1 - 50 of 102 results

Open Targets

star_border star_border star_border star_border star_border
star star star star star
A data integration and visualization platform that provides evidence about the association of known and potential drug targets with diseases. Open Targets platform is designed to support identification and prioritization of biological targets for follow-up. Each drug target is linked to a disease using integrated genome-wide data from a broad range of data sources. The platform provides either a target-centric workflow to identify diseases that may be associated with a specific target, or a disease-centric workflow to identify targets that may be associated with a specific disease. Users can easily transition between these target- and disease-centric workflows. Open Targets platform provides free data access through your web browser or through an API (Application Programming Interface).


A multimodal web interface that presents the data from the Target Central Resource Database (TCRD) which collates many heterogeneous gene and protein datasets. Pharos serves as entry point into the druggable genome. TCRD integrates a wide array of knowledge and data types about genes, proteins and small molecules collected and processed from numerous resources. It includes text-mined bibliometric associations and statistics from the biomedical and patent literature, mRNA and protein expression data, disease and phenotype associations, bioactivity data, drug target interactions, and processed datasets about the functions of genes and proteins from 66 resources organized into 114 datasets imported from the Harmonizome. Pharos application provides facile access to all data types collected. Given the complexity of the data surrounding any target, efficient and intuitive visualization has been a high priority, to enable users to quickly navigate and summarize search results and rapidly identify patterns.

MOST / MOst-Similar ligand-based Target

Creates constraint-based models of metabolism, load existing models, export models, and run analyses on these models to predict the production of desired compounds by microbes under genetic manipulations. MOST implements GDBB (Genetic Design through Branch and Bound) in an intuitive user-friendly interface with Excel-like editing functionality, as well as implementing FBA (Flux Balance Analysis). The updated version implements visualization of models if metabolites in the model are identified with KEGG ids or ChEBI ids.


Automates the high throughput in silico vaccine candidate prediction process for the identification of putative vaccine candidates against the proteome of bacterial pathogens. VacSol rapidly and efficiently screens the whole bacterial pathogen proteome to identify a few predicted putative vaccine candidate proteins. It saves computational costs and time by efficiently reducing false positive candidate hits. The results do not depend on any universal set of rules and may vary based on the provided input.


A dual-regularized one class collaborative filtering algorithm for biological relation prediction. REMAP explores continuous chemical space, protein space, and their interactome on a large scale. When tested in a reliable, extensive, and cross-gene family benchmark, REMAP outperforms the state-of-the-art methods. It can screen a dataset of 200 thousand chemicals against 20 thousand proteins within 2 hours. Using the reconstructed genome-wide target profile as the fingerprint of a chemical compound, we predicted that seven FDA-approved drugs can be repurposed as novel anti-cancer therapies. The anti-cancer activity of six of them is supported by experimental evidences. Thus, REMAP is a valuable addition to the existing in silico toolbox for drug target identification, drug repurposing, phenotypic screening, and side effect prediction.


A web service enabling drug developers to carry out network pharmacology-based prediction and analysis by integrating results from structural biology with systems biology. Its user-friendly GUI interface simplifies essential operations for large-scale screening. Using the predictive docking approach, systemsDock can test a large number of target proteins with good prediction accuracy. This will reduce the number of tests for bioassay. Together with a curated pathway map, systemsDock helps to comprehensively characterize the underlying mechanism of a drug candidate and to interpret its cascading effects, improving the prediction of drug efficacy and safety.

SELF-BLM / self-training Bipartite Local Mode

Facilitates the identification of potential interactions. SELF-BLM categorizes unlabeled interactions and negative interactions among unknown interactions using a clustering method. It uses k-medoids clustering and a self-training support vector machine (SVM) algorithm. The tool does not require any known drug-target interaction information that is hardly known in novel molecules. It can help to deal with data imbalance problems or unlabeled data in many other areas.

