Verisimlife

Introduction

AI drug design uses advanced computational approaches to allow researchers to design proprietary chemical entities, compounds, and drug candidates more quickly and economically than other drug design and computational chemistry methods. While conventional computational chemistry methodologies use only the information regarding a biological target and its known active binders, recent advances in AI drug discovery are leveraging quantum mechanical calculations as well as machine learning (ML), deep learning (DL), and other related AI-based technologies to explore the broadest chemical spaces possible – utilizing both state of the art computational chemistry methods and vast data troves from available scientific literature and databases to comprehensively consider biology. Standard de novo drug design methods can be limited by existing knowledge around receptor–ligand interactions. But AI drug discovery uses breakthrough deep learning methods that combine advancements in computational chemistry and artificial neural networks with reinforcement learning in order to discover novel drug candidates that are virtually "template-free."

Situation

By leveraging computational modeling, virtual screening and AI algorithms, AI drug discovery is pushing the boundaries of traditional drug development approaches, potentially revolutionizing the early stages of the drug design and development process.

Two of the major pain points currently facing AI drug discovery are:

• Synthetic Feasibility– Conventional DNDD methods partially consider the feasibility of generated molecules by considering a limited number of retrosynthetic organic reactions. However, in molecular structures created by an unconstrained generative AI engine, there’s the potential to create physically improbable drugs, or drugs that are so complex they might be considered unnatural or impossible to successfully reproduce.

• Lack of Biological Validation– Computational chemical synthesis may identify structurally promising molecules based on target engagement. But their translatability to biology may only be considered referentially based on similar known molecules. The resulting molecular “hits”—potentially in the thousands—must be experimentally validated at great expense and time.

• Regulatory & Community Acceptance – Many of the DL methods used in AI drug discovery are considered to be in the early stages of development, necessitating additional transparency and documentation around data sets and code, the sharing of training datasets, and the eventual development of regulatory standards for model validation and model-sharing platforms.

The VeriSIM Life advantage

VeriSIM Life (VSL)'s AtlasGEN™ Novel Drug Designer, a part of the BIOiSIM® platform, is making it easier to address both the synthetic accessibility of AI drug discovery compounds and any related black box transparency concerns head on.

Using its groundbreaking Translational Index™️ technology, AtlasGEN™ constrains everything by its translatability, rating compound hits in order to deliver truly feasible de novo molecules. The Translational Index™️ also reveals the underlying computational calculations, aiding regulatory and community acceptance, reducing AI-based skepticism, and ultimately establishing well-balanced profiles for candidate drugs. In this way, Translational Index™ helps avoid the pursuit of dead end candidates, advancing only the most promising drug candidates through R&D to investigational new drug (IND) application.

AtlasGEN™️ Novel Drug Designer and Translational Index™️ technology

Which advance only the most promising novel drug candidates through R&D to investigational new drug (IND) application, offers actionable insights of unprecedented value to the drug development industry.

AltlasGEN™ Novel Drug Designer synergistically marries powerful novel drug design chemistry with biological validation to discover clinically successful novel therapies. It efficiently identifies new molecules based on favorable chemical properties and simultaneously evaluates them for clinical safety and effectiveness based on biology using VeriSIM Life’s groundbreaking Translational Index™ technology.

AtlasGEN™️ Novel Drug Designer benefits

The BIOiSIM® platform features a robust data lake foundation, integrating:

Vast chemical search space: The ability to generate target engaging compound hits depends largely on the size of the molecular search library. The AtlasGEN search space is supported by more than 1012 compounds.

Super fast discovery: AtlasGEN accurately predicts protein-lygand binding affinity by combining geometric conformer analysis with machine learning based on experimental data X% more efficiently than molecular docking-based approaches.

Pre-validated hits: Iterative ranking of target engaging hits by their Translational Index values reduces the time and cost associated with other computational hit discovery approaches, while compressing the hit-to-lead refinement and optimization process by pre-validating hits for translatability. This unique integration dramatically reduces the number of compounds to evaluate in subsequent experimental research.

Translation-informed De Novo Drug Discovery

Challenge

VeriSIM Life’s partner needed a novel compound ready for synthesis and validation studies in weeks, but conventional drug discovery typically takes from between 5 to 36 months.

Solution

Using its Translational Index™️ technology, the BIOiSIM® platform enabled compound mapping and selection in order to identify the highest potential translatable compounds.

Methods

• AtlasGEN™ Novel Drug Designer enabled target screening, structure validation, drug-like properties, viability and synthesizability.
• BIOiSIM® generated novel Tyrosine Kinase inhibitor compounds based on 5 big-brand marketed structures.
• Synthesized compounds were optimized in discovery based on superior bioavailability at lower dosing.

Outcome

In only one month of discovery and pre-validation, VeriSIM Life generated three novel, high-potential candidates, representing a 50% reduction in overall development time. Leveraging AtlasGEN™ Novel Drug Designer also resulted in more streamlined translational research.

"The BIOiSIM platform gave us a novel compound ready for synthesis and validation studies in just weeks versus the months or even years typical of conventional methods." Biotech client

Additional VeriSIM Life Case Studies & Content

Evolve your pipeline

Bring better drugs to market, faster, with AtlasGEN Novel Drug Designer

Now you can accelerate the discovery of new therapies based on existing compounds with VeriSIM Life’s AtlasGEN Drug Designer computational platform – purpose-built to decode chemistry and biology at scale. With the industry’s most generalistic AI platform, your innovation is no longer limited to experimental constraints.