Machine learning models reveal microbial signatures in healthy human tissues, challenging the sterility of human organs

BackgroundThe presence of microbes within healthy human internal organs still remains under question. Our study endeavors to discern microbial signatures within normal human internal tissues using data from the Genotype-Tissue Expression (GTEx) consortium. Machine learning (ML) models were developed...

Full description

Saved in:
Bibliographic Details
Main Authors: Anargyros Skoulakis, Giorgos Skoufos, Armen Ovsepian, Artemis G. Hatzigeorgiou
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-01-01
Series:Frontiers in Microbiology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmicb.2024.1512304/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832584557987102720
author Anargyros Skoulakis
Anargyros Skoulakis
Giorgos Skoufos
Giorgos Skoufos
Armen Ovsepian
Armen Ovsepian
Artemis G. Hatzigeorgiou
Artemis G. Hatzigeorgiou
author_facet Anargyros Skoulakis
Anargyros Skoulakis
Giorgos Skoufos
Giorgos Skoufos
Armen Ovsepian
Armen Ovsepian
Artemis G. Hatzigeorgiou
Artemis G. Hatzigeorgiou
author_sort Anargyros Skoulakis
collection DOAJ
description BackgroundThe presence of microbes within healthy human internal organs still remains under question. Our study endeavors to discern microbial signatures within normal human internal tissues using data from the Genotype-Tissue Expression (GTEx) consortium. Machine learning (ML) models were developed to classify each tissue type based solely on microbial profiles, with the identification of tissue-specific microbial signatures suggesting the presence of distinct microbial communities inside tissues.MethodsWe analyzed 13,871 normal RNA-seq samples from 28 tissues obtained from the GTEx consortium. Unaligned sequencing reads with the human genome were processed using AGAMEMNON, an algorithm for metagenomic microbial quantification, with a reference database comprising bacterial, archaeal, and viral genomes, alongside fungal transcriptomes. Gradient-boosting ML models were trained to classify each tissue against all others based on its microbial profile. To validate the findings, we analyzed 38 healthy living tissue samples (samples from healthy tissues obtained from living individuals, not deceased) from an independent study, as the GTEx samples were derived from post-mortem biopsies.ResultsTissue-specific microbial signatures were identified in 11 out of the 28 tissues while the signatures for 8 tissues (Muscle, Heart, Stomach, Colon tissue, Testis, Blood, Liver, and Bladder tissue) demonstrated resilience to in silico contamination. The models for Heart, Colon tissue, and Liver displayed high discriminatory performance also in the living dataset, suggesting the presence of a tissue-specific microbiome for these tissues even in a living state. Notably, the most crucial features were the fungus Sporisorium graminicola for the heart, the gram-positive bacterium Flavonifractor plautii for the colon tissue, and the gram-negative bacterium Bartonella machadoae for the liver.ConclusionThe presence of tissue-specific microbial signatures in certain tissues suggests that these organs are not devoid of microorganisms even in healthy conditions and probably they harbor low-biomass microbial communities unique to each tissue. The discoveries presented here confront the enduring dogma positing the sterility of internal tissues, yet further validation through controlled laboratory experiments is imperative to substantiate this hypothesis. Exploring the microbiome of internal tissues holds promise for elucidating the pathophysiology underlying both health and a spectrum of diseases, including sepsis, inflammation, and cancer.
format Article
id doaj-art-eda987c4e2a74a248598299fd1dd0480
institution Kabale University
issn 1664-302X
language English
publishDate 2025-01-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Microbiology
spelling doaj-art-eda987c4e2a74a248598299fd1dd04802025-01-27T12:57:47ZengFrontiers Media S.A.Frontiers in Microbiology1664-302X2025-01-011510.3389/fmicb.2024.15123041512304Machine learning models reveal microbial signatures in healthy human tissues, challenging the sterility of human organsAnargyros Skoulakis0Anargyros Skoulakis1Giorgos Skoufos2Giorgos Skoufos3Armen Ovsepian4Armen Ovsepian5Artemis G. Hatzigeorgiou6Artemis G. Hatzigeorgiou7DIANA-Lab, Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, GreeceHellenic Pasteur Institute, Athens, GreeceDIANA-Lab, Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, GreeceHellenic Pasteur Institute, Athens, GreeceDIANA-Lab, Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, GreeceHellenic Pasteur Institute, Athens, GreeceDIANA-Lab, Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, GreeceHellenic Pasteur Institute, Athens, GreeceBackgroundThe presence of microbes within healthy human internal organs still remains under question. Our study