DOI | Resolve DOI: https://doi.org/10.1016/j.neucom.2018.02.096 |
---|
Author | Search for: Li, Yifeng1; Search for: Fauteux, François1; Search for: Zou, Jinfeng2; Search for: Nantel, André2; Search for: Pan, Youlian1 |
---|
Affiliation | - National Research Council of Canada. Digital Technologies
- National Research Council of Canada. Human Health Therapeutics
|
---|
Format | Text, Article |
---|
Subject | cancer diagnosis; whole exome sequencing; deep learning; multi-modal deep Boltzmann machine |
---|
Abstract | When diagnosed at an advanced stage, most cancer patients suffer from treatment failure, recurrences and low survival. Taking advantage of high-throughput sequencing and deep learning techniques, we developed an early cancer monitoring method based on multi-modal deep Boltzmann machine to (1) learn association between matched germline and somatic mutations captured by whole exome sequencing from available samples of cancer patients, and (2) predict patient-specific high-risk genes whose somatic mutations are required to drive normal tissues to a tumor state. Our experiments on a set of breast cancer samples show that our method significantly outperforms the currently used frequency-based method in the personalized prediction of genes carrying critical mutations. |
---|
Publication date | 2018-05-22 |
---|
Publisher | Elsevier |
---|
In | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
NPARC number | 23003839 |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | 28a1b558-61f2-4be0-b15c-043854aacf54 |
---|
Record created | 2018-08-14 |
---|
Record modified | 2020-03-16 |
---|