Using Digital Twins To Improve Drug Development and Delivery

Drug delivery is a complex process involving numerous factors such as drug properties, patient physiology, and delivery mechanisms. Traditional drug development and delivery processes frequently involve trial-and-error methods, which can be time-consuming and expensive. By creating virtual models that can simulate drug behavior in the body and predict efficacy and safety, digital twins provide a solution.

Digital twins have a large market potential in drug delivery because the technology has the potential to significantly improve drug development processes and patient outcomes. According to MarketsandMarkets, the global digital twin market is expected to grow at a compound annual growth rate of 58.9% from $3.1 billion in 2020 to $48.2 billion by 2026.

To improve drug development processes and shorten the time to market, the pharmaceutical industry is increasingly investing in digital twin technology. Researchers can use digital twins to simulate drug behavior in the body and predict drug efficacy and safety, allowing them to optimize drug formulations and dosages prior to clinical trials.

What are digital twins?

A “digital twin” is a virtual replica of a real-world person, physical entity, or process. For example, the digital twin of an aircraft engine is a precise virtual copy of the machinery, powered by artificial intelligence (AI). Streaming data collected from sensors onboard the engine is relayed to the digital twin in real time. This enables aircraft engineers to monitor the engine’s performance and predict when it may fail.

Now, imagine building a digital twin of a real person to replicate how they would behave and respond in specific situations. You could track their health, diagnose diseases, and plan preventive treatments.

How does it apply to the pharmaceutical industry?

A “digital twin” is a virtual representation of a drug, process, or system that is used to optimize the drug development process in the pharmaceutical industry. As stated above, digital twins can be created using data from a variety of sources, such as electronic health records, wearable devices, and imaging technologies. Digital twins can be used in the pharmaceutical industry to simulate the behavior of a drug in the body, allowing researchers to better understand potential side effects and tailor dosage and administration accordingly. Patients may benefit from more personalized and effective treatment as a result of this. This can save time and resources by identifying bottlenecks or potential issues before they occur in the physical process.

Here are a few examples:

1. AstraZeneca - AstraZeneca has partnered with Insilico Medicine to use digital twin technology to optimize drug development processes and identify new drug candidates.
2. Pfizer - Pfizer has partnered with BioLingus to use digital twin technology to optimize the formulation and delivery of biologics.
3. Roche - Roche has invested in Physiomics to use digital twin technology to optimize drug development processes and improve patient outcomes in cancer care.
4. Novartis - Novartis has partnered with Lattice AI to use digital twin technology to simulate drug behavior in the body and predict drug efficacy and safety.
5. Sanofi - Sanofi has invested in Owkin, a startup that uses digital twin technology to accelerate drug discovery and development processes.

Use of Digital Twins for Drug Delivery:

Using patient-specific data such as genetics, physiology, and lifestyle factors, digital twins can be used to simulate drug behavior in the human body, allowing researchers to optimize drug development and delivery processes. Digital twins, for example, can be used to predict drug absorption, distribution, metabolism, and excretion (ADME) in the body, allowing researchers to identify potential problems and optimize drug formulations (1). Furthermore, researchers can use digital twins to simulate drug delivery mechanisms such as implantable devices or nanocarriers, allowing them to optimize drug release rates and dosages (2).

As part of the Virtual Human System project, Oklahoma State researchers have been working with Ansys to develop a digital twin to improve drug delivery using models of simulated lungs. They discovered that only about 20% of many drugs reached their intended target. The digital twins enabled them to redesign the drug's particle size and composition characteristics, resulting in a 90% increase in delivery efficiency.

The development of drug delivery robots is another potential application of digital twins in drug delivery. Researchers can use digital twins to simulate drug delivery robot behavior in the human body, allowing them to optimize their design and function (4). This method has the potential to improve drug delivery precision while also lowering the risk of human error.

The Advantages of Using Digital Twins for Drug Delivery

The use of digital twins in drug delivery has a number of potential advantages, including:

1. Reduced drug development and delivery costs and time
2. Enhancement of drug efficacy and safety
3. Individualized drug delivery for patients
4. Increased precision and accuracy in drug delivery

Here are two examples of the use of digital twins in drug delivery:

1. Using a digital twin to improve nanoparticle drug delivery:

A digital twin model was used by researchers at the University of California, San Diego, to optimize the delivery of cancer drugs using nanoparticles. Using patient-specific data, researchers were able to simulate drug delivery and predict the efficacy of various drug dosages and nanoparticle formulations. The digital twin model accurately predicted drug delivery and was used in preclinical trials to optimize drug dosages and nanoparticle formulations.

2. Drug toxicity prediction using a digital twin:

Insilico Medicine researchers used a digital twin model to predict drug toxicity and optimize drug development processes. The digital twin model was built using patient-specific data and artificial intelligence and machine learning algorithms to predict drug toxicity based on the chemical structure of the drug and other factors. The digital twin model predicted drug toxicity accurately and was used to screen potential drug candidates and optimize drug development processes.

Companies working in the field:

Some of the challenges that face digital twin implementation in Drug Delivery include:

Data quality

Artificial intelligence systems in digital twins learn from available biomedical data, but because the data is collected by private companies, the data quality may be poor. As a result, analyzing and representing such data becomes difficult. This eventually has a negative impact on the models, lowering their reliability in the diagnosis and treatment processes.

Data privacy

The applications of digital twins necessitate the collection of increasing amounts of individual-level data by healthcare organizations and insurance companies. Over time, these health organizations develop a detailed portrait of a person's biological, genetic, physical, and lifestyle-related data. Such personalized data may be used to benefit the company rather than the individual. For example, insurance companies could use the data to improve the precision of personal identity distinctions.

As an investor in life science, are you aware of this cross-talk between Tech and Biotech? If so, are you investing in this topic? Leave a comment below.

Welcome to the BioBusinesss newsletter. Your source for Biotech and Business news. Feel free to reach out for consulting or sponsorship opportunities.

Are you enjoying the newsletter? Help us make it better by sharing it with your colleagues and friends.

See you in two weeks — Adrian

References:

1. Di L. Strategic Approaches to Optimizing Drug ADME Properties. AAPS J. 2015;17(1):134-43.
2. Wang S, Wang X, Yu X, et al. Nanoparticle-mediated drug delivery systems: an overview of the challenges and opportunities for cancer therapy. Biomaterials Science. 2019;7(3):915-930.
3. Salloum S, Shrestha S, Gursoy RN, Swaan PW. Personalized Medicine: The Role of Technomics and Digital Twins. Clin Pharmacol Ther. 2020;107(4):808-817.
4. Wang X, Wang C, Yu X, et al. Current progress in the development of nanorobots for bioapplications. Nanoscale. 2019;11(16):7726-7743.