A Dynamic Quantitative Systems Pharmacology Model of Inflammatory Bowel Disease: Part 1 - Model Framework

Machine Learning for Predicting Biologic Agent Efficacy in Ulcerative Colitis: An Analysis for Generalizability and Combination with Computational Models

Machine learning (ML) has been applied to predict the efficacy of biologic agents in ulcerative colitis (UC). ML can offer precision, personalization, efficiency, and automation. Moreover, it can improve decision support in predicting clinical outcomes. However, it faces challenges related to data quality and quantity, overfitting, generalization, and interpretability. This paper comments on two recent ML models that predict the efficacy of vedolizumab and ustekinumab in UC. Models that consider multiple pathways, multiple ethnicities, and combinations of real-world and clinical trial data are required for optimal shared decision-making and precision medicine. This paper also highlights the potential of combining ML with computational models to enhance clinical outcomes and personalized healthcare. Key Insights: (1) ML offers precision, personalization, efficiency, and decision support for predicting the efficacy of biologic agents in UC. (2) Challenging aspects in ML prediction include data quality, overfitting, and interpretability. (3) Multiple pathways, multiple ethnicities, and combinations of real-world and clinical trial data should be considered in predictive models for optimal decision-making. (4) Combining ML with computational models may improve clinical outcomes and personalized healthcare.

Mathematical modeling in autoimmune diseases: from theory to clinical application

The research & development (R&D) of novel therapeutic agents for the treatment of autoimmune diseases is challenged by highly complex pathogenesis and multiple etiologies of these conditions. The number of targeted therapies available on the market is limited, whereas the prevalence of autoimmune conditions in the global population continues to rise. Mathematical modeling of biological systems is an essential tool which may be applied in support of decision-making across R&D drug programs to improve the probability of success in the development of novel medicines. Over the past decades, multiple models of autoimmune diseases have been developed. Models differ in the spectra of quantitative data used in their development and mathematical methods, as well as in the level of "mechanistic granularity" chosen to describe the underlying biology. Yet, all models strive towards the same goal: to quantitatively describe various aspects of the immune response. The aim of this review was to conduct a systematic review and analysis of mathematical models of autoimmune diseases focused on the mechanistic description of the immune system, to consolidate existing quantitative knowledge on autoimmune processes, and to outline potential directions of interest for future model-based analyses. Following a systematic literature review, 38 models describing the onset, progression, and/or the effect of treatment in 13 systemic and organ-specific autoimmune conditions were identified, most models developed for inflammatory bowel disease, multiple sclerosis, and lupus (5 models each). ≥70% of the models were developed as nonlinear systems of ordinary differential equations, others - as partial differential equations, integro-differential equations, Boolean networks, or probabilistic models. Despite covering a relatively wide range of diseases, most models described the same components of the immune system, such as T-cell response, cytokine influence, or the involvement of macrophages in autoimmune processes. All models were thoroughly analyzed with an emphasis on assumptions, limitations, and their potential applications in the development of novel medicines.

Machine learning using clinical data at baseline predicts the medium-term efficacy of ustekinumab in patients with ulcerative colitis

Predicting the therapeutic response to biologics before administration is a key clinical challenge in ulcerative colitis (UC). We previously reported a model for predicting the efficacy of vedolizumab (VDZ) for UC using a machine-learning approach. Ustekinumab (UST) is now available for treating UC, but no model for predicting its efficacy has been developed. When applied to patients with UC treated with UST, our VDZ prediction model showed positive predictive value (PPV) of 56.3% and negative predictive value (NPV) of 62.5%. Given this limited predictive ability, we aimed to develop a UST-specific prediction model with clinical features at baseline including background factors, clinical and endoscopic activity, and blood test results, as we did for the VDZ prediction model. The top 10 features (Alb, monocytes, height, MCV, TP, Lichtiger index, white blood cell count, MCHC, partial Mayo score, and CRP) associated with steroid-free clinical remission at 6 months after starting UST were selected using random forest. The predictive ability of a model using these predictors was evaluated by fivefold cross-validation. Validation of the prediction model with an external cohort showed PPV of 68.8% and NPV of 71.4%. Our study suggested the importance of establishing a drug-specific prediction model.

A Quantitative Systems Pharmacology Model Describing the Cellular Kinetic-Pharmacodynamic Relationship for a Live Biotherapeutic Product to Support Microbiome Drug Development

Live biotherapeutic products (LBPs) are human microbiome therapies showing promise in the clinic for a range of diseases and conditions. Describing the kinetics and behavior of LBPs poses a unique modeling challenge because, unlike traditional therapies, LBPs can expand, contract, and colonize the host digestive tract. Here, we present a novel cellular kinetic-pharmacodynamic quantitative systems pharmacology model of an LBP. The model describes bacterial growth and competition, vancomycin effects, binding and unbinding to the epithelial surface, and production and clearance of butyrate as a therapeutic metabolite. The model is calibrated and validated to published data from healthy volunteers. Using the model, we simulate the impact of treatment dose, frequency, and duration as well as vancomycin pretreatment on butyrate production. This model enables model-informed drug development and can be used for future microbiome therapies to inform decision making around antibiotic pretreatment, dose selection, loading dose, and dosing duration.

A quantitative systems pharmacology model of the pathophysiology and treatment of COVID-19 predicts optimal timing of pharmacological interventions

A quantitative systems pharmacology (QSP) model of the pathogenesis and treatment of SARS-CoV-2 infection can streamline and accelerate the development of novel medicines to treat COVID-19. Simulation of clinical trials allows in silico exploration of the uncertainties of clinical trial design and can rapidly inform their protocols. We previously published a preliminary model of the immune response to SARS-CoV-2 infection. To further our understanding of COVID-19 and treatment, we significantly updated the model by matching a curated dataset spanning viral load and immune responses in plasma and lung. We identified a population of parameter sets to generate heterogeneity in pathophysiology and treatment and tested this model against published reports from interventional SARS-CoV-2 targeting mAb and antiviral trials. Upon generation and selection of a virtual population, we match both the placebo and treated responses in viral load in these trials. We extended the model to predict the rate of hospitalization or death within a population. Via comparison of the in silico predictions with clinical data, we hypothesize that the immune response to virus is log-linear over a wide range of viral load. To validate this approach, we show the model matches a published subgroup analysis, sorted by baseline viral load, of patients treated with neutralizing Abs. By simulating intervention at different time points post infection, the model predicts efficacy is not sensitive to interventions within five days of symptom onset, but efficacy is dramatically reduced if more than five days pass post symptom onset prior to treatment.

CYTOCON: The manually curated database of human in vivo cell and molecule concentrations

Cell and cYTOkine CONcentrations DataBase (CYTOCON DB) is a project undertaken by the InSysBio team and aimed at the development of a database that allows collecting, processing, and visualizing publicly available in vivo human data on baseline concentrations of cells, cytokines, chemokines, and other molecules. Besides manual curation, an important feature of CYTOCON is that most values found in papers are converted from a huge variety of original units (i.e., mg/ml and number of cells per mm² of biopsy surface section) to unified units: "pM" for cytokine and "kcell/L" for cell concentration. These features of the database can help researchers facilitate the creation and calibration of quantitative systems pharmacology (QSP) models. Possible applications can be: estimation of the average value or variability of the cell, cytokine or chemokine concentrations for patient groups with different characteristics, such as age, gender, disease severity, disease subtype, etc.; and analysis of correlations among the cell, cytokine, or chemokine concentrations in patients with different characteristics, such as severity of the disease.

Under the Umbrella of Clinical Pharmacology: Inflammatory Bowel Disease, Infliximab and Adalimumab, and a Bridge to an Era of Biosimilars

Monoclonal antibodies (MAbs) have revolutionized the treatment of many chronic inflammatory diseases, including inflammatory bowel disease (IBD). IBD is a term that comprises two quite similar, yet distinctive, disorders—Crohn’s disease (CD) and ulcerative colitis (UC). Two blockbuster MAbs, infliximab (IFX) and adalimumab (ADL), transformed the pharmacological approach of treating CD and UC. However, due to the complex interplay of pharmacology and immunology, MAbs face challenges related to their immunogenicity, effectiveness, and safety. To ease the burden of IBD and other severe diseases, biosimilars have emerged as a cost-effective alternative to an originator product. According to the current knowledge, biosimilars of IFX and ADL in IBD patients are shown to be as safe and effective as their originators. The future of biosimilars, in general, is promising due to the potential of making the health care system more sustainable. However, their use is accompanied by misconceptions regarding their effectiveness and safety, as well as by controversy regarding their interchangeability. Hence, until a scientific consensus is achieved, scientific data on the long-term effectiveness and safety of biosimilars are needed.

Current practices for QSP model assessment: an IQ consortium survey

Quantitative Systems Pharmacology (QSP) modeling is increasingly applied in the pharmaceutical industry to influence decision making across a wide range of stages from early discovery to clinical development to post-marketing activities. Development of standards for how these models are constructed, assessed, and communicated is of active interest to the modeling community and regulators but is complicated by the wide variability in the structures and intended uses of the underlying models and the diverse expertise of QSP modelers. With this in mind, the IQ Consortium conducted a survey across the pharmaceutical/biotech industry to understand current practices for QSP modeling. This article presents the survey results and provides insights into current practices and methods used by QSP practitioners based on model type and the intended use at various stages of drug development. The survey also highlights key areas for future development including better integration with statistical methods, standardization of approaches towards virtual populations, and increased use of QSP models for late-stage clinical development and regulatory submissions.

Recent Advances in Translational Pharmacokinetics and Pharmacodynamics Prediction of Therapeutic Antibodies Using Modeling and Simulation

Therapeutic monoclonal antibodies (mAbs) have been a promising therapeutic approach for several diseases and a wide variety of mAbs are being evaluated in clinical trials. To accelerate clinical development and improve the probability of success, pharmacokinetics and pharmacodynamics (PKPD) in humans must be predicted before clinical trials can begin. Traditionally, empirical-approach-based PKPD prediction has been applied for a long time. Recently, modeling and simulation (M&S) methods have also become valuable for quantitatively predicting PKPD in humans. Although several models (e.g., the compartment model, Michaelis–Menten model, target-mediated drug disposition model, and physiologically based pharmacokinetic model) have been established and used to predict the PKPD of mAbs in humans, more complex mechanistic models, such as the quantitative systemics pharmacology model, have been recently developed. This review summarizes the recent advances and future direction of M&S-based approaches to the quantitative prediction of human PKPD for mAbs.

Computational models in inflammatory bowel disease

Inflammatory bowel disease (IBD) is a chronic and relapsing disease with multiple underlying influences and notable heterogeneity among its clinical and response-to-treatment phenotypes. There is no cure for IBD, and none of the currently available therapies have demonstrated clinical efficacies beyond 40%-60%. Data collected about its omics, pathogenesis, and treatment strategies have grown exponentially with time making IBD a prime candidate for artificial intelligence (AI) mediated discovery support. AI can be leveraged to further understand or identify IBD features to improve clinical outcomes. Various treatment candidates are currently under evaluation in clinical trials, offering further approaches and opportunities for increasing the efficacies of treatments. However, currently, therapeutic plans are largely determined using clinical features due to the lack of specific biomarkers, and it has become necessary to step into precision medicine to predict therapeutic responses to guarantee optimal treatment efficacy. This is accompanied by the application of AI and the development of multiscale hybrid models combining mechanistic approaches and machine learning. These models ultimately lead to the creation of digital twins of given patients delivering on the promise of precision dosing and tailored treatment. Interleukin-6 (IL-6) is a prominent cytokine in cell-to-cell communication in the inflammatory responses' regulation. Dysregulated IL-6-induced signaling leads to severe immunological or proliferative pathologies, such as IBD and colon cancer. This mini-review explores multiscale models with the aim of predicting the response to therapy in IBD. Modeling IL-6 biology and generating digital twins enhance the credibility of their prediction.

A Computational Platform Integrating a Mechanistic Model of Crohn's Disease for Predicting Temporal Progression of Mucosal Damage and Healing

INTRODUCTION

Physicians are often required to make treatment decisions for patients with Crohn's disease on the basis of limited objective information about the state of the patient's gastrointestinal tissue while aiming to achieve mucosal healing. Tools to predict changes in mucosal health with treatment are needed. We evaluated a computational approach integrating a mechanistic model of Crohn's disease with a responder classifier to predict temporal changes in mucosal health.

METHODS

A hybrid mechanistic-statistical platform was developed to predict biomarker and tissue health time courses in patients with Crohn's disease. Eligible patients from the VERSIFY study (n = 69) were classified into archetypical response cohorts using a decision tree based on early treatment data and baseline characteristics. A virtual patient matching algorithm assigned a digital twin to each patient from their corresponding response cohort. The digital twin was used to forecast response to treatment using the mechanistic model.

RESULTS

The responder classifier predicted endoscopic remission and mucosal healing for treatment with vedolizumab over 26 weeks, with overall sensitivities of 80% and 75% and overall specificities of 69% and 70%, respectively. Predictions for changes in tissue damage over time in the validation set (n = 31), a measure of the overall performance of the platform, were considered good (at least 70% of data points matched), fair (at least 50%), and poor (less than 50%) for 71%, 23%, and 6% of patients, respectively.

CONCLUSION

Hybrid computational tools including mechanistic components represent a promising form of decision support that can predict outcomes and patient progress in Crohn's disease.

Recent applications of quantitative systems pharmacology and machine learning models across diseases

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.