Molsoft is a leading provider of tools, databases and consulting services in the area of structure prediction, structural proteomics, bioinformatics, cheminformatics, molecular visualization and animation, and rational drug design. Molsoft offers complete solutions customized for a biotechnology or pharmaceutical company in the areas of computational biology and chemistry. Molsoft is committed to continuous innovation, scientific excellence, the development of the cutting edge technologies and original ideas.
Molsoft company was founded in 1994 by Ruben Abagyan as Biosoft and was renamed in 1995 to Molsoft.

The Molsoft molecular modeling technology is based on the Internal Coordinate Mechanics (ICM) approach which gives a general modeling and structure prediction framework for many tasks of structural biology and rational drug design. The ICM project was initiated by the founder in 1985, and is being continuously developed ever since.
ICM PRO
.

ICM-Pro is MolSoft’s primary desktop modeling software offering the most of the core functionalities like: ICM Pocket Finder, ICM 3D Interactive Editor, 2D ligand-receptor interaction diagrams, Small Molecule Docking, Protein-Protein/Peptide/RNA Docking, Induced Fit Docking, PROTAC Modeling, Molecular Dynamics, Predict Effect of Mutation, Crystallographic Analysis Tool, Protein Structure Prediction and Analysis, Sequence Analysis & Alignments and many other functionalities. To know more click here
ICM Pro Homology
.

The ICM-Homology modeling algorithm is recognized as one of the most reliable tools for protein modeling. After positioning the aligned polypeptide chain onto the template structure predicting side-chain torsion angles through global energy optimization of non-identical residues. It uses internal coordinate representation and efficient Biased Probability Monte Carlo (BPMC) optimization for side-chain and loop modeling. To know more click here.
Molscreen

MolScreen offers a comprehensive collection of high-quality 2D fingerprint and 3D pharmacophore models designed to cover a wide range of pharmacology and toxicology targets. These models are ideal for lead discovery and counter-screening applications. They leverage MolSoft’s advanced 2D QSAR/Fingerprint technology and 3D Atomic Property Fields methods (Totrov, 2008). Currently, the library includes approximately 2,500 models targeting 1,200 distinct biomolecular targets. To know more click here.
RIDGE

RIDGE (Rapid Docking GPU Engine) is an exceptionally fast and accurate method for structure-based virtual ligand screening. RIDGE leverages MolSoft’s extensive expertise in GPU programming to deliver a fully GPU-powered docking engine. With RIDGE users can dock ~100 compounds/second on an RTX 4090 GPU and can screen 10 million compounds in under 30 hours on a single $4K desktop. RIDGE integrates seamlessly with existing ICM docking projects, requiring no additional setup. To know more click here
ICM Chemist-Pro

ICM Chemist Pro is a standalone cheminformatics products containing a wide set of 3D chemical tools, chemical superposition, 3D interactive ligand-receptor editing wherein users can interactively edit a chemical inside a receptor binding pocket, modify atoms and groups and see the effect of the changes on ligand binding energy and score. ICM Chemist pro also includes various SAR capabilities like Matched Pair analysis, SALI analysis, Free Wilson Regression, and QSAR. To know more click here
ICM Pro – VLS (VIRTUAL LIGAND SCREENING)

ICM Virtual Ligand Screening (VLS) allows you to undertake high throughput structure (Docking based) and Ligand (Pharmacophore) based virtual screening on a local server or cloud. Some commonly used features include: Ligand Docking – Batch, Covalent Docking, Structure-based VLS, Ligand-based VLS (APF), Fragment-based VLS, Dock on the fly Markush generated libraries, All ICM Chemist Pro Features including SAR analysis and ICM 3D ligand editor are also included. To know more click here.
RIDE – Rapid Isostere Discovery Engine

RIDE (Rapid Isostere Discovery Engine) is a high-speed 3D molecular similarity search method based on Atomic Property Fields, developed by MolSoft. It efficiently scans databases of compound conformers to identify molecules isosteric to the query—those with similar 3D structures and atomic property distributions. CPU-RIDE is included in the ICM-Pro + VLS package. The GPU version can search up to 1.5 million conformers/sec/GPU. To know more click here.
GINGER