PSDDF / Pathogen Specific DNA Drug Finder

Identifies DNA motifs in a selected pathogenic bacterium or virus. PSDDF aims to improve DNA targeted drug discovery by allowing user to target a specific sequence and scan corresponding compounds through virtual screening for detecting small drug candidates. The tool uses full sequenced genome information of more than 5900 bacteria extracted from the NCBI database It also permits to filter candidate molecules by using binding free energy estimations.


A web-based application for analysis of drug effects. It provides an intuitive interface to be used by anybody interested in leveraging microarray data to gain insights into the pharmacological effects of a drug, mainly identification of candidate targets, elucidation of mode of action and understanding of off-target effects. The core of Galahad is a network-based analysis method of gene expression. As an input, Galahad takes raw Affymetrix human microarray data from treatment versus control experiments and provides quality control and data exploration tools, as well as computation of differential expression. Alternatively, differential expression values can be uploaded directly. Using these differential expression values, drug target prioritization and both pathway and disease enrichment can be calculated and visualized. Drug target prioritization is based on the integration of the gene expression data with a functional protein association network.


Enables cloud computing and sourcing services and provides powerful computational algorithms. AlzPlatform is an integrated cloud computing server that assembles a large repertoire of Alzheimer’s disease (AD) related chemogenomics data, including genes, protein targets, and small chemical molecules with their bioactivity records, bioassays, and references, as well as approved drugs or those in clinical trial for AD treatments. Therefore, AlzPlatform is a valuable platform for investigating and sharing AD targets and small chemical drug molecules at chemogenomics scale for better understanding the mechanisms of system polypharmacology in aid of new anti-AD drug discovery.

PBIT / Pipeline Builder for Identification of drug Targets

Enables users to access information on all these aspects for studying microbial proteomes. PBIT is an online webserver that has been developed for screening of microbial proteomes for critical features of human drug targets such as being non-homologous to human proteome as well as the human gut microbiota, essential for the pathogen’s survival, participation in pathogen-specific pathways etc. The tool has been validated by analyzing 57 putative targets of Candida albicans documented in literature. PBIT integrates various in silico approaches known for drug target identification and will facilitate high throughput prediction of drug targets for infectious diseases, including multi-pathogenic infections.


A network analysis method for predicting the genetic perturbations caused by a drug or chemical compound using gene expression profiles. DeltaNet is also based on an ordinary differential equation (ODE) model of the gene regulatory network (GRN), but does not require a separate step of GRN inference. Instead, the target predictions are obtained directly from the data, while the GRN is only inferred implicitly. DeltaNet relies on the least angle regression (LAR) and the LASSO regularization to tackle the curse of dimensionality of the underlying regression problem. The method requires little to no expert supervision, while providing accurate gene target predictions.

SNPLS / Sparse Network-regularized Partial Least Squares

Identifies combinatorial gene-drug co-modules by integrating gene expression and drug response data across a set of cell lines as well as a gene interaction network. We first demonstrated the effectiveness of SNPLS using a set of simulation data and compared it with two typical methods. Further, we applied it to gene expression profiles for 13 321 genes and pharmacological profiles for 98 anticancer drugs across 641 cancer cell lines consisting of diverse types of human cancers. We identified 20 gene-drug co-modules, each of which consists of 30 cell lines, 137 genes and 2 drugs on average. The majority of identified co-modules have significantly functional implications and coordinated gene-drug associations.

NRLMF / Neighborhood Regularized Logistic Matrix Factorization

A drug-target interaction prediction algorithm. NRLMF method focuses on modeling the probability that a drug would interact with a target by logistic matrix factorization, where the properties of drugs and targets are represented by drug-specific and target-specific latent vectors, respectively. NRLMF assigns higher importance levels to positive observations (i.e., the observed interacting drug-target pairs) than negative observations (i.e., the unknown pairs). Because the positive observations are already experimentally verified, they are usually more trustworthy. Furthermore, the local structure of the drug-target interaction data has also been exploited via neighborhood regularization to achieve better prediction accuracy. We conducted extensive experiments over four benchmark datasets, and NRLMF demonstrated its effectiveness compared with five state-of-the-art approaches.

