TWOSIDES [ 18] is a database that contains predicted side effects associated with pairs of drugs.
It is true that, if I advise someone "Get drunk", he might respond "Are you telling me to have a hangover?" Yet this inference is not acceptable as leading from one intention to another; for predicted side-effects of realizing one's intentions are not thereby intended, even if (in another case) they are welcome.
Our first research goal of big data application is to predict side effect of drug which is one of screening methods in drug discovery.
Predicting side effects of drugs is a critical issue for the drug discovery.
In drug discovery, this approach can identify potential alternate uses for drug candidates or predict side effects of pharmaceuticals that might arise from unintended interactions with other targets (i.e., off-target effects), thus producing adverse outcomes.
The fixed-backbone model performs reasonably well with an overall rmsd between computed and predicted side-chain order parameters of 0.26.
In order to solve this specific problem, we formulate approved drugs, side effect terms and drug side effect associations as a recommender system, and transform the problem of predicting side effects into a recommender task.
Since adverse events are often remarkably idiosyncratic, pharmacogenomics may offer a way of predicting side effects and their severity from a particular drug or drug class in individual patients.
So, 7 dataset patterns of pinpoint data are prepared to be able to predict side effect incidence even if some of those explanatory variables are missing.
In previous literature, chemical structure fingerprints were used for predicting side effect profiles in the framework of OCCA (Atias and Sharan, 2011) and SCCA (Pauwels et al., 2011).
