Christopher Cole

At AAPS PharmSci 360 2025, Elly Zhou says digital twins helped forecast the effects of drugs on human drugs via a digital control arm.

Achieving a Personalized Digital Control Arm for Preclinical Drug Evaluation 

In this interview regarding the poster presentation “A Novel Approach to Preclinical Drug Development Using Digital Twins of Ex Vivo Human Lungs” at 

, Elly (Xuanzi) Zhou, MS, PhD-Candidate, University Health Network, Toronto, Canada, discusses a project that seeks to address significant limitations inherent in traditional randomized control trials, namely, she says, the limited availability of human organs for testing and the high inter-subject variability that often complicates result interpretation. Furthermore, Zhou notes that conventional evaluation models like animal models or organoids often fail to fully capture the complexity of the human system.

The central innovation of her research is using digital twins to create a personalized digital control for every organ being treated. The digital twin leverages large-scale multimodal datasets to train machine learning models that accurately forecast future lung and organ function, Zhou notes. Specifically, after a human lung receives a drug treatment, the digital twin generates the hypothetical untreated effects—the outcome 

 the organ was not treated. This, she adds, serves as a robust digital control arm, enabling direct comparison between the observed treatment effects and the digital twin-generated untreated effects within the same lung. By reducing the reliance on traditional cohort-based analysis and the number of human lungs needed for control groups, this approach is designed to reduce study size and accelerate clinical trials, according to Zhou.

The foundation of the data collection is an

 lung perfusion (EVLP) system, an artificial circuit developed by thoracic surgeons at Toronto General Hospital in 2008. EVLP keeps human lungs alive outside the body by perfusing the organ through vasculature and keeping the lungs ventilated at 37 degrees Celsius. This method allowed Zhou and colleagues to test human lungs directly with a condition of interest, such as perfusing a lung with disease on the circuit. The resulting data are considered highly valuable because they are“clean and capture the lungs in isolation,” free from the systemic effects of the rest of the human body, Zhou explains.

The models incorporate multiple layers of data, including lung physiology (air pressure, compliance, gas exchange), biochemistry (pH level, electrolytes), imaging data (X-rays taken during EVLP), proteomic analysis, metabolic biomarkers, and transcriptomic pathways, says Zhou. This rich dataset is used to generate personalized forecasts. As she summarized,"If you are treating a lung in real life,… you give the treatment and then you observe the treatment effects in terms of organ function and behavior, but... digital twins… generate… untreated effects to serve as this personalized digital control for this organ being treated." Furthermore, the EVLP system demonstrated utility in Zhou and team’s study beyond testing, having been used as a therapeutic platform to perform gene editing using CRISPR technology on human lungs.

*Editor’s Note: This transcript is a direct, unedited rendering of the original audio/video content. It may contain errors, informal language, or omissions as spoken in the original recording.



 Hi everyone, my name is Elly. I'm a third year PhD candidate at the University of Toronto in Canada, and my supervisor is Dr. Andrew Sage. And my project is focused on developing digital twins of ex vivo human lungs to potentially accelerate preclinical drug development.

Yeah. So if you think about a randomized control trial where you have the two arm design, you have the control and the treatment. So essentially what happens is that we face two major challenges. The first is the limited availability of human organs for testing, and a second is, we're looking at a significant variability within the inter subject conditions that can cause the result interpretation to be very difficult.

So what digital twins can do is that it can generalize a personalized control for every organ that's been treated. So essentially after you provide a drug to treat the human lung, and then what you observe is essentially the observed treatment effects. And then for the digital twin part is that it's going to generate the untreated effects as if the organ was not treated.

So essentially this will allow us to reduce the reliance on a cohort based analysis where we can do direct comparisons between the untreated and treatment effects within the same lung. So this will reduce the study size because this will reduce the number of human lungs we use as controls. So in that way we'll be able to have a faster clinical trial.

