Quantitative Approaches to Accelerate MASH Drug Discovery and Development

CPT: Pharmacometrics & Systems Pharmacology - Inception, Maturation, and Future Vision.

[Introduction] Quantitative Systems Pharmacology (QSP) modeling is a promising technique for model-informed drug discovery and development, and various QSP models for immuno-oncology (IO) have been published. Syngeneic tumor mice are often used for in vivo pharmacology study, and many kinds of IO QSP models have been reported to understand in vivo data and make prediction. However, published QSP models have varying structures across tumor types that makes it difficult to analyze data across different syngeneic tumor models. In addition, there are few QSP models calibrated by actual data of tumor infiltrating lymphocyte (TIL) dynamics. In this study, we present platform IO QSP modeling for syngeneic tumor mice (MC38, B16F10, CT26, 4T1 and LLC1) with a unified structure based on observed data of TIL dynamics and antitumor efficacy of anti-programmed cell death-1 (anti-PD-1) treatment. [Methods] (Mouse study for TIL dynamics) Five mouse tumors were inoculated into C57BL/6 (MC38, B16F10, LLC1) or BALB/c (CT26, 4T1). Tumors were sampled at three time points (mean tumor volume was about 50 mm3, 300-700 mm3 and 500-2000 mm3) and immune cells in the tumors were analyzed by flow cytometry. (IO QSP platform development) The structure of IO QSP platform was based on a published QSP model for CT26-bearing mice [1] and modified with reference to a comprehensive IO QSP model for breast cancer in human [2] to improve physiological interpretability of model components. The TIL dynamics data and published anti-mouse PD-1 (anti-mPD-1) antibody efficacy data for syngeneic tumor mice [3] were used for model calibration. The platform model was validated by confirming predictability of combination therapy of anti-mPD-1 antibody with a multiple kinase inhibitor (lenvatinib) for syngeneic tumor mice. [Results] The IO QSP platform model contains 12 tumor-specific parameters for each tumor type of syngeneic mice and successfully captured the observed TIL dynamics and antitumor effect of anti-mPD-1 antibody treatment. Mechanism of action of lenvatinib was incorporated into the IO QSP platform and calibrated with published data. The final model was successfully validated by comparing simulation and observation of combination therapy of anti-mPD-1 antibody with lenvatinib. [Conclusions] The IO QSP platform was established for several types of syngeneic tumor mice, which captured TIL dynamics and antitumor efficacy of anti-mPD-1 antibody. This platform model enables us to test a hypothesis by incorporating candidate compounds, to support study design with a translational biomarker and to investigate combination strategies, thus having the potential to facilitate new drug development. [References] [1] Kosinsky Y, et al. J Immunother Cancer. 2018;6(1):17. [2] Wang H, et al. Front Bioeng Biotechnol. 2020;8:141. [3] Georgiev P, et al. Mol Cancer Ther. 2022;21(3):427-439. Citation Format: Takeshi Nakayama, Aya Kikuchi, Kota Toshimoto, Hiroyuki Sayama, Taisuke Nakazawa, Masayo Oishi. Establishment of a quantitative systems pharmacology platform for syngeneic tumor mouse models: Application in immuno-oncology drug development [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 6274.

The Changing Face of Oncology Research, Drug Development, and Clinical Practice: Toward Patient-Focused Precision Therapeutics.

Physiological Indirect Response Model to Omics-Powered Quantitative Systems Pharmacology Model

Systems pharmacology approaches have the capability of quantitatively linking the key biological molecules relevant to a drug candidate's mechanism of action (drug-induced signaling pathways) to the clinical biomarkers associated with the proposed target disease, thereby quantitatively facilitating its development and life cycle management. In this review, the model attributes of published quantitative systems pharmacology (QSP) modeling for lowering cholesterol, treating salt-sensitive hypertension, and treating rare diseases as well as describing bone homeostasis and related pharmacological effects are critically reviewed with respect to model quality, calibration, validation, and performance. We further reviewed the common practices in optimizing QSP modeling and prediction. Notably, leveraging genetics and genomic studies for model calibration and validation is common. Statistical and quantitative assessment of QSP prediction and handling of model uncertainty are, however, mostly lacking as are the quantitative and statistical criteria for assessing QSP predictions and the covariance matrix of coefficients between the parameters in a validated virtual population. To accelerate advances and application of QSP with consistent quality, a list of key questions is proposed to be addressed when assessing the quality of a QSP model in hopes of stimulating the scientific community to set common expectations. The common expectations as to what constitutes the best QSP modeling practices, which the scientific community supports, will advance QSP modeling in the realm of informed drug development. In the long run, good practices will extend the life cycles of QSP models beyond the life cycles of individual drugs.

Quantitative systems pharmacology (QSP) is a quantitative and mechanistic platform describing the phenotypic interaction between drugs, biological networks, and disease conditions to predict optimal therapeutic response. In this meta-analysis study, we review the utility of the QSP platform in drug development and therapeutic strategies based on recent publications (2019–2021). We gathered recent original QSP models and described the diversity of their applications based on therapeutic areas, methodologies, software platforms, and functionalities. The collection and investigation of these publications can assist in providing a repository of recent QSP studies to facilitate the discovery and further reusability of QSP models. Our review shows that the largest number of QSP efforts in recent years is in Immuno-Oncology. We also addressed the benefits of integrative approaches in this field by presenting the applications of Machine Learning methods for drug discovery and QSP models. Based on this meta-analysis, we discuss the advantages and limitations of QSP models and propose fields where the QSP approach constitutes a valuable interface for more investigations to tackle complex diseases and improve drug development.

Rare diseases, affecting millions globally, present significant drug development challenges. This is due to the limited patient populations and the unique pathophysiology of these diseases, which can make traditional clinical trial designs unfeasible. Quantitative Systems Pharmacology (QSP) models offer a promising approach to expedite drug development, particularly in rare diseases. QSP models provide a mechanistic representation of the disease and drug response in virtual patients that can complement routinely applied empirical modeling and simulation approaches. QSP models can generate digital twins of actual patients and mechanistically simulate the disease progression of rare diseases, accounting for phenotypic heterogeneity. QSP models can also support drug development in various drug modalities, such as gene therapy. Impactful QSP models case studies are presented here to illustrate their value in supporting various aspects of drug development in rare indications. As these QSP model applications continue to mature, there is a growing possibility that they could be more widely integrated into routine drug development steps. This integration could provide a robust framework for addressing some of the inherent challenges in rare disease drug development.

Quantitative systems pharmacology (QSP) modeling is applied to address essential questions in drug development, such as the mechanism of action of a therapeutic agent and the progression of disease. Meanwhile, machine learning (ML) approaches also contribute to answering these questions via the analysis of multi-layer ‘omics’ data such as gene expression, proteomics, metabolomics, and high-throughput imaging. Furthermore, ML approaches can also be applied to aspects of QSP modeling. Both approaches are powerful tools and there is considerable interest in integrating QSP modeling and ML. So far, a few successful implementations have been carried out from which we have learned about how each approach can overcome unique limitations of the other. The QSP + ML working group of the International Society of Pharmacometrics QSP Special Interest Group was convened in September, 2019 to identify and begin realizing new opportunities in QSP and ML integration. The working group, which comprises 21 members representing 18 academic and industry organizations, has identified four categories of current research activity which will be described herein together with case studies of applications to drug development decision making. The working group also concluded that the integration of QSP and ML is still in its early stages of moving from evaluating available technical tools to building case studies. This paper reports on this fast-moving field and serves as a foundation for future codification of best practices.

The goal of this collaboration was to provide early quantitative decision making guidance for the project team by developing and interrogating a quantitative systems pharmacology (QSP) model of the co-modulation inhibitory receptors PD-1 and TIM-3 in immuno-oncology. The QSP model was to: (1) provide predictions of the best-in-class profile for a PD-1 and TIM-3 dual antagonist, (2) accelerate project timelines, (3) provide biological insights, and (4) reduce experimental costs. The QSP model was based on first principles as a system of elementary mass-action, mechanistic PKPD, ordinary differential equations. The model parameters and reactions were based on biophysics, and are interpretable. The model reactions include protein synthesis and elimination, ligand-receptor and drug-target formation and turnover, and drug administration and first order clearance. There were four versions of the model: PD-1 monospecific, TIM-3 monospecific, PD-1 x TIM-3 bispecific and fixed dose combination (FDC) targeting PD-1 and TIM-3. The monospecific models were then benchmarked against published data such that model parameter values were set to known values and unknown parameters were estimated. Once benchmarked, the FDC and bispecific models were analyzed by systematically investigating how tuning the model parameters (e.g., affinity, avidity, dose, half-life, target expression, etc.) impacted target inhibition, and to simulate patient variability. The model was in good agreement with published clinical data from nivolumab and pembrolizumab, and data from RMT3-23 in the TIM-3 driven mouse model. QSP model analysis predicted: (1) there would be diminishing returns on very tight binding biologics due to Target Mediated Drug Disposition (TMDD) that offsets potency, and (2) there is no advantage between FDC, 2-2 bispecific, and 2-1 bispecific formats, which are predicted to be roughly equivalent. As a result of these analyses, there was a significant reduction in the number of experiments, and acceleration of project timelines by (1) eliminating rounds of affinity maturation, as drug leads were in predicted optimal drug parameter ranges, and (2) eliminating the need to construct and evaluate bi-specific constructs and proceed with FDCs. Citation Format: Joshua F. Apgar, Jamie Wong, Ryan Ryan Phennicie, Mike Briskin, John M. Burke. Quantitative systems pharmacology approaches accelerate lead generation and optimization of a PD-1 x TIM-3 therapeutic in immuno-oncology. [abstract]. In: Proceedings of the AACR-NCI-EORTC International Conference: Molecular Targets and Cancer Therapeutics; 2015 Nov 5-9; Boston, MA. Philadelphia (PA): AACR; Mol Cancer Ther 2015;14(12 Suppl 2):Abstract nr A151.

AZD5305 is a potent and selective PARP1 inhibitor and trapper which is hypothesized to improve therapeutic index over first generation nonselective PARP inhibitors. AZD5305 demonstrated significant and sustained antitumor activity in multiple BRCA1/2 mutant xenograft models. Here we present a mechanistic Quantitative Systems Pharmacology (QSP) model to analyze dose-dependent antitumor activity of AZD5305 (0.01-10 mg/kg) across a selection of xenograft models with different homologous recombination repair (HRR) status (Capan-1, DLD-1 BRCA2 KO, HBCx-9, HBCx-17, MDA-MB-436 and SUM149PT). A QSP model was developed based on a system of ordinary differential equations (ODEs) to address formation and repair of trapped PARP-DNA fragments and longitudinal changes in tumor size as a function of pharmacokinetic (PK) profiles in individual animals. Tumor growth data as well as intratumoral PARylation inhibition from xenograft models were utilized for model development and qualification. Model parameters characterizing intrinsic tumor growth and cancer cell sensitivity to accumulated DNA damage, were set to be different across xenograft models, to provide unbiased data reproduction. Sensitivity analyses were performed to identify model parameters which have the most impact on differential antitumor activity observed across various xenograft models. Maximal antitumor efficacy was seen at 0.1 to 1 mg/kg AZD5305, depending on the tumor model. Exposures at 1 mg/kg were similar to those causing peak PARP1 trapping in vitro. The QSP model adequately captures antitumor activity across different xenograft models. Simulations indicate antitumor activity of AZD5305 was driven mainly by differences in the HRR status-related model parameter (khrr). Xenograft models with HRR deficiency such as HBCx-17, DLD-1 BRCA2 KO and MDA-MB-436 (with a very low khrr) were the most sensitive to AZD5305 and treatment led to tumor regressions. In contrast, tumor models with partial sensitivity, such as HBCx-9, Capan-1, SUM149PT (with khrr up to 1000-fold higher than in the sensitive tumors), AZD5305 only achieved tumor growth inhibition. Dosing AZD5305 at 0.03 mg/kg daily was associated with tumor regression in HBCx-17 and MDA-MB-436 xenografts, whereas 1 mg/kg daily dosing was required to achieve tumor regression in the DLD-1 BRCA2 KO model, and maximal tumor growth inhibition in less sensitive models. Further biomarker analyses to assess functional HRR status (e.g. via RAD51 foci score) in these xenograft models is ongoing to validate model estimated khrr parameters. The calibrated model was used to predict antitumor activity of AZD5305 at clinically relevant exposures observed in the phase I clinical study PETRA. Model-based simulations indicated near maximal efficacy at clinical doses equivalent to 1 mg/kg AZD5305 exposure in xenograft models. Citation Format: Ganesh Moorthy, Veronika Voronova, Cesar Pichardo, Kirill Peskov, Giuditta Illuzzi, Anna Staniszewska, Mark Albertella, Holly Kimko. A Quantitative Systems Pharmacology (QSP) model to characterize dose-dependent antitumor activity of AZD5305, PARP1 selective inhibitor, across multiple xenograft models [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 2794.

Quantitative Systems Pharmacology (QSP) has emerged as a cornerstone of modern drug development, providing a robust framework to integrate data from preclinical and clinical studies, enhance decision-making, and optimize therapeutic strategies. By modeling biological systems and drug interactions, QSP enables predictions of outcomes, optimization of dosing regimens, and personalized medicine applications. Recent advancements in artificial intelligence (AI) and machine learning (ML) hold the potential to significantly transform QSP by enabling enhanced data extraction, fostering the development of hybrid mechanistic ML models, and supporting the introduction of surrogate models and digital twins. This manuscript explores the transformative role of AI and ML in reshaping QSP modeling workflows. AI/ML tools now enable automated literature mining, the generation of dynamic models from data, and the creation of hybrid frameworks that blend mechanistic insights with data-driven approaches. Large Language Models (LLMs) further revolutionize the field by transitioning AI/ML from merely a tool to becoming an active partner in QSP modeling. By facilitating interdisciplinary collaboration, lowering barriers to entry, and democratizing QSP workflows, LLMs empower researchers without deep coding expertise to engage in complex modeling tasks. Additionally, the integration of Artificial General Intelligence (AGI) holds the potential to autonomously propose, refine, and validate models, further accelerating innovation across multiscale biological processes. Key challenges remain in integrating AI/ML into QSP workflows, particularly in ensuring rigorous validation pipelines, addressing ethical considerations, and establishing robust regulatory frameworks to address the reliability and reproducibility of AI-assisted models. Moreover, the complexity of multiscale biological integration, effective data management, and fostering interdisciplinary collaboration present ongoing hurdles. Despite these challenges, the potential of AI/ML to enhance hybrid model development, improve model interpretability, and democratize QSP modeling offers an exciting opportunity to revolutionize drug development and therapeutic innovation. This work highlights a pathway toward a transformative era for QSP, leveraging advancements in AI and ML to address these challenges and drive innovation in the field.

A workshop on artificial intelligence and machine learning (AI/ML) for advanced reactors (AR) was held October 5-6, 2021. The workshop was to be attended in-person at ANL but COVID restrictions forced the workshop to go virtual. The objectives of the workshop were to identify the most promising AI/ML opportunities for improving advanced reactor design, optimizing plant performance, and enhancing economic competitiveness and to develop an understanding of the scientific, engineering and licensing challenges facing their application. The workshop planning committee included GAIN, EPRI and NEI and members of three national laboratories (ANL, INL, and ORNL). The workshop was attended by more than 200 individuals representing academic and scientific institutions and the nuclear power industry. The definition put forth for an AI/ML system was one that perceives its environment and takes actions that maximize its chance of achieving its goals. In this report AI/ML refers to next generation algorithms that include deep learning, statistical analysis and data analytics and associated scientific computing and their potential application to the design, licensing, operation and maintenance of ARs. These methods typically incorporate models built from process data and may also include data generated by simulations that represent the behavior of a system. The workshop was organized in response to the growing interest in application of AI/ML for improving the economic competitiveness of nuclear energy. Increasingly more resources are being allocated to investigating the benefits of AI/ML methods. The DOE created the Artificial Intelligence & Technology Office to promote their development. And within the Office of Nuclear Energy, resources have been allocated to explore and understand the potential benefits of AI/ML. Additionally, the national laboratories are strategically positioned with DOE computing facilities such as Summit, Perlmutter, Aurora and Frontier that support large-scale simulations, hybrid HPC models with AI surrogates, and the exploration of new types of generative models emerging from multi-model data streams and sources. The workshop was organized with members of the AR community to understand the effort and to identify the level of interest and progress in this emerging technology. The workshop discussions focused on identifying opportunities for AI/ML across diverse areas of the nuclear industry and identifying current scientific and engineering challenges for advanced reactors that might be addressed through transformational uses of AI/ML. Discussion panels focused on four high-interest technical domains for advanced reactors: design, maintenance and operations, energy storage, and materials. The results of those discussions are summarized in this report. This includes opportunities that were identified for exploiting AI techniques and methods to improve the efficacy and efficiency of reactor analysis and to improve the operation and optimization of advanced reactors. Advanced reactor developers expressed an interest in learning more about AI/ML methods and their application. This included understanding whether ML methods can provide an advantage over existing nonlinear data regression methods for collapsing high-fidelity simulation results into faster running models. A consensus emerged that AR advances planned for the next decade will benefit from the use of AI/ML tools. The need exists to understand and model complex systems across length scales and modalities. AI/ML is a tool for discovery that can yield a set of engineering principles for use by nuclear engineers, licensing bodies, and operators to solve problems in plant design, safety analyses, autonomous operation, and predictive maintenance. While AI/ML represents a new set of tools, an awareness by the nuclear community of the full potential is still in the early stages so there is a need to increase awareness. It appears that the wide-spread a

