Predicting serious rare adverse reactions of novel chemicals
2018
Adverse drug reactions (ADRs) are one of the main causes of death and a major financial burden on the world9s economy. Due to the limitations of the animal model, computational prediction of severe ADRs is invaluable. However, current state-of-the-art computational methods for prediction of rare and serious ADRs do not yield significantly better results than random guessing. We present a novel computational method, based on the theory of “compressed sensing”, that can accurately and reliably predict serious side-effects of candidate and market drugs. Not only is our method able to infer new chemical-ADR associations using existing noisy, biased, and incomplete databases, but our data also demonstrates that the accuracy of our approach in predicting a serious adverse reaction (ADR) for a candidate drug increases with increasing knowledge of other ADRs associated with the drug. Namely, as the candidate drug moves up the different stages of clinical trials, the prediction accuracy of our method will increase accordingly. Thus, the compressed sensing based computational method reported here represents a major advance in predicting severe rare ADRs, and may facilitate reducing the time and cost of drug discovery and development.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
27
References
2
Citations
NaN
KQI