So if we think about the traditional drug evaluation models, for example, animal models or organoids, they typically don't fully or often fully capture this. Complexity within the human body or system. So what digital twins can do is that we actually leverage a large scale multimodal data set to train the machine learning models to accurately forecast lung function, organ function of future time points.

So in this way we'll be able to essentially say what is the untreated effects of this drug in this given lung that's been treated? And in addition on this EVLP system, ex vivo lung perfusion, we’ll actually be able to test human lung with the condition of interest directly.

Like for example, we can perfuse a human lung with disease directly on the circuit and observe its behavior, the organ function.

So for this model, we actually incorporate multiple layers of data. So we have lung physiology data, for example, lung, air pressure, compliance, gas, like oxygenation exchange and also biochemistry data such as pH level, acid base and different electrolytes. We also have imaging data, x-ray images because on this EVLP profusion system, we can actually take x-ray images of the lungs.

And in addition to that, we also have proteomic analysis metabolic biomarkers and also transcriptomic pathways. And they have all been incorporated into the model.

Yeah. And so what digital twin does is its going to serve as this robust and also effective digital control arm in the study. So if you can imagine if you are treating a lung in real life while you give the treatment and then you observe the treatment effects in terms of organ function and behavior but what digital twins do, is that it's going to generate this, I guess, untreated effects to serve as this personalized digital control for this organ being treated. So by doing this comparison between the treatment effects and digital twin-generated, untreated effects, we can actually do a direct comparison to say, what is this drug's impact on this organ been treated.

Yeah, so what EVLP system is Ex vivo lung perfusion, which means we're trying to keep a set of human lungs alive outside the human body. So what we do is that we have this artificial circuit that was originally developed in 2008 by a group of thoracic surgeons at Toronto General Hospital. So what we do is we perfuse the organ through vasculature, keep the lungs ventilated through the trachea, keep everything at 37 degrees Celsius in a physiologically protective environment.

So during the process we'll be able to collect a set of clean multimodal lung function data. That can be used to train the digital twin model. And also this data is very clean in the sense that we're actually just looking at the lungs in isolation without systemic effects of the human body.

And in addition to that, at our hospital, we actually have demonstrated that the EVLP system can be used as a therapeutic platform in the work or in the study led by Dr. Shaf Keshavjee at Toronto General Hospital, we have shown that you can actually do gene editing on a set of human lung using CRISPR technology during EVLP

Videos

Scientist operating precision equipment for 3d printing or biomedical research, illustration | Image Credit: © pramestydwi - stock.adobe.com

IgA nephropathy (IgAN) is recognized as a significant contributor to chronic kidney disease and is a primary driver of kidney failure, characterized by progressive, chronic autoimmune damage to the kidneys (1). Effective treatment requires targeted intervention. Budesonide is the first treatment approved by the FDA shown to reduce the rate of kidney function loss in adult patients managing IgAN (2). The mechanism hinges on the drug acting locally on the terminal ileum to reduce the amount of IgA1 antibodies, thereby treating the IgAN. In parallel, three-dimensional (3D) printing is an emerging technology that offers innovative solutions for both patients and the pharmaceutical industry (3). This technology can greatly benefit drug product design by allowing precise construction of the structure of dosage forms. Furthermore, 3D printing facilitates patient-centric treatment, such as personalized dosing, accommodates the treatment of specific disease states or patient populations, and provides versatile release modes to meet clinical requirements.

For a study presented via the poster “3D Printed Ileum Targeted Tablet for the Treatment of IgA Nephropathy” by Xiaoling Li, PhD, professor/CSO at Triastek, Inc., at 

, held Nov 9-12, 2025 in San Antonio, Texas (5), Li and colleagues at Triastek, Inc—Zhaoyao Chu, PhD, scientist, Formulation Development; Aiming Ma, PhD, senior manager, Formulation Development; Lanfang Chen, PhD, senior industry analyst; Fenge Zhang, director, CMC; and Senping Cheng, PhD, founder and CEO—focused on designing a 3D-printed tablet specifically for budesonide delivery to the ileum, aiming to modulate the activity and numbers of B-cells.

