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 401–500 of 666
DeepBiome: A Phylogenetic Tree Informed Deep Neural Network for Microbiome Data Analysis
Zhai, J., Choi, Y., Yang, X., Chen, Y., Knox, K. S., Twigg, H. L., Won, J., Zhou, H., & Zhou, J. J. (2024) · Statistics in Biosciences · doi:10.1007/s12561-024-09434-9 · Cited by 6
“DeepBiome required 290 ± 69 seconds to fully train the network for one replicate with 1000 samples, 50 mini-batches and 5000 epochs.”
Rahman, M. A., LaPierre, N., & Rangwala, H. (2017) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2017.2758782 · Cited by 5
“MetAML [11] assessed potential microbiome-phenotype associations using Random Forest (RF) and support vector machine classifiers.”
BackgroundMethodAn Integrative Framework for Functional Analysis of Cattle Rumen Microbiomes
Wassan, J. T., Zheng, H., Browne, F., Bowen, J. M., Walsh, P., Roehe, R., Dewhurst, R. J., Palu, C. C., Kelly, B., & Wang, H. (2018) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2018.8621104 · Cited by 5
Manning, T., Wassan, J. T., Palu, C. C., Wang, H., Browne, F., Zheng, H., Kelly, B., & Walsh, P. (2018) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm.2018.8621543 · Cited by 6
“The differences observed in the genetic profiles of the microbiota can then be used to, for example, detect traits in a host [2]–[4] or perform functional analysis [5]–[7].”
BackgroundOMARU: a robust and multifaceted pipeline for metagenome-wide association study
Kishikawa, T., Tomofuji, Y., Inohara, H., & Okada, Y. (2022) · NAR Genomics and Bioinformatics · doi:10.1093/nargab/lqac019 · Cited by 6
Moradigaravand, D., Li, L., Dechesne, A., Nesme, J., de la Cruz, R., Ahmad, H., Banzhaf, M., Sørensen, S. J., Smets, B. F., & Kreft, J. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad400 · Cited by 7
“, disease association [14, 15] or ecological status [16].”
BackgroundRevisit of Machine Learning Supported Biological and Biomedical Studies
Yu, X., Wang, L., & Zeng, T. (2018) · Methods in molecular biology · doi:10.1007/978-1-4939-7717-8_11 · Cited by 5
Enhancing Disease Prediction on Imbalanced Metagenomic Dataset by Cost-Sensitive
Nguyễn, H. T., Bao, T., Minh, Q., Hoang, H., Phuoc, T., & Cong, N. (2020) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2020.0110778 · Cited by 5
“The proposed approach performance is evaluated on the Inflammatory Bowel Disease (IBD) dataset [18], more details are in Table I.”
MethodMicrobial Evolution: An overlooked biomarker of host diet
Garud, N. R. (2022) · Cell Host & Microbe · doi:10.1016/j.chom.2022.01.009 · Cited by 5
Zhou, J., Wang, X., Ye, Y., & Jiang, J. (2021) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-021-01705-5 · Cited by 5
“Many people now use the above sequencing data to carry out prediction research [21, 24, 27].”
BackgroundMethodInfluentialThomas, A. M., Lima, F. P., Moura, L. M. S., da Silva, A. M., Dias‐Neto, E., & Setúbal, J. C. (2017) · Methods in molecular biology · doi:10.1007/978-1-4939-7463-4_8 · Cited by 6
Cross-validation approaches for multi-study predictions
Ren, B., Patil, P., Dominici, F., Parmigiani, G., & Trippa, L. (2025) · Electronic Journal of Statistics · doi:10.1214/25-ejs2450 · Cited by 9
“Gener-alist PFs have been studied from meta-analytic perspectives (Tseng et al., 2012; Pasolli et al., 2016) and using hierarchical models (Ventz et al., 2020; Rashid et al., 2020), often assuming study exchangeability.”
The evolutionary signal in metagenome phyletic profiles predicts many gene functions
Vidulin, V., Šmuc, T., Džeroski, S., & Supek, F. (2018) · Microbiome · doi:10.1186/s40168-018-0506-4 · Cited by 5
HIV infection among women and children and antidiscrimination laws: an overview.
