1 - 50 of 53 results


Streamlines the steps of performing a virtual screening and analyzes results. Raccoon is a graphical user interface (GUI) that includes (i) automated server connection manager and installation of docking services, (ii) ligand library for upload and management of large ligand collections, (iii) receptor management from multiple targets and flexible residues, (iv) graphical management of jobs on computational resources, (v) automated retrieval and preprocessing of results to extract features of interest, and many others.


Provides an online, interactive environment for the virtual screening of large compound databases using pharmacophores, molecular shape and energy minimization. Users can import, create and edit virtual screening queries in an interactive browser-based interface. Queries are specified in terms of a pharmacophore, a spatial arrangement of the essential features of an interaction, and molecular shape. Search results can be further ranked and filtered using energy minimization. In addition to a number of pre-built databases of popular compound libraries, users may submit their own compound libraries for screening. Pharmit uses state-of-the-art sub-linear algorithms to provide interactive screening of millions of compounds. Queries typically take a few seconds to a few minutes depending on their complexity. This allows users to iteratively refine their search during a single session. The easy access to large chemical datasets provided by Pharmit simplifies and accelerates structure-based drug design.

DOVIS / DOcking-based VIrtual Screening

Automates docking jobs with AutoDock. DOVIS is a utility software and a Linux cluster-based application that can reliably screen millions of compounds against a receptor and automatically save the top percentage of high-scoring hits. It runs in parallel on hundreds of central processing units (CPUs) and docks large numbers (millions) of ligands to a target receptor. It also automatically partitions input ligands, prepares parameter files for AutoDock, launches parallel AutoDock runs, parses results, and saves a set of top-ranking docked ligands.

Neural Network scoring

Aids the computational identification of small-molecule ligands. NNscore is based on a neural-network scoring function and provides a single estimate of the pKd. It attempts to simulate, albeit inadequately, the microscopic organization of the brain. The tool can be used to successfully characterize the binding affinities of protein-ligand complexes. It appears that its major strength is largely orthogonal to other kinds of functions based on force fields, linear regression, and statistical analyses.


A web tool for rapid ligand-based virtual screening (LBVS) of small to ultralarge libraries of small molecules. SwissSimilarity offers the possibility to perform LBVS on more than 30 chemical databases which list drugs, bioactive and commercial molecules, as well as 205 million of virtual compounds readily synthesizable from commercially available synthetic reagents. Predictions can be carried out on-the-fly using six different screening approaches, including 2D molecular fingerprints as well as superpositional and fast nonsuperpositional 3D similarity methodologies. User interface and backend have been designed for simplicity and ease of use, to provide proficient virtual screening capabilities to specialists and nonexperts in the field.


Allows covalent docking and virtual screening in molecular operating environment (MOE). DOCKTITE combines the knowledge-based scoring function drug score extended (DSX) and the empirical scoring functions implemented in MOE. The software can differentiate binders from nonbinders and rank active compounds regarding their experimentally determined binding affinity values in a congeneric series of ligands. It is a useful workflow for large-scale virtual screening purposes and can aid at all stages of a modern drug development process.


Allows to evaluate protein-ligand binding. MedusaScore is a scoring function that describes the protein-ligand binding using physical interaction model. The function includes an explicit hydrogen-bonding model and EEF1 pairwise implicit solvent model, which allows accurate modeling of the hydrogen-bonding and desolvation effect without large-scale molecular dynamics (MD) simulations. Since the MedusaScore does not rely on parameter training using protein-ligand binding data, it is transferable to targets and small molecules beyond the tested datasets.

MLViS / Machine Learning-based Virtual screening tool

Classifies molecules as drug-like and nondrug-like molecules. MLViS is based on various machine learning methods, including discriminant, tree-based, kernel-based, ensemble and other algorithms. Besides classification, this application has also the ability to create heat map and dendrogram for visual inspection of the molecules through hierarchical cluster analysis. Moreover, users can connect the PubChem database to download molecular information and to create two-dimensional structures of compounds.

PASS Targets

Predicts interactions between protein targets and drug-like compounds. PASS Targets is able to predict interactions of drug-like compounds with 2507 protein targets from different organisms based on analysis of structure-activity relationships for 589107 different chemical compounds. This tool was developped using data extracted from the 19th version of the ChEMBL database as a training set and a Bayesian-like method realized in PASS software. PASS (Prediction of Activity Spectra for Substances) provides simultaneous predictions of many types of biological activity based on the structure of organic compounds. It estimates the probable biological activity profiles for compounds under study based on their structural formulae presented in MOLfile or SDfile format.


Predicts anticancer potency of an unknown molecule and its GI50 across different cancer cell lines. CancerIN is a web server that consists of three modules for designing, library screening and chemical analogs screening. This web application provides a user-friendly interface with options to draw a chemical compound using Marvin applet. A standalone version of CancerIN is also available and allows users to scan a vast library of molecules for the screening of potential anticancer molecules.