A novel 3D-printed tablet was created using 3D microstructure design platforms. Fabrication of this tablet, which featured a coating sheet structure, was achieved utilizing melt extrusion deposition (MED®) 3D printing technology (4). To verify performance 

, X-ray imaging was used to track the gastrointestinal (GI) transition and subsequent budesonide release. Barium sulfate was incorporated into the formulation to serve as the tracking agent during the 

How was the delayed release successfully achieved?

Through the application of 3D micro-structure design coupled with MED 3D printing technology, a functional delayed-release tablet was successfully designed and fabricated. X-ray images captured during the study indicated that the drug release occurred at four hours, confirming the successful targeting of the distal small intestine. Crucially, a human pharmacokinetic study demonstrated a more consistent delivery of budesonide within the ileum when compared against a traditional targeted-release formulation of the drug (Figure). This enhanced consistency was confirmed by observing a measured decrease in the variability of both Tlag (lag time) and Tmax (time to maximum concentration).

 Adapted from: Li, X; Chu, Z; Ma, A; et al. 3D Printed Ileum Targeted Tablet for the Treatment of IgA Nephropathy. AAPS PharmSci 360 Poster Abstract. Accessed Nov 12, 2025.

What is the long-term impact on drug development variability?

The research validates that MED 3D printing technology and 3D microstructure design can be successfully leveraged to develop drug products with precise, desired release profiles targeted to specific GI locations. Ultimately, these 3D-printed, budesonide delayed-release tablets achieved a more precise delivery of the drug to the lower small intestine area, resulting in a significant reduction of 

Long-term Renal Survival and Related Risk Factors in Patients with IgA Nephropathy: Results From a Cohort of 1155 Cases in a Chinese Adult Population

IgA Nephropathy: Current Understanding and Perspectives on Pathogenesis and Targeted Treatment

3D Printing: Innovative Solutions for Patients and Pharmaceutical Industry

Melt Extrusion Deposition (MED™) 3D Printing Technology – A Paradigm Shift in Design and Development of Modified Release Drug Products

3D Printed Ileum Targeted Tablet for the Treatment of IgA Nephropathy

. AAPS PharmSci 360 Poster Abstract. Accessed Nov 12, 2025.

Articles

IgA nephropathy significantly contributes to chronic kidney disease, necessitating targeted treatments like budesonide, which reduces kidney function loss by acting on the ileum. The advent of 3D printing technology offers innovative solutions for drug design, enabling precise dosage forms and personalized treatments. A study demonstrated the successful creation of a 3D-printed budesonide tablet using MED 3D printing, achieving targeted ileum delivery and reduced in-vivo variability. This approach promises to enhance drug development by ensuring precise release profiles and consistent drug delivery to specific gastrointestinal locations.

At AAPS PharmSci 360, Xialing Li, PhD, says 3D-printed budesonide tablets achieve precise, delayed delivery to the ileum for IgA nephropathy, lowering in vivo variability.

How 3D-Printed Tablets Can Optimize IgA Nephropathy Treatment

Digital twin industrial process modeling software technology concept | Image Credit: © WrightStudio - stock.adobe.com

The process of pharmaceutical R&D frequently encounters significant hurdles, including high costs and prolonged timelines, often stemming from the decreased translatability of findings from preclinical models, according to Xuanzi Zhou, PhD-student, University Health Network in Toronto, Canada, who presented a poster at 

, held Nov 9-12, 2025 in San Antonio, Texas. Conventional methods, such as animal models and tissue organoids, often prove inadequate in fully capturing the dynamic complexity inherent to the human body, Zhou and colleagues at the University of Toronto—Bo Wang, PhD, Professor; Yiyang Wei, master’s student; Serena Hacker, machine learning researcher; Sumin Kim, PhD-student; Marcelo Cypel, professor; Shaf Keshavjee, MD, professor; and Andrew Sage, PhD, professor—stated.

 lung perfusion (EVLP) offers an advanced platform developed to assess isolated human lungs under physiological conditions, thereby enabling therapeutic testing for applications like stem cell therapy, gene therapy, and immunomodulation (1-6). Despite its utility, standardizing drug evaluation within EVLP using the conventional randomized two-arm study design presents challenges, say the researchers, specifically due to the limited availability of human organs, which prolongs enrollment and increases costs, and the substantial inter-subject variability, which complicates the interpretation of results.

To address these limitations, the team explored the emerging concept of digital twins—computer simulations of physical objects—an approach that is promising in medicine but largely unexplored in drug discovery (7). Given that EVLP procedures generate real-time, multi-modal data on lung function, according to Zhou, et al, this environment offers a unique opportunity to train machine learning (ML) models. The core objective of their study was the development of an ML-based methodology that uses more than 300 ML algorithms operating simultaneously to accurately simulate the future function of a human lung. As a demonstration of clinical utility, the researchers aimed to validate these digital twins for the preclinical evaluation of both the safety and efficacy of an EVLP-targeted therapy.

How were the digital lung models developed and trained?

The modeling effort was based on a comprehensive clinical dataset derived from EVLP clinical cases performed between 2008 and 2024 at the Toronto General Hospital. The resulting multi-modal data included a broad spectrum of human lung characteristics, such as physiological measurements, medical imaging features, transcriptomics, and various proteomic, metabolomic, and biochemical biomarkers.

To create the forecasting models, the investigators trained multi-modal models using k-fold cross-validation, employing a deep learning-based model known as a Gated Recurrent Unit alongside a tree-based XGBoost model. Model performance was quantitatively measured using mean absolute error and mean absolute percentage error.

Two distinct modeling strategies were deployed in developing the digital twins of the human lungs. The 'static' digital twin strategy used a single, static baseline dataset of lung function as input to forecast future function. In contrast, the 'dynamic' digital twin approach was designed to be recalibrated using additional functional data, forecasting only the immediate next time point based on the most recent lung function data.

For the proof-of-concept validation of these digital lungs, the researchers studied a cohort of 16 lungs that had previously received tissue-type plasminogen activator (tPA), a thrombolytic therapy. The therapeutic efficacy, quantified by pulmonary arterial pressure (PAP), and safety, assessed by edema levels, were evaluated on a personalized, case-by-case basis using the corresponding digital twin for each treated lung.

Did the digital twins reveal therapeutic effects missed by traditional methods?

The development was successful, resulting in a digital twin of an 

 human lung that accurately predicted lung function across more than 75 distinct functional parameters measured during EVLP. The digital twin approach demonstrated high reliability, achieving greater than 90% accuracy in both short- and long-term forecasting of physiology, biochemistry, metabolites, and transcriptomics (Figure).

The study team found that the digital twin approach for preclinical therapeutic evaluation outperformed conventional preclinical study designs. A key advantage is the ability of the digital twins to successfully predict the counterfactual outcome—the state of the lung if the therapy had not been applied. This capability enabled a paired statistical analysis between the corresponding treated lung and its untreated digital twin. As a representative example, one EVLP case treated with tPA displayed a reduction in PAP compared with its digital twin, without any significant increase in edema.

When performing paired analyses on the cohort of human lungs treated with tPA, the digital twin methodology revealed a significant reduction in PAP within two hours of treatment (

=0.031). This finding contrasts sharply with results from a conventional two-arm study design, which, when applied to the same cohort data, displayed no significant differences in PAP at either one or two hours post-treatment. Consequently, the study demonstrated that only the digital twin approach was sensitive enough to identify the preclinical treatment-induced reductions in PAP.

The digital twin approach resulted in a virtual model of human lungs built upon the world’s largest available dataset of clinical 

 lung perfusion procedures, state Zhou and team. These digital twins successfully and accurately predicted a comprehensive range of lung physiology parameters, in addition to proteomic, metabolomic, transcriptomic, and biochemical biomarkers. The models’ utility for preclinical therapeutic evaluation was validated using real-world data, demonstrating their capacity to reveal new insights into the effects of treatment. By facilitating direct comparisons between a physical human organ and its virtual counterpart, digital twins are poised to support advances in precision therapeutics and accelerate the process of preclinical drug discovery, concludes Zhou.

Technique for Prolonged Normothermic Ex Vivo Lung Perfusion

Normothermic ex vivo lung perfusion in clinical lung transplantation

Immunomodulation of the Donor Lung with CRISPR-mediated Activation of IL-10 Expression

Nakajima, D; Watanabe, Y; Ohsumi, A; et al. 

Mesenchymal Stromal Cell Therapy During Ex Vivo Lung Perfusion Ameliorates Ischemia-reperfusion Injury in Lung Transplantation

Ex vivo Enzymatic Treatment Converts Blood Type A Donor Lungs into Universal Blood Type Lungs

Nykänen, A; Mariscal, A; Duong, A; et al. 

Lung Transplant Immunomodulation with Genetically Engineered Mesenchymal Stromal Cells-Therapeutic Window for Interleukin-10

A Novel Approach to Preclinical Drug Development Using Digital Twins of Ex Vivo Human Lungs

. AAPS PharmSci 360 2025 Poster Abstract. Accessed Nov 11, 2025.

Pharmaceutical R&D faces challenges like high costs and long timelines due to low translatability of preclinical models. Ex vivo lung perfusion (EVLP) offers a promising platform for testing therapies, but standardizing drug evaluation is difficult. Researchers explored digital twins, using machine learning to simulate lung function, improving preclinical evaluation. The digital twin approach outperformed traditional methods, accurately predicting lung function and revealing therapeutic effects missed by conventional studies. This method could advance precision therapeutics and accelerate drug discovery by enabling direct comparisons between physical and virtual organs.

At AAPS PharmSci 360, Xuanzi Zhou says digital twins accurately predict ex vivo lung function, revealing therapeutic effects missed by conventional preclinical drug testing.

AI-Powered Digital Twins Achieve High Accuracy in Human Lung Function Forecasting

At AAPS PharmSci 360 2025, Siddhant Sojitra, Alexion, defines an agitation model to reliably test stability for early-stage biologics.

A Scientifically Justified Agitation Stress Model for Early-Stage Biologics 

Siddhant Sojitra, Associate Scientist III, Injectable Drug Product Development, Alexion Pharmaceuticals, discusses the primary role played by scale-down agitation in the development of high-concentration biologics by simulating mechanical stress on drug products in this interview regarding the poster presentation “

Defining a Scale-Down Agitation Model for Early-Stage High Concentration Biologics Formulation Development

. This stress, often encountered as shaking and mixing, occurs throughout the drug product lifecycle, including during manufacturing, transportation, storage, and administration, Sojitra and colleagues 

. Utilizing this model offers crucial insights into how varying levels of agitation impact drug products. Ultimately, the goal is to develop more stable formulations capable of sustaining these mechanical forces without compromising the drug's quality or effectiveness, he adds.

Mechanical stress testing is essential because constant agitation leads to significant negative impacts on product quality, primarily protein aggregation and particulates formation, Sojitra notes. The shaking can expose the protein’s hydrophobic patches, causing nucleation and aggregation, and may also unfold the protein structure. Aggregation severely compromises the protein’s potency, while the formation of particulates raises the risk of immunogenicity and can violate regulatory guidelines, the study team notes in their poster.

To assess the stability of biologic formulations against these stresses, quality attributes (QAs) are demonstrated through various testings, including analysis of appearance, turbidity, size/charge variance, aggregates formation, and particulates formation, says Sojitra. The researchers specifically utilized analytical methods, such as size-exclusion ultra-performance liquid chromatography, to measure high molecular-weight species (HMWS), micro flow imaging to detect subvisible particles (SVP), and optical density (OD) to assess turbidity.

The study systematically evaluated three physical agitation models: an orbital shaker, a multichannel vortexer, and a bench-top shipping simulator (VR5500). Comparisons showed that both the orbital shaker (at 200 RPM) and the vortexer (at 1200 RPM) subjected samples to more severe mechanical stress than the VR5500, making them suitable for robust formulation development studies. A key finding was that the different models impacted distinct QAs. The orbital shaker was found to predominantly promote the formation of HMWS, whereas the vortexer was more likely to induce the generation of SVP.

Based on the study's findings, the optimal, scientifically justified agitation model for early-stage formulation development was defined. Recognizing the need for smaller sizes due to material constraints in early development, the standard configuration selected was the 2R vial. The data support using the 2R vials with a minimum fill volume of 1 mL, positioned in a horizontal placement, and subjected to orbital shaker agitation at ambient temperatures for up to 24 hours. This setup provides a reliable and consistent method to assess the impact of mechanical stress, thereby helping to identify stable formulations early in the development pipeline, Sojitra and team stated.

Check out Sojitra’s take on the roles and barriers to AI and digital technology in biologics, our 



I am Siddhant Sojitra. I work as an associate scientist three in drug injectable drug product development team at Alexion, AstraZeneca. I have three plus years of working experience in the pharmaceutical industry now. My specialization includes biologics drug product formulation development, especially high concentration monoclonal antibody-based formulations.

I have an engineering background. I did my masters in chemical engineering from Northeastern University of Boston.

So the primary role of scale-down agitation model is to simulate agitation stress on drug products. This mechanical stress is in the form of agitation, which means drug products are getting exposed to shaking, mixing, and this is often encountered during manufacturing, transportation, storage, administration.

So that's where the scale-down agitation model comes in. Having this model gives us crucial insights about how different label of agitation impacts drug products, and can also help us to develop formulations much more stable version of drug products, which can sustain all this shaking without compromising its quality and effectiveness.

The major impact on drug product quality are protein aggregation and particulates formation. So because of this constant shaking and agitation, proteins often get exposed to its hydrophobic patches, which can nucleate segregation. It can also unfold protein, and because of this aggregation, it impacts protein's potency, and particulates formation increases immunogenicity risk, and it can also violate guidelines.

Drug products’ quality attributes are demonstrated by various testings, such as appearance and turbidity, measuring size and charge variance, aggregates formation, particulates formation. This is how the drug products quality attributes are demonstrated.

So for early-stage stress testing, we are keeping material constraints in mind. We focused on smaller size vials, which are widely used and our data shows that at least 1 mL in 2R vials when shaken horizontally, using an orbital shaker up to 24 hours, provides a reliable approach to study early-stage stress testing.

Following mechanical stress, there are various testings done, which includes appearance, turbidity, particulate formation, using microflow imaging techniques or light obscuration techniques, aggregates formation using size-exclusion chromatography. And this gives us an idea how drug product is behaving and how the impact of agitation is on drug product.

Siddhant Sojitra, Alexion, defines in an AAPS PharmSci 360 2025 presentation an agitation model to reliably test stability for early-stage biologics.

Defining An Agitation Model for Early-Stage, High Concentration Biologics Formulation Development

Doctor technology AI integrates big data analytics with clinical research, enabling precise treatment plans tailored to individual patient needs and genetic profiles | Image Credit: © Suriyo - stock.adobe.com

 by Dineli Ranathunga, PhD, scientist III, Research and Development at Thermo Fisher Scientific, at 

, held Nov 9-12, 2025 in San Antonio, Texas, investigators sought to use in-silico modeling to identify the best formulation approaches for use with poorly soluble drugs in order to support early decision making. Dr. Ranathunga, Thurman Falk, scientist III, Early Development at Thermo Fisher Scientific; Tom Reynolds, PhD, manager, Research and Development at Thermo Fisher Scientific; Nairuti Milan Mehta, scientist II, Research and Development at Thermo Fisher Scientific; Thomas Yonker, VP of Operations at Cerevance; and Sanjay Konagurthu, PhD, senior director, Science and Innovation at Thermo Fisher Scientific conducted the study based on the premise that the pharmaceutical industry faces persistent hurdles in bringing new treatments to market, particularly when dealing with compounds that are difficult to dissolve.

