Explainable AI reveals changes in skin microbiome composition linked to phenotypic differences
Abstract Alterations in the human microbiome have been observed in a variety of conditions such as asthma, gingivitis, dermatitis and cancer, and much remains to be learned about the links between the microbiome and human health. The fusion of artificial intelligence with rich microbiome datasets ca...
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-02-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-021-83922-6 |
| _version_ | 1818400826274611200 |
|---|---|
| author | Anna Paola Carrieri Niina Haiminen Sean Maudsley-Barton Laura-Jayne Gardiner Barry Murphy Andrew E. Mayes Sarah Paterson Sally Grimshaw Martyn Winn Cameron Shand Panagiotis Hadjidoukas Will P. M. Rowe Stacy Hawkins Ashley MacGuire-Flanagan Jane Tazzioli John G. Kenny Laxmi Parida Michael Hoptroff Edward O. Pyzer-Knapp |
| author_facet | Anna Paola Carrieri Niina Haiminen Sean Maudsley-Barton Laura-Jayne Gardiner Barry Murphy Andrew E. Mayes Sarah Paterson Sally Grimshaw Martyn Winn Cameron Shand Panagiotis Hadjidoukas Will P. M. Rowe Stacy Hawkins Ashley MacGuire-Flanagan Jane Tazzioli John G. Kenny Laxmi Parida Michael Hoptroff Edward O. Pyzer-Knapp |
| author_sort | Anna Paola Carrieri |
| collection | DOAJ |
| description | Abstract Alterations in the human microbiome have been observed in a variety of conditions such as asthma, gingivitis, dermatitis and cancer, and much remains to be learned about the links between the microbiome and human health. The fusion of artificial intelligence with rich microbiome datasets can offer an improved understanding of the microbiome’s role in human health. To gain actionable insights it is essential to consider both the predictive power and the transparency of the models by providing explanations for the predictions. We combine the collection of leg skin microbiome samples from two healthy cohorts of women with the application of an explainable artificial intelligence (EAI) approach that provides accurate predictions of phenotypes with explanations. The explanations are expressed in terms of variations in the relative abundance of key microbes that drive the predictions. We predict skin hydration, subject's age, pre/post-menopausal status and smoking status from the leg skin microbiome. The changes in microbial composition linked to skin hydration can accelerate the development of personalized treatments for healthy skin, while those associated with age may offer insights into the skin aging process. The leg microbiome signatures associated with smoking and menopausal status are consistent with previous findings from oral/respiratory tract microbiomes and vaginal/gut microbiomes respectively. This suggests that easily accessible microbiome samples could be used to investigate health-related phenotypes, offering potential for non-invasive diagnosis and condition monitoring. Our EAI approach sets the stage for new work focused on understanding the complex relationships between microbial communities and phenotypes. Our approach can be applied to predict any condition from microbiome samples and has the potential to accelerate the development of microbiome-based personalized therapeutics and non-invasive diagnostics. |
| first_indexed | 2024-12-14T07:42:44Z |
| format | Article |
| id | doaj.art-cb1dd98e135247c4b14f7dc863db1e07 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-14T07:42:44Z |
| publishDate | 2021-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-cb1dd98e135247c4b14f7dc863db1e072022-12-21T23:10:59ZengNature PortfolioScientific Reports2045-23222021-02-0111111810.1038/s41598-021-83922-6Explainable AI reveals changes in skin microbiome composition linked to phenotypic differencesAnna Paola Carrieri0Niina Haiminen1Sean Maudsley-Barton2Laura-Jayne Gardiner3Barry Murphy4Andrew E. Mayes5Sarah Paterson6Sally Grimshaw7Martyn Winn8Cameron Shand9Panagiotis Hadjidoukas10Will P. M. Rowe11Stacy Hawkins12Ashley MacGuire-Flanagan13Jane Tazzioli14John G. Kenny15Laxmi Parida16Michael Hoptroff17Edward O. Pyzer-Knapp18The Hartree Centre, Sci-Tech Daresbury, IBM ResearchT.J. Watson Research Center, IBM ResearchThe Hartree Centre, Sci-Tech Daresbury, IBM ResearchThe Hartree Centre, Sci-Tech Daresbury, IBM ResearchUnilever Research & DevelopmentUnilever Research and DevelopmentUnilever Research & DevelopmentUnilever Research & DevelopmentScientific Computing Department, STFC Daresbury LabThe Hartree Centre, Sci-Tech Daresbury, IBM ResearchIBM Research - ZurichUniversity of BirminghamUnilever Research & DevelopmentUnilever Research & DevelopmentUnilever Research & DevelopmentInstitute of Integrative Biology, The University of LiverpoolT.J. Watson Research Center, IBM ResearchUnilever Research & DevelopmentThe Hartree Centre, Sci-Tech Daresbury, IBM ResearchAbstract Alterations in the human microbiome have been observed in a variety of conditions such as asthma, gingivitis, dermatitis and cancer, and much remains to be learned about the links between the microbiome and human health. The fusion of artificial intelligence with rich microbiome datasets can offer an improved understanding of the microbiome’s role in human health. To gain actionable insights it is essential to consider both the predictive power and the transparency of the models by providing explanations for the predictions. We combine the collection of leg skin microbiome samples from two healthy cohorts of women with the application of an explainable artificial intelligence (EAI) approach that provides accurate predictions of phenotypes with explanations. The explanations are expressed in terms of variations in the relative abundance of key microbes that drive the predictions. We predict skin hydration, subject's age, pre/post-menopausal status and smoking status from the leg skin microbiome. The changes in microbial composition linked to skin hydration can accelerate the development of personalized treatments for healthy skin, while those associated with age may offer insights into the skin aging process. The leg microbiome signatures associated with smoking and menopausal status are consistent with previous findings from oral/respiratory tract microbiomes and vaginal/gut microbiomes respectively. This suggests that easily accessible microbiome samples could be used to investigate health-related phenotypes, offering potential for non-invasive diagnosis and condition monitoring. Our EAI approach sets the stage for new work focused on understanding the complex relationships between microbial communities and phenotypes. Our approach can be applied to predict any condition from microbiome samples and has the potential to accelerate the development of microbiome-based personalized therapeutics and non-invasive diagnostics.https://doi.org/10.1038/s41598-021-83922-6 |
| spellingShingle | Anna Paola Carrieri Niina Haiminen Sean Maudsley-Barton Laura-Jayne Gardiner Barry Murphy Andrew E. Mayes Sarah Paterson Sally Grimshaw Martyn Winn Cameron Shand Panagiotis Hadjidoukas Will P. M. Rowe Stacy Hawkins Ashley MacGuire-Flanagan Jane Tazzioli John G. Kenny Laxmi Parida Michael Hoptroff Edward O. Pyzer-Knapp Explainable AI reveals changes in skin microbiome composition linked to phenotypic differences Scientific Reports |
| title | Explainable AI reveals changes in skin microbiome composition linked to phenotypic differences |
| title_full | Explainable AI reveals changes in skin microbiome composition linked to phenotypic differences |
| title_fullStr | Explainable AI reveals changes in skin microbiome composition linked to phenotypic differences |
| title_full_unstemmed | Explainable AI reveals changes in skin microbiome composition linked to phenotypic differences |
| title_short | Explainable AI reveals changes in skin microbiome composition linked to phenotypic differences |
| title_sort | explainable ai reveals changes in skin microbiome composition linked to phenotypic differences |
| url | https://doi.org/10.1038/s41598-021-83922-6 |
| work_keys_str_mv | AT annapaolacarrieri explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT niinahaiminen explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT seanmaudsleybarton explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT laurajaynegardiner explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT barrymurphy explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT andrewemayes explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT sarahpaterson explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT sallygrimshaw explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT martynwinn explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT cameronshand explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT panagiotishadjidoukas explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT willpmrowe explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT stacyhawkins explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT ashleymacguireflanagan explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT janetazzioli explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT johngkenny explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT laxmiparida explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT michaelhoptroff explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences AT edwardopyzerknapp explainableairevealschangesinskinmicrobiomecompositionlinkedtophenotypicdifferences |