Distinguishing prognostic and predictive biomarkers: An information theoretic approach
- Submitting institution
-
The University of Manchester
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 78247392
- Type
- D - Journal article
- DOI
-
10.1093/bioinformatics/bty357
- Title of journal
- Bioinformatics
- Article number
- -
- First page
- 3365
- Volume
- 34
- Issue
- 19
- ISSN
- 1367-4803
- Open access status
- Compliant
- Month of publication
- May
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
5
- Research group(s)
-
A - Computer Science
- Citation count
- 11
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- "Data-driven biomarker selection is a key part of pharmaceutical pipelines: in designing tailored therapies, and clinical trial planning. This was the first work to show a computational method of distinguishing two important classes of biomarker - predictive and prognostic.
Keynote talk at Applied ML Days Conference (Brown).
Currently in use by Roche Switzerland (contact: Group Director, Neuroscience Analytics, PHC Data Science), for Huntington''s Patients, and has recently led to a Roche collaboration grant (GBP200,000) to UoM.
Postdoc (Sechidis) on the project used this as a basis for a job at Roche, and was appointed as Senior Data Scientist."
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