DNILMF / dual-network integrated logistic matrix factorization

Predicts potential drug-target interactions (DTI). DNILMF is composed of four steps: (1) inference of new drug/target profiles and construction of profile kernel matrix; (2) diffusion of drug profile kernel matrix with drug structure kernel matrix; (3) diffusion of target profile kernel matrix with target sequence kernel matrix; and (4) building of DNILMF model and smoothing of new drug/target predictions based on their neighbors.

DINIES / Drug-target Interaction Network Inference Engine based on Supervised Analysis

Allows prediction of unknown drug–target interaction networks from various types of biological data. DINIES is a web server that provides two options: DINIES Search for exploring pre-calculated drug–target interaction networks that were predicted with available data in KEGG or other databases and DINIES Prediction with a “simple” and an “advanced” mode. The flexibility of the input data, allows analysis of drug–target interaction networks in various aspects.

GIT / Genetic Interaction network-assisted target Identification

Scores a gene by combining its fitness defect with the screen outcomes of the gene’s neighbors in the genetic interaction network. GIT is a network analysis method for drug target identification. It identifies many compound-target interactions that comprise existing curated database as well as novel compound-target interactions that are supported by literature evidence. This method also significantly improves target identification and elucidates molecular and functional mechanisms of drug action.


Predicts novel drug-target interactions from the constructed heterogeneous network. DTINet captures the context information of individual networks, as well as the topological properties of nodes (e.g., drugs or proteins) across multiple networks. Based on these low-dimensional feature vectors, DTINet then finds an optimal projection from drug space onto target space, which enables the prediction of new DTIs according to the geometric proximity of the mapped vectors in a unified space. DTINet achieves substantial performance improvement over other state-of-the-art methods for DTI prediction.


forum (1)
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.

KBMF / Kernelized Bayesian Matrix Factorization

Combines kernel-based nonlinear dimensionality reduction, matrix factorization and binary classification for predicting drug-target interaction networks using only chemical similarity between drug compounds and genomic similarity between target proteins. KBMF is a fully probabilistic formulation for drug-target interaction network inference. We show its performance on four benchmark datasets using three experimental scenarios with practical importance: (i) exploratory data analysis using low-dimensional projections, (ii) predicting interactions for the out-of-sample drug compounds and (iii) predicting unknown interactions of the given network. KBMF can make use of multiple side information sources about the objects (both rows and columns) and be applied in various scenarios including recommender systems, interaction network modeling, multilabel classification, and multiple output regression.


An integrated structure- and system-based approach of drug-target prediction to enable the large-scale discovery of new targets for small molecules, such as pharmaceutical drugs, co-factors and metabolites (collectively called 'drugs'). For a given drug, our method uses sequence order-independent structure alignment, hierarchical clustering, and probabilistic sequence similarity to construct a probabilistic pocket ensemble (PPE) that captures promiscuous structural features of different binding sites on known targets. A drug's PPE is combined with an approximation of its delivery profile to reduce false positives.


Integrates and compares ten miRNA target prediction methods of interest. ChemiRs provides comprehensive features to facilitate both experimental and computational target predictions. In addition, ChemiRs incorporates flexible search modules including (i) search by miRNA, (ii) search by gene, (iii) search by gene list, (iv) search by chemical, (v) search by disease and (vi) search by pathway. Moreover, ChemiRs can make predictions for Homo sapiens miRNAs of interest, and also allow fast search of query results for multiple miRNA selection and logical restriction. The service is unique in that it integrates a large number of miRNA target prediction methods, experiment results, genes, chemicals, diseases and GO terms with instant and visualization functionalities.

CSNAP / Chemical Similarity Network Analysis Pull-down

A computational approach for compound target identification based on network similarity graphs. Query and reference compounds are populated on the network connectivity map and a graph-based neighbor counting method is applied to rank the consensus targets among the neighborhood of each query ligand. The CSNAP approach can facilitate high-throughput target discovery and off-target prediction for any compound set identified from phenotype-based or cell-based chemical screens.