GelGenie: an AI-powered framework for gel electrophoresis image analysis
Abstract Gel electrophoresis is a ubiquitous laboratory method for the separation and semi-quantitative analysis of biomolecules. However, gel image analysis principles have barely advanced for decades, in stark contrast to other fields where AI has revolutionised data processing. Here, we show that...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-59189-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849729113880788992 |
|---|---|
| author | Matthew Aquilina Nathan J. W. Wu Kiros Kwan Filip Bušić James Dodd Laura Nicolás-Sáenz Alan O’Callaghan Peter Bankhead Katherine E. Dunn |
| author_facet | Matthew Aquilina Nathan J. W. Wu Kiros Kwan Filip Bušić James Dodd Laura Nicolás-Sáenz Alan O’Callaghan Peter Bankhead Katherine E. Dunn |
| author_sort | Matthew Aquilina |
| collection | DOAJ |
| description | Abstract Gel electrophoresis is a ubiquitous laboratory method for the separation and semi-quantitative analysis of biomolecules. However, gel image analysis principles have barely advanced for decades, in stark contrast to other fields where AI has revolutionised data processing. Here, we show that an AI-based system can automatically identify gel bands in seconds for a wide range of experimental conditions, surpassing the capabilities of current software in both ease-of-use and versatility. We use a dataset containing 500+ images of manually-labelled gels to train various U-Nets to accurately identify bands through segmentation, i.e. classifying pixels as ‘band’ or ‘background’. When applied to gel electrophoresis data from other laboratories, our system generates results that quantitatively match those of the original authors. We have publicly released our models through GelGenie, an open-source application that allows users to extract bands from gel images on their own devices, with no expert knowledge or experience required. |
| format | Article |
| id | doaj-art-9a62f270986d48fa924e1c6c2b00946c |
| institution | DOAJ |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-9a62f270986d48fa924e1c6c2b00946c2025-08-20T03:09:19ZengNature PortfolioNature Communications2041-17232025-05-0116111710.1038/s41467-025-59189-0GelGenie: an AI-powered framework for gel electrophoresis image analysisMatthew Aquilina0Nathan J. W. Wu1Kiros Kwan2Filip Bušić3James Dodd4Laura Nicolás-Sáenz5Alan O’Callaghan6Peter Bankhead7Katherine E. Dunn8Institute for Bioengineering, School of Engineering, University of EdinburghInstitute for Bioengineering, School of Engineering, University of EdinburghInstitute for Bioengineering, School of Engineering, University of EdinburghInstitute for Bioengineering, School of Engineering, University of EdinburghInstitute for Bioengineering, School of Engineering, University of EdinburghCentre for Genomic & Experimental Medicine, Institute of Genetics and Cancer, University of EdinburghCentre for Genomic & Experimental Medicine, Institute of Genetics and Cancer, University of EdinburghCentre for Genomic & Experimental Medicine, Institute of Genetics and Cancer, University of EdinburghInstitute for Bioengineering, School of Engineering, University of EdinburghAbstract Gel electrophoresis is a ubiquitous laboratory method for the separation and semi-quantitative analysis of biomolecules. However, gel image analysis principles have barely advanced for decades, in stark contrast to other fields where AI has revolutionised data processing. Here, we show that an AI-based system can automatically identify gel bands in seconds for a wide range of experimental conditions, surpassing the capabilities of current software in both ease-of-use and versatility. We use a dataset containing 500+ images of manually-labelled gels to train various U-Nets to accurately identify bands through segmentation, i.e. classifying pixels as ‘band’ or ‘background’. When applied to gel electrophoresis data from other laboratories, our system generates results that quantitatively match those of the original authors. We have publicly released our models through GelGenie, an open-source application that allows users to extract bands from gel images on their own devices, with no expert knowledge or experience required.https://doi.org/10.1038/s41467-025-59189-0 |
| spellingShingle | Matthew Aquilina Nathan J. W. Wu Kiros Kwan Filip Bušić James Dodd Laura Nicolás-Sáenz Alan O’Callaghan Peter Bankhead Katherine E. Dunn GelGenie: an AI-powered framework for gel electrophoresis image analysis Nature Communications |
| title | GelGenie: an AI-powered framework for gel electrophoresis image analysis |
| title_full | GelGenie: an AI-powered framework for gel electrophoresis image analysis |
| title_fullStr | GelGenie: an AI-powered framework for gel electrophoresis image analysis |
| title_full_unstemmed | GelGenie: an AI-powered framework for gel electrophoresis image analysis |
| title_short | GelGenie: an AI-powered framework for gel electrophoresis image analysis |
| title_sort | gelgenie an ai powered framework for gel electrophoresis image analysis |
| url | https://doi.org/10.1038/s41467-025-59189-0 |
| work_keys_str_mv | AT matthewaquilina gelgenieanaipoweredframeworkforgelelectrophoresisimageanalysis AT nathanjwwu gelgenieanaipoweredframeworkforgelelectrophoresisimageanalysis AT kiroskwan gelgenieanaipoweredframeworkforgelelectrophoresisimageanalysis AT filipbusic gelgenieanaipoweredframeworkforgelelectrophoresisimageanalysis AT jamesdodd gelgenieanaipoweredframeworkforgelelectrophoresisimageanalysis AT lauranicolassaenz gelgenieanaipoweredframeworkforgelelectrophoresisimageanalysis AT alanocallaghan gelgenieanaipoweredframeworkforgelelectrophoresisimageanalysis AT peterbankhead gelgenieanaipoweredframeworkforgelelectrophoresisimageanalysis AT katherineedunn gelgenieanaipoweredframeworkforgelelectrophoresisimageanalysis |