Gittler, J., & Rennert, S. (1992) · PubMed · Cited by 5
Feng, J., Yang, K., Liu, X., Song, M. S., Zhan, P., Zhang, M., Chen, J., & Liu, J. (2023) · PeerJ · doi:10.7717/peerj.16304 · Cited by 4
Jiménez-Arroyo, C., Molinero, N., del Campo, R., Delgado, S., & Moreno-Arribas, M. V. (2025) · Enfermedades Infecciosas y Microbiología Clínica · doi:10.1016/j.eimc.2025.06.017 · Cited by 5
Haque, S., Bantun, F., Jalal, N. A., Faidah, H. S., Babalghith, A. O., Alobaidy, M. A., Aldairi, A. F., & Ahmad, F. (2025) · Gut Pathogens · doi:10.1186/s13099-025-00712-5 · Cited by 4
Ojetti, V., Petruzziello, C., Migneco, A., Candelli, M., & Saviano, A. (2025) · Biomedicines · doi:10.3390/biomedicines13112840 · Cited by 4
“These probiotics are able to enhance the production of mucin, strength the tight junctions, promote immune T-reg cell responses, and increase the release of anti-inflammatory cytokines such as interleukin-10 (IL-10) [13].”
Discovery of nitrogen-responsive microbial indicators as metrics of freshwater ecosystem health
Warren, J., de Vries, C. S., Hunt, L. H., Thorpe, A. C., Busi, S. B., KELLY, M. G., Simons, D., Taylor, J. D., Read, D. S., & Walsh, K. A. (2026) · Water Research · doi:10.1016/j.watres.2026.125959 · Cited by 4
“Such models have been widely applied to other microbiome data, particularly in healthcare settings (Pasolli et al. 2016; Ai et al. 2019; Zhou and Gallins 2019; Kosciolek et al. 2021).”
Balkrishna, A., Chaudhary, P., Singh, S., Saini, A., Kumari, A., Mahato, K. I., & Arya, V. (2026) · Frontiers in Microbiomes · doi:10.3389/frmbi.2026.1860559 · Cited by 3
“According to Pasolli et al. (2016), because microbiome machine-learning methods collect cohort-speci fi c microbial signatures rather than conserved biological patterns, they frequently show decreased repeatability across independent cohorts.”
Principal microbial groups: compositional alternative to phylogenetic grouping of microbiome data
Boyraz, A., Pawlowsky‐Glahn, V., Egozcue, J. J., & Acar, A. C. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac328 · Cited by 4
Huang, J., Lu, Y., Tian, F., & Ni, Y. (2024) · mSystems · doi:10.1128/msystems.01345-24 · Cited by 4
“Overall, although there are several machine learning techniques recognized for their ability to analyze high-dimensional data and perform feature selection (67–69), the unique complexity of microbiome count data should not be overlooked when effectively analyzing studies.”
Diagnostic potential of gut microbiota in Parkinson’s disease
Петров, В. А., Alifirova, V. M., Saltykova, I. V., Zhukova, I. A., Жукова, Н. Г., Dorofeeva, Y. B., Ikkert, O. P., Titova, M. A., Mironova, Y. S., Сазонов, А. Э., et al. (2020) · Bulletin of Siberian Medicine · doi:10.20538/1682-0363-2019-4-92-101 · Cited by 4
“The structure of metagenomic data is highly complex; for this reason, the use of validation samples to verify the quality of classifiers is especially important [26].”
BackgroundHuman Gut Microbiome Data Analysis for Disease Likelihood Prediction Using Autoencoders
Wickramaratne, D., Wijesinghe, R., & Weerasinghe, R. (2021) · International Conference on Advances in ICT for Emerging Regions · doi:10.1109/icter53630.2021.9774811 · Cited by 4
EpiK: A Knowledge Base for Epidemiological Modeling and Analytics of Infectious Diseases
Hasan, S. M. S., Fox, E. A., Bisset, K. R., & MARATHE, M. V. (2017) · Journal of Healthcare Informatics Research · doi:10.1007/s41666-017-0010-9 · Cited by 6
Nguyễn, H. T., Phan, N. Y. K., Luong, H. H., Le, T. P., & Tran, N. C. (2020) · Advances in Science Technology and Engineering Systems Journal · doi:10.25046/aj050368 · Cited by 4
Microbiome Biomarkers: One Step Closer in NAFLD Cirrhosis
Simon, T. G., Chan, A. T., & Huttenhower, C. (2020) · Hepatology · doi:10.1002/hep.31660 · Cited by 5
Li, B., Zhong, D., Qiao, J., & Jiang, X. (2022) · Methods · doi:10.1016/j.ymeth.2022.05.007 · Cited by 4
Gene-based microbiome representation enhances host phenotype classification
Deschênes, T., Tohoundjona, F. W. E., Plante, P.-L., Marzo, V. D., & Raymond, F. (2023) · mSystems · doi:10.1128/msystems.00531-23 · Cited by 9
“To deal with this problem, we used an embedded feature selection technique that consisted in training a random forest, ranking the features according to the resulting models, and learning on subsets of these ranked features, a method that has been used previously (6, 11).”