Currently, between 70% and 90% of drug candidates under development are categorized as poorly soluble (1). This widespread issue necessitates the early integration of appropriate formulation technologies into the development pipeline to prevent expensive delays later in the process, according to Dr, Ranathunga and team. Their work demonstrates how integrated predictive modeling can be leveraged to guide these critical, early-stage decisions for poorly soluble drugs, they stated.

The approach utilizes computational tools to rapidly identify optimal solubilization methods. As a case study, the researchers evaluated the poorly soluble compound CVN424. The study began by assessing the chemical structure and physicochemical properties of the compound, using in-house artificial intelligence (AI) and machine learning (ML) models to predict properties when experimental measurements were unavailable. All computational work, including quantum mechanical calculations, molecular dynamics simulations, and statistical modeling, was performed using the Quadrant 2 program.

How can predictive modeling streamline formulation selection?

The initial step in this systematic approach involved applying the Developability Classification System to categorize CVN424 based on its inherent characteristics. A combined framework of AI, ML, and statistical algorithms was then employed to steer the formulation technology choice. This framework analyzed several critical drug characteristics, including lipophilicity (Log P), pKa, melting point, dose, solubility, precipitation kinetics, and thermal stability. The analysis generated recommendations for the most effective solubilization technologies designed to enhance both solubility and bioavailability.

Following the selection of initial technologies, further computational studies focused on identifying appropriate excipients. The selection of suitable excipients is vital, the study team noted, as it reduces the time and expense associated with the typical empirical screening of the vast number of commercially available excipients. High-level quantum mechanical calculations were used to perform a conformational distribution analysis of CVN424. Advanced quantitative structure-activity relationship models, incorporating AI and ML, generated molecular descriptors (such as electrostatic potentials and hydrogen-bond donors/acceptors). These descriptors, combined with molecular interaction energies derived from molecular dynamics simulations, helped analyze drug–excipient interactions. By comparing these analyses against an extensive excipient database, the study predicted suitable polymeric dispersion excipients. Furthermore, molecular dynamics simulations were conducted at varying drug loadings to evaluate how CVN424 dispersed within the excipient matrix and to calculate the maximum feasible drug loading for each promising excipient.

What formulation strategies were recommended and tested?

The results of the predictive modeling provided specific recommendations. For instance, the findings displayed the predicted success likelihood for various formulation technologies across three dose ranges (Table), recognizing that the dose amount significantly impacts the formulation strategy, particularly when exact dosing is still unknown. The study specifically recommended lead excipients and their calculated maximum drug loadings for use in amorphous solid dispersion formulations, such as those created via spray drying. Snapshots from the molecular dynamics simulations visually represented the dispersion behavior of CVN424 within the excipient matrix as a function of drug loading.

Based on these computational predictions, Dr. Ranathunga and team selected spray-dried formulations and nano-milled suspensions for further evaluation. Spray-dried intermediate formulations were manufactured using five polymers—HPMCAS-H, HPMCAS-M, HPMC E3LV, Eudragit L100, and Soluplus—chosen based on the insights from the modeling and initial screening. Nano-milled suspensions of CVN424 were also developed; these suspensions were subsequently isolated using a spray-drying process. The feasibility of the chosen formulations was assessed using such methods as physical characteristics, chemical and physical stability, and 

 performance, including biorelevant two-stage dissolution performance.

This work highlights the utility of an integrated predictive approach in accelerating the formulation process for compounds like CVN424. By identifying suitable excipient candidates and solubilization strategies through computational means, the study efficiently guided the selection of spray-dried and nano-milled formulations for later evaluation. Ultimately, this process minimizes reliance on empirical trial-and-error, demonstrating the clear potential of predictive modeling to accelerate the overall development timeline, according to the poster presentation.