Conformer generation is a critical step in molecular modeling and computer-aided drug discovery workflows, including 3D ligand-based virtual screening and fast GPU docking. GINGER (Graph Internal-coordinate Neural-network conformer Generator with Energy Refinement) is MolSoft’s state-of-the-art software, designed for ultra-fast, high-quality conformer library generation on GPUs. GINGER explores the conformational space of molecules, providing diverse, low-energy conformers. To know more click here.
GigaScreen

The GigaScreen method leverages machine learning and deep learning to address the computational challenges of screening massive chemical libraries. A key advantage of this protocol is its ability to screen giga-sized libraries on a single machine, eliminating the need for costly computational resources or additional software. For a database of two billion compounds with five iterations, the full workflow can be completed in approximately 3–4 days. To know more click here
ICM – Internal Co-ordinate Mechanics
MolSoft’s ICM software package is based on the internal coordinates (IC) representation of molecular objects that naturally reflects the covalent bond geometry of molecules (Abagyan et al., 1994). Unlike simple Cartesian coordinates, IC variables consist of covalent bond lengths and angles, torsion angles and six positional coordinates of a molecular object. Because of chemical bond rigidity, most molecular objects can be accurately represented by free torsion variables while keeping covalent bond coordinates fixed. This dramatically reduces the number of free variables in the system without sacrificing accuracy, while improving convergence time for conformational optimizations at least 1000-fold.
Biased Probability Monte Carlo
The core technology used in most of Molsoft’s structure prediction algorithms is global free energy optimization in a subset of internal coordinates that describes inter or inter-molecular geometry. For structure prediction and large scale conformational sampling ICM employs a family of new global optimization techniques such as: Biased Probability Monte Carlo (Abagyan and Totrov, 1994), pseudo-Brownian docking algorithm (Abagyan et al., 1994) and local deformation loop movements.
Atomic Property Fields
The Atomic Property Field (APF) method developed by MolSoft ( Totrov 2008) is a 3D pharmacophoric potential implemented on a continuously distributed grid which can be used for ligand docking and scoring. APF can be generated from one or more high affinity scaffolds and seven properties are assigned from empiric physico-chemical components. These properties include: hydrogen bond donors, acceptors, Sp2 hybridization, lipophilicity, size, electropositive/negative and charge. A single ligand atom can contribute to multiple fields; multiple similar ligand atoms in a spatially consistent location result in a strong pharmacophore signal for their features in this location. APF has also been extended to multiple flexible ligand alignments using an iterative procedure. APF uses Monte Carlo minimization in the atomic property fields potentials in conjunction with standard force-field energies.
Optimal Docking Area
The ICM Optimal Docking Area method is a useful way of prediciting likely protein-protein interaction interfaces. If you do not have mutational data or other experimental data which indicates the likely protein-protein docking site this method will be useful. This procedure can save you time during the docking procedure by focusing your docking only on areas on the receptor and ligand most likely to interact.
ODA (Optimal Docking Areas) is a new method to predict protein-protein interaction sites on protein surfaces. It identifies optimal surface patches with the lowest docking desolvation energy values as calculated by atomic solvation parameters (ASP) derived from octanol/water transfer experiments and adjusted for protein-protein docking. The predictor has been benchmarked on 66 non-homologous unbound structures, and the identified interactions points (top 10 ODA hot-spots) are correctly located in 70% of the cases (80% if we disregard NMR structures). For a description of the method see Fernandez-Recio et al Proteins (2005) 127: 9632.
ICM- REBEL
Solvation is an important effect to consider when undertaking protein energy simulations. Many solvation methods are too computationally expensive to be used efficiently for protein simulation. MolSoft has developed a fast and accurate electrostatics method called REBEL (Rapid Exact-Boundary Electrostatics).
The method solves the Poisson equation for a molecule without a grid and with exact positions of electric charges and is a powerful implementation of the boundary element method with analytical molecular surface as dielectric boundary. The energy calculated by this method consists of the intramolecular Coulomb energy and the solvation energy which can be analyzed separately.
Newsroom
Help Centre
Release Notes
If you are interested in all the latest news and blogs from Molsoft, please click this link to go to the news page
If you are want to have a look at the documentation or raise a support ticket please visit the support page by clicking this link.
Stay updated with the latest release notes from Molsoft to understand the new features and improvements incorporated in the latest version. Click this link to know more.