Personalized neoantigen prediction is challenging due to the scarcity of positive samples, the noise of the experimental data, the severe class imbalance trait and the complex of immunogenicity features. Prior arts, such as linear regression and XGBoost fail to model long-range dependencies and contextual relationships within peptide features, therefore the performance of neoantigen positive recall rate is limited. In this paper, we present a novel deep learning framework based on Transformer, coined as TransNRank. By leveraging the self-attention mechanism, our model captures both local and global feature contexts, enabling more accurate recognition of immunogenic neoantigens. A positive-aware training objective is utilized to handle the class imbalance problem, assigning more weights to those few positive samples. Extensive experiments are performed on NCI, TESLA and HiTIDE datasets. Notably, our TransNRank can push the upper bound top 20 recall rate of neoantigen prediction from 46.9% (45 from 96) to 53.1% (51 from 96), while reducing the training epochs from 200 epochs to 20 epochs. Furthermore, we analyze the features contribution based on TransNRank and find that the mutation at anchor and TCGA expression level play an unexpected important role in neoantigen prediction, and removing insignificant features to reduce the input dimensionality of peptides does not drastically impair the overall performance of the model. Our paradigm not only streamlines the prediction pipeline but also sets a new state-of-the-art for neoantigen discovery, with broad implications for accurate immuno-oncology.
Zhiyin An, Yue-Nan Hou, Shumeng Duan et al.· 0 citations
Systemic lupus erythematosus (SLE) and rheumatoid arthritis (RA) are autoimmune diseases driven by autoreactive B cells and plasma cells, leading to chronic inflammation and organ damage. Current therapies targeting B cells, such as anti-CD20 monoclonal antibodies, are ineffective in depleting long-lived plasma cells. This limitation highlights the need for novel therapeutic strategies to reset the immune system in these diseases.
We developed lipid nanoparticle-encapsulated mRNA (mRNab-LNPs) encoding anti-CD19 antibodies to deplete autoreactive B cells and plasma cells. mRNab-LNPs were administered intramuscularly to lupus and RA mouse models. We evaluated the therapeutic efficacy by assessing the depletion of CD19+ B cells and plasma cells, and the subsequent reduction in disease-related histopathological damage.
Intramuscular injection of mRNab-LNPs in both lupus and RA mice led to high and sustained production of anti-CD19 antibodies. This resulted in significant depletion of circulating CD19+ B cells and tissue-resident plasma cells. Histopathological analysis showed reduced damage in the skin, kidneys, and joints of treated mice. Additionally, mRNab-LNPs exhibited favorable pharmacokinetics with prolonged antibody production and minimal systemic inflammatory response.
mRNab-LNPs effectively target and deplete both B cells and plasma cells in lupus and RA mouse models. These findings suggest that mRNab-LNPs offer a promising alternative to current therapies, providing a safer, more efficient approach to treating autoimmune diseases by resetting the humoral immune system.
This work was supported by the following grants: National Natural Foundation of China Grant (Nos. 81970632 and 52473328), Guangdong Science and Technology Department Grant (Nos. 2020B1212060018 and 2020B1212030004), Sun Yat-sen Pilot Scientific Research F
Therapeutic Approaches to Autoimmunity (THER)
Renal cell carcinoma (RCC) remains highly resistant to conventional therapies, highlighting the need for innovative treatments. Tumor-associated macrophages (TAMs) play a critical role in RCC progression by promoting immune evasion and supporting tumor growth. Manganese ions have been shown to activate the cGAS-STING pathway, enhancing anti-tumor immunity. However, precise targeting and controlled release of manganese in the tumor microenvironment remain major challenges.
We developed manganese-polydopamine nano-immunomodulators (PDA-Mn-HA NPs), coated with hyaluronic acid (HA), to selectively target CD44 receptors on TAMs and RCC cells. These nanoparticles were characterized for their size, surface charge, and manganese release profile. In vitro, we assessed their ability to induce M1 macrophage polarization, stimulate cytokine production, and generate reactive oxygen species (ROS). We also evaluated their potential to induce pyroptosis in RCC cells and tested their therapeutic effects in a preclinical RCC mouse model.
PDA-Mn-HA NPs effectively induced M1 macrophage polarization, promoting the release of pro-inflammatory cytokines and chemokines crucial for immune activation. Transcriptomic analysis showed significant changes in gene expression related to immune response in macrophages, confirming the nanoparticles’ immunomodulatory role. In RCC cells, PDA-Mn-HA NPs induced ROS-mediated pyroptosis through the caspase-3/GSDME pathway, further enhancing immune system activation. In vivo, PDA-Mn-HA NPs not only inhibited RCC tumor growth but also increased immune cell infiltration, particularly cytotoxic T cells, reshaping the tumor microenvironment to promote anti-tumor immunity.
PDA-Mn-HA NPs offer a promising strategy for RCC treatment by synergistically targeting both TAMs and RCC cells. This dual action enhances anti-tumor immunity and addresses the challenges of manganese ion delivery, presenting a novel approach to RCC immunotherapy.
This work was funded by the National Natural Science Foundation of China (Grant No. 81801913) and the Guangdong Basic and Applied Basic Research Foundation (Grant No. 2020B1515020036).
Tumor Immunology: Checkpoints, Prevention, and Treatment (TIPT)
CAR T cell therapy has shown success in treating hematologic malignancies but faces challenges in solid tumors due to antigen heterogeneity and the complex tumor microenvironment (TME). CAFs expressing fibroblast activation protein (FAP) contribute to immune suppression by creating physical barriers and immune-suppressive environment that blocks T cell infiltration and persistence. Overcoming these barriers is crucial for enhancing CAR T cell therapy in solid tumors.
We engineered a modular CAR T cell platform using anti-FLAG CAR T cells conjugated with FLAG-tagged monoclonal antibodies, allowing flexible targeting of both tumor cells and CAFs. This platform was tested in B-cell lymphoma and pancreatic cancer models, both in vitro and in vivo. Cytotoxicity was evaluated through flow cytometry. TME remodeling and cytokine production were assessed using immunostaining, multiplex cytokine assays, and qPCR. In vivo efficacy was evaluated in subcutaneous and orthotopic models.
In B-cell lymphoma, FLAG CAR T cells, combined with FLAG-tagged CD19 antibodies, exhibited strong anti-tumor activity, significantly increasing tumor cell lysis and achieving cytotoxicity comparable to traditional CD19 CAR T cell