Machine learning-based meta-analysis reveals gut microbiome alterations associated with Parkinson's disease
From BugSigDB
Jump to:navigation, search
Study information
-
Quality control
- Retracted paper
- Contamination issues suspected
- Batch effect issues suspected
- Uncontrolled confounding suspected
- Results are suspect (various reasons)
- Tags applied
study design
Citation
PMID PubMed identifier for scientific articles.
DOI Digital object identifier for electronic documents.
URI Uniform resource identifier for web resources.
Authors
Romano S, Wirbel J, Ansorge R, Schudoma C, Ducarmon QR, Narbad A, Zeller G
Journal
Nature communications
Year
2025
There is strong interest in using the gut microbiome for Parkinson's disease (PD) diagnosis and treatment. However, a consensus on PD-associated microbiome features and a multi-study assessment of their diagnostic value is lacking. Here, we present a machine learning meta-analysis of PD microbiome studies of unprecedented scale (4489 samples). Within most studies, microbiome-based machine learning models accurately classify PD patients (average AUC 71.9%). However, these models are study-specific and do not generalise well across other studies (average AUC 61%). Training models on multiple datasets improves their generalizability (average LOSO AUC 68%) and disease specificity as assessed against microbiomes from other neurodegenerative diseases. Moreover, meta-analysis of shotgun metagenomes delineates PD-associated microbial pathways potentially contributing to gut health deterioration and favouring the translocation of pathogenic molecules along the gut-brain axis. Strikingly, microbial pathways for solvent and pesticide biotransformation are enriched in PD. These results align with epidemiological evidence that exposure to these molecules increases PD risk and raise the question of whether gut microbes modulate their toxicity. Here, we offer the most comprehensive overview to date about the PD gut microbiome and provide future reference for its diagnostic and functional potential.
Experiment 1
Needs review
Subjects
- Location of subjects
- Australia
- Canada
- China
- Finland
- Germany
- Italy
- Japan
- Malaysia
- Russian Federation
- South Korea
- United States of America
- Host species Species from which microbiome was sampled. Contact us to have more species added.
- Homo sapiens
- Body site Anatomical site where microbial samples were extracted from according to the Uber Anatomy Ontology
- Feces Cow dung,Cow pat,Droppings,Dung,Excrement,Excreta,Faeces,Fecal material,Fecal matter,Fewmet,Frass,Guano,Matières fécales@fr,Merde@fr,Ordure,Partie de la merde@fr,Piece of shit,Porción de mierda@es,Portion of dung,Portion of excrement,Portion of faeces,Portion of fecal material,Portion of fecal matter,Portion of feces,Portion of guano,Portion of scat,Portionem cacas,Scat,Spoor,Spraint,Stool,Teil der fäkalien@de,Feces,feces
- Condition The experimental condition / phenotype studied according to the Experimental Factor Ontology
- Parkinson's disease IDIOPATHIC PARKINSON DIS,Idiopathic Parkinson Disease,Idiopathic Parkinson's Disease,IDIOPATHIC PARKINSONS DIS,Idiopathic PD,LEWY BODY PARKINSON DIS,Lewy Body Parkinson Disease,Lewy Body Parkinson's Disease,Paralysis agitans,paralysis agitans,PARKINSON DIS,PARKINSON DIS IDIOPATHIC,Parkinson disease,Parkinson Disease, Idiopathic,Parkinson syndrome,Parkinson's,Parkinson's disease,Parkinson's disease (disorder),Parkinson's disease NOS,Parkinson's disease NOS (disorder),Parkinson's Disease, Idiopathic,Parkinson's Disease, Lewy Body,Parkinson's syndrome,Parkinsonian disorder,Parkinsonism, Primary,Parkinsons,PARKINSONS DIS,PARKINSONS DIS IDIOPATHIC,PARKINSONS DIS LEWY BODY,Parkinsons disease,Primary Parkinsonism,parkinson's disease
- Group 0 name Corresponds to the control (unexposed) group for case-control studies
- Controls
- Group 1 name Corresponds to the case (exposed) group for case-control studies
- Parkinson's disease patients
- Group 1 definition Diagnostic criteria applied to define the specific condition / phenotype represented in the case (exposed) group
- Parkinson's disease cases across case-control studies
- Group 0 sample size Number of subjects in the control (unexposed) group
- 17
- Group 1 sample size Number of subjects in the case (exposed) group
- 17
Lab analysis
- Sequencing type
- 16S
- 16S variable region One or more hypervariable region(s) of the bacterial 16S gene
- Not specified
Statistical Analysis
- Data transformation Data transformation applied to microbial abundance measurements prior to differential abundance testing (if any).
- relative abundances
- Significance threshold p-value or FDR threshold used for differential abundance testing (if any)
- 0.05
- MHT correction Have statistical tests be corrected for multiple hypothesis testing (MHT)?
- Yes
Signature 1
Needs review
Source: Figure 6; Supplementary Data 4
Description: Taxa enriched in Parkinson's disease patients in 16S meta-analysis. Relative abundances determined using Agresti Generalized Odds Ratios.
Abundance in Group 1: increased abundance in Parkinson's disease patients
Revision editor(s): Kristin.abraham
Signature 2
Needs review
Source: Figure 6; Supplementary Data 4
Description: Taxa depleted in Parkinson's disease patients in 16S meta-analysis. Relative abundances determined using Agresti Generalized Odds Ratios.
Abundance in Group 1: decreased abundance in Parkinson's disease patients
Revision editor(s): Kristin.abraham
Experiment 2
Needs review
Differences from previous experiment shown
Subjects
- Location of subjects
- China
- Germany
- United States of America
- Group 0 name Corresponds to the control (unexposed) group for case-control studies
- controls
- Group 0 sample size Number of subjects in the control (unexposed) group
- 7
- Group 1 sample size Number of subjects in the case (exposed) group
- 7
Signature 1
Needs review
Source: Figure 6; Supplementary Data 5
Description: Taxa enriched in Parkinson's disease patients in SMG meta-analysis. Relative abundances determined using Agresti Generalized Odds Ratios.
Abundance in Group 1: increased abundance in Parkinson's disease patients
Revision editor(s): Kristin.abraham
Signature 2
Needs review
Source: Figure 6; Supplementary Data 5
Description: Taxa depleted in Parkinson's disease patients in SMG meta-analysis. Relative abundances determined using Agresti Generalized Odds Ratios.
Abundance in Group 1: decreased abundance in Parkinson's disease patients
Revision editor(s): Kristin.abraham
Retrieved from "https://bugsigdb.org/w/index.php?title=40335465&oldid=207482"
