Verisimlife

Introduction

In the process of drug development, accounting for potential drug-drug interactions (DDIs) is a critical step. DDIs are defined as “two or more drugs interacting in such a manner that the effectiveness or toxicity of one or more drugs is altered.” 1 Computational methods of identifying possible DDIs are growing in prominence throughout the industry, as their predictive ability allows researchers to identify these interactions sooner, saving time, money and other resources in the drug development process to lead to faster IND approval and improved ROI.

%20brief.pdf)

Situation

Adverse drug reactions (ADRs) are one of the major roadblocks to having a new drug approved, and aside from possibly preventing the drug from making it to market, not properly accounting for ADRs will result in patient harm and other serious consequences for a drug manufacturer down the road.

According to NIH’s National Library of Medicine, “the prevalence of clinically relevant drug interactions is about 6% in patients taking 2–4 medications, 50% in those taking 5, and almost 100% in those taking 10 medications.” This makes it a core component of drug discovery that manufacturers need to get right, as ADRs are a leading cause of patient morbidity and mortality. Often, such outcomes are a result of toxicity created when clearance functions are unintentionally inhibited by a DDI. Other times, drugs are withdrawn from market and trials by the FDA due to adverse reactions linked to CYP450 isozymes.

A second critical area in which AI-enabled methods surpass traditional methods of predicting DDIs is in the area of drug efficacy. The worst outcome of a DDI is patient mortality, but a second negative outcome is impact on the effectiveness of the drug. One reason for this is drugs that share common proteins or pathways may compete for the same target, resulting in neither drug achieving the intended outcome.

When applying for IND, patient safety and drug efficacy are both concerns that encourage the FDA to ensure that drug developers make reasonable efforts to predict potential DDIs. FDA guidelines suggest specific areas of interest and experimental evidence to document a drug’s likelihood of triggering ADRs. If sufficient evidence is not provided, applications may be denied or approved conditionally. This can lead to lengthy delays and additional costs.

The VeriSIM Life advantage

Today, there’s good news for pharma researchers embarking on the process of predicting drug-drug interactions. Innovations in AI-driven technologies have allowed for the streamlining and de-risking of many aspects of early-stage drug development, including the process of predicting DDIs.

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 account for possible drug-drug interactions for a particular drug candidate, among other drug discovery-related tasks. This includes identifying new drugs as inhibitors, substrates, inducers of interaction with targets, pathways and enzymes of interest, such as potentially problematic classes, and those identified by the FDA of particular concern.

BIOiSIM, and VSL’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.

BIOiSIM, and its groundbreaking Translational Index™️ technology,

which advances only the most promising drug candidates through R&D to investigational new drug (IND) application, offers 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-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.

Support for genomics data integration More than 3,000,000 real compounds including proprietary data from multiple partnerships Validation by real-world observed data

Proof of Value

In Silico Development of Combinatorial Therapeutic Approaches Targeting Key Signaling Pathways in Metabolic Syndrome

Challenge

A common and an initial approach to improve and or reverse the deleterious nature of clinical risks in metabolic syndrome (MetS) is changes in lifestyle diet with increased physical activity. Nevertheless, often these lifestyle modifications are not enough to sway the balance towards normality in patients, hence, treatment may require a different therapeutic approach, a multi-drug therapy regimen. However, a multi-drug regimen or polypharmacy has been known to be a major problem for the treatment of patients with MetS due to suboptimal patient compliance, off-target effects, and potential drug-drug interactions.

Solution

We used BIOiSIM to take a DPP4 inhibitor, a small molecule, and anti-IL-17a, a biologic with a completely distinct mechanism of action to address and combat outcomes of dysregulation of a wide range of key metabolic pathways involved in insulin resistance and inflammation. Specifically, the key dysregulated metabolic pathways in part, originate from impaired glucose control and disorders in lipid metabolism. This leads to elevated blood lipid level resulting in insulin resistance and chronic inflammation due to the release of proinflammatory cytokines.

Methods

Outcome

Overall, our results suggest that simultaneously targeting lipid metabolic pathways, impaired glucose control, insulin resistance, and chronic inflammation with DPP-4 inhibitor Evogliptin and IL-17A inhibitor Secukinumab will likely provide a high likelihood of ameliorating a significant portion of the clustered clinical risk associated with MetS. Read the full article.