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 the management of all drugs, all laboratory results, and all standard nursing statements (SNSs). CLEAR is an algorithm, consisting in an electronic health record (EHR)–based pharmacovigilance method, that serves for adverse drug reaction (ADR) signal detection. It matches each drug-exposed patient to up to 4 non-exposed patients by age, gender, admitting department, and diagnosis.
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.
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 adverse drug reactions (ADRs) and serious side-effects of candidate and market drugs. This program is based on a compressed sensing (CS) algorithm to infer new chemical-ADR associations by exploiting existing noisy, biased and incomplete data stored in the SIDER database. It improves the prediction feature with the increasing knowledge of other ADRs associated with the chemical.
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.
Assists users in finding causal genetic biomarkers of adverse drug reactions. HUME is a model for discovering relations between specific Drug-Reactions and the Genetic biomarkers (G-DRs). This multi-phase algorithm is composed of a network scoring system to select candidate relations between the biomarkers and the drug reactions, and a quasi-experimental design test for evaluating causal significance of the candidate relations.
A comprehensive proteome scale approach that predicts human protein targets and side effects of drugs. We develop a comprehensive proteome scale approach that predicts human protein targets and side effects of drugs. For drug-protein interaction prediction, FINDSITEcomb, whose average precision is ~30% and recall ~27%, is employed. For side effect prediction, a new method is developed with a precision of ~57% and a recall of ~24%. DR. PRODIS provides protein targets of drugs, drugs for a given protein target, associated diseases and side effects of drugs, as well as an interface for the virtual target screening of new compounds.
An integrative label propagation framework to predict drug-drug interaction (DDI) by integrating label side effects, off-label side effects, and chemical structures. A systematic comparison of the experimental results shows (1) side effect profiles are more predictive features than chemical structures in DDI prediction. It greatly benefits from the fact that clinical side effects are human phenotypic data obviating translation issues. (2) label propagation algorithm boosted the DDI prediction by considering high-order relationships between drugs. (3) our proposed integrative label propagation algorithm effectively integrated multiple drug properties and outperformed competitors. Furthermore, we applied the proposed algorithm to all known drugs which have one or more side effect profiles and obtained 145,068 predicted DDIs. These predicted DDIs can be leveraged for clinical surveillance and real-world drug discovery.
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.
Predicts five adverse effects of drugs (ADEs). ADVERPred is a web service that can estimate the ability of druglike compounds to cause myocardial infarction, arrhythmia, cardiac failure, hepatotoxicity and nephrotoxicity based on their structural formulas. The software can be used for estimation of the corresponding adverse effects for hits and lead compounds at the early stages of drug discovery.
Implements a local non-sequential searching for similar binding sites on protein surfaces with a controlled amount of flexibility. PatchSearch is based on an efficient and original quasi-clique detection approach to recognize specific patches. It is able to accurately align patch locally on a whole off-target surface. The tool can recognize patches with a controlled amount of flexibility through the parameter ∆d that corresponds to the maximal detectable conformation change.
Allows users to detect and annotate temporally anchored mentions of Adverse drug events (ADEs) from a clinical text corpus. ADEPt is a modular pipeline that first perform ADE mentions’ identification, and then, organize it, for finally refining the classification thanks to contextual indicators furnished by the source. The application also includes a way for targeting ADE-specific patterns in psychiatric clinical text and an expandable dictionary depicting over 60 common ADEs.
Allows users to predict drugs side effects. DrugClust is a flexible package that provides a multistep machine learning tool which implements three algorithms: K-Means, PAM and K-Seeds. It generates clusters of drugs from chemical or protein interaction profiles. In addition, it also authorizes pathway enrichment analysis for investigating presumable interaction between groups of drugs with similar chemical and protein interaction profiles, side effects and pathways.
Predicts the probability of a compound presenting with different tissue-specific drug adverse events. MAESTER is based on a data-driven machine learning approach and incorporates information on a compound’s structure, targets, and downstream effects. This algorithm combines compound and target properties to predict the likelihood of events. It can directly predict clinical effects and can be improved to predict patient specific adverse events.
Compiles information from a broad selection of resources and limits display of the information to user-selected areas of interest. ToxReporter is a PERL-based web-application which utilizes a MySQL database to streamline this process by categorizing public and proprietary domain-derived information into predefined safety categories according to a customizable lexicon. It also uses a scoring system based on relative counts of the red-flags to rank all genes for the amount of information pertaining to each safety issue.
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.
Allows protein ligand-binding site comparison and database searching. SMAP-WS is a computation environment designed for web accessible 3D ligand-binding site comparison and similarity searching on a structural proteome scale. The software is capable of an all-by-all comparison of binding sites for a complete structural proteome. It can assist users in addressing practical problems in biology and drug discovery.
An online implementation of a recently published computational model for target prediction based on a reference library containing 533 individual targets with 179,807 active ligands. TarPred accepts interactive graphical input or input in the chemical file format of SMILES. Given a query compound structure, it provides the top ranked 30 interacting targets. For each of them, TarPred not only shows the structures of three most similar ligands that are known to interact with the target, but also highlights the disease indications associated with the target. This information is useful for understanding the mechanisms of action and toxicities of active compounds, and can provide drug repositioning opportunities.
0 - 0 of 0
0 - 0 of 0