BackgroundMethodA large-scale Twitter dataset for drug safety applications mined from publicly existing resources
Tekumalla, R., & Banda, J. M. (2020) · Figshare · doi:10.5281/zenodo.3606862 · Cited by 4
Wang, N., Wu, M.-J., Gu, W., Dai, C., Shao, Z., & Subbalakshmi, K. P. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf217 · Cited by 8
“Subsequently, MetAML [31] was utilized to preprocess these abundance profiles by specifically selecting desired species-level features while excluding sub-species-level features.”
ATOMIC: a graph attention network for atopic dermatitis prediction using human gut microbiome
Bong, H., Min, J., Kim, S., Lım, W., Lim, D., Eom, H., Her, Y., & Jeon, M. (2026) · Frontiers in Immunology · doi:10.3389/fimmu.2025.1670993 · Cited by 3
“For example, Pasolli et al. (23) proposed MetAML, which applies random forests (RFs) and support vector machines (SVMs) to predict diseases using 2,424 publicly available microbiome samples.”
Ashango, Z. A., Seyum, E. G., & Nwogha, J. S. (2026) · Infection Genetics and Evolution · doi:10.1016/j.meegid.2026.105941 · Cited by 3
Synergizing multi-omics and artificial intelligence to unravel gut microbiome complexity: A review
Singh, J. R., & Singh, P. (2026) · Innovative Medicines & Omics · doi:10.36922/imo025490068 · Cited by 4
Rethinking Colorectal Cancer Microbiome: From Universal Biomarkers to Patient-Stratified Signatures
Schena, C. A., Laterza, V., Covino, M., & Rosa, F. (2026) · Gastrointestinal Disorders · doi:10.3390/gidisord8020026 · Cited by 3
“The shift from universal to patient-specific microbiome biomarkers is primarily an analytical and conceptual challenge, not a data limitation [59].”
Machine Learning Prediction of Nitrification From Ammonia- and Nitrite-Oxidizer Community Structure
Lee, C., Amini, F., Hu, G., & Halverson, L. J. (2022) · Frontiers in Microbiology · doi:10.3389/fmicb.2022.899565 · Cited by 3
“Machine learning provides one possible solution to these challenges and is increasingly used for modeling complex biological data (Pasolli et al., 2016; Chang et al., 2017; Thompson et al., 2019).”
BackgroundEbrahimi, F., Maleki, H., Ebrahimi, M., & Beiki, A. H. (2025) · Endocrinología Diabetes y Nutrición (English ed ) · doi:10.1016/j.endinu.2025.501561 · Cited by 5
Pham, C. M., Rankin, T. J., Stinear, T. P., Walsh, C. J., & Ryan, F. J. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf173 · Cited by 5
“Select taxon sets from mBodyMap covering non-gut sites (mouth, skin, vaginal tract) were included as the presence of non-gut associated bacteria can be a feature of dysbiosis [29, 30].”
