Dataset Information

Integrating Multiple Evidence Sources to Predict Adverse Drug Reactions Based on a Systems Pharmacology Model.

ABSTRACT: Identifying potential adverse drug reactions (ADRs) is critically important for drug discovery and public health. Here we developed a multiple evidence fusion (MEF) method for the large-scale prediction of drug ADRs that can handle both approved drugs and novel molecules. MEF is based on the similarity reference by collaborative filtering, and integrates multiple similarity measures from various data types, taking advantage of the complementarity in the data. We used MEF to integrate drug-related and ADR-related data from multiple levels, including the network structural data formed by known drug-ADR relationships for predicting likely unknown ADRs. On cross-validation, it obtains high sensitivity and specificity, substantially outperforming existing methods that utilize single or a few data types. We validated our prediction by their overlap with drug-ADR associations that are known in databases. The proposed computational method could be used for complementary hypothesis generation and rapid analysis of potential drug-ADR interactions.

SUBMITTER: Cao DS

PROVIDER: S-EPMC4592529 | biostudies-literature | 2015 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Integrating Multiple Evidence Sources to Predict Adverse Drug Reactions Based on a Systems Pharmacology Model.

Cao D-S DS Xiao N N Li Y-J YJ Zeng W-B WB Liang Y-Z YZ Lu A-P AP Xu Q-S QS Chen A F AF

CPT: pharmacometrics & systems pharmacology 20150911 9

Identifying potential adverse drug reactions (ADRs) is critically important for drug discovery and public health. Here we developed a multiple evidence fusion (MEF) method for the large-scale prediction of drug ADRs that can handle both approved drugs and novel molecules. MEF is based on the similarity reference by collaborative filtering, and integrates multiple similarity measures from various data types, taking advantage of the complementarity in the data. We used MEF to integrate drug-relate ...[more]

PMID: 26451329

Similar Datasets

Project description:BackgroundWomen experience adverse drug reactions, ADRs, nearly twice as often as men, yet the role of sex as a biological factor in the generation of ADRs is poorly understood. Most drugs currently in use were approved based on clinical trials conducted on men, so women may be overmedicated. We determined whether sex differences in drug pharmacokinetics, PKs, predict sex differences in ADRs.MethodsSearches of the ISI Web of Science and PubMed databases were conducted with combinations of the terms: drugs, sex or gender, pharmacokinetics, pharmacodynamics, drug safety, drug dose, and adverse drug reaction, which yielded over 5000 articles with considerable overlap. We obtained information from each relevant article on significant sex differences in PK measures, predominantly area under the curve, peak/maximum concentrations, and clearance/elimination rates. ADRs were identified from every relevant article and recorded categorically as female-biased, male-biased, or not sex-biased.ResultsFor most of the FDA-approved drugs examined, elevated blood concentrations and longer elimination times were manifested by women, and these PKs were strongly linked to sex differences in ADRs. Of the 86 drugs evaluated, 76 had higher PK values in women; for 59 drugs with clinically identifiable ADRs, sex-biased PKs predicted the direction of sex-biased ADRs in 88% of cases. Ninety-six percent of drugs with female-biased PK values were associated with a higher incidence of ADRs in women than men, but only 29% of male-biased PKs predicted male-biased ADRs. Accessible PK information is available for only a small fraction of all drugs CONCLUSIONS: Sex differences in pharmacokinetics strongly predict sex-specific ADRs for women but not men. This sex difference was not explained by sex differences in body weight. The absence of sex-stratified PK information in public records for hundreds of drugs raises the concern that sex differences in PK values are widespread and of clinical significance. The common practice of prescribing equal drug doses to women and men neglects sex differences in pharmacokinetics and dimorphisms in body weight, risks overmedication of women, and contributes to female-biased adverse drug reactions. We recommend evidence-based dose reductions for women to counteract this sex bias.

Dataset Information

Integrating Multiple Evidence Sources to Predict Adverse Drug Reactions Based on a Systems Pharmacology Model.

Publications

Integrating Multiple Evidence Sources to Predict Adverse Drug Reactions Based on a Systems Pharmacology Model.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets