Scale Automatic Feature Selection for Biomarker Discovery in High-Dimensional OMICs Data
Leclercq, M., Vittrant, B., Martin‐Magniette, M., Scott‐Boyer, M., Périn, O., Bergeron, A., Fradet, Y., & Droit, A. (2019) · Frontiers in Genetics · doi:10.3389/fgene.2019.00452 · Cited by 134
“These signatures, which are measurable indicators for predicting a biological phenomenon, are usually identified using machine learning (Pasolli et al., 2016) or statistical multivariate analysis approaches (Rohart et al., 2017c).”
BackgroundChanda, D., & De, D. (2024) · Gut Microbes · doi:10.1080/19490976.2024.2304900 · Cited by 128
“Random forest (RF) algorithm was used as a backend classifier in MetAML as it outperforms other machine learning algorithms with microbiome data 23.”
MethodLaPierre, N., Ju, C. J.-T., Zhou, G., & Wang, W. (2019) · Methods · doi:10.1016/j.ymeth.2019.03.003 · Cited by 114
“In the context of metagenome-based disease prediction, these features are the microbes or the functional elements that contribute most to the disease prediction, enhancing the interpretability of the model [5, 9, 7, 21].”
BackgroundMethodResultInfluentialD’Urso, F., & Broccolo, F. (2024) · Applied Sciences · doi:10.3390/app14198627 · Cited by 112
Machine Learning and Artificial Intelligence in the Multi-Omics Approach to Gut Microbiota
Rozera, T., Pasolli, E., Segata, N., & Ianiro, G. (2025) · Gastroenterology · doi:10.1053/j.gastro.2025.02.035 · Cited by 112
Self-citationMoreno-Indias, I., Lahti, L., Nedyalkova, M., Elbere, I., Roshchupkin, G., Adilovic, M., Aydemir, O., Bakir-Gungor, B., Santa Pau, E. C.-D., D’Elia, D., et al. (2021) · Frontiers in Microbiology · doi:10.3389/fmicb.2021.635781 · Cited by 112
“Common ML algorithms such as random forest, support vector machines (SVM), elastic net, and LASSO have all been used for disease-prediction tasks (Pasolli et al., 2016), and automated feature selection schemes have been reported to perform will in comparison with standard tests in disease…”
BackgroundMethodShukla, V., Singh, S., Verma, S., Verma, S., Rizvi, A. A., & Abbas, M. (2024) · Clinical Nutrition ESPEN · doi:10.1016/j.clnesp.2024.08.005 · Cited by 133
The significance of microbiome in personalized medicine
Behrouzi, A., Nafari, A. H., & Siadat, S. D. (2019) · Clinical and Translational Medicine · doi:10.1186/s40169-019-0232-y · Cited by 120
Piperni, E., Nguyen, L. H., Manghi, P., Kim, H., Pasolli, E., Andreu‐Sánchez, S., Arrè, A., Bermingham, K. M., Blanco‐Míguez, A., Manara, S., et al. (2024) · Cell · doi:10.1016/j.cell.2024.06.018 · Cited by 115
“…(CV, median area under the receiver operating characteristic curve AUC = 0.87) and a leave-one-dataset-out (LODO, median AUC = 0.88) framework, 77,78 indicating a strong and reproducible association between the bacterial and archaeal population in the microbiome and Blastocystis (Figure 5A).”
InfluentialSelf-citationFecal Microbial Transplantation for Diseases Beyond Recurrent Clostridium Difficile Infection
D’Haens, G. R., & Jobin, C. (2019) · Gastroenterology · doi:10.1053/j.gastro.2019.04.053 · Cited by 98
“Whole-genome metagenome and 16S rDNA analyses revealed differences in microbiome composition and gene richness between feces of obese subjects and healthy lean subjects (101–103), but these differences were not large enough to distinguish between the groups (104).”
BackgroundLee, S. T. M., Kahn, S. A., Delmont, T. O., Shaiber, A., Esen, Ö. C., Hubert, N. A., Morrison, H. G., Antonopoulos, D. A., Rubin, D. T., & Eren, A. M. (2017) · Microbiome · doi:10.1186/s40168-017-0270-x · Cited by 102
“We used 151 Human Microbiome Project (HMP) gut metagenomes [50] to estimate the detection of our MAGs and to compare the taxonomic profiles of our metagenomes in the context of the HMP participants.”
MethodExplainable AI reveals changes in skin microbiome composition linked to phenotypic differences
Carrieri, A. P., Haiminen, N., Maudsley-Barton, S., Gardiner, L.-J., Murphy, B., Mayes, A. E., Paterson, S., Grimshaw, S., Winn, M., Shand, C., et al. (2021) · Scientific Reports · doi:10.1038/s41598-021-83922-6 · Cited by 94
Taxonomy-aware feature engineering for microbiome classification
Oudah, M., & Henschel, A. (2018) · BMC Bioinformatics · doi:10.1186/s12859-018-2205-3 · Cited by 96
“Recent work on microbiota/metagenome classification, such as Fizzy [11] and MetAML [12], utilize standard feature selection algorithms, not capitalizing on the evolutionary relationship and thus the hierarchical structure of features.”
