Drug side effect detection software tools | Drug discovery data analysis
Discovering the unintended “off-targets” that predict adverse drug reactions (ADRs) is daunting by empirical methods alone. Drugs can act on multiple protein targets, some of which can be unrelated by traditional molecular metrics, and hundreds of proteins have been implicated in side effects.
Generates different feature sets for adverse drug reaction (ADR) prediction. adr-prediction is based on the utilization of knowledge graphs. It can be easily extended to other feature sources or machine learning methods.
Allows to identify possible side effects of potential drug treatments on the human body. BioSight works with an algorithm which permits to predict all of the potential biological targets that are at risk of interacting with a potential drug treatment. It helps researchers to better develop their molecules or reduce the failure rate during the clinical trial phase.
A web server that integrates chemical and biological information to elucidate the molecular mechanisms underlying drug side effects. IntSide currently catalogs 1175 side effects caused by 996 drugs, associated with drug features divided into eight categories, belonging to either biology or chemistry. On the biological side, IntSide reports drug targets and off-targets, pathways, molecular functions and biological processes. From a chemical viewpoint, it includes molecular fingerprints, scaffolds and chemical entities.
Predicts Blood-Brain-Barrier (BBB) permeability from drug clinical phenotypes (drug side effects and drug indications). CASE-BBB prediction can apply to both small compounds and macro-molecules penetrating BBB through various mechanisms besides passive diffusion. It accounts for passive diffusion as well as a putative contribution by active transport and other complex mechanisms. This method not only applies to the Food and Drug Administration (FDA) approved drugs but also applies to the tested/testing drugs, the failed drugs due to lack of expected efficiency, and the withdrawn drugs due to toxic or others reasons, as long as clinical phenotype data of these drugs are available.
A machine learning classifier to prioritize adverse drug reactions (ADRs) for approved drugs and pre-clinical small-molecule compounds by combining chemical structure (CS) and gene expression (GE) features. The GE data is from the Library of Integrated Network-based Cellular Signatures (LINCS) L1000 dataset that measured changes in GE before and after treatment of human cells with over 20,000 small molecule compounds including most of the FDA-approved drugs. Using various benchmarking methods, we show that the integration of GE data with the CS of the drugs can significantly improve the predictability of ADRs. Moreover, transforming GE features to enrichment vectors of biological terms further improves the predictive capability of the classifiers. The most predictive biological-term features can assist in understanding the drug mechanisms of action.
Assists in predicting side effects of drug pairs. Decagon is a general graph convolutional neural network designed to operate on a large multimodal graph where nodes can be connected through a large number of different relation types. It infers a prediction model that can identify side effects of pairs of drugs. This application predicts an association between a side effect and a co-prescribed drug pair to identify side effects that cannot be attributed to either drug alone.
Provides a multiple response partial least-squares (PLS) algorithm for graph mining. GPL is composed of two principal functions: (i) gSpan, which runs a frequent subgraph mining algorithm from graph data and (ii) gPLS which performs a (multiple) graph PLS regression. Results can be visualized thanks to an additional module, only available with MacOs, which converts subgraphs patterns.