Lucas, A., Schäffer, D. E., Wickramasinghe, J. M., & Auslander, N. (2025) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1013470 · Cited by 3
Vaysi, N., Mahaleh, S. A. H. H. S., Hosseingholi, E. Z., Nami, Y., & Panahi, B. (2025) · Applied Food Research · doi:10.1016/j.afres.2025.101396 · Cited by 3
Role of Computational Biology in Microbiome Research
Noor, F., Khurshid, M., Aslam, B., & Ashfaq, U. A. (2024) · Springer eBooks · doi:10.1007/978-981-97-3790-1_4 · Cited by 3
Revolutionizing colorectal cancer detection: A breakthrough in microbiome data analysis
Mulenga, M., Rajamanikam, A., Kumar, S., Muhammad, S., Bhassu, S., Samudid, C., Sabri, A. Q. M., Seera, M., & Eke, C. I. (2025) · PLoS ONE · doi:10.1371/journal.pone.0316493 · Cited by 3
Machine Learning in Identification of Disease-Associated Microbiota
Reiman, D. J., Sosa, U., & Dai, Y. D. (2021) · Physiology in health and disease · doi:10.1007/978-3-030-67951-4_15 · Cited by 3
Bioinformatics Pre-Processing of Microbiome Data with An Application to Metagenomic Forensics
Anyaso-Samuel, S., Sachdeva, A., Guha, S., & Datta, S. (2021) · Frontiers in probability and the statistical sciences · doi:10.1007/978-3-030-73351-3_3 · Cited by 4
Kashyap, S., & Das, A. (2023) · Acta Microbiologica et Immunologica Hungarica · doi:10.1556/030.2023.02054 · Cited by 5
Liu, Z., Wang, Q., Ma, A., Feng, S., Chung, D., Zhao, J., Ma, Q., & Liu, B. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107458 · Cited by 4
Skladaný, Ľ., Koller, T., Kukla, M., & Šoltýs, K. (2023) · Advances in predictive, preventive and personalised medicine · doi:10.1007/978-3-031-34884-6_9 · Cited by 4
Ma, Z. S. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108852 · Cited by 4
A new method for a priori practical identifiability
Thompson, P. E., Andersson, B. J., Sundqvist, N., & Cedersund, G. (2025) · PLoS ONE · doi:10.1371/journal.pone.0327593 · Cited by 4
Ruiz, B., Belcour, A., Blanquart, S., Buffet‐Bataillon, S., Huërou‐Luron, I. L., Siegel, A., & Cunff, Y. L. (2024) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1012577 · Cited by 4
“We applied SPARTA to six publicly available datasets, previously explored in articles such as MetAML [19] or DeepMicro [18].”
InfluentialThe Gut Microbiome and Ankylosing Spondylitis
Sternes, P. R., & Brown, M. A. (2019) · Elsevier eBooks · doi:10.1016/b978-0-323-56800-5.00006-0 · Cited by 3
Telalović, J. H., Pašić, L., & Bašić-Čičak, D. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-72805-2_6 · Cited by 4
Zhou, Z., Hu, S., Zhang, R., Ma, Y., Du, K., Sun, M., Zhang, H., Jiang, X., Tu, H., Wang, X., et al. (2021) · Food Bioscience · doi:10.1016/j.fbio.2021.101188 · Cited by 3
Hinton, A. L., & Mucha, P. J. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.12.08.471758 · Cited by 3
“Indeed, standard approaches such as those in MetaML 12 ignore compositional data constraints intrinsic in relative abundance data; as a result, model interpretability and beyond-study generalizability may be severely limited.”
BackgroundA permutable MLP-like architecture for disease prediction from gut metagenomic data
Jiang, C. F., Yang, J. P., Peng, X., & Li, X. (2024) · BMC Bioinformatics · doi:10.1186/s12859-024-05856-w · Cited by 3
“…the competitive performance and robustness of MetaP in both binary and multiclass classification tasks through benchmark testing with several well-established machine learning methods (RF, SVM) [11] and other deep learning methods (MetaNN [16], PopPhy-CNN [10]) on three publicly available datasets.”
BackgroundMethodInfluentialMeta-omic and machine learning approaches to understand microbial cross talks
Bombaywala, S., & Dafale, N. A. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-91631-8.00008-1 · Cited by 2
Disease Prediction From Human Microbiome by Utilizing Machine Learning
Temel, B. E., Kocapinar, B., & Işık, Z. (2024) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk63289.2024.10773434 · Cited by 2
“Various (cid:1) studies (cid:1) such (cid:1) as (cid:1) MetAML (cid:1) [3], (cid:1) Micro-Pro (cid:1) [4], (cid:1) DeepMico (cid:1) [5], (cid:1) MetaDR (cid:1) [6] (cid:1) have (cid:1) succeeded (cid:1) in (cid:1) developing (cid:1) models (cid:1) with (cid:1) high (cid:1) accuracy (cid:1) rates…”
InfluentialAR-CDT NET: a deep deformable convolutional network for gut microbiome-based disease classification
Li, J., Sun, Z., Chai, S., Li, H.-J., Wang, Y., & Tian, J. (2025) · BMC Bioinformatics · doi:10.1186/s12859-025-06357-0 · Cited by 2
“…we performed a series of systematic ablation experiments, including removing each module independently, replacing the deformable MS-DConv with standard fixed-shape convolutions, and simplifying the multi-scale configuration from the full [3, 5, 7] design to dual-scale and sin-gle-scale variants.”
InfluentialProbiotic-fortified functional foods: integrating nutrient delivery and gut health benefits
Alsanie, S. A. (2026) · Frontiers in Nutrition · doi:10.3389/fnut.2026.1815558 · Cited by 4
“Future research should prioritize well-designed randomized controlled trials, standardized reporting frameworks, strain-specific validation, and multi-omics approaches to establish causal relationships and improve clinical applicability (12, 69).”
Zalila‐Kolsi, I., & Al-Barazie, R. (2026) · Biology · doi:10.3390/biology15090665 · Cited by 2
“Validation of the different machine learning models used is crucial; thus, Pasolli et al. (2016) developed a software framework and consistently handled microbiome profiles of samples to assist follow-up research and the evaluation of new approaches [147].”
Soil microbial biogeography: from maps to blueprints
Gao, G., Jiao, S., Dong, K., Liu, X., Xin, X., Chen, B., Fan, K., Shi, Y. J., Shen, C., Yang, T., et al. (2026) · Soil Ecology Letters · doi:10.1007/s42832-026-0423-6 · Cited by 2
The gut microbiome in colorectal cancer: molecular paradigms and translational frontiers
Liu, Y., & Mei, D. (2026) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2026.1864299 · Cited by 2
“Ensemble methods, particularly Random Forest and XGBoost, deliver strong performance due to their ability to model non-linear relationships and complex feature interactions while generating interpretable importance scores (Knights et al., 2011; Pasolli et al., 2016).”
Thompson, K. N., Ma, S., Bhosle, A., Nickols, W. A., Shen, J., Ghazi, A. R., Dang, N. H., Zhang, Y., Nzabarushimana, É., Kim, H., et al. (2026) · Gastroenterology · doi:10.1053/j.gastro.2026.06.023 · Cited by 4
Discovering microbe functionality in human disease with a gene-ontology-aware model
Liu, Y., Zhang, Y., & Imoto, S. (2021) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm52615.2021.9669492 · Cited by 2
A Deep Learning Approach to Predict Health Status Using Microbiome Profiling
Wickramaratne, D., Wijesinghe, C. R., & Weerasinghe, A. R. (2022) · International Conference on Advances in ICT for Emerging Regions · doi:10.1109/icter58063.2022.10024102 · Cited by 2
“Finally, the deep learning model was compared with MetAML [13].”
BackgroundMethodResultInfluentialDecoding the link between microbial secondary metabolites and colorectal cancer
Wang, S., & Wu, M. (2025) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2025.108372 · Cited by 2
Binning Approach based on Classical Clustering for Type 2 Diabetes Diagnosis
Nguyễn, H. T., Yen, N. P. X., Hoang, H., Hong, N., & Huynh, H. X. (2020) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2020.0110379 · Cited by 2
“The last table (Table IV), we present the best results with Random Forest and also compare to state-of-the-art in MetAML [14].”
