Spatial transformation of multi-omics data unlocks novel insights into cancer biology
The application of next-generation sequencing (NGS) has transformed cancer research. As costs have decreased, NGS has increasingly been applied to generate multiple layers of molecular data from the same samples, covering genomics, transcriptomics, and methylomics. Integrating these types of multi-o...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
eLife Sciences Publications Ltd
2023-09-01
|
| Series: | eLife |
| Subjects: | |
| Online Access: | https://elifesciences.org/articles/87133 |
| _version_ | 1797692256756432896 |
|---|---|
| author | Mateo Sokač Asbjørn Kjær Lars Dyrskjøt Benjamin Haibe-Kains Hugo JWL Aerts Nicolai J Birkbak |
| author_facet | Mateo Sokač Asbjørn Kjær Lars Dyrskjøt Benjamin Haibe-Kains Hugo JWL Aerts Nicolai J Birkbak |
| author_sort | Mateo Sokač |
| collection | DOAJ |
| description | The application of next-generation sequencing (NGS) has transformed cancer research. As costs have decreased, NGS has increasingly been applied to generate multiple layers of molecular data from the same samples, covering genomics, transcriptomics, and methylomics. Integrating these types of multi-omics data in a combined analysis is now becoming a common issue with no obvious solution, often handled on an ad hoc basis, with multi-omics data arriving in a tabular format and analyzed using computationally intensive statistical methods. These methods particularly ignore the spatial orientation of the genome and often apply stringent p-value corrections that likely result in the loss of true positive associations. Here, we present GENIUS (GEnome traNsformatIon and spatial representation of mUltiomicS data), a framework for integrating multi-omics data using deep learning models developed for advanced image analysis. The GENIUS framework is able to transform multi-omics data into images with genes displayed as spatially connected pixels and successfully extract relevant information with respect to the desired output. We demonstrate the utility of GENIUS by applying the framework to multi-omics datasets from the Cancer Genome Atlas. Our results are focused on predicting the development of metastatic cancer from primary tumors, and demonstrate how through model inference, we are able to extract the genes which are driving the model prediction and are likely associated with metastatic disease progression. We anticipate our framework to be a starting point and strong proof of concept for multi-omics data transformation and analysis without the need for statistical correction. |
| first_indexed | 2024-03-12T02:25:02Z |
| format | Article |
| id | doaj.art-5eb6910b14814b319ff2f70d309e251b |
| institution | Directory Open Access Journal |
| issn | 2050-084X |
| language | English |
| last_indexed | 2024-03-12T02:25:02Z |
| publishDate | 2023-09-01 |
| publisher | eLife Sciences Publications Ltd |
| record_format | Article |
| series | eLife |
| spelling | doaj.art-5eb6910b14814b319ff2f70d309e251b2023-09-05T16:47:40ZengeLife Sciences Publications LtdeLife2050-084X2023-09-011210.7554/eLife.87133Spatial transformation of multi-omics data unlocks novel insights into cancer biologyMateo Sokač0https://orcid.org/0000-0001-9896-1544Asbjørn Kjær1https://orcid.org/0009-0006-3307-0031Lars Dyrskjøt2Benjamin Haibe-Kains3Hugo JWL Aerts4Nicolai J Birkbak5https://orcid.org/0000-0003-1613-9587Department of Molecular Medicine, Aarhus University Hospital, Aarhus, Denmark; Department of Clinical Medicine, Aarhus University, Aarhus, Denmark; Bioinformatics Research Center, Aarhus University, Aarhus, DenmarkDepartment of Molecular Medicine, Aarhus University Hospital, Aarhus, Denmark; Department of Clinical Medicine, Aarhus University, Aarhus, Denmark; Bioinformatics Research Center, Aarhus University, Aarhus, DenmarkDepartment of Molecular Medicine, Aarhus University Hospital, Aarhus, Denmark; Department of Clinical Medicine, Aarhus University, Aarhus, DenmarkPrincess Margaret Cancer Centre, University Health Network, Temerty Faculty of Medicine, University of Toronto, Toronto, CanadaArtificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, United States; Departments of Radiation Oncology and Radiology, Brigham and Women’s Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, United States; Radiology and Nuclear Medicine, CARIM & GROW, Maastricht University, Maastricht, NetherlandsDepartment of Molecular Medicine, Aarhus University Hospital, Aarhus, Denmark; Department of Clinical Medicine, Aarhus University, Aarhus, Denmark; Bioinformatics Research Center, Aarhus University, Aarhus, DenmarkThe application of next-generation sequencing (NGS) has transformed cancer research. As costs have decreased, NGS has increasingly been applied to generate multiple layers of molecular data from the same samples, covering genomics, transcriptomics, and methylomics. Integrating these types of multi-omics data in a combined analysis is now becoming a common issue with no obvious solution, often handled on an ad hoc basis, with multi-omics data arriving in a tabular format and analyzed using computationally intensive statistical methods. These methods particularly ignore the spatial orientation of the genome and often apply stringent p-value corrections that likely result in the loss of true positive associations. Here, we present GENIUS (GEnome traNsformatIon and spatial representation of mUltiomicS data), a framework for integrating multi-omics data using deep learning models developed for advanced image analysis. The GENIUS framework is able to transform multi-omics data into images with genes displayed as spatially connected pixels and successfully extract relevant information with respect to the desired output. We demonstrate the utility of GENIUS by applying the framework to multi-omics datasets from the Cancer Genome Atlas. Our results are focused on predicting the development of metastatic cancer from primary tumors, and demonstrate how through model inference, we are able to extract the genes which are driving the model prediction and are likely associated with metastatic disease progression. We anticipate our framework to be a starting point and strong proof of concept for multi-omics data transformation and analysis without the need for statistical correction.https://elifesciences.org/articles/87133deep learningmulti-omicscancerintegrated gradientsimmunotherapybladder cancer |
| spellingShingle | Mateo Sokač Asbjørn Kjær Lars Dyrskjøt Benjamin Haibe-Kains Hugo JWL Aerts Nicolai J Birkbak Spatial transformation of multi-omics data unlocks novel insights into cancer biology eLife deep learning multi-omics cancer integrated gradients immunotherapy bladder cancer |
| title | Spatial transformation of multi-omics data unlocks novel insights into cancer biology |
| title_full | Spatial transformation of multi-omics data unlocks novel insights into cancer biology |
| title_fullStr | Spatial transformation of multi-omics data unlocks novel insights into cancer biology |
| title_full_unstemmed | Spatial transformation of multi-omics data unlocks novel insights into cancer biology |
| title_short | Spatial transformation of multi-omics data unlocks novel insights into cancer biology |
| title_sort | spatial transformation of multi omics data unlocks novel insights into cancer biology |
| topic | deep learning multi-omics cancer integrated gradients immunotherapy bladder cancer |
| url | https://elifesciences.org/articles/87133 |
| work_keys_str_mv | AT mateosokac spatialtransformationofmultiomicsdataunlocksnovelinsightsintocancerbiology AT asbjørnkjær spatialtransformationofmultiomicsdataunlocksnovelinsightsintocancerbiology AT larsdyrskjøt spatialtransformationofmultiomicsdataunlocksnovelinsightsintocancerbiology AT benjaminhaibekains spatialtransformationofmultiomicsdataunlocksnovelinsightsintocancerbiology AT hugojwlaerts spatialtransformationofmultiomicsdataunlocksnovelinsightsintocancerbiology AT nicolaijbirkbak spatialtransformationofmultiomicsdataunlocksnovelinsightsintocancerbiology |