Revealing General Patterns of Microbiomes That Transcend Systems: Potential and Challenges of Deep Transfer Learning
ABSTRACT A growing body of research has established that the microbiome can mediate the dynamics and functional capacities of diverse biological systems. Yet, we understand little about what governs the response of these microbial communities to host or environmental changes. Most efforts to model m...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Society for Microbiology
2022-02-01
|
| Series: | mSystems |
| Subjects: | |
| Online Access: | https://journals.asm.org/doi/10.1128/msystems.01058-21 |
| _version_ | 1819279420662218752 |
|---|---|
| author | Maude M. David Christine Tataru Quintin Pope Lydia J. Baker Mary K. English Hannah E. Epstein Austin Hammer Michael Kent Michael J. Sieler Ryan S. Mueller Thomas J. Sharpton Fiona Tomas Rebecca Vega Thurber Xiaoli Z. Fern |
| author_facet | Maude M. David Christine Tataru Quintin Pope Lydia J. Baker Mary K. English Hannah E. Epstein Austin Hammer Michael Kent Michael J. Sieler Ryan S. Mueller Thomas J. Sharpton Fiona Tomas Rebecca Vega Thurber Xiaoli Z. Fern |
| author_sort | Maude M. David |
| collection | DOAJ |
| description | ABSTRACT A growing body of research has established that the microbiome can mediate the dynamics and functional capacities of diverse biological systems. Yet, we understand little about what governs the response of these microbial communities to host or environmental changes. Most efforts to model microbiomes focus on defining the relationships between the microbiome, host, and environmental features within a specified study system and therefore fail to capture those that may be evident across multiple systems. In parallel with these developments in microbiome research, computer scientists have developed a variety of machine learning tools that can identify subtle, but informative, patterns from complex data. Here, we recommend using deep transfer learning to resolve microbiome patterns that transcend study systems. By leveraging diverse public data sets in an unsupervised way, such models can learn contextual relationships between features and build on those patterns to perform subsequent tasks (e.g., classification) within specific biological contexts. |
| first_indexed | 2024-12-24T00:27:37Z |
| format | Article |
| id | doaj.art-c61c7a62031040ea9d097219f7235c9b |
| institution | Directory Open Access Journal |
| issn | 2379-5077 |
| language | English |
| last_indexed | 2024-12-24T00:27:37Z |
| publishDate | 2022-02-01 |
| publisher | American Society for Microbiology |
| record_format | Article |
| series | mSystems |
| spelling | doaj.art-c61c7a62031040ea9d097219f7235c9b2022-12-21T17:24:23ZengAmerican Society for MicrobiologymSystems2379-50772022-02-017110.1128/msystems.01058-21Revealing General Patterns of Microbiomes That Transcend Systems: Potential and Challenges of Deep Transfer LearningMaude M. David0Christine Tataru1Quintin Pope2Lydia J. Baker3Mary K. English4Hannah E. Epstein5Austin Hammer6Michael Kent7Michael J. Sieler8Ryan S. Mueller9Thomas J. Sharpton10Fiona Tomas11Rebecca Vega Thurber12Xiaoli Z. Fern13Department of Microbiology, Oregon State University, Corvallis, Oregon, USADepartment of Microbiology, Oregon State University, Corvallis, Oregon, USASchool of Electrical Engineering and Computer Science, Oregon State University, Corvallis, Oregon, USADepartment of Microbiology, Oregon State University, Corvallis, Oregon, USADepartment of Microbiology, Oregon State University, Corvallis, Oregon, USADepartment of Microbiology, Oregon State University, Corvallis, Oregon, USADepartment of Microbiology, Oregon State University, Corvallis, Oregon, USADepartment of Microbiology, Oregon State University, Corvallis, Oregon, USADepartment of Microbiology, Oregon State University, Corvallis, Oregon, USADepartment of Microbiology, Oregon State University, Corvallis, Oregon, USADepartment of Microbiology, Oregon State University, Corvallis, Oregon, USAInstituto Mediterráneo de Estudios Avanzados, IMEDEA, Esporles, Balearic Islands, SpainDepartment of Microbiology, Oregon State University, Corvallis, Oregon, USASchool of Electrical Engineering and Computer Science, Oregon State University, Corvallis, Oregon, USAABSTRACT A growing body of research has established that the microbiome can mediate the dynamics and functional capacities of diverse biological systems. Yet, we understand little about what governs the response of these microbial communities to host or environmental changes. Most efforts to model microbiomes focus on defining the relationships between the microbiome, host, and environmental features within a specified study system and therefore fail to capture those that may be evident across multiple systems. In parallel with these developments in microbiome research, computer scientists have developed a variety of machine learning tools that can identify subtle, but informative, patterns from complex data. Here, we recommend using deep transfer learning to resolve microbiome patterns that transcend study systems. By leveraging diverse public data sets in an unsupervised way, such models can learn contextual relationships between features and build on those patterns to perform subsequent tasks (e.g., classification) within specific biological contexts.https://journals.asm.org/doi/10.1128/msystems.01058-21deep learningembeddingsmachine learningmicrobial ecology |
| spellingShingle | Maude M. David Christine Tataru Quintin Pope Lydia J. Baker Mary K. English Hannah E. Epstein Austin Hammer Michael Kent Michael J. Sieler Ryan S. Mueller Thomas J. Sharpton Fiona Tomas Rebecca Vega Thurber Xiaoli Z. Fern Revealing General Patterns of Microbiomes That Transcend Systems: Potential and Challenges of Deep Transfer Learning mSystems deep learning embeddings machine learning microbial ecology |
| title | Revealing General Patterns of Microbiomes That Transcend Systems: Potential and Challenges of Deep Transfer Learning |
| title_full | Revealing General Patterns of Microbiomes That Transcend Systems: Potential and Challenges of Deep Transfer Learning |
| title_fullStr | Revealing General Patterns of Microbiomes That Transcend Systems: Potential and Challenges of Deep Transfer Learning |
| title_full_unstemmed | Revealing General Patterns of Microbiomes That Transcend Systems: Potential and Challenges of Deep Transfer Learning |
| title_short | Revealing General Patterns of Microbiomes That Transcend Systems: Potential and Challenges of Deep Transfer Learning |
| title_sort | revealing general patterns of microbiomes that transcend systems potential and challenges of deep transfer learning |
| topic | deep learning embeddings machine learning microbial ecology |
| url | https://journals.asm.org/doi/10.1128/msystems.01058-21 |
| work_keys_str_mv | AT maudemdavid revealinggeneralpatternsofmicrobiomesthattranscendsystemspotentialandchallengesofdeeptransferlearning AT christinetataru revealinggeneralpatternsofmicrobiomesthattranscendsystemspotentialandchallengesofdeeptransferlearning AT quintinpope revealinggeneralpatternsofmicrobiomesthattranscendsystemspotentialandchallengesofdeeptransferlearning AT lydiajbaker revealinggeneralpatternsofmicrobiomesthattranscendsystemspotentialandchallengesofdeeptransferlearning AT marykenglish revealinggeneralpatternsofmicrobiomesthattranscendsystemspotentialandchallengesofdeeptransferlearning AT hannaheepstein revealinggeneralpatternsofmicrobiomesthattranscendsystemspotentialandchallengesofdeeptransferlearning AT austinhammer revealinggeneralpatternsofmicrobiomesthattranscendsystemspotentialandchallengesofdeeptransferlearning AT michaelkent revealinggeneralpatternsofmicrobiomesthattranscendsystemspotentialandchallengesofdeeptransferlearning AT michaeljsieler revealinggeneralpatternsofmicrobiomesthattranscendsystemspotentialandchallengesofdeeptransferlearning AT ryansmueller revealinggeneralpatternsofmicrobiomesthattranscendsystemspotentialandchallengesofdeeptransferlearning AT thomasjsharpton revealinggeneralpatternsofmicrobiomesthattranscendsystemspotentialandchallengesofdeeptransferlearning AT fionatomas revealinggeneralpatternsofmicrobiomesthattranscendsystemspotentialandchallengesofdeeptransferlearning AT rebeccavegathurber revealinggeneralpatternsofmicrobiomesthattranscendsystemspotentialandchallengesofdeeptransferlearning AT xiaolizfern revealinggeneralpatternsofmicrobiomesthattranscendsystemspotentialandchallengesofdeeptransferlearning |