Predicting the Frequencies of Drug Side effects
- Submitting institution
-
Royal Holloway and Bedford New College
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 39318452
- Type
- D - Journal article
- DOI
-
10.1038/s41467-020-18305-y
- Title of journal
- Nature Communications
- Article number
- 4575
- First page
- 1
- Volume
- 11
- Issue
- -
- ISSN
- 2041-1723
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2020
- 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
-
3
- Research group(s)
-
-
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The first method for computationally predicting the frequencies of drug side effects in the population. Our machine learning algorithm, based on matrix decomposition, learns a small set of latent features encoding the biological interplay between drugs and side effects. Our predictions are explainable: the latent features can be interpreted in terms of drug effects on specific physiological systems. Important for pharma industries and regulatory agencies: can be used in early phase clinical trials to direct risk assessment in later clinical trials or after a drug has entered the market; or for estimation of the cohort size needed in clinical trials.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -