Application of machine learning approaches for predicting hemophilia A severity.

BACKGROUND: Hemophilia A (HA) is an X-linked congenital bleeding disorder, which leads to deficiency of clotting factor (F) VIII. It mostly affects males, and females are considered carriers. However, it is now recognized that variants of F8 in females can result in HA. Nonetheless, most females go undiagnosed and untreated for HA, and their bleeding complications are attributed to other causes. Predicting the severity of HA for female patients can provide valuable insights for treating the conditions associated with the disease, such as heavy bleeding. OBJECTIVES: To predict the severity of HA based on F8 genotype using a machine learning (ML) approach. METHODS: Using multiple datasets of variants in the F8 and disease severity from various repositories, we derived the sequence for the FVIII protein. Using the derived sequences, we used ML models to predict the severity of HA in female patients. RESULTS: Utilizing different classification models, we highlight the validity of the datasets and our approach with predictive F1 scores of 0.88, 0.99, 0.93, 0.99, and 0.90 for all the validation sets. CONCLUSION: Although with some limitations, ML-based approaches demonstrated the successful prediction of disease severity in female HA patients based on variants in the F8. This study confirms previous research findings that ML can help predict the severity of hemophilia. These results can be valuable for future studies in achieving better treatment and clinical outcomes for female patients with HA, which is an urgent unmet need.

Engineering and evaluation of FXa bypassing agents that restore hemostasis following Apixaban associated bleeding.

Direct oral anticoagulants (DOACs) targeting activated factor Xa (FXa) are used to prevent or treat thromboembolic disorders. DOACs reversibly bind to FXa and inhibit its enzymatic activity. However, DOAC treatment carries the risk of anticoagulant-associated bleeding. Currently, only one specific agent, andexanet alfa, is approved to reverse the anticoagulant effects of FXa-targeting DOACs (FXaDOACs) and control life-threatening bleeding. However, because of its mechanism of action, andexanet alfa requires a cumbersome dosing schedule, and its use is associated with the risk of thrombosis. Here, we present the computational design, engineering, and evaluation of FXa-variants that exhibit anticoagulation reversal activity in the presence of FXaDOACs. Our designs demonstrate low DOAC binding affinity, retain FXa-enzymatic activity and reduce the DOAC-associated bleeding by restoring hemostasis in mice treated with apixaban. Importantly, the FXaDOACs reversal agents we designed, unlike andexanet alfa, do not inhibit TFPI, and consequently, may have a safer thrombogenic profile.

Investigation of thrombin concentration at the time of clot formation in simultaneous thrombin and fibrin generation assays.

Thrombin generation (TG) and fibrin clot formation represent the central process of blood coagulation. Up to 95% of thrombin is considered to be generated after the clot is formed. However, this was not investigated in depth. In this study, we conducted a quantitative analysis of the Thrombin at Clot Time (TCT) parameter in 5758 simultaneously recorded TG and clot formation assays using frozen plasma samples from commercial sources under various conditions of activation. These samples were supplemented with clotting factor concentrates, procoagulant lipid vesicles and a fluorogenic substrate and triggered with tissue factor (TF). We found that TCT is often close to a 10% of thrombin peak height (TPH) yet it can be larger or smaller depending on whether the sample has low or high TPH value. In general, the samples with high TPH are associated with elevated TCT. TCT appeared more sensitive to some procoagulant phenotypes than other commonly used parameters such as clotting time, TPH or Thrombin Production Rate (TPR). In a minority of cases, TCT were not predicted from TG parameters. For example, elevated TCT (above 15% of TPH) was associated with either very low or very high TPR values. We conclude that clotting and TG assays may provide complementary information about the plasma sample, and that the TCT parameter may serve as an additional marker for the procoagulant potential in plasma sample.

Factor VIII moiety of recombinant Factor VIII Fc fusion protein impacts Fc effector function and CD16+ NK cell activation.

Recombinant Factor VIII-Fc fusion protein (rFVIIIFc) is an enhanced half-life therapeutic protein product used for the management of hemophilia A. Recent studies have demonstrated that rFVIIIFc interacts with Fc gamma receptors (FcγR) resulting in the activation or inhibition of various FcγR-expressing immune cells. We previously demonstrated that rFVIIIFc, unlike recombinant Factor IX-Fc (rFIXFc), activates natural killer (NK) cells via Fc-mediated interactions with FcγRIIIA (CD16). Additionally, we showed that rFVIIIFc activated CD16+ NK cells to lyse a FVIII-specific B cell clone. Here, we used human NK cell lines and primary NK cells enriched from peripheral blood leukocytes to study the role of the FVIII moiety in rFVIIIFc-mediated NK cell activation. Following overnight incubation of NK cells with rFVIIIFc, cellular activation was assessed by measuring secretion of the inflammatory cytokine IFNγ by ELISA or by cellular degranulation. We show that anti-FVIII, anti-Fc, and anti-CD16 all inhibited indicating that these molecules were involved in rFVIIIFc-mediated NK cell activation. To define which domains of FVIII were involved, we used antibodies that are FVIII domain-specific and demonstrated that blocking FVIII C1 or C2 domain-mediated membrane binding potently inhibited rFVIIIFc-mediated CD16+ NK cell activation, while targeting the FVIII heavy chain domains did not. We also show that rFVIIIFc binds CD16 with about five-fold higher affinity than rFIXFc. Based on our results we propose that FVIII light chain-mediated membrane binding results in tethering of the fusion protein to the cell surface, and this, together with increased binding affinity for CD16, allows for Fc-CD16 interactions to proceed, resulting in NK cellular activation. Our working model may explain our previous results where we observed that rFVIIIFc activated NK cells via CD16, whereas rFIXFc did not despite having identical IgG1 Fc domains.

Dose optimization of an adjuvanted peptide-based personalized neoantigen melanoma vaccine.

The advancements in next-generation sequencing have made it possible to effectively detect somatic mutations, which has led to the development of personalized neoantigen cancer vaccines that are tailored to the unique variants found in a patient's cancer. These vaccines can provide significant clinical benefit by leveraging the patient's immune response to eliminate malignant cells. However, determining the optimal vaccine dose for each patient is a challenge due to the heterogeneity of tumors. To address this challenge, we formulate a mathematical dose optimization problem based on a previous mathematical model that encompasses the immune response cascade produced by the vaccine in a patient. We propose an optimization approach to identify the optimal personalized vaccine doses, considering a fixed vaccination schedule, while simultaneously minimizing the overall number of tumor and activated T cells. To validate our approach, we perform in silico experiments on six real-world clinical trial patients with advanced melanoma. We compare the results of applying an optimal vaccine dose to those of a suboptimal dose (the dose used in the clinical trial and its deviations). Our simulations reveal that an optimal vaccine regimen of higher initial doses and lower final doses may lead to a reduction in tumor size for certain patients. Our mathematical dose optimization offers a promising approach to determining an optimal vaccine dose for each patient and improving clinical outcomes.

Proceedings of the 14th European immunogenicity platform open symposium on immunogenicity of biopharmaceuticals.

Biologics have revolutionized disease management in many therapeutic areas by addressing unmet medical needs and overcoming resistance to standard-of-care treatment in numerous patients. However, the development of unwanted immune responses directed against these drugs, humoral and/or cellular, can hinder their efficacy and have safety consequences with various degrees of severity. Health authorities ask that a thorough immunogenicity risk assessment be conducted during drug development to incorporate an appropriate monitoring and mitigation plan in clinical studies. With the rapid diversification and complexification of biologics, which today include modalities such as multi-domain antibodies, cell-based products, AAV delivery vectors, and nucleic acids, developers are faced with the challenge of establishing a risk assessment strategy sometimes in the absence of specific regulatory guidelines. The European Immunogenicity Platform (EIP) Open Symposium on Immunogenicity of Biopharmaceuticals and its one-day training course gives experts and newcomers across academia, industry, and regulatory agencies an opportunity to share experience and knowledge to overcome these challenges. Here, we report the discussions that took place at the EIP's 14th Symposium, held in April 2023. The topics covered included immunogenicity monitoring and clinical relevance, non-clinical immunogenicity risk assessment, regulatory aspects of immunogenicity assessment and reporting, and the challenges associated with new modalities, which were discussed in a dedicated session.

The MHC Associated Peptide Proteomics assay is a useful tool for the non-clinical assessment of immunogenicity.

The propensity of therapeutic proteins to elicit an immune response, poses a significant challenge in clinical development and safety of the patients. Assessment of immunogenicity is crucial to predict potential adverse events and design safer biologics. In this study, we employed MHC Associated Peptide Proteomics (MAPPS) to comprehensively evaluate the immunogenic potential of re-engineered variants of immunogenic FVIIa analog (Vatreptacog Alfa). Our finding revealed the correlation between the protein sequence affinity for MHCII and the number of peptides identified in a MAPPS assay and this further correlates with the reduced T-cell responses. Moreover, MAPPS enable the identification of "relevant" T cell epitopes and may contribute to the development of biologics with lower immunogenic potential.

Emerging approaches to induce immune tolerance to therapeutic proteins.

Immunogenicity affects the safety and efficacy of therapeutic proteins. This review is focused on approaches for inducing immunological tolerance to circumvent the immunogenicity of therapeutic proteins in the clinic. The few immune tolerance strategies that are used in the clinic tend to be inefficient and expensive and typically involve global immunosuppression, putting patients at risk of infections. The hallmark of a desirable immune tolerance regimen is the specific alleviation of immune responses to the therapeutic protein. In the past decade, proof-of-principle studies have demonstrated that emerging technologies, including nanoparticle-based delivery of immunomodulators, cellular targeting and depletion, cellular engineering, gene therapy, and gene editing, can be leveraged to promote tolerance to therapeutic proteins. We discuss the potential of these novel approaches and the barriers that need to be overcome for translation into the clinic.

Corrigendum to "Computational design of nanomolar-binding antibodies specific to multiple SARS-CoV-2 variants by engineering a specificity switch of antibody 80R using RosettaAntibodyDesign (RAbD) results in potential generalizable therapeutic antibodies for novel SARS-CoV-2 virus" [Heliyon 9(4) (April 2023) e15032].

[This corrects the article DOI: 10.1016/j.heliyon.2023.e15032.].

Understanding preclinical and clinical immunogenicity risks in novel biotherapeutics development.

Immunogenicity continues to pose a challenge in the development of biotherapeutics like conventional therapeutic-proteins and monoclonal antibodies as well as emerging modalities such as gene-therapy components, gene editing, and CAR T cells. The approval of any therapeutic is based on a benefit-risk evaluation. Most biotherapeutics address serious medical conditions where the standard of care has a poor outcome. Consequently, even if immunogenicity limits the utility of the therapeutic in a sub-set of patients, the benefit-risk assessment skews in favor of approval. Some cases resulted in the discontinuation of biotherapeutics due to immunogenicity during drug development processes, This special issue presents a platform for review articles offering a critical assessment of accumulated knowledge as well as novel findings related to nonclinical risks that extend our understanding of the immunogenicity of biotherapeutics. Some of the studies in this collection leveraged assays and methodologies refined over decades to support more clinically relevant biological samples. Others have applied rapidly advancing methodologies in pathway-specific analyses to immunogenicity. Similarly, the reviews address urgent issues such as the rapidly emerging cell and gene therapies which hold immense promise but could have limited reach as a significant number of the patient population could potentially not benefit due to immunogenicity. In addition to summarizing the work presented in this special issue we have endeavored to identify areas where additional studies are required to understand the risks of immunogenicity and develop appropriate mitigation strategies.

A machine learning approach for identifying variables associated with risk of developing neutralizing antidrug antibodies to factor VIII.

A key unmet need in the management of hemophilia A (HA) is the lack of clinically validated markers that are associated with the development of neutralizing antibodies to Factor VIII (FVIII) (commonly referred to as inhibitors). This study aimed to identify relevant biomarkers for FVIII inhibition using Machine Learning (ML) and Explainable AI (XAI) using the My Life Our Future (MLOF) research repository. The dataset includes biologically relevant variables such as age, race, sex, ethnicity, and the variants in the F8 gene. In addition, we previously carried out Human Leukocyte Antigen Class II (HLA-II) typing on samples obtained from the MLOF repository. Using this information, we derived other patient-specific biologically and genetically important variables. These included identifying the number of foreign FVIII derived peptides, based on the alignment of the endogenous FVIII and infused drug sequences, and the foreign-peptide HLA-II molecule binding affinity calculated using NetMHCIIpan. The data were processed and trained with multiple ML classification models to identify the top performing models. The top performing model was then chosen to apply XAI via SHAP, (SHapley Additive exPlanations) to identify the variables critical for the prediction of FVIII inhibitor development in a hemophilia A patient. Using XAI we provide a robust and ranked identification of variables that could be predictive for developing inhibitors to FVIII drugs in hemophilia A patients. These variables could be validated as biomarkers and used in making clinical decisions and during drug development. The top five variables for predicting inhibitor development based on SHAP values are: (i) the baseline activity of the FVIII protein, (ii) mean affinity of all foreign peptides for HLA DRB 3, 4, & 5 alleles, (iii) mean affinity of all foreign peptides for HLA DRB1 alleles), (iv) the minimum affinity among all foreign peptides for HLA DRB1 alleles, and (v) F8 mutation type.

Computational design of nanomolar-binding antibodies specific to multiple SARS-CoV-2 variants by engineering a specificity switch of antibody 80R using RosettaAntibodyDesign (RAbD) results in potential generalizable therapeutic antibodies for novel SARS-CoV-2 virus.

The human infectious disease COVID-19 caused by the SARS-CoV-2 virus has become a major threat to global public health. Developing a vaccine is the preferred prophylactic response to epidemics and pandemics. However, for individuals who have contracted the disease, the rapid design of antibodies that can target the SARS-CoV-2 virus fulfils a critical need. Further, discovering antibodies that bind multiple variants of SARS-CoV-2 can aid in the development of rapid antigen tests (RATs) which are critical for the identification and isolation of individuals currently carrying COVID-19. Here we provide a proof-of-concept study for the computational design of high-affinity antibodies that bind to multiple variants of the SARS-CoV-2 spike protein using RosettaAntibodyDesign (RAbD). Well characterized antibodies that bind with high affinity to the SARS-CoV-1 (but not SARS-CoV-2) spike protein were used as templates and re-designed to bind the SARS-CoV-2 spike protein with high affinity, resulting in a specificity switch. A panel of designed antibodies were experimentally validated. One design bound to a broad range of variants of concern including the Omicron, Delta, Wuhan, and South African spike protein variants.

Pharmacokinetics of antibodies during Pregnancy: Impact of pregnancy on the pharmacokinetics of antibodies (Part 2).

In Part 1, we provided a general description of macromolecules, pharmacokinetics (PK) characteristics in non-pregnant subjects, and the physiological changes during pregnancy. Here we further elaborate on the impact of pregnancy on the PK of antibodies through illustrative case studies (immunoglobulins, infliximab, adalimumab and eculizumab). Using published data from nonclinical and clinical studies, we present measured or calculated PK parameters from pregnant subjects comparing with data from non-pregnant subjects, if available. Due to the paucity of PK data evaluating PK of antibodies during pregnancy, we also provide examples of PK studies for small molecules. Finally, we draw conclusions on the nature and direction of PK changes for both antibodies and small molecules as well as provide recommendations for areas that would benefit from further studies.

A Retrospective Review of Center for Biologics Evaluation and Research Advisory Committee Meetings in the Context of the FDA's Benefit-Risk Framework.

The US FDA Center for Biologics Evaluation and Research (CBER) is responsible for the regulation of biologically derived products. FDA has established Advisory Committees (AC) as vehicles to seek external expert advice on scientific and technical matters related to the development and evaluation of products regulated by the agency. We aimed to identify and evaluate common topics discussed in CBER AC meetings during the regulatory decision-making process for biological products and medical devices. We analyzed the content of 119 CBER-led AC meetings between 2009 and 2021 listed on the FDA AC webpage. We reviewed publicly available meeting materials such as briefing documents, summaries, and transcripts. Using a structured review codebook based on FDA benefit-risk guidance, we identified important considerations within the benefit-risk dimensions discussed at the AC meetings: therapeutic context, benefit, risk and risk management, and benefit-risk trade-off, where evidence and uncertainty are critical parts of the FDA benefit-risk framework. Based on a detailed review of 24 topics discussed in 23 selected AC meetings conducted between 2016 and 2021, the two most frequently discussed considerations were "Uncertainty about assessment of the safety profile" and "Uncertainty about assessment of the benefit based on clinical trial data" (16/24 times each) as defined in our codebook. Most of the reviewed meetings discussed Investigational New Drug or Biologics License Applications of products. This review could help sponsors better plan and design studies by contextualizing how the benefit-risk dimensions were embedded in the AC discussions and the considerations that went into the final AC recommendations.

Pharmacokinetics of antibodies during pregnancy: General pharmacokinetics and pregnancy related physiological changes (Part 1).

Pharmacokinetics (PK) studies are important to determine a safe and effective dose of both small and large molecule drugs. Intrinsic factors such as pregnancy can substantially alter the PK of a drug. Several PK studies have been published for small molecules administered during pregnancy, but such investigations are scarce for macromolecules including monoclonal and polyclonal antibodies. In this part 1 of 2 reviews, we first provide a general description of macromolecule drugs, the PK differences with small molecules, and current knowledge on their absorption, distribution, metabolism and elimination in non-pregnant subjects. We then review in detail the physiological changes during pregnancy. While some of the physiologic adaptions of pregnancy, for example increased plasma volume and cardiac output, are expected to impact PK of antibody therapeutics, the effects of others, such as increased GFR and altered immune responses are not fully understood. We conclude that further investigations are needed to fully elucidate how pregnancy can impact PK properties of macromolecules.

Endotoxin contamination in commercially available Cas9 proteins potentially induces T-cell mediated responses.

Immune responses to Cas proteins have been demonstrated recently and these may prove to be an impediment to their clinical use in gene editing. To make meaningful assessments of Cas9 immunogenicity during drug development and licensure it is imperative the reagents are free of impurities that could affect in vitro assessments of immunogenicity. Here we address the issue of endotoxin levels in laboratory grade Cas9 proteins used to measure T-cell memory responses. Many of these reagents have not been developed for immunogenicity assays, are or microbial origin and carry varying levels of endotoxin. The use of these reagents, off the shelf, without measuring endotoxin levels is likely to introduce incorrect estimates of the prevalence of memory T-cell responses in research studies. We demonstrate wide variation in endotoxin levels in Cas9 proteins from seven suppliers. Different lots from the same supplier also contained varying levels of endotoxin. ELISPOT assays showed similar large variations in the interferon-γ signals. Finally, when we carried out endotoxin depletion in four Cas9 proteins with strong signals in the ELISPOT assay, we found dampening of the interferon-γ signals.

A structural homology approach to identify potential cross-reactive antibody responses following SARS-CoV-2 infection.

The emergence of the novel SARS-CoV-2 virus is the most important public-health issue of our time. Understanding the diverse clinical presentations of the ensuing disease, COVID-19, remains a critical unmet need. Here we present a comprehensive listing of the diverse clinical indications associated with COVID-19. We explore the theory that anti-SARS-CoV-2 antibodies could cross-react with endogenous human proteins driving some of the pathologies associated with COVID-19. We describe a novel computational approach to estimate structural homology between SARS-CoV-2 proteins and human proteins. Antibodies are more likely to interrogate 3D-structural epitopes than continuous linear epitopes. This computational workflow identified 346 human proteins containing a domain with high structural homology to a SARS-CoV-2 Wuhan strain protein. Of these, 102 proteins exhibit functions that could contribute to COVID-19 clinical pathologies. We present a testable hypothesis to delineate unexplained clinical observations vis-à-vis COVID-19 and a tool to evaluate the safety-risk profile of potential COVID-19 therapies.

Structural, functional, and immunogenicity implications of F9 gene recoding.

Hemophilia B is a blood clotting disorder caused by deficient activity of coagulation factor IX (FIX). Multiple recombinant FIX proteins are currently approved to treat hemophilia B, and several gene therapy products are currently being developed. Codon optimization is a frequently used technique in the pharmaceutical industry to improve recombinant protein expression by recoding a coding sequence using multiple synonymous codon substitutions. The underlying assumption of this gene recoding is that synonymous substitutions do not alter protein characteristics because the primary sequence of the protein remains unchanged. However, a critical body of evidence shows that synonymous variants can affect cotranslational folding and protein function. Gene recoding could potentially alter the structure, function, and in vivo immunogenicity of recoded therapeutic proteins. Here, we evaluated multiple recoded variants of F9 designed to further explore the effects of codon usage bias on protein properties. The detailed evaluation of these constructs showed altered conformations, and assessment of translation kinetics by ribosome profiling revealed differences in local translation kinetics. Assessment of wild-type and recoded constructs using a major histocompatibility complex (MHC)-associated peptide proteomics assay showed distinct presentation of FIX-derived peptides bound to MHC class II molecules, suggesting that despite identical amino acid sequence, recoded proteins could exhibit different immunogenicity risks. Posttranslational modification analysis indicated that overexpression from gene recoding results in suboptimal posttranslational processing. Overall, our results highlight potential functional and immunogenicity concerns associated with gene-recoded F9 products. These findings have general applicability and implications for other gene-recoded recombinant proteins.

Mathematical model of a personalized neoantigen cancer vaccine and the human immune system.

Cancer vaccines are an important component of the cancer immunotherapy toolkit enhancing immune response to malignant cells by activating CD4+ and CD8+ T cells. Multiple successful clinical applications of cancer vaccines have shown good safety and efficacy. Despite the notable progress, significant challenges remain in obtaining consistent immune responses across heterogeneous patient populations, as well as various cancers. We present a mechanistic mathematical model describing key interactions of a personalized neoantigen cancer vaccine with an individual patient's immune system. Specifically, the model considers the vaccine concentration of tumor-specific antigen peptides and adjuvant, the patient's major histocompatibility complexes I and II copy numbers, tumor size, T cells, and antigen presenting cells. We parametrized the model using patient-specific data from a clinical study in which individualized cancer vaccines were used to treat six melanoma patients. Model simulations predicted both immune responses, represented by T cell counts, to the vaccine as well as clinical outcome (determined as change of tumor size). This model, although complex, can be used to describe, simulate, and predict the behavior of the human immune system to a personalized cancer vaccine.