1 - 29 of 29 results

Inner- and Outer RNN / Inner and Outer Recursive Neural Networks for Chemoinformatics

Assists users in classifying recursive neural network approaches in two classes: inner and outer approaches. Inner- and Outer RNN is appropriate for dealing with regression and classification problems on small molecules in chemoinformatics. The inner approach exploits recursion inside the underlying graph while the outer approach uses recursion outside. Both approaches can be combined via averaging to generate an ensemble prediction.

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.


Features an evolutionary algorithm for structure elucidation and is available as a graphical user interface (GUI) client or as a stand-alone command-line executable. The SENECA system is an open-source java-based desktop application to perform Computer Assisted Structure Elucidation (CASE) for organic molecules. It takes a molecular formula generated from high resolution mass spectrometry and spectral data from a suite of nuclear magnetic resonance (NMR) experiments and performs a stochastic search in the constitutional space, guided by a fitness function.

Meteor Nexus

Provides a knowledge-based software that gives users accurate metabolism predictions quickly. Meteor Nexus is a cost-effective solution for that provides information for decision-making when there is little or no experimental metabolism data available. It helps to interpret data from mass spectrometry (MS) metabolism studies quickly and accurately. Furthermore, it shows predicted biotransformation and metabolite information graphically, and shows extensive supporting data from the knowledge base.


Provides a systems biology software tool for multiscale physiological modeling and simulation. Mobi can import almost any kind of (biological) model, within the restrictions of ordinary differential equations, or set up from scratch. Examples include biochemical reaction networks, compartmental disease progression models, or physiologically based pharmacokinetic (PBPK) models. However, de novo development of a PBPK model, for example, is very cumbersome such that the preferred procedure is to import them from PK-Sim. Importantly, MoBi also allows for the combination of the described examples and thereby is a very powerful tool for modeling and simulation of multi-scale physiological systems covering molecular details on the one hand and whole-body architecture on the other hand. PK-Sim and MoBi are parts of The Computational Systems Biology Software Suite.


Provides a comprehensive software tool for whole-body physiologically based pharmacokinetic modeling. PK-Sim enables rapid access to all relevant anatomical and physiological parameters for humans and the most common laboratory animals (mouse, rat, minipig, dog, and monkey) that are contained in the integrated database. Moreover, access to different physiologically-based pharmacokinetic (PBPK) calculation methods to allow for fast and efficient model building and parameterization is provided. PK-Sim is designed for use by non-modeling experts and allows for minor structural model modifications. More importantly, PK-Sim is fully compatible with the expert modeling software tool MoBi, thereby allowing full access to all model details including the option for extensive model modifications and extensions. This way customized systems pharmacology models may be set up to deal with the challenges of modern drug research and development. PK-Sim and MoBi are parts of The Computational Systems Biology Software Suite.


Predicts binding affinity, inhibition constants or other measures of interaction with biological targets, directly from chemical structure. chemTarget uses Cyprotex’s pattern recognition software to build models from existing data sets (provided by the customer or from the literature). It analyses approximately 10000 descriptors using linear, random forest, neural network and nearest neighbour methods. Furthermore, it provides clinically relevant binding/inhibition/activation when used in combination with the pharmacokinetic predictor, chemPK and provides an early-stage filter for directing chemistry and prioritising screening.


Predicts key toxicity parameters (Ames mutagenicity, rat acute dose LD50 following iv or po administration) and aqueous solubility directly from structure. chemTox principal features allows: no in vitro physicochemical or toxicity data requirements, to save money and time by allowing toxicity to be assessed virtually (no synthesis required), to provide early stage filter for directing chemistry and prioritising screening. chemTox is implemented as a node for the KNIME analytics platform.


Predicts key human oral and intravenous pharmacokinetic parameters directly from structure. chemPK principal features allows: no in vitro absorption, distribution, metabolism and excretion (ADME) or physicochemical data requirements, to save money and time by allowing pharmacokinetics to be characterised virtually (no synthesis required), to provide early stage filter for directing chemistry and prioritising screening, superior approach which uses PBPK model optimised from human clinical (in vivo) data. chemPK utilises a KNIME workflow-based approach.


Predicts ADME data and builds drug-like library using in silico method. PreADMET is a web-based application and can be accessed by browsers such as Netscape or Internet Explorer. It consists of four main parts as following: Molecular Descriptor Calculation, Drug-likeness Prediction, ADME Prediction, and Toxicity prediction. PreADMET supports friendly user interface and MS-Windows optimized software architecture, which easily provide useful numerical information related to absorption - distribution - metabolism - excretion (ADME) and toxicity (ADMET) of chemical compound, from the early step of drug discovery.

ADMET Descriptors

Allows to get an early assessment of query compounds. ADMET Descriptors calculates the predicted absorption, distribution, metabolism, excretion and toxicity (ADMET) properties for collections of molecules such as synthesis candidates, vendor libraries, and screening collections. Use the calculated results to eliminate compounds with unfavorable ADMET characteristics and evaluate proposed structural refinements, designed to improve ADMET properties prior to synthesis. ADMET descriptors include: Human intestinal absorption, aqueous solubility, blood brain barrier penetration, plasma protein binding, CYP2D6 binding, hepatotoxicity, filter sets of small molecules for undesirable function groups based on published SMARTS rules. ADMET Descriptors is part of the BIOVIA Discovery Studio software.


Filters out molecules with unwanted properties. Filter-it is built on top of OpenBabel open source C++ API for rapid calculation of molecular properties. The program is packaged with a number of pre-programmed molecular properties. These properties include, amongst others: Physicochemical parameters, such as logP, topological polar surface area criteria, number of hydrogen bond acceptors and donors, and Lipinski’s rule-of-five; Graph-based properties, including ring-based parameters and rotatable bond criteria; Selection criteria by means of smarts patterns; Similarity criteria; Three-dimensional distances between user-definable fragments. Filter-it is available as a free command line-driven program.


Identifies promising drug candidates through a lead selection and the prioritisation of drug candidates. MolScore-Drugs is based on a variety of reliable models. Structure-activity relationships allow the estimation of useful drug-like chemical space. Structure-property relationships which are derived from the ADME/Tox-database are applied to predict absorption, distribution, metabolism, excretion and toxicity (ADMET) properties and to identify potential risks in order to reduce clinical failures. The results of MolScore-Drugs can easily be integrated into customer’s database. This will allow virtual screening, ranking and selecting compounds from external suppliers before they have to be purchased. MolScore-Drugs can also be used to detect future blockbusters. All models which have been integrated into the expert system have been successfully validated with independent data sets.


Accelerates drug discovery and development. IMPACT-F calculates oral bioavailability of future drugs in humans. IMPACT-F is used by pharmaceutical companies in different therapeutic areas such as diabetes, inflammation, antivirals, autoimmune diseases and cancer for selection and prioritisation of drug candidates, to optimise prodrugs and to evaluate oral bioavailability before clinical trials in humans. IMPACT-F is easy to use, it requires no chemical synthesis or animal experiments, it is much more reliable than animal trials and results are almost immediately available.


Provides a high-speed virtual (in silico) screening system intended for simultaneous evaluation of the absorption, distribution, metabolism, excretion and toxicity (ADMET) properties of compounds. ADMEWORKS Predictor complements existing in silico technologies for evaluating pharmacological properties. Simultaneous evaluation of the pharmacological as well as the ADMET properties of compounds is useful in the discovery phase to produce balanced quality hits, and also in the lead optimization phase to lessen the occurrence of faulty leads. ADMEWORKS Predictor also makes it possible to prioritize while simultaneously evaluating these properties. By freely ranking the properties according to their relative importance, ADMEWORKS Predictor allows for a more focused screening of compounds, stressing only the properties that are of highest interest.

ADMEWORKS ModelBuilder

Builds quantitative structure-activity relationship/quantitative structure-property relationships (QSAR/QSPR) models that can later be used for predicting various chemical and biological properties of compounds. ADMEWORKS ModelBuilder provides two classes of models (Qualitative and Quantitative) that can be built using various algorithms. The models are based on values of physicochemical, topological, geometrical, and electronic properties derived from the molecular structure. Models created in ADMEWORKS ModelBuilder are easily imported into ADMEWORKS Predictor (optional product) which is a high-speed virtual (In Silico) screening system intended for simultaneous evaluation of the ADMET properties of compounds. Simultaneous evaluation of the pharmacological as well as the ADMET properties of compounds is useful in the discovery phase to produce balanced quality hits, and also in the lead optimization phase to lessen the occurrence of faulty leads.

MedChem Studio

Provides an intuitive medicinal chemistry platform for computational and medicinal chemists supporting lead identification and optimization, in silico ligand based design, and clustering/classifying of compound libraries. MedChem Studio is fully integrated with MedChem Designer and ADMET Predictor. It provides a computer-aided drug design (CADD) capability to see how changes in molecular structures affect not just one or a handful of properties, but over 140 properties from the industry’s top-ranked quantitative structure-activity relationship (QSAR) property prediction program, providing a powerful in silico molecule design capability.


Creates 128 molecular descriptors from 3D Molecular Interaction Fields (MIFs) produced by the GRID software, which are particularly relevant to ADME (absorption, distribution, metabolism and excretion) prediction and are also simple to interpret. VolSurf+ comes with a number of models which have been developed using both public and pharmaceutical data, including passive intestinal absorption, blood-brain barrier permeation, solubility, protein binding, volume of distribution, and metabolic stability.