| Autor: |
Colin Targonski, M. Reed Bender, Benjamin T. Shealy, Benafsh Husain, Bill Paseman, Melissa C. Smith, F. Alex Feltus |
| Jazyk: |
angličtina |
| Rok vydání: |
2020 |
| Předmět: |
|
| Zdroj: |
Patterns, Vol 1, Iss 6, Pp 100087- (2020) |
| Druh dokumentu: |
article |
| ISSN: |
2666-3899 |
| DOI: |
10.1016/j.patter.2020.100087 |
| Popis: |
Summary: We introduce the Transcriptome State Perturbation Generator (TSPG) as a novel deep-learning method to identify changes in genomic expression that occur between tissue states using generative adversarial networks. TSPG learns the transcriptome perturbations from RNA-sequencing data required to shift from a source to a target class. We apply TSPG as an effective method of detecting biologically relevant alternate expression patterns between normal and tumor human tissue samples. We demonstrate that the application of TSPG to expression data obtained from a biopsy sample of a patient's kidney cancer can identify patient-specific differentially expressed genes between their individual tumor sample and a target class of healthy kidney gene expression. By utilizing TSPG in a precision medicine application in which the patient sample is not replicated (i.e., n=1), we present a novel technique of determining significant transcriptional aberrations that can be used to help identify potential targeted therapies. The Bigger Picture: Deep learning has shown tremendous success in image and natural language processing; however, attempts to apply the tools of machine learning to better understanding biological systems are still in the stage of early adoption. We propose a novel deep-learning tool that can be used to process samples of RNA-sequencing data. By applying the Transcriptome State Perturbation Generator to human samples, we show that deep learning derives insight into the gene expression shifts required for transition between two biological conditions (e.g., normal versus tumor). RNA-sequencing data derived from a single patient's tumor were analyzed using this tool to determine gene expression aberrations specific to that patient's tumor. As medicine shifts from cohort-based population studies to individual-based precision treatments, our example demonstrates that deep learning is a powerful ally in the quest to understand how complex biological systems have shifted for a single patient. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
