DeepMicro: Deep representation learning for disease prediction based on microbiome data
Open accessPublished version of a preprint
Abstract
Human microbiota plays a key role in human health and growing evidence supports the potential use of microbiome as a predictor of various diseases. However, the high-dimensionality of microbiome data, often in the order of hundreds of thousands, yet low sample sizes, poses great challenge for machine learning-based prediction algorithms. This imbalance induces the data to be highly sparse, preventing from learning a better prediction model. Also, there has been little work on deep learning applications to microbiome data with a rigorous evaluation scheme. To address these challenges, we propose DeepMicro, a deep representation learning framework allowing for an effective representation of microbiome profiles. DeepMicro successfully transforms high-dimensional microbiome data into a robust low-dimensional representation using various autoencoders and applies machine learning classification algorithms on the learned representation. In disease prediction, DeepMicro outperforms the current best approaches based on the strain-level marker profile in five different datasets. In addition, by significantly reducing the dimensionality of the marker profile, DeepMicro accelerates the model training and hyperparameter optimization procedure with 8X-30X speedup over the basic approach. DeepMicro is freely available at https://github.com/minoh0201/DeepMicro.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
AI-based predictions are currently considered experimental and must undergo rigorous external validation and biological confirmation before regulators consider them.
“In contrast, AI-based predictions are currently considered experimental and must undergo rigorous external validation and biological confirmation before they can be considered by regulators, highlighting that computational methods complement existing safety assessments based on standardized phenotypic testing and strain-level documentation [151,153,167].”
From Current Concepts in Probiotic Safety and Efficacy (2026) · cites this paper as [167]
The Introduction (page unavailable) says a rigorous validation framework is needed to estimate model performance on unseen data, and describes excluding the test set from hyperparameter optimization. It does not call for external validation or biological confirmation, or discuss experimental status, regulatory consideration, or standardized safety assessments. (LLM, conf=0.78)
Experimental — accuracy not yet measuredCARD and ResFinder use carefully curated databases to identify known antibiotic resistance genes, providing clear results but may fail to detect novel, unusual, or modulated resistance mechanisms.
“In contrast, CARD and ResFinder use carefully curated databases to identify known antibiotic resistance genes, providing clear results but may fail to detect novel, unusual, or modulated resistance mechanisms [67,152,167,168].”
From Current Concepts in Probiotic Safety and Efficacy (2026) · cites this paper as [167]
The Results and Methods sections discuss microbiome profiles and disease prediction, not antibiotic-resistance-gene identification. Searches for CARD, ResFinder, curated resistance databases, and novel resistance mechanisms found no passage addressing the claim; page numbers were unavailable in our copy. (LLM, conf=0.76)
Experimental — accuracy not yet measuredAcceptance of AI and deep learning models by regulatory authorities is hampered by lack of clarity in their performance, as uninterpretable predictions do not provide a clear link to biological processes and specific safety characteristics of strains.
“Although AI and deep learning models have potential in probiotic research, their acceptance by regulatory authorities is hampered by the lack of clarity in their performance, as uninterpretable predictions do not provide a clear link to biological processes and specific safety characteristics of strains [167,170].”
From Current Concepts in Probiotic Safety and Efficacy (2026) · cites this paper as [167]
Split into 2 atoms — 0 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 2 unverifiable. Expand the claim to see per-atom verdicts.
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 27 · Cited by 190
Research works printed but not linked: 3
- [21]Glorot, X. & Bengio, Y. in Proceedings of the thirteenth international conference on artificial intelligence and statistics. 249-256.
- [24]Krizhevsky, A., Sutskever, I. & Hinton, G. E. in Advances in neural information processing systems. 1097-1105.
- [28]Bingham, E. & Mannila, H. in Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining. 245-250 (ACM).
- Authors
- Oh, M., & Zhang, L.
- Affiliations
- Virginia Tech (US)
- Corresponding author
- Zhang, Liqing
- ORCID
- Venue
- Scientific Reports
- Published
- 2020-04-07
- Volume
- 10
- Issue
- 1
- Pages
- 6026-6026
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC7138789
- OpenAlex
- W3014810983
- Cited by
- 190
- References
- 27
- Citations by year
- 2026: 32 · 2025: 44 · 2024: 34 · 2023: 14 · 2022: 34 · 2021: 25 · 2020: 6
- FWCI
- 6.41
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Scientific Reports (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- VTechWorks (Virginia Tech) (submittedVersion, cc-by)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gut microbiota and health
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
- Keywords
- microbiome, disease prediction, deep representation learning, autoencoder, dimensionality reduction, high-dimensional sparse data, human microbiota
- MeSH terms
- Machine Learning, Diagnosis, Computer-Assisted, Humans, Prognosis, Computational Biology, Microbiota
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
