Discovery Toolkit

powerful ways of data generation and characterization
ChemAxon’s Discovery Toolkit is a software suite, which implements expert knowledge, and provides robust, class-leading performance to computational and medicinal chemists, aiding the in silico drug discovery process. It covers aspects of design, assessment and analysis of custom virtual screening libraries, and will thus leverage well-founded decisions in lead identification and optimization. Download in JChem

Discovery Workflow

Compound Enumeration
Reactor allows the user to perform various multi-step virtual syntheses, using generic reaction equations and ChemAxon’s Chemical Terms scripting language. It serves as a tool to quickly explore chemical space, starting from fragment-based or small chemical compound libraries. Modes of operation include high-throughput combinatorial library generation, diverse library and scaffold generation, and metabolite enumeration. Reactor is ChemAxon’s virtual reaction enumeration engine. It is a powerful tool for mastering in silico combinatorial chemistry and virtual compound library design in drug discovery workflows.
Reaction rules Reactor ships with more than 200 atom-mapped reaction schemes for out-of-the-box virtual synthesis. Customisable reaction rules provide chemical intelligence towards creating synthetically feasible compounds. Learn more about Reactor »

Calculator Plugins

Filtering by PhysChem Properties
Calculator Plugins are modules of ChemAxon’s Java-based Marvin and JChem cheminformatic platforms. They include a wide range of structure-based prediction tools to explore the physicochemical properties of chemical compounds (e.g. elemental analysis, pKa, logP, polarizability, conformers, etc.).
File support Through ChemAxon’s Chemical Terms scripting language, these plugins are organically integrated into lead discovery processes, providing easily accessible search and filter criteria for your databases. Learn more about Calculator Plugins »


Library Screening
Molecule and structure 3D manipulations ChemAxon’s Screen software suite provides tools for pharmacophore analysis and ligand-based high throughput virtual screening. Screen can be used during drug discovery and lead optimization to identify the most relevant molecules for docking studies and wet screening.
Screen implements a variety of different fingerprints (ChemAxon’s chemical fingerprint, Pharmacophore fingerprint, ECFP, FCFP), is aware of several different dissimilarity metrics, and can perform metrics optimization for chemical (2D) similarity searches. In addition to topology based screening, the Screen Suite offers tools for shape (3D) similarity searches of large molecular libraries. Learn more about Screen »


Library Analysis by Clustering
JKlustor is ChemAxon’s solution to explorative data mining in combinatorial chemistry and drug design processes, where a large number of chemical compounds need to be analyzed. It performs similarity- and structure-based clustering of compound libraries and focused sets and facilitates both hierarchical (e.g. Ward’s method) and non-hierarchical (e.g. K-means, Sphere exclusion, Jarvis-Patrick) approaches. JKlustor is a versatile tool, which can handle a variety of molecular fingerprints, common substructure measures and other chemical descriptor types.
Showing its versatility, Jklustor can handle a variety of molecular fingerprints, common substructure and other descriptor types.

JKlustor 7

Learn more about JKlustor »

Articles in the library

Small Molecules in Big Data: Proceed with Caution!

Sep 14, 2016 - Presentation
The Schürer research group at The University of Miami is one of three sites for the Big Data to Knowledge (BD2K) Data Coordination Integration Center (DCIC) of the Library of Integrated …


Sep 15, 2016 - Presentation
Chemicalize was created as a free, online demonstration and advertising application of ChemAxon’s naming and calculation technologies eight years ago. Currently this is one of the most …

Fast similarity searching – making the virtual real

May 24, 2016 - Presentation
Similarity searching is a key component of many chemoinformatic processes including compound collection design, compound clustering and lead hopping. We have command-line tools for bespok…

Still have questions?

Have a look on our support forum or drop us a line