Biologically informed deep neural network for prostate cancer discovery.
Elmarakeby HA, Hwang J, Arafeh R, Crowdis J, Gang S, Liu D, AlDubayan SH, Salari K, Kregel S, Richter C, Arnoff TE, Park J, Hahn WC, Van Allen EM. · 2021
Read Biologically informed deep neural network for prostate cancer discovery. by Elmarakeby HA, Hwang J, Arafeh R, Crowdis J, Gang S, Liu D, AlDubayan SH, Salari K, Kregel S, Richter C, Arnoff TE, Park J, Hahn WC, Van Allen EM. (2021) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/europmc-pmc8514339.txt.
Description
Elmarakeby and co-authors build P-NET, a deep learning model shaped by biology, for prostate cancer study. Which molecular traits drive aggressive prostate cancer is a major open question. Machine learning that can be read and explained may help find them.
P-NET sorts patients by treatment-resistance state from molecular data. It beat other modeling approaches in their tests. Its built-in clarity points to the traits that drive each call. Known and new candidates emerged, among them MDM4 and FGFR1. Lab tests backed their role in advanced disease. The authors argue that clear, biology-based networks can serve both discovery and clinical prediction. The frame may fit other cancers too.
Catalog record
| CREATOR | Elmarakeby HA, Hwang J, Arafeh R, Crowdis J, Gang S, Liu D, AlDubayan SH, Salari K, Kregel S, Richter C, Arnoff TE, Park J, Hahn WC, Van Allen EM. |
|---|---|
| YEAR | 2021 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 65 KB |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |