Kristoffer Haurum Johansen

Accurate prediction of T cell receptor (TCR) specificity can potentially accelerate development of novel immunotherapies, yet public databases used to train these models contain substantial label noise. This uncertainty complicates model evaluation and limits the reliability of predicted TCR-pMHC interactions. In this work, we present a simple supervised machine learning denoising scheme to identify low-quality labels in TCR specificity data. We evaluated the framework using the TCRvdb validation dataset and further corroborated it via structural modeling with AlphaFold 3. Here, our denoising approach successfully identified non-validated TCRs, achieving an average MCC of 0.47 for filtering non-validated examples while retaining high sensitivity for validated examples. Applying our denoising approach to the complete NetTCR training dataset, we observed that data associated with known noisy attributes were significantly enriched in the filtered subset. Furthermore, TCR-pMHC complexes identified as noise consistently produced lower AlphaFold 3 confidence scores, providing independent evidence of misannotation. Experimental validation of 30 selected TCRs further supported the approach, with 80% of TCRs predicted as noise failing to demonstrate functional reactivity. Our findings demonstrate that current performance metrics may be obscured by dataset inaccuracies and provide a method for refining training data in the absence of gold-standard benchmarks.

Deep generative models have become a leading approach for designing therapeutic molecules, yet efficiently exploring vast biomolecular sequence spaces remains difficult, particularly for targets with limited training data. The prior distribution that seeds a generative model shapes which regions of sequence space it explores, and recent work suggests that non-classical distributions sampled from quantum processors can serve as a structured alternative to the factorised Gaussian priors used by default. Whether such priors help on complex biological design tasks has been largely untested. Here we present what is, to our knowledge, the first end-to-end hybrid quantum-classical pipeline for de novo design of MHC class I-binding peptides, coupling a generative adversarial network (GAN) to latent vectors sampled from a real photonic quantum processor. Tested in silico across 131 HLA alleles, quantum-derived priors increased the yield of predicted strong binders, with the largest relative gains for understudied alleles where classical baselines perform worst. We selected three understudied alleles for further evaluation, finding that large gains coincided with broader sequence exploration at non-anchor positions while anchor specificity was preserved. On these three alleles, we validated the designs in vitro using peptide-MHC stability ELISAs, confirming that quantum-designed peptides are potent stabilisers of peptide-MHC class I complexes. These results establish structured, hardware-realisable non-classical priors as a useful inductive bias for generative peptide design, with direct relevance to personalised immunotherapies and vaccines.

Allergic diseases arise from aberrant immune recognition of otherwise harmless environmental proteins and are driven by epitope‐specific interactions between allergens and the adaptive immune system. Although component‐resolved diagnostics have improved molecular characterisation of sensitization, they remain limited to whole‐allergen resolution and do not capture the fine specificity and heterogeneity of immune recognition that ultimately determine clinical reactivity, cross‐reactivity, and treatment outcomes. Increasing evidence indicates that allergic sensitization, severity, and tolerance are governed by discrete B‐ and T‐cell epitopes rather than entire allergen molecules. This review provides a comprehensive overview of established and emerging technologies for allergen epitope mapping at molecular resolution. For B‐cell epitopes, we discuss peptide‐based screening approaches, display technologies, deep mutational scanning, structural and biophysical methods, and advances in in silico prediction. For T‐cell epitopes, we summarise experimental and computational strategies to identify allergen‐derived peptides presented by HLA molecules and recognised by T‐cell receptors, highlighting the influence of HLA diversity on individualised immune responses. Finally, we explore the clinical and translational implications of epitope‐resolved allergen profiling for next‐generation diagnostics, functional cell‐based assays, improved risk stratification, cross‐reactivity prediction, and the rational design of safer and more precise immunotherapies. Together, these approaches support the development of precision medicine strategies in allergic disease.

Recent evidence suggests that CD8+ T cells contribute to rheumatoid arthritis (RA) pathogenesis, however, their landscape of immune recognition, clonality, phenotypic and transcriptional characteristics, as well as functional properties remain poorly understood. Using in silico epitope prediction, barcoded pMHC multimer screening, single-cell transcriptomic and TCR repertoire analysis in blood and tissue of RA patients, we systematically interrogated CD8+ T-cell responses targeting RA-associated peptides. First, we identified HLA class I-restricted CD8+ T-cell responses against RA autoantigens. Second, we demonstrate that epitope-specific CD8+ T cells from RA patients display a distinct transcriptional footprint compared to healthy donors, which is characterized by features consistent with antigen experience, cytotoxicity and effector differentiation. In parallel, our data indicate that citrullination can modulate cross-recognition between peptide epitopes, suggesting that this post-translational modification may broaden or reshape antigen recognition within the CD8+ T-cell repertoire. Finally, we show that RA-associated TCR clonotypes are stable in peripheral blood over time, are comprised of phenotypically antigen-experienced cells, and can be detected in synovial tissue. Together, our study defines a set of HLA class I-restricted CD8+ T-cell epitopes associated with RA and provides mechanistic insight into how citrullinations may influence CD8+ T-cell recognition as well as interrogating the RA-associated CD8+ T cell clonotype landscape. These findings support a direct role for autoreactive CD8+ T cells in RA and provide a foundation for targeted immunotherapy.

Cross-allergies affect a significant proportion of the population, and contribute to detrimental health and socioeconomic impacts, yet allergen immunotherapies often target a single allergen source disregarding cross-reactive allergens from other sources. Here we introduce an immunization approach developed for improved desensitization in cross-allergic patients using a consensus allergen (cnsLTP1), which contains orthologous non-specific lipid transfer proteins (nsLTP) derived from relevant fruit and pollen allergens. In BALB/c mice, vaccination via either mRNA-lipid nanoparticle (LNP) vehicle or traditional protein formulation induces cnsLTP1-specific IgGs capable of recognizing and binding to multiple nsLTPs. These IgGs block allergen binding by patient serum IgEs and prevent humanized rat basophil degranulation in vitro. Meanwhile, in an allergic mouse model, the mRNA-LNP formulation is tolerated and induces allergen-specific IgG responses but does not ameliorate subsequent allergen challenge responses. Regardless, this cross-allergen mRNA-LNP-based immunotherapy may have translation value once route of administration, formulation and/or dosing are optimized.

Determining T-cell specificity forms a crucial step toward understanding T-cell involvement in health and disease. Single-cell sequencing technologies allow for co-capture of TCR alpha and beta chains, and their antigen specificity can be determined through peptide-MHC (pMHC) multimer binding and capture of a co-attached barcode oligo. However, SC sequencing often includes a high level of dropouts and risk of cross-contamination. Similarly, barcoded pMHC readouts often suffer from significant background noise. These issues complicate the automatic assignment of pMHC recognition to TCR clonotypes. To overcome these challenges, we developed a method for data denoising - Improved T-cell Receptor Antigen Paring 2 (ITRAP2). This approach significantly reduces noise in single-cell pMHC readouts and allows for accurate identification of TCR specificity. ITRAP2 incorporates statistical tests and confidence metrics for each TCR-pMHC pairing, offering user flexibility in pairing rigor, and allows multiple pMHC assignments to the same T-cell clone in the event of cross-binding within the pMHC multimer library. We tested this method on an in-house generated dataset of 8141 single cells, screened for CD8⁺ T-cell binding using a panel of 100 different barcode-labelled pMHC multimers holding virus-derived peptides, and on a larger public dataset from 10x Genomics with 208,589 T-cells evaluated for recognition using a panel of 50 different pMHCs. In both datasets, ITRAP2 was able to recover TCR-pMHC hits that were missed either when investigating the raw data or analyzing the data using alternative tools. Importantly, we demonstrate that the size of the pMHC multimer library is crucial for accurate pMHC-TCR pairing and that a minimum of 25 pMHC multimer should be included to optimally determine background characteristic, and assigning true positive events.

Summary: The engineering of autologous T cells to express chimeric antigen receptors (CARs) can induce profound clinical responses in haematological malignancies, while T cell receptor-engineered T (TCR T) cells have led to durable responses in clinical trials for solid tumours. However, clinical manufacturing of engineered T cells is resource-intensive and often yields highly differentiated, exhausted effector T cells. To circumvent this, we have developed an antigen-scaffold (Ag-scaffold) technology to preferentially expand genetically engineered T cells. Such Ag-scaffolds present cognate antigen together with stimulatory factors such as cytokines. By providing a specific and receptor-engaging stimulation to CAR/TCR T cells, the expanded product is highly enriched for engineered T cells with a favourable proliferative and efficacious phenotype. We expanded TCR T cells with Ag-scaffolds presenting peptide MHC (pMHC), and anti-CD19 CAR T cells with Ag-scaffolds presenting CD19 antigen. By applying cognate pMHC Ag-scaffolds, we achieved >80% antigen-specific T cells (83.62%±9.2%) after 14 days of culture with a distinct cytotoxic, proliferative phenotypical profile. Ag-scaffold expansion enhanced initial TCR and CAR cytotoxicity; sustained control was observed after repeated rechallenges of CAR T cells. In vivo , Ag-scaffold-expanded CRISPR/Cas9-engineered anti-CD19 CAR T also showed complete tumour eradication in a B-cell lymphoma xenograft model with a low dose of CAR T cells, which was not achieved using IL2/7/15 expansion.

The recognition of intracellular antigens by CD8 ⁺ T cells through T cell receptors (TCRs) is central for adaptive immunity against infections and cancer. However, the identification of TCRs from patient material remains complex. We present a rapid de novo minibinder (miBd) design platform leveraging state-of-the-art generative models to engineer miBds targeting the cancer-associated peptide-bound major histocompatibility complex (pMHC) SLLMWITQC/HLA-A*02:01 (NY-ESO-1). Incorporating in silico cross-panning enabled computational prescreening of specificity, and molecular dynamics simulations allowed for improved predictability of in vitro success. We identified a high-affinity NY-ESO-1 binder and confirmed its structure using cryo–electron microscopy, which, when incorporated in a chimeric antigen receptor, induced killing of NY-ESO-1 ⁺ melanoma cells. We further designed and validated binders to a neoantigen pMHC complex, RVTDESILSY/HLA-A*01:01, with unknown structure, demonstrating the potential for precision immunotherapy.

The recognition of intracellular antigens by CD8+ T cells through T cell receptors (TCRs) is central to adaptive immunity, enabling responses against infections and cancer. The recent approval of TCR-gene-edited T cells for cancer therapy demonstrates the therapeutic advantage of using pMHC recognition to eliminate cancer. However, identification and selection of TCRs from patient material is complex and influenced by the TCR repertoire of the donors used. To overcome these limitations, we here present a rapid and robust de novo binder design platform leveraging state-of-the-art generative models, including RFdiffusion, ProteinMPNN, and AlphaFold2, to engineer minibinders (miBds) targeting the cancer-associated pMHC complex, NY-ESO-1(157-165)/HLA-A*02:01. By incorporating in silico cross-panning and molecular dynamics simulations, we enhanced specificity screening to minimise off-target interactions. We identified a miBd that exhibited high specificity for the NY-ESO-1-derived peptide SLLMWITQC in complex with HLA-A*02:01 and minimal cross-reactivity in mammalian display assays. We further demonstrate the therapeutic potential of this miBd by integrating it into a chimeric antigen receptor, as de novo Binders for Immune-mediated Killing Engagers (BIKEs). BIKE-transduced T cells selectively and effectively killed NY-ESO-1+ melanoma cells compared to non-transduced controls, demonstrating the promise of this approach in precision cancer immunotherapy. Our findings underscore the transformative potential of generative protein design for accelerating the discovery of high-specificity pMHC-targeting therapeutics. Beyond CAR-T applications, our workflow establishes a foundation for developing miBds as versatile tools, heralding a new era of precision immunotherapy.

Pollen-food allergy syndrome (PFAS) affects a significant proportion of the global population with a major health and socioeconomic impact. Patients are generally treated against the major sensitized allergen which does not warrant protection against cross-reactive allergens, leading to long and ineffective treatment regimens. For food allergies, patient guidelines rely on source avoidance, leading to dietary restrictions and reduced quality of life - in particular for those suffering from PFAS. To overcome these limitations, we introduce a novel allergy immunotherapy (AIT) approach utilizing consensus allergens and mRNA technology to achieve broader, safer, and faster desensitization in PFAS patients. We first designed a consensus allergen of orthologs of non-specific Lipid Transfer Proteins (cnsLTP-1) representing a broad spectrum of nsLTP allergens prevalent in food and pollen sources. CnsLTP-1 was delivered to naïve BALB/c mice using mRNA-lipid nanoparticles (mRNA-LNP) as vehicle, or by a traditional protein formulation, to assess if it elicits broad protection against allergens from different sources. Immunization with both mRNA-LNP and protein formulations demonstrated that cnsLTP-1-specific IgGs could be induced, whilst the mRNA-LNP formulation notably avoided the induction of allergen-specific IgEs. The induced antibodies were capable of recognizing and binding to a variety of nsLTPs, and effectively blocked the binding of allergens by allergic patient serum IgEs. This study thus demonstrates that the presented AIT strategy, based on mRNA-LNP technology and consensus allergens, could find clinical utility by addressing the limitations of current AIT. Further development of this technology platform could pave the way for more effective and patient-friendly treatments for PFAS and other cross-reactive allergies.