endeavors to discern microbial signatures within normal human internal tissues using data from the Genotype-Tissue Expression (GTEx) consortium. Machine learning (ML) models were developed to classify each tissue type based solely on microbial profiles, with the identification of tissue-specific microbial signatures suggesting the presence of distinct microbial communities inside tissues.MethodsWe analyzed 13,871 normal RNA-seq samples from 28 tissues obtained from the GTEx consortium. Unaligned sequencing reads with the human genome were processed using AGAMEMNON, an algorithm for metagenomic microbial quantification, with a reference database comprising bacterial, archaeal, and viral genomes, alongside fungal transcriptomes. Gradient-boosting ML models were trained to classify each tissue against all others based on its microbial profile. To validate the findings, we analyzed 38 healthy living tissue samples (samples from healthy tissues obtained from living individuals, not deceased) from an independent study, as the GTEx samples were derived from post-mortem biopsies.ResultsTissue-specific microbial signatures were identified in 11 out of the 28 tissues while the signatures for 8 tissues (Muscle, Heart, Stomach, Colon tissue, Testis, Blood, Liver, and Bladder tissue) demonstrated resilience to in silico contamination. The models for Heart, Colon tissue, and Liver displayed high discriminatory performance also in the living dataset, suggesting the presence of a tissue-specific microbiome for these tissues even in a living state. Notably, the most crucial features were the fungus Sporisorium graminicola for the heart, the gram-positive bacterium Flavonifractor plautii for the colon tissue, and the gram-negative bacterium Bartonella machadoae for the liver.ConclusionThe presence of tissue-specific microbial signatures in certain tissues suggests that these organs are not devoid of microorganisms even in healthy conditions and probably they harbor low-biomass microbial communities unique to each tissue. The discoveries presented here confront the enduring dogma positing the sterility of internal tissues, yet further validation through controlled laboratory experiments is imperative to substantiate this hypothesis. Exploring the microbiome of internal tissues holds promise for elucidating the pathophysiology underlying both health and a spectrum of diseases, including sepsis, inflammation, and cancer.https://www.frontiersin.org/articles/10.3389/fmicb.2024.1512304/fullhuman tissueshuman organstissuesmicrobiomemicrobial communitiesmicroorganisms
spellingShingle Anargyros Skoulakis
Anargyros Skoulakis
Giorgos Skoufos
Giorgos Skoufos
Armen Ovsepian
Armen Ovsepian
Artemis G. Hatzigeorgiou
Artemis G. Hatzigeorgiou
Machine learning models reveal microbial signatures in healthy human tissues, challenging the sterility of human organs
Frontiers in Microbiology
human tissues
human organs
tissues
microbiome
microbial communities
microorganisms
title Machine learning models reveal microbial signatures in healthy human tissues, challenging the sterility of human organs
title_full Machine learning models reveal microbial signatures in healthy human tissues, challenging the sterility of human organs
title_fullStr Machine learning models reveal microbial signatures in healthy human tissues, challenging the sterility of human organs
title_full_unstemmed Machine learning models reveal microbial signatures in healthy human tissues, challenging the sterility of human organs
title_short Machine learning models reveal microbial signatures in healthy human tissues, challenging the sterility of human organs
title_sort machine learning models reveal microbial signatures in healthy human tissues challenging the sterility of human organs
topic human tissues
human organs
tissues
microbiome
microbial communities
microorganisms
url https://www.frontiersin.org/articles/10.3389/fmicb.2024.1512304/full
work_keys_str_mv AT anargyrosskoulakis machinelearningmodelsrevealmicrobialsignaturesinhealthyhumantissueschallengingthesterilityofhumanorgans
AT anargyrosskoulakis machinelearningmodelsrevealmicrobialsignaturesinhealthyhumantissueschallengingthesterilityofhumanorgans
AT giorgosskoufos machinelearningmodelsrevealmicrobialsignaturesinhealthyhumantissueschallengingthesterilityofhumanorgans
AT giorgosskoufos machinelearningmodelsrevealmicrobialsignaturesinhealthyhumantissueschallengingthesterilityofhumanorgans
AT armenovsepian machinelearningmodelsrevealmicrobialsignaturesinhealthyhumantissueschallengingthesterilityofhumanorgans
AT armenovsepian machinelearningmodelsrevealmicrobialsignaturesinhealthyhumantissueschallengingthesterilityofhumanorgans
AT artemisghatzigeorgiou machinelearningmodelsrevealmicrobialsignaturesinhealthyhumantissueschallengingthesterilityofhumanorgans
AT artemisghatzigeorgiou machinelearningmodelsrevealmicrobialsignaturesinhealthyhumantissueschallengingthesterilityofhumanorgans