Harness cutting edge models for 3D ligand-based and structure-based drug design

Struggling to generate accurate conformers for your macrocycles or structurally-novel compounds? With ForceGen, you can identify the most likely conformers for all your compounds, from small molecules to large macrocycles.

ForceGen’s patented, template-free method systematically applies 3D physical manipulations to explore the geometrical configurations of your ligands, generating ensembles of low-energy conformers. It can evaluate complex macrocycles in minutes, with the option of applying NMR constraints to increase search efficiency.

Access top-tier docking enrichment and accurate pose prediction with reliable automated docking procedures. Automate protein preparation and reduce inappropriate bias with Surflex-Dock’s easy-to-use workflows. Surflex-Dock supports your 3D structure-based design efforts, allowing you to model ligands from small molecules to large macrocycles.

With Surflex-Dock, ensembles of protein conformations take into account the variability in the binding pocket and relevant interactions, to give a more realistic picture of molecular docking.

Surflex-Dock enables highly accurate non-cognate ligand docking, so you can correctly predict poses for future potential ligands for your protein complex, making use of known prior bound ligand poses with eSim.

Looking for fast, reliable 3D ligand-based drug design and virtual screening? eSim considers molecular similarity from a protein’s perspective of a ligand, creating a surface representation of the molecule based on shape, electrostatic field, and hydrogen-bond preferences. This information can then be used to:

• Carry out large scale, high performance 3D virtual screening against known actives to find novel potent compounds
• Achieve significantly higher enrichment in your virtual screens than leading competitors
• Inform 3D design with industry-leading pose prediction

eSim is also available as part of our StarDrop drug discovery platform, so you can include 3D ligand-based drug design as part of your integrative, intuitive drug discovery workflow.

The BioPharmics QuanSA (Quantitative Surface-field Analysis) method lets you predict the affinity of your ligands using machine learning models based on physical principles. QuanSA’s 3D ligand-based models achieve equivalent accuracy to market-leading methods such as FEP+, while providing transferablility, even across scaffolds. With QuanSA, you can:

• Predict binding affinity without protein structural information
• Build accurate affinity models, even with only a small number of known actives
• Find novel active compounds with prediction confidence metrics