background pattern

De Novo Design Workflow

Fully-integrated, cloud-based design system for ultra-large scale chemical space exploration and refinement

Expand your compound design strategies with unbiased chemical space exploration for hit-to-lead and lead opt

Schrödinger’s De Novo Design Workflow is a fully-integrated, cloud-based design system for ultra-large scale chemical space exploration and refinement. Starting from a hit molecule or lead series, the technology identifies synthetically tractable molecules that meet key project criteria by combining multiple compound enumeration strategies with an advanced filtering cascade (AutoDesigner) and rigorous potency scoring with free energy calculations (Active Learning FEP+).

Key Capabilities

Dramatically improve synthetic tractability of the identified molecules

Through built-in reaction-based enumeration combined with advanced filtering to rule out undesired and unrealistic chemistry

Efficiently identify potent lead compounds in favorable physicochemical property space

By leveraging accurate potency predictions combined with active learning

Fast-track ligand optimization and program success

By efficiently evaluating up to billions of project-relevant virtual molecules

Accelerated, seamless exploration of large chemical space

The De Novo Design Workflow offers a cloud-deployable solution with the flexibility to customize settings and property space for the unique needs of your program.

Target Property Space
1. Control the chemical space to be explored with project-specific input parameters

Define the starting molecule, the portion of the molecule to explore, the desired physicochemical property space, and additional project-specific filters within LiveDesign, a web-based enterprise molecular design and collaboration platform.

Expand into synthetically-tractible space of interest to medicinal chemists
2. Expand into synthetically-tractible space of interest to medicinal chemists

Automatically carry out successive rounds of compound generation and filtering within desired chemical space using cloud-native, multi-stage enumeration strategies combined with an advanced filtering cascade based on physical properties, amenability to FEP+, IP, and docking.

Score idea molecules with a highly accurate in silico binding affinity assay
3. Score idea molecules with a highly accurate in silico binding affinity assay

Leverage a well-validated, automated workflow which trains a machine learning model on project-specific FEP+ data to allow processing of up to millions of compounds with highly accurate FEP+ calculations efficiently.

Analyze and prioritize output molecules with a collaborative design platform
4. Analyze and prioritize output molecules with a collaborative design platform

Review the top scoring compounds and use the FEP+-trained machine learning model in LiveDesign — allowing evaluation, interactive optimization, and prioritization by the project team.

FeaturedHit to development candidate in 10-months: Rapid discovery of a novel, potent MALT1 inhibitor

Hit to development candidate in 10-months: Rapid discovery of a novel, potent MALT1 inhibitor

In a recent MALT1 drug discovery program led by Schrödinger’s Therapeutics Group, the De Novo Design Workflow amplified the team’s design efforts.

view case study

Training & Resources

Online certification courses

Level up your skill set with hands-on, online molecular modeling courses. These self-paced courses cover a range of scientific topics and include access to Schrödinger software and support.

Tutorials

Learn how to deploy the technology and best practices of Schrödinger software for your project success. Find training resources, tutorials, quick start guides, videos, and more.