Identifies inhibitors of a known modulator of G protein-coupled receptor signaling. Screenlamp facilitates: (1) the comparison of molecules in a database for similarity with a known bioactive molecule, (2) the definition of the spatial relationships between chemical groups in a small molecule allowing activation or inhibition of a biological receptor, and (3) the docking of small molecules into a receptor structure to identify the subset of molecules that most favorably interact with the receptor.

LigBEnD / Ligand-Biased Ensemble Docking

Provides a hybrid ligand/receptor structure-based docking. LigBEnD was developed by incorporating the atomic property field (APF) method into structure-based ensemble docking. This method assumes the following: (1) compounds that are similar to co-crystallized ligands are likely to bind in a similar pose, (2) compounds that are chemically dissimilar to co-crystallized ligands might share similarity in the properties of atoms occupying the same 3D space and (3) compounds belonging to the same chemical class should have consistent, similar poses.

mRAISE / m RApid Index-based Screening Engine

Provides biologically relevant molecular alignments of the ligands. mRAISE is a tool for ligand-based virtual screening based on the RApid Index-based Screening Engine (RAISE) technology. The triangle-descriptor abstraction of small molecules allows fast non-sequential screening of millions of compounds. Calculated alignments are scored using a Gaussian-type scoring function which scores the general shape overlap as well as the compatibility of physicochemical features of aligned molecules.


Enables any user to estimate polypharmacology profiles and side effects of compounds based on the molecular similarity concept. ElectroShape is a method that compares the distance and charge distributions of a molecule from 4 different surrounding points, which allows its 3D similarity to other molecules to be assessed in a very fast and efficient way. In addition, the calculated molecular descriptors can be stored for further use, which speeds up subsequent searches. ElectroShape provides a significant addition to the family of ultra-fast ligand-based virtual screening methods, and its higher-dimensional shape recognition approach has great potential for extension and generalisation.


Corrects genome-wide siRNA screens for seed mediated off-target effect. ScsR offers suitable functions to identify the effective seeds/miRNAs and to visualize their effect. In example, it presents method that takes as input a dataframe containing the results of an siRNA screen. Then it adds a set of column that are useful for sorting to the dataframe. This screen must contain the siRNA sequences in a dedicated column (the sequences have to be provided in the guide/antisense orientation).


Generates computational models from user-defined small molecule datasets based on structural features identified in hit and non-hit molecules in different screens. Each new model is applied to all datasets in the database to classify compound specificity. MolClass thus defines a likelihood value for each compound entry and creates an activity fingerprint across diverse sets of screens. MolClass uses a variety of machine-learning methods to find molecular patterns and can therefore also assign a priori predictions of bioactivities for previously untested molecules.


Creates in silico simulated high throughput screening data sets for use in testing and selecting appropriate statistical techniques for quality determination and hit identification. NoiseMaker can be useful for broader comparisons of available hit identification methods. This simulation software offers two main features: (i) the ability to generate a random set of ‘true hits’ that conform to expected characteristics and (ii) the ability to apply user-specified noise to a list of true hits to model realistically messy screening results.


A package which provides a fast and easy way to generate molecular models derived from known inhibitors without the need for information about the receptor. LigMerge algorithm creates novel compounds with structural features similar to those of known ligands. Once generated, LigMerge-derived compounds can be docked into receptor structures to identify likely inhibitors for subsequent synthesis and experimental validation. This tool is useful for those designing custom virtual screening, small-molecule databases when many ligands, potent or otherwise, have been identified experimentally or theoretically via virtual screening.

SABRE / Shape-Approach-Based Routines Enhanced

Consists of a rational ligand/structure shape-based virtual screening approach. SABRE is a program that combines ligand shape-based similarity SABRE and the 3D shape of the receptor binding site. The program can be useful for the identification of active compounds that are similar to reference molecules and the prediction of activity against other targets. Its performance were assessed using he Database of Useful Decoys (DUD) and the filtered version (WOMBAT) of 10 DUD targets.

USRCAT / Ultrafast Shape Recognition with CREDO Atom Types

Provides a solution to the lack of atom type information in the ultrafast shape recognition (USR) algorithm. Researchers, particularly those with only limited resources, who wish to use ligand-based virtual screening in order to discover new hits, will benefit the most. Online chemical databases that offer a shape-based similarity method might also find advantage in using USRCAT due to its accuracy and performance. The source code is freely available and can easily be modified to fit specific needs.


An innovative software tool for ligand-based drug design. ViCi uses a combination of mathematical descriptors of molecular size, shape and topology to describe small molecule structures. Following input of a template molecule, typically that of a known ligand in its bound conformation in a particular protein, the software tool will rapidly screen a database (currently 8 million compounds) and extract those predicted to have similar shape and electrostatic compositions and therefore to be possible ligands for the same protein. Results are typically obtained in a matter of hours and are returned to the user ranked by probability of binding.