Verisimlife

Introduction

Evaluating potential toxic effects of a drug candidate is a critical step in the process of taking a new drug to market. Developing a safety profile is a way to evaluate and measure toxic effects of a drug when administered at various doses over specified time periods. This process involves monitoring overall response to the drug, including any adverse reactions in target organs. Specifically, scientists will use pharmacokinetics to study how the drug moves through the body via absorption, distribution, metabolism and excretion. The stronger a drug candidate’s safety profile, the lesser the chances of adverse reactions.

Situation

When pursuing the development of novel treatments, programs tend to prioritize focus on efficacy - the safety aspect of treatments is often left to be determined after significant efficacy and PK work determines a therapeutic window, and is limited to small clinical datasets. This often results in late-stage toxicity surprises, which can be disastrous for drug developers.

Late-stage toxicity and off-target effect findings can significantly hinder progress as they often require extensive investigation and potentially necessitate redesigning or abandoning a drug candidate. Delays in addressing these toxicity concerns can lead to substantial setbacks in the drug development process, resulting in increased costs and a longer time to market.

Simply put, R&D teams need earlier insights to prevent these types of surprises from occurring later down the line in the drug development process and causing critical hold-ups in the road to investigational new drug (IND) approval.

Identifying potential toxicity issues early on allows for necessary modifications and adjustments to the drug's chemistry, formulation or dosage regimen - without such insights, a drug may progress to advanced stages of development, such as Phase II or Phase III clinical trials, only to encounter unforeseen toxicities that can derail the entire process.

The VeriSIM Life advantage

Today, there’s good news for pharma researchers studying safety-toxicity profiles in drug candidates. Innovations in AI-driven technologies have allowed for the streamlining and de-risking of many aspects of early-stage drug development, including making these types of toxicity predictions.

VeriSIM Life (VSL)’s drug decision engine, BIOiSIM®, is a computational platform deploying advanced artificial intelligence and machine learning, a proprietary big data foundation, and state-of-the-art mechanistic models to predict and validate the translation of novel therapies.

BIOiSIM, and VeriSIM Life’s associated services, can be used to problem-solve some of the most significant challenges facing early-stage drug R&D – meeting development timelines faster, at lower costs, and with better results than traditional approaches.

The BIOiSIM AI-driven technology framework supports safety/toxicity predictions and addresses the pain point of needing earlier safety-toxicity insights by:

Combining multiple toxicity domain predictions and PK to understand toxicity in the context of drug dosing and its concentration in organs early to better inform in vivo experimentation and program decision-making.
Allows drug developers to assess dose-dependent toxicity early in the candidate development stage.
Accurate toxicity predictions are performed in the context of organ drug concentration and dosing in parallel with efficacy and overall PK assessment.
Guided by these insights, R&D teams can reduce experimentation to determine safety, in vivo.
Utilizing chemical and biological modeling along with AI and ML techniques to provide a Translational Index™ demonstrating confidence in drug compound scenarios to de-risk and guide go/no go decisions in preclinical development and testing. This includes toxicity predictions. Accuracy is achieved through the use of 4 domains of toxicity: Clinical tox - Preclinical tox - Hepatotoxicity - Cardiotoxicity.
Revealing, via predictive analysis, underlying candidate features at root of toxicity signals to inform drug design decisions.

BIOiSIM advances only the most promising drug candidates through R&D to IND application,

offering actionable insights of unprecedented value to the drug development industry. Combining thousands of validation data sets, multi-compartmental models, and its integrated AI/ML engine, BIOiSIM achieves superior physiological and biological relevance within three classes of therapeutics: small molecules, large molecules, and re-engineered viruses/gene therapy.

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-ligand 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.

Support for genomics data integration.

More than 3,000,000 real compounds including proprietary data from multiple partnerships.

Validation by real-world observed data.

Predicting PK/PD Profiles of NOX4 Compounds Using the BIOiSIM™ Translational AI/ML Platform

Challenge

The subject of this case study was a client project where the BIOiSIM platform was deployed to predict the PK profiles and PD properties for the group of compounds with a similar type of pharmacological activity - inhibition of the NADPH oxidase 4 (NOX4). NOX4 inhibition has been demonstrated to be a promising approach in the treatment of fibrotic disorders and other clinical indications with accelerated lipid peroxidation leading to similar fibrotic outcomes. VeriSIM Life’s in silico approach elucidated a group of target compounds comprising the general structural commonalities suggesting high levels of NOX4 inhibition, without triggering hERG related toxicity.

Solution

BIOiSIM generated a Translational Index parallelizing predictions of PK, PD, Metabolic stability, and hERG toxicity in order to further develop a subset of NOX4 inhibiting compounds with the highest likelihood of interspecies translatability to assess drug behavior in humans, and eliminate “dead-end” compounds from further development. Simulations were run across 3 different routes of administration, and both mouse and human species.

Outcome

With respect to human cardiotoxicity, high risk potential of hERG blockage was found across more than 50% of the test compounds, impacting the Translational Index for each, and triaging the overall consideration set dramatically. While conventional approaches will take ~2 years, VeriSIM Life, in just 4 months of modeling and simulation, computationally identified 15% of the proposed compounds as safe and efficacious by route of administration, further ranking 2 compounds as having the strongest clinical success potential.

With VeriSIM’s support, we predicted PK/PD profiles and translatability of a group of compounds to identify suitable leads for the treatment of fibrotic disorders and other clinical indications with accelerated lipid peroxidation leading to similar fibrotic outcomes.

Lab Leader at large university research center

Additional VeriSIM Life Case Studies & Content

Optimizing Dosing with AI/ML Driven Transdermal Drug Permeation Simulation

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.