1 - 50 of 61 results


star_border star_border star_border star_border star_border
star star star star star
An integrated web-based platform for molecular descriptor and fingerprint computation. ChemDes provides more than 3,679 molecular descriptors that are divided into 61 logical blocks. In addition, it provides 59 types of molecular fingerprint systems for drug molecules, including topological fingerprints, electro-topological state fingerprints, MACCS keys, FP4 keys, atom pairs fingerprints, topological torsion fingerprints and Morgan/circular fingerprints.

CORAL / CORelations And Logic

Allows users to construct quantitative structure property/activity relationships (QSPR/QSAR). CORAL is a standalone software for building models from SMILES files according to the Monte Carlo method. It also includes some databases providing physicochemical parameters and biological activity which can be utilized to perform analysis or to create new models. CORAL can also analyze QSAR analysis, especially for detecting carcinogenic endpoint. The program is a part of the CHEMPREDICT project.

lazar / lazy structure–activity relationships

Helps for the prediction of complex toxicological endpoints, like carcinogenicity, long-term, and reproductive toxicity. lazar is a generic prediction algorithm for any biological endpoint with sufficient experimental data. It uses data mining algorithms to derive predictions for untested compounds from experimental training data. It also utilizes open source chemoinformatics libraries to calculate a range of physico-chemical descriptors.


A web server for the prediction of rodent oral toxicity. The prediction method is based on the analysis of the similarity of compounds with known median lethal doses (LD50) and incorporates the identification of toxic fragments, therefore representing a novel approach in toxicity prediction. In addition, the web server includes an indication of possible toxicity targets which is based on an in-house collection of protein-ligand-based pharmacophore models ('toxicophores') for targets associated with adverse drug reactions.

BioPPSy / BIOchemical Property Prediction System

Provides an easy-to-use graphical interface for quantitative structure-property relationship (QSPR) modelling. The BioPPSy program has 2 main functionalities, (i) the creation of a QSPR/QSAR model and (ii) the prediction of properties using this model. The reliability of QSPR and quantitative structure-activity relationship (QSAR) models is often difficult to assess due to the problems of accessing the tools and data used to build the models. BioPPSy aims to fill the gap by providing an easy-to-use open-source software platform.

CarcinoPred-EL / Carcinogenicity Prediction using Ensemble Learning methods

Classifies compounds as Carcinogens and Non-Carcinogens using only their two-dimensional structures. CarcinoPred-EL is a free carcinogenicity prediction online server. This web server has integrated three novel ensemble learning models, namely Ensemble XGBoost, Ensemble support vector machine (SVM) and Ensemble random forest (RF), to predict the carcinogenicity of chemicals. This method can be conveniently applied to the prediction of other toxicity endpoints or other pathological drug properties of chemicals.


Allows to rationalize a prediction at the molecular level by analyzing the binding mode of the tested compound towards all 16 target proteins in real-time 3D/4D. The VirtualToxLab is an in silico tool for predicting the toxic potential (endocrine and metabolic disruption, some aspects of carcinogenicity and cardiotoxicity) of drugs, chemicals and natural products. It simulates and quantifies their interactions towards a series of proteins known to trigger adverse effects using automated, flexible docking combined with multi-dimensional QSAR (mQSAR). Currently, the VirtualToxLab comprises 16 models of proteins known or suspected to trigger adverse effects: the androgen, aryl hydrocarbon, estrogen α, estrogen β, glucocorticoid, hERG, liver X, mineralocorticoid, progesterone, thyroid α, thyroid β and peroxisome proliferator-activated receptor γ as well as the enzymes CYP450 1A2, 2C9, 2D6 and 3A4.

Derek Nexus

Gives accurate toxicity predictions quickly. Derek Nexus is a knowledge-based expert systems that predicts the toxicity and metabolism of a chemical, respectively. It offers an effective mechanism for the sharing of data and knowledge on chemical toxicity and metabolism. It also provides a more direct assessment of predictive performance, avoiding the inherent difficulties of reference to published studies, by allowing the user to access information directly on predictive performance for an alert within the version of the software.

TOPKAT / TOxicity Prediction by Komputer Assisted Technology

Calculates the compound performance in experimental assays and animal models. TOPKAT exploits the molecular structure to measure and approve assessments of the toxic and environmental effects of chemicals. This software utilizes cross-validated quantitative structure toxicity relationship (QSTR) models for evaluating various measures of toxicity and interprets results via a patented Optimal Predictive Space (OPS) validation method.


An integrated framework for creating multiple regression models. RRegrs offers the option of ten simple and complex regression methods combined with repeated 10-fold and leave-one-out cross-validation. Methods include multiple linear regression, generalized linear model with stepwise feature selection, partial least squares regression, Lasso regression, and support vector machines recursive feature elimination. The framework is an automated fully validated procedure which produces standardized reports to quickly oversee the impact of choices in modelling algorithms and assess the model and cross-validation results.

ECOSAR / Ecological Structure Activity Relationships

Estimates aquatic toxicity. ECOSAR is a computerized version of the ecotoxicity analysis procedures as practiced by the Office of Pollution Prevention and Toxics (OPPT) when data are lacking for risk assessment development. The software, using computerized Structure Activity Relationships (SARs), allows to predict both short-term and long -term toxicity to aquatic organism. ECOSAR is menu-driven and contains various help functions to assist the user.

ChemoPy / Chemoinformatics in python

An open-source python package for calculating the commonly used structural and physicochemical features. ChemoPy computes 16 drug feature groups composed of 19 descriptors that include 1135 descriptor values. In addition, it provides seven types of molecular fingerprint systems for drug molecules, including topological fingerprints, electro-topological state (E-state) fingerprints, MACCS keys, FP4 keys, atom pairs fingerprints, topological torsion fingerprints and Morgan/circular fingerprints. By applying a semi-empirical quantum chemistry program MOPAC, ChemoPy can also compute a large number of 3D molecular descriptors conveniently.


Performs toxicity prediction based on Deep Learning. DeepTox consists of: (1) cleaning and quality control of the data containing the chemical description of the compounds, (2) creation of chemical descriptors as input features for the models, (3) model selection including feature selection if required by the model class, (4) evaluation of the quality of models to choose the best ones, and (5) combination of models and ensemble predictors. The pipeline was built under the “Tox21 Data Challenge”.

CASE Ultra

Supports both Statistical Alert based models and Expert Rule based predictions. CASE Ultra is an easy to use and capable quantitative structure-activity relationship (QSAR) software. It can automatically derive alerts from data using statistical methods or use alerts obtained using expert knowledge for predicting bioactivity of untested compounds. CASE Ultra mines alerts (fragments of chemical structures) that are statistically related to the activity being modeled. A CASE Ultra model is therefore a collection of relevant alerts with a detailed account of their statistical relationship with the activity. In addition, a number of physicochemical descriptors (logP, water solubility, charges, E-states, surface descriptors, etc.) are employed to build local QSARs for each alert.


Considers the bioavailability of the compounds by a simple but powerful model. HazardExpert is an ideal tool for quick prediction of compound's toxicity in the drug discovery process or during the dispositional research phase. It is an essential software tool for initial estimation of toxic symptoms of organic compounds in humans and in animals. HazardExpert is a rule-based system with open architecture, in other words, the chemists, toxicologists, drug disposition experts or environmental managers can understand, expand, modify or optimize the data on which the toxicity estimation relies. The input of the rules is facilitated by an easy-to-use graphical interface, and the toxicity estimation results are displayed by a graph which is easy to interpret and suitable for reporting.