Aiming to make the process faster and smarter, NVIDIA on Wednesday released the NIM Agent Blueprint for AI-based generative virtual sensing.
This innovative approach will reduce the time and cost of developing life-saving medicines, enabling faster access to critical treatments for patients.
This NIM agent model introduces a paradigm shift in the drug discovery process, particularly in the crucial “hit-to-lead” transition, by moving from traditional fixed database screening to generative AI-driven molecule design and pre-optimization, enabling researchers to design better molecules faster.
What is a NIM? What is a NIM Agent Model?
NVIDIA NIM microservices are cloud-native, modular components that accelerate the deployment and execution of AI models. These microservices enable researchers to integrate and scale advanced AI models within their workflows, enabling faster and more efficient processing of complex data.
The NIM Agent Blueprint, a comprehensive guide, shows how these microservices can optimize key stages of drug discovery, such as hit identification and lead optimization.
How are they used?
Drug discovery is a complex process with three critical stages: target identification, drug-hit identification, and lead drug optimization. Target identification involves choosing the right biology to modify to treat the disease; drug-hit identification involves identifying potential molecules that will bind to that target; and lead drug optimization involves improving the design of those molecules to make them safer and more effective.
This NVIDIA NIM agent model, called Generative Virtual Screening for Accelerated Drug Discovery, identifies and improves virtual hits in a smarter and more efficient way.
At its core are three essential AI models, now including the newly integrated AlphaFold2 as part of NVIDIA NIM microservices.
- AlphaFold2, recognized for its groundbreaking impact on protein structure prediction, is now available as NVIDIA NIM.
- MolMIM is a new model developed by NVIDIA that generates molecules while optimizing multiple properties, such as high solubility and low toxicity.
- DiffDock is an advanced tool for rapidly modeling the binding of small molecules to their protein targets.
These models work together to improve the process of converting one product to another, making it more efficient and faster.
Each of these AI models is packaged within NVIDIA NIM Microservices — portable containers designed to accelerate performance, shorten time to market, and simplify the deployment of generative AI models anywhere.
The NIM agent model integrates these microservices into a generative, scalable, and flexible AI workflow that can help transform drug discovery.
Leading biotechnology and computational drug discovery software vendors currently using NIM microservices, such as Benchling, Dotmatics, Terray, TetraScience, and Cadence Molecular Sciences (OpenEye), are using NIM Agent Blueprints in their computational drug discovery platforms.
These integrations aim to make the drug discovery process faster and smarter, leading to the identification of more viable drug candidates in less time and at a lower cost.
Global professional services firm Accenture is poised to tailor the NIM Agent model to the specific needs of drug development programs, optimizing the molecule generation step with input from pharmaceutical partners to inform the MolMIM NIM.
Additionally, the NIM microservices that comprise the NIM Agent Blueprint will soon be available on AWS HealthOmics, a purpose-built service that helps customers orchestrate biological analyses. This includes streamlining the integration of AI into existing drug discovery workflows.
Revolutionizing drug development with AI
There is a lot at stake in drug discovery.
The development of a new drug typically costs around $2.6 billion. and can take between 10 and 15 years, with a success rate of less than 10%.
By making molecular design smarter with NVIDIA AI-powered NIM Agent Blueprint, pharmaceutical companies can reduce these costs and shorten development timelines. The $1.5 trillion global pharmaceutical market.
This NIM agent model represents a significant shift from traditional drug discovery methods and offers a generative AI approach that pre-optimizes molecules to achieve desired therapeutic properties.
For example, MolMIM, the generative molecule model within this NIM agent model, uses advanced features to direct the generation of molecules with optimized pharmacokinetic properties (such as absorption rate, protein binding, half-life, and other properties), a notable advance over previous methods.
This smarter approach to small molecule design improves the potential for successful lead product optimization, accelerating the overall drug discovery process.
This leap in technology could lead to faster and more targeted treatments, addressing growing challenges in healthcare, from rising costs to an aging population.
NVIDIA’s commitment to supporting researchers with the latest advances in accelerated computing underscores its role in solving the most complex problems in drug discovery.
Visit build.nvidia.com to download the NIM Agent blueprint for generative AI-based virtual screening and take the first step toward faster and more efficient drug development.
See warning regarding software product information.