The application of in-silico modeling in drug formulation is akin to using a sophisticated digital blueprint before laying a single brick in construction, the investigators stated. Instead of blindly testing hundreds of materials and combinations, the predictive technology narrows down the most structurally sound options, saving immense amounts of time and resources before physical experimentation even begins.



1. Ranathunga, D; Falk, T; Reynolds, T; Mehta NM; Yonker, T; Konagurthu, S. 

AI/ML Model Informed Early-Stage Drug Development

. AAPS PharmSci 360 Poster Presentation. Nov 12, 2025.

In-silico modeling is being utilized to address the challenge of poorly soluble drug candidates, which constitute 70-90% of drugs under development. This approach integrates AI, ML, and statistical algorithms to predict optimal solubilization methods, as demonstrated with the compound CVN424. The study employed computational tools to recommend formulation strategies, such as spray-dried and nano-milled formulations, minimizing empirical trial-and-error. This predictive modeling accelerates the drug development process by efficiently identifying suitable excipients and solubilization strategies, ultimately reducing time and resource expenditure.

In a poster presentation at AAPS PharmSci 360, by Dineli Ranathunga, PhD, indicates that AI/ML in-silico modeling can accelerate poorly soluble drug development.

Using AI and Molecular Dynamics to Overcome the Poor Solubility Challenge

AI is transforming pharma R&D, bioanalysis, and manufacturing. The industry faces intense competition (obesity wars) and FDA regulatory instability

PharmTech Weekly News Roundup – Week of November 3, 2025

In this PharmTech video feature, we highlight the week’s industry news in an easy-to-consume, fun format. New roundups will drop every Friday, so be sure to come back each week.

Two major themes cut across the week’s news: the profound integration of advanced technology, particularly Artificial Intelligence (AI), and the complexity of the modern pharmaceutical business landscape, characterized by intense competition and regulatory uncertainty.

The AAPS PharmSci 360 2025 (AAPS) annual meeting, held Nov 9-12 in San Antonio, 

will center on the transformative role of AI

, highlighting its integration into every facet of bio/pharmaceutical research, including basic discovery, analytics, formulation, and manufacturing. Cutting-edge topics like AI-designed drugs, spatial transcriptomics, and gene therapy progress will also be featured at this essential platform for pharmaceutical innovation.

Ahead of his presentation at AAPS, Steve Lowes, senior director of Scientific Affairs at IQVIA Laboratories, tells us that 

liquid chromatography–mass spectrometry (LC–MS) is becoming the preferred tool for bioanalysis

 of complex molecules like protein-based biologic drugs and oligonucleotide therapeutics, offering benefits over traditional ligand binding assays. This shift occurs as LC–MS actively addresses past sensitivity challenges and helps mitigate issues related to critical reagents used in immunoassays.

The pharmaceutical landscape is currently defined by significant regulatory uncertainty, stemming from an accelerating loss of expertise and a fractious organizational structure within the FDA’s vaccine center, according to our 

. Intense corporate battles dominate the lucrative obesity drug market, exemplified by major lawsuits and massive revenue guidance increases for key industry players.

, Long Yuan, PhD, director of the Department of Drug Metabolism and Pharmacokinetics at Biogen, explains that AI, machine learning, and large language models are poised to significantly enhance bioanalysis, promising improvements in quality, efficiency, compliance, and reduced human errors. These technologies are utilized to automate tasks, predict optimal assay conditions for method development, and streamline the entire biomedical workflow, including data processing and report generation.

planned acquisition of Kenvue by Kimberly-Clark for approximately $48.7 billion

, which underscores the convergence of consumer health and pharmaceutical markets. This deal necessitates reviews of supply chain resilience, may influence regulatory risk tolerance due to ongoing Tylenol litigation, and could lead to manufacturing footprint consolidation.

AI is transforming pharma R&D, bioanalysis, and manufacturing. The industry faces intense competition (obesity wars) and FDA regulatory instability.