BackgroundMethodInfluentialBinning on Metagenomic Data for Disease Prediction Using Linear Discriminant Analysis and K-Means
Phan, N. Y. K., & Nguyễn, H. T. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-3394-3_46 · Cited by 2
Nguyễn, H. T., Luong, H. H., Tran, T. T., Nguyen, N. V., & Nguyen, K. D. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-3394-3_77 · Cited by 2
Current Progress of Bioinformatics for Human Health
Zhao, J., Zhang, S., Wu, S., Zhang, W., & Su, X. (2023) · Translational bioinformatics · doi:10.1007/978-981-19-8210-1_8 · Cited by 1
Influence of Commensal Microbiota and Metabolite for Mucosal Immunity
Pope, J. L., Tomkovich, S., & Jobin, C. (2019) · Elsevier eBooks · doi:10.1016/b978-0-12-811924-2.00009-2 · Cited by 3
Nutrition and cholesterol metabolism
Soliman, G. A. (2022) · Elsevier eBooks · doi:10.1016/b978-0-323-85857-1.00020-1 · Cited by 3
Ткач, С. М., Dorofeyev, A., Kuzenko, I., Boyko, N., Falalyeyeva, T. M., & Kobyliak, N. M. (2023) · Advances in predictive, preventive and personalised medicine · doi:10.1007/978-3-031-19564-8_10 · Cited by 3
Liu, Y., Zhang, Y., & Imoto, S. (2023) · PLoS ONE · doi:10.1371/journal.pone.0290307 · Cited by 2
Predictive and Comparative Network Analysis of the Gut Microbiota in Type 2 Diabetes
Abbas, M. M., & EL‐Manzalawy, Y. (2017) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/3107411.3107472 · Cited by 2
“Reduction in the abundance of members of Lachnospiraceae family and faecalibacterium prausnitzii has been previously linked to T2D [4, 29].”
BackgroundMethodPitti, J. Á., de Blas, A., & Lurbe, E. (2020) · Nutrients · doi:10.3390/nu12113508 · Cited by 5
Growing Self-Organizing Maps for Metagenomic Visualizations Supporting Disease Classification
Nguyễn, H. T., Nguyen, B. A., Nguyen, M. N., Truong, Q.-D., Nguyen, L. C., Banh, T. T. N., & Phung, L. D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63924-2_9 · Cited by 4
Reject and Cascade Classifier with Subgroup Discovery for Interpretable Metagenomic Signatures
Queyrel, M., Templier, A., & Zucker, J. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-93736-2_5 · Cited by 2
Liu, B., Sträuber, H., Saraiva, J., Harms, H., Silva, S. G., Kasmanas, J. C., Kleinsteuber, S., & da Rocha, U. N. (2021) · Research Square · doi:10.21203/rs.3.rs-78714/v2 · Cited by 2
Ma, S., Huttenhower, C., & Janson, L. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.06.04.596112 · Cited by 6
“In recent years, microbiome studies increasingly adopt modern machine learning to identify microbial signature patterns associated with host health 25,28,29 .”
BackgroundRoy, G., Belda, E., Prifti, E., Chevaleyre, Y., & Zucker, J. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.05.06.652444 · Cited by 3
“To train and evaluate our method, we used two metagenomic datasets, also employed in the MetaML study Pasolli et al., 2016.”
najih, N. E., & Moussa, P. A. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-47366-1_1 · Cited by 1
Oral metagenomics changes the game in carcinogenesis
Marzbali, M. Y., Banakar, M., Mousavi, S. M., & Lai, C. W. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-13531-6.00007-0 · Cited by 1
Machine learning to predict gut microbiomes of agricultural pests
Jobayer, M., Taylor, A., Hasan, M. R., Ahmed, K. A., & Hossain, M. Z. (2025) · Neural Computing and Applications · doi:10.1007/s00521-025-10999-9 · Cited by 2
“This qualitative predictive ML model has an advantage over the traditional approach in using quantitative microbiome profiles like species-level relative abundances and strain-specific markers to generate accurate predictionsPasolli et al. (2016).”
Dosso, S. D., Christoforidis, D., Merlo, E., Vannelli, A., Popeskou, S. G., Gaffuri, P., Lollo, G., Ambrosiani, L., Radaelli, F., Frattini, M., et al. (2025) · ESMO Gastrointestinal Oncology · doi:10.1016/j.esmogo.2025.100169 · Cited by 2
Microbiome-based dietary supplements for better development and healthy brain
Upadhyay, R., Mani, S., & Sevanan, M. (2025) · International review of neurobiology · doi:10.1016/bs.irn.2025.03.009 · Cited by 1
Abdelbary, E. R., Ramadan, M., Amin, I. A., Abd-Elsamea, F. S., Elsaghier, A. M., Abd-Alrahman, E., Ozbak, H. A., Hemeg, H. A., Almutawif, Y. A., Zakai, S. A., et al. (2025) · Viruses · doi:10.3390/v17121542 · Cited by 1
“Techniques from machine learning have been utilized and validated for research on microbiomes to identify microbial signatures that differentiate between comparable groups [44].”
