Efficacy Predictions

How AI helps drug developers in the context of safety and efficacy predictions.


The pharmacological effect of any potential drug candidate must always be carefully vetted for safety and efficacy.

In the context of drug development, efficacy is defined as a medicine’s ability to produce a desired effect or treat a specifically indicated condition. Measured under expert supervision with a group of patients most likely to have a response to a drug, an estimated 40%–50% of all clinical phase drug development fails due to poor efficacy. 

Understandably, novel approaches which can help predict the efficacy of treatments during preclinical and clinical studies are an area of great opportunity and interest to pharma researchers and industry players – potentially representing major time, cost and patient benefit.

Download PDF

Within the lengthy, complex and expensive landscape of drug development, poor efficacy remains the most common cause of late-phase drug development failure

The VeriSIM Life advantage

Thankfully, advancements in biomarker discovery and validation methods, spurred on by innovations in instrumentation and in silico predictive tools, are playing a crucial role in improving efficacy prediction in drug development.  

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 discover novel therapies from existing molecules. 

BIOiSIM® helps not only measure and predict the effects of investigational treatments in humans during clinical trials, but also successfully complete target validation across in vitro, animal, or human disease models. This provides a more comprehensive prediction of a drug’s efficacy and significantly reduces discrepancies between models.

Additionally, VSL’s groundbreaking Translational Index™️ technology helps establish a well-balanced profile between efficacy and safety for candidate drugs, advancing only the most promising drug candidates through R&D to investigational new drug (IND) application.

BIOiSIM further supports efficacy prediction through:

  • Simulating and predicting pharmacokinetics (PK) and pharmacodynamics (PD) of compounds known to match the targeted pathway in therapeutics with an established mechanism-of-action
  • Leveraging predictive simulation capabilities which guide the development of new drug combinations
  • Applying machine learning to predict drug pathways and anticipated disease response in lieu of experimental data
  • Predicting drug solubility and model variations for individuals, including interactions between API and carrier, solubility parameters, and by simulating amorphous solid dispersions (ASD) formation and dissolution mechanisms
  • Predicting drug stability faster, and at a significantly lower cost, than human and animal studies, using molecular dynamics simulations which model and predict ASD physical stability
  • Using advanced modeling software as a starting point for pinpointing the most appropriate dose for human consumption, helping elucidate the relationship between compound exposure and therapeutic effect, including immune response, therapeutic window, and safety and efficacy for compounds in Phase-1 trials
  • Reducing the need for costly, resource-intensive formulation studies on humans and animals, predicting computationally how the API interacts with virtual versions of animal and human subjects

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.

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

1 trillion potential compounds search space for de novo synthesis and structural screening

Physiological data from 7 different animal species, plus humans

Support for genomics data integration

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

Proprietary experimental data from scientific literature and other sources

Validation by real-world observed data

Proof of Value

Predicting Translatable Drug Combinations for ADCs


Among blood cancers, acute myeloid leukemia (AML) and diffuse large B-cell lymphoma (DLBCL) are the most rapidly progressing tumors. One of the promising approaches to AML and DLBCL therapies includes the administration of antibody-drug conjugates (ADC) delivering highly toxic antitumor agent payloads linked to highly specific antibodies. However, current chemotherapy regimens cure only a minority of patients with AML and DLBCL.


Unlike conventional systemic distributed chemotherapy, VeriSIM Life (VSL) investigated a novel drug combination strategy for its partner which combined ADCs with current therapies in order to enhance their effectiveness and reduce tumor burden. VSL’s BIOiSIM®, ranked the predicted optimal combinations with regard to efficacy based on our multi-dimensional Translational Index™ technology. This approach targeted specific cancer cells, reducing the toxic side effects patients would otherwise endure during treatment.


  • PKPD monotherapy digital models were designed to evaluate the efficacy of a monotherapy at an arbitrary dosing regimen.
  • Tumor-specific ML models were then trained to provide concentration-dependent predictions of synergy or inhibition between two therapeutic agents.
  • A matrix of dosing regimens was created for each combinatorial therapy to evaluate the predicted combinatorial efficacy at different dosing regimens.
  • A combinatorial therapy’s dosing matrix was analyzed to establish key metrics, e.g. maximum and average inhibition predicted across a dosing matrix. Each metric became a component of the project-specific Translational Index. 


VeriSIM Life generated a multidimensional Translational Index score for each combinatorial therapy, producing a ranking of the partner’s combinatorial therapies from the most to least efficacious combination of therapeutic agents. Crucially, the multidimensional Translational Index provided a customizable, transparent, and objective summary of a therapy's experimental and predicted outcomes. This approach enabled investigators to make informed decisions about which compounds to progress to the next stage of development and their potential likelihood for clinical success.

“This approach was especially useful because experimental efficacy data is typically sparse or non-existent for novel therapeutic agent combinations.”

Biotech client
Case studies

Additional VeriSIM Life Case Studies & Content


How to Evolve from Traditional Model-Informed Drug Discovery & Development to an AI-Informed Approach

Read the full article

Predicting Patient-Specific Drug Bioavailability with AI

Read the full article
Evolve your pipeline

Bring better drugs to market, faster, with BIOiSIM®

Now you can accelerate the discovery of new therapies based on existing compounds with VeriSIM Life’s BIOiSIM® 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.

Contact us today to schedule a demonstration of BIOiSIM®