BackgroundMethodChen, W.-P., Chang, S., Tang, C. Y., Liou, M., Tsai, S. J., & Lin, Y.-L. (2018) · BioMed Research International · doi:10.1155/2018/3130607 · Cited by 109
Chen, Y., Wang, H., Lu, W., Wu, T., Yuan, W., Zhu, J., Lee, Y. K., Zhao, J., Zhang, H., & Chen, W. (2022) · Gut Microbes · doi:10.1080/19490976.2021.2025016 · Cited by 94
“8,9 Second, because metagenomic data are usually sparse and presented as a high-dimensional matrix with high noise, 10 there is an urgent need for an optimal machine learning method to decipher the links between aging and microflora composition and functions.”
BackgroundExploring Linkages between Taxonomic and Functional Profiles of the Human Microbiome
Langille, M. G. I. (2018) · mSystems · doi:10.1128/msystems.00163-17 · Cited by 109
“Machine learning methods based on metagenomic taxonomic profiles have shown promise for the classification of various diseases such as colorectal cancer, obesity, diabetes, and Crohn’s disease (8).”
BackgroundHarnessing machine learning for development of microbiome therapeutics
McCoubrey, L. E., Elbadawi, M., Orlu, M., Gaisford, S., & Basit, A. W. (2021) · Gut Microbes · doi:10.1080/19490976.2021.1872323 · Cited by 93
“A variety of ML methods, such as support vector machines, neural networks, and logistic regression, have been utilized to identify microbiota features present in several disease states.(61) Gupta et al.”
MethodManandhar, I., Alimadadi, A., Aryal, S., Munroe, P. B., Joe, B., & Cheng, X. (2021) · American Journal of Physiology-Gastrointestinal and Liver Physiology · doi:10.1152/ajpgi.00360.2020 · Cited by 91
A framework for microbiome science in public health
Wilkinson, J. E., Franzosa, E. A., Everett, C., Li, C., trainees, H. R. A., Bae, S., Berzansky, I., Bhosle, A., Bjørnevik, K., Brennan, C. A., et al. (2021) · Nature Medicine · doi:10.1038/s41591-021-01258-0 · Cited by 99
Mills, S., Lane, J. A., Smith, G. J., Grimaldi, K. A., Ross, R. P., & Stanton, C. (2019) · Nutrients · doi:10.3390/nu11071468 · Cited by 88
“Indeed, machine learning models for predicting disease from metagenomic datasets have already been developed [248].”
BackgroundPredicting Growth and Carcass Traits in Swine Using Microbiome Data and Machine Learning Algorithms
Maltecca, C., Lu, D., Schillebeeckx, C., McNulty, N. P., Schwab, C. R., Shull, C. M., & Tiezzi, F. (2019) · Scientific Reports · doi:10.1038/s41598-019-43031-x · Cited by 104
Dissecting microbial communities and resistomes for interconnected humans, soil, and livestock
Maciel-Guerra, A., Baker, M., Hu, Y., Wang, W., Zhang, X., Rong, J., Zhang, Y., Zhang, J., Kaler, J., Renney, D., et al. (2022) · The ISME Journal · doi:10.1038/s41396-022-01315-7 · Cited by 94
Kumar, B., Lorusso, E., Fosso, B., & Pesole, G. (2024) · Frontiers in Microbiology · doi:10.3389/fmicb.2024.1343572 · Cited by 103
Measuring the microbiome: Best practices for developing and benchmarking microbiomics methods
Bokulich, N. A., Ziemski, M., Robeson, M. S., & Kaehler, B. D. (2020) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2020.11.049 · Cited by 114
“Automated tools now exist for cross validation of sample classi-fication methods [110,137] and taxonomic classification methods [144].”
BackgroundMethodInfluentialMuñoz, R. R. S., Mantz, S., Martínez, I., Li, F., Schmaltz, R. J., Pudlo, N. A., Urs, K., Martens, E. C., Walter, J., & Ramer‐Tait, A. E. (2022) · The ISME Journal · doi:10.1038/s41396-022-01208-9 · Cited by 96
“Moreover, numerous studies have documented differences in microbiome composition and function between healthy and diseased humans and animals [8, 9].”
BackgroundMicrobiome epidemiology and association studies in human health
VanEvery, H., Franzosa, E. A., Nguyen, L. H., & Huttenhower, C. (2022) · Nature Reviews Genetics · doi:10.1038/s41576-022-00529-x · Cited by 94
Ong, I. M., Gonzalez, J. G., McIlwain, S. J., Sawin, E. A., Schoen, A. J., Adluru, N., Alexander, A. L., & Yu, J.-P. J. (2018) · Translational Psychiatry · doi:10.1038/s41398-017-0022-5 · Cited by 83
Asgari, E., Garakani, K., McHardy, A. C., & Mofrad, M. R. K. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty296 · Cited by 87
“Classification: Random Forests and linear SVM are the state-of-the-art classical approaches for categorical prediction on 16S rRNA sequencing [31, 39, 34] and in general for many machine learning problems in bioinformatics [64].”
Advances in flux balance analysis by integrating machine learning and mechanism-based models
Sahu, A., Blätke, M. A., Szymański, J., & Töpfer, N. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.08.004 · Cited by 97
“Both learning methods have been widely used to analyze large-scale biological datasets [56,57] and have also been integrated with FBA.”
Method
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.