Cmai: Predicting Antigen-Antibody Interactions from Massive Sequencing Data.

The interaction between antigens and antibodies (B cell receptors, BCRs) is the key step underlying the function of the humoral immune system in various biological contexts. The capability to profile the landscape of antigen-binding affinity of a vast number of BCRs will provide a powerful tool to reveal novel insights at unprecedented levels and will yield powerful tools for translational development. However, current experimental approaches for profiling antibody-antigen interactions are costly and time-consuming, and can only achieve low-to-mid throughput. On the other hand, bioinformatics tools in the field of antibody informatics mostly focus on optimization of antibodies given known binding antigens, which is a very different research question and of limited scope. In this work, we developed an innovative Artificial Intelligence tool, Cmai, to address the prediction of the binding between antibodies and antigens that can be scaled to high-throughput sequencing data. Cmai achieved an AUROC of 0.91 in our validation cohort. We devised a biomarker metric based on the output from Cmai applied to high-throughput BCR sequencing data. We found that, during immune-related adverse events (irAEs) caused by immune-checkpoint inhibitor (ICI) treatment, the humoral immunity is preferentially responsive to intracellular antigens from the organs affected by the irAEs. In contrast, extracellular antigens on malignant tumor cells are inducing B cell infiltrations, and the infiltrating B cells have a greater tendency to co-localize with tumor cells expressing these antigens. We further found that the abundance of tumor antigen-targeting antibodies is predictive of ICI treatment response. Overall, Cmai and our biomarker approach filled in a gap that is not addressed by current antibody optimization works nor works such as AlphaFold3 that predict the structures of complexes of proteins that are known to bind.

Differences in systemic immune parameters in individuals with lung cancer according to race.

Introduction: Racial and ethnic disparities in the presentation and outcomes of lung cancer are widely known. To evaluate potential factors contributing to these observations, we measured systemic immune parameters in Black and White patients with lung cancer. Methods: Patients scheduled to receive cancer immunotherapy were enrolled in a multi-institutional prospective biospecimen collection registry. Clinical and demographic information were obtained from electronic medical records. Pre-treatment peripheral blood samples were collected and analyzed for cytokines using a multiplex panel and for immune cell populations using mass cytometry. Differences between Black and White patients were determined and corrected for multiple comparisons. Results: A total of 187 patients with non-small cell lung cancer (Black, 19; White, 168) were included in the analysis. There were no significant differences in baseline characteristics between Black and White patients. Compared to White patients, Black patients had significantly lower levels of CCL23 and CCL27, and significantly higher levels of CCL8, CXCL1, CCL26, CCL25, CCL1, IL-1 b, CXCL16, and IFN-γ (all P <0.05, FDR<0.1). Black patients also exhibited greater populations of non-classical CD16+ monocytes, NKT-like cells, CD4+ cells, CD38+ monocytes, and CD57+ gamma delta T cells (all P <0.05). Conclusions: Black and White patients with lung cancer exhibit several differences in immune parameters, with Black patients exhibiting greater levels of numerous pro-inflammatory cytokines and cell populations. The etiology and clinical significance of these differences warrant further evaluation.

pan-MHC and cross-Species Prediction of T Cell Receptor-Antigen Binding.

Profiling the binding of T cell receptors (TCRs) of T cells to antigenic peptides presented by MHC proteins is one of the most important unsolved problems in modern immunology. Experimental methods to probe TCR-antigen interactions are slow, labor-intensive, costly, and yield moderate throughput. To address this problem, we developed pMTnet-omni, an Artificial Intelligence (AI) system based on hybrid protein sequence and structure information, to predict the pairing of TCRs of αß T cells with peptide-MHC complexes (pMHCs). pMTnet-omni is capable of handling peptides presented by both class I and II pMHCs, and capable of handling both human and mouse TCR-pMHC pairs, through information sharing enabled this hybrid design. pMTnet-omni achieves a high overall Area Under the Curve of Receiver Operator Characteristics (AUROC) of 0.888, which surpasses competing tools by a large margin. We showed that pMTnet-omni can distinguish binding affinity of TCRs with similar sequences. Across a range of datasets from various biological contexts, pMTnet-omni characterized the longitudinal evolution and spatial heterogeneity of TCR-pMHC interactions and their functional impact. We successfully developed a biomarker based on pMTnet-omni for predicting immune-related adverse events of immune checkpoint inhibitor (ICI) treatment in a cohort of 57 ICI-treated patients. pMTnet-omni represents a major advance towards developing a clinically usable AI system for TCR-pMHC pairing prediction that can aid the design and implementation of TCR-based immunotherapeutics.

Association between Antibiotic Exposure and Systemic Immune Parameters in Cancer Patients Receiving Checkpoint Inhibitor Therapy.

Antibiotic administration is associated with worse clinical outcomes and changes to the gut microbiome in cancer patients receiving immune checkpoint inhibitors (ICI). However, the effects of antibiotics on systemic immune function are unknown. We, therefore, evaluated antibiotic exposure, therapeutic responses, and multiplex panels of 40 serum cytokines and 124 antibodies at baseline and six weeks after ICI initiation, with p < 0.05 and false discovery rate (FDR) < 0.2 considered significant. A total of 251 patients were included, of whom the 135 (54%) who received antibiotics had lower response rates and shorter survival. Patients who received antibiotics prior to ICI initiation had modestly but significantly lower baseline levels of nucleolin, MDA5, c-reactive protein, and liver cytosol antigen type 1 (LC1) antibodies, as well as higher levels of heparin sulfate and Matrigel antibodies. After ICI initiation, antibiotic-treated patients had significantly lower levels of MDA5, CENP.B, and nucleolin antibodies. Although there were no clear differences in cytokines in the overall cohort, in the lung cancer subset (53% of the study population), we observed differences in IFN-γ, IL-8, and macrophage inflammatory proteins. In ICI-treated patients, antibiotic exposure is associated with changes in certain antibodies and cytokines. Understanding the relationship between these factors may improve the clinical management of patients receiving ICI.

Association between body mass index, dosing strategy, and efficacy of immune checkpoint inhibitors.

BACKGROUND: Increased body mass index (BMI) has been associated with improved response to immune checkpoint inhibitors (ICIs) in multiple cancer types. We evaluated associations between BMI, ICI dosing strategy, and clinical outcomes. METHODS: We abstracted clinical data on patients with cancer treated with ICI, including age, sex, cancer type, BMI, ICI type, dosing strategy (weight-based or fixed), radiographic response, overall survival (OS), and progression-free survival (PFS). We compared clinical outcomes between low-BMI and high-BMI populations using Kaplan-Meier curves, Cox regressions, and Pearson product-moment correlation coefficients. RESULTS: A total of 297 patients were enrolled, of whom 40% were women and 59% were overweight (BMI≥25). Of these, 204 (69%) received fixed and 93 (31%) received weight-based ICI dosing. In the overall cohort, overweight BMI was associated with improved PFS (HR 0.69; 95% CI 0.51 to 0.94; p=0.02) and had a trend toward improved OS (HR 0.77; 95% CI 0.57 to 1.04; p=0.08). For both endpoints, improved outcomes in the overweight population were limited to patients who received weight-based ICI dosing (PFS HR 0.53; p=0.04 for weight-based; vs HR 0.79; p=0.2 for fixed dosing) (OS HR 0.56; p=0.03 for weight-based; vs HR 0.89; p=0.54 for fixed dosing). In multivariable analysis, BMI was not associated with PFS or OS. However, the interaction of BMI≥25 and weight-based dosing had a trend toward association with PFS (HR 0.53; 95% CI 0.26 to 1.10; p=0.09) and was associated with OS (HR 0.50; 95% CI 0.25 to 0.99; p=0.05). Patients with BMI<25 tended to have better outcomes with fixed-dose compared with weight-based ICI, while patients with BMI≥25 tended to have better outcomes with weight-based ICI, although these differences did not achieve statistical significance. There was no association between radiographic response and BMI with fixed-dose ICI (p=0.97), but a near-significant trend with weight-based ICI (p=0.1). In subset analyses, the association between BMI, ICI dosing strategy, and clinical outcomes appeared limited to men. CONCLUSIONS: The clinical benefit of ICI in high-BMI populations appears limited to individuals receiving weight-based ICI dosing. Further research into optimal ICI dosing strategies may be warranted.

Statin Intolerance, Anti-HMGCR Antibodies, and Immune Checkpoint Inhibitor-Associated Myositis: A "Two-Hit" Autoimmune Toxicity or Clinical Predisposition?

Immune-related adverse events induced by immune checkpoint inhibitor (ICI) therapy may affect diverse organ systems, including skeletal and cardiac muscle. ICI-associated myositis may result in substantial morbidity and occasional mortality. We present a case of a patient with advanced non-small cell lung cancer who developed grade 4 myositis with concurrent myocarditis early after initiation of anti-programmed death ligand 1 therapy (durvalumab). Autoantibody analysis revealed marked increases in anti-3-hydroxy-3-methylglutaryl-coenzyme A reductase antibody levels that preceded clinical toxicity, and further increased during toxicity. Notably, the patient had a history of intolerable statin myopathy, which had resolved clinically after statin discontinuation and prior to ICI initiation. This case demonstrates a potential association between statin exposure, autoantibodies, and ICI-associated myositis.

Late-Onset Immunotherapy Toxicity and Delayed Autoantibody Changes: Checkpoint Inhibitor-Induced Raynaud's-Like Phenomenon.

Immune checkpoint inhibitor (ICI)-induced immune-related adverse events (irAEs) may affect almost any organ system and occur at any point during therapy. Autoantibody analysis may provide insight into the mechanism, nature, and timing of these events. We report a case of ICI-induced late-onset Raynaud's-like phenomenon in a patient receiving combination immunotherapy. A 53-year-old woman with advanced non-small lung cancer received combination anti-cytotoxic T-lymphocyte antigen 4 and anti-programmed death 1 ICI therapy. She developed early (hypophysitis at 4 months) and late (Raynaud's at >20 months) irAEs. Longitudinal assessment of 124 autoantibodies was correlated with toxicity. Although autoantibody levels were generally stable for the first 18 months of therapy, shortly before the development of Raynaud's, a marked increase in multiple autoantibodies was observed. This case highlights the potential for delayed autoimmune toxicities and provides potential biologic insights into the dynamic nature of these events. KEY POINTS: A patient treated with dual anti-PD1 and anti-CTLA4 therapy developed Raynaud's-like signs and symptoms more than 18 months after starting therapy. In this case, autoantibody changes became apparent shortly before onset of clinical toxicity. This case highlights the potential for late-onset immune-related adverse events checkpoint inhibitors, requiring continuous clinical vigilance. The optimal duration of checkpoint inhibitor therapy in patients with profound and prolonged responses remains unclear.

Immune dysregulation in cancer patients developing immune-related adverse events.

BACKGROUND: Up to 40% of cancer patients on immune checkpoint inhibitors develop clinically significant immune-related adverse events (irAEs). The role of host immune status and function in predisposing patients to the development of irAEs remains unknown. METHODS: Sera from 65 patients receiving immune checkpoint inhibitors and 13 healthy controls were evaluated for 40 cytokines at pre-treatment, after 2-3 weeks and after 6 weeks and analysed for correlation with the development of irAEs. RESULTS: Of the 65 cancer patients enrolled, 55% were women; the mean age was 65 years and 98% received anti-PD1/PDL1 therapy. irAEs occurred in 35% of cases. Among healthy controls, cytokine levels were stable over time and lower than those in cancer patients at baseline. Significant increases in CXCL9, CXCL10, CXCL11 and CXCL13 occurred 2 weeks post treatment, and in CXCL9, CXCL10, CXCL11, CXCL13, IL-10 and CCL26 at 6 weeks post treatment. Patients who developed irAEs had lower levels of CXCL9, CXCL10, CXCL11 and CXCL19 at baseline and exhibited greater increases in CXCL9 and CXCL10 levels at post treatment compared to patients without irAEs. CONCLUSIONS: Patients who developed irAEs have lower baseline levels and greater post-treatment increases in multiple cytokine levels, suggesting that underlying immune dysregulation may be associated with heightened risk for irAEs.