Communications Biology (Dec 2022)
Machine learning multi-omics analysis reveals cancer driver dysregulation in pan-cancer cell lines compared to primary tumors
- Lauren M. Sanders,
- Rahul Chandra,
- Navid Zebarjadi,
- Holly C. Beale,
- A. Geoffrey Lyle,
- Analiz Rodriguez,
- Ellen Towle Kephart,
- Jacob Pfeil,
- Allison Cheney,
- Katrina Learned,
- Rob Currie,
- Leonid Gitlin,
- David Vengerov,
- David Haussler,
- Sofie R. Salama,
- Olena M. Vaske
Affiliations
- Lauren M. Sanders
- Department of Biomolecular Engineering, UC Santa Cruz
- Rahul Chandra
- Paul G. Allen School of Computer Science and Engineering, University of Washington
- Navid Zebarjadi
- UC Santa Cruz Genomics Institute
- Holly C. Beale
- UC Santa Cruz Genomics Institute
- A. Geoffrey Lyle
- UC Santa Cruz Genomics Institute
- Analiz Rodriguez
- Department of Neurosurgery, University of Arkansas for Medical Sciences
- Ellen Towle Kephart
- UC Santa Cruz Genomics Institute
- Jacob Pfeil
- Department of Biomolecular Engineering, UC Santa Cruz
- Allison Cheney
- UC Santa Cruz Genomics Institute
- Katrina Learned
- Department of Biomolecular Engineering, UC Santa Cruz
- Rob Currie
- Department of Biomolecular Engineering, UC Santa Cruz
- Leonid Gitlin
- Department of Microbiology and Immunology, University of California, San Francisco
- David Vengerov
- Oracle Labs, Oracle Corporation
- David Haussler
- Department of Biomolecular Engineering, UC Santa Cruz
- Sofie R. Salama
- Department of Biomolecular Engineering, UC Santa Cruz
- Olena M. Vaske
- UC Santa Cruz Genomics Institute
- DOI
- https://doi.org/10.1038/s42003-022-04075-4
- Journal volume & issue
-
Vol. 5,
no. 1
pp. 1 – 11
Abstract
Using a support vector machine learning approach and multi-omics data, dysregulation of key cancer driver pathways is revealed in cancer cell lines compared to primary tumors.