.PurposeTo introduce developers to medical device regulatory processes and data considerations in artificial intelligence and machine learning (AI/ML) device submissions and to discuss ongoing AI/ML-related regulatory challenges and activities.ApproachAI/ML technologies are being used in an increasing number of medical imaging devices, and the fast evolution of these technologies presents novel regulatory challenges. We provide AI/ML developers with an introduction to U.S. Food and Drug Administration (FDA) regulatory concepts, processes, and fundamental assessments for a wide range of medical imaging AI/ML device types.ResultsThe device type for an AI/ML device and appropriate premarket regulatory pathway is based on the level of risk associated with the device and informed by both its technological characteristics and intended use. AI/ML device submissions contain a wide array of information and testing to facilitate the review process with the model description, data, nonclinical testing, and multi-reader multi-case testing being critical aspects of the AI/ML device review process for many AI/ML device submissions. The agency is also involved in AI/ML-related activities that support guidance document development, good machine learning practice development, AI/ML transparency, AI/ML regulatory research, and real-world performance assessment.ConclusionFDA’s AI/ML regulatory and scientific efforts support the joint goals of ensuring patients have access to safe and effective AI/ML devices over the entire device lifecycle and stimulating medical AI/ML innovation.

Artificial intelligence and machine learning (AI/ML) have attracted a great deal of attention from the atmospheric science community. The explosion of attention on AI/ML development carries implications for the operational community, prompting questions about how novel AI/ML advancements will translate from research into operations. However, the field lacks empirical evidence on how National Weather Service (NWS) forecasters, as key intended users, perceive AI/ML and its use in operational forecasting. This study addresses this crucial gap through structured interviews conducted with 29 NWS forecasters from October 2021 through July 2023 in which we explored their perceptions of AI/ML in forecasting. We found that forecasters generally prefer the term “machine learning” over “artificial intelligence” and that labeling a product as being AI/ML did not hurt perceptions of the products and made some forecasters more excited about the product. Forecasters also had a wide range of familiarity with AI/ML, and overall, they were (tentatively) open to the use of AI/ML in forecasting. We also provide examples of specific areas related to AI/ML that forecasters are excited or hopeful about and that they are concerned or worried about. One concern that was raised in several ways was that AI/ML could replace forecasters or remove them from the forecasting process. However, forecasters expressed a widespread and deep commitment to the best possible forecasts and services to uphold the agency mission using whatever tools or products that are available to assist them. Last, we note how forecasters’ perceptions evolved over the course of the study.

Immuno-oncology (IO) is a fast-expanding field due to recent success using IO therapies in treating cancer. As IO therapies do not directly kill tumor cells but rather act upon the patients' own immune cells either systemically or in the tumor microenvironment, new and innovative approaches are required to inform IO therapy research and development. Quantitative systems pharmacology (QSP) modeling describes the biological mechanisms of disease and the mode of action of drugs with mathematical equations, which has significant potential to address the big challenges in the IO field, from identifying patient populations that respond to different therapies to guiding the selection, dosing, and scheduling of combination therapy. To assess the perspectives of the community on the impact of QSP modeling in IO drug development and to understand current applications and challenges, the IO QSP working group-under the QSP Special Interest Group (SIG) of the International Society of Pharmacometrics (ISoP)-conducted a survey among QSP modelers, non-QSP modelers, and non-modeling IO program stakeholders. The survey results are presented here with discussions on how to address some of the findings. One of the findings is the differences in perception among these groups. To help bridge this perception gap, we present several case studies demonstrating the impact of QSP modeling in IO and suggest actions that can be taken in the future to increase the real and perceived impact of QSP modeling in IO drug research and development.