Decoding Gut Microbiome Dysbiosis as a Non-Invasive Diagnostic Biomarker for Alopecia Areata
Aguado-García, Á., Huertas-López, F., Martínez-Moreno, D., Serrano-López, E. M., Martínez-Villaescusa, M., Carazo-Díaz, C., & Navarro‐López, V. (2025) · Cosmetics · doi:10.3390/cosmetics12060274 · Cited by 1
“Similarly, Collinsella has been shown to enhance IL-17A production and disrupt epithelial tight junctions [59].”
Syama, K., & Jothi, J. A. A. (2025) · IEEE International Symposium on Technology and Society (ISTAS) · doi:10.1109/istas65609.2025.11269618 · Cited by 1
“The first such work, presented in [11] comprehensively assessed the performance of different ML algorithms on the human gut microbiome metagenomic data for disease prediction (MetAML).”
Interpretable Metadata-Based Microbial Risk Prediction Using Large Language Models
Yoo, H., & ROSEN, G. L. (2025) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/3765612.3767197 · Cited by 1
Advancing Personalized Medicine With AI-Driven Microbiome and Nutrigenomics
Sah, A. K., Maurya, A. K., Mishra, P. S., Mishra, R., & Choudhary, R. K. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-4849-0.ch004 · Cited by 1
Luo, S., Ye, H., Liu, Y., Zeng, W., Zuo, H., Jiang, Y., & Wei, Q. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356767 · Cited by 1
Akram, H. M., & Saliem, S. S. (2026) · Bacteria · doi:10.3390/bacteria5010011 · Cited by 3
“The cross-validation strategy used for evaluating the performance of machine learning algorithms should also consider the hierarchical structure of the data, as well as any confounding variables [112].”
Respiratory microbiota maturation enables machine learning based age prediction in chickens
Moreno-León, A., López-Morales, A., Höfle, Ú., Barral, M., Majó, N., & Lavín, J. L. (2026) · BMC Microbiology · doi:10.1186/s12866-026-04947-3 · Cited by 1
“We evaluated the generalizability of microbial signatures using a Leave-One-Study-Out (LOSO) cross-validation framework [28, 29].”
Distinct Gut Microbiome Characteristics Associated with Mental Health Symptoms of Healthy Adults
Lee, S., Welch, C. B., Zinka, K., Evans, M., Park, H. J., Lozada-Fernández, V. V., & West, F. D. (2026) · Brain Sciences · doi:10.3390/brainsci16040382 · Cited by 1
“Reduced performance upon external validation is common in microbiome-based machine learning studies and reflects well-documented challenges in model transportability [81–83].”
Wang, S., Xie, L., Yan, Z., Ma, J., & Zhao, R. (2026) · Frontiers in Microbiology · doi:10.3389/fmicb.2026.1821073 · Cited by 1
Cerreto, M., Maestri, M., Pallozzi, M., Cerrito, L., Stella, L., Ianiro, G., Gasbarrini, A., & Ponziani, F. R. (2026) · Life · doi:10.3390/life16040641 · Cited by 2
“Using Lasso-based models [32,36], the authors evaluated whether microbial taxonomic and functional features could distinguish responders from nonresponders.”
Oral-gut microbiome dysbiosis in obese smokers reveals compartment-specific shifts
Ramadan, M., Hassan, E. K., Abdalla, S., Ahmed, A. A. A., Azab, M., Ibrahim, K. A., Amin, I. A., Ali, M. E., Alharbi, A. E., & Salah, M. (2026) · AMB Express · doi:10.1186/s13568-026-02048-y · Cited by 1
“Machine learning techniques have been employed and validated for microbiome research to identify microbial signatures distinguishing Obese-Smokers from matched groups (Pasolli et al. 2016).”
Kenneth, M. J., Wu, C.-C., Fang, C., Hussain, B., Abbas, A., Tsai, H., & Hsu, B. (2026) · Pharmacological Research - Modern Chinese Medicine · doi:10.1016/j.prmcm.2026.100820 · Cited by 1
Shi, K., Wang, S., Liu, Q., Ji, Q., Zhao, P., He, Q., Chen, W., & Chen, H. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110396 · Cited by 1
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.