BIOVIA Generative Therapeutics Design

BIOVIA Generative Therapeutics Design (GTD) is an agile, cloud-based solution developed by Dassault Systèmes that leverages artificial intelligence and machine learning to transform small molecule drug discovery. By combining advanced data science, cheminformatics, and structure-based modeling, GTD enables research teams to explore vast chemical spaces and automate the virtual creation, testing, and selection of novel drug candidates with greater speed and precision.

GTD is designed for pharmaceutical and life sciences organizations seeking to accelerate lead optimization, reduce research costs, and increase the likelihood of success in preclinical and clinical studies. Its secure, scalable cloud deployment makes it an attractive option for drug discovery teams of all sizes looking to modernize their workflows with AI-driven approaches.

Key Benefits of AI-Driven Drug Design

• Accelerated compound ideation: AI enables researchers to rapidly explore a large and diverse chemical space, identifying the most promising drug candidates for testing and reducing the time spent on physical experiments.
• Intellectual property consideration: Machine learning models can incorporate existing intellectual property into the design process, helping ensure new compounds do not infringe on existing patents and streamlining the path to market.
• Agile, secure, and cost-effective deployment: Operating in a secure cloud-based environment provides scalability, flexibility, and a low total cost of ownership while maintaining data security.
• Significant cost savings: By optimizing the drug discovery process and increasing candidate success rates, GTD helps organizations save millions in research expenditure and gain a competitive edge by bringing novel therapies to market faster.
• Shortened lead optimization phase: AI-driven models help discovery teams identify the best candidates more quickly, accelerating the overall drug development timeline.
• Increased success rate in preclinical and clinical studies: Teams can tailor lead compounds against complex target product profiles (TPPs), predicting how candidates will perform and addressing potential concerns during the design phase to reduce the risk of costly late-stage failures.

Virtual and Real (V+R) Active Learning Workflow

• Virtual cycles explore chemical space by learning from real experimental data. The system virtually screens and optimizes candidate compounds using a combination of machine learning models and structure-based modeling and simulation methods. Multi-parameter optimization algorithms balance competing objectives including pharmacokinetics, pharmacodynamics, ADME (absorption, distribution, metabolism, and excretion), bioavailability, and drug metabolism.
• Real cycles incorporate experimental data collected from the synthesis and laboratory testing of the most promising virtual compounds. This data is fed back into the system to improve predictive models and refine the exploration of chemical space.
• Iterative V+R active learning cycles continue until compounds meeting the desired target product profile (TPP) are identified, creating a continuous innovation loop between virtual modeling and real-world experimentation.

Platform Capabilities

• Integration of machine learning and cheminformatics for automated compound generation and evaluation
• Structure-based modeling and simulation to support virtual screening
• Multi-parameter optimization to simultaneously balance complex and competing drug design objectives
• Support for active learning cycles that iteratively refine models as new experimental data becomes available
• Cloud-based architecture ensuring security, scalability, and accessibility for distributed research teams

BIOVIA Generative Therapeutics Design is part of the broader BIOVIA portfolio of solutions for research, development, quality, and manufacturing. It integrates within the Dassault Systèmes ecosystem alongside tools such as BIOVIA Discovery Studio and BIOVIA Pipeline Pilot, supporting seamless collaboration and sustainable innovation across the life sciences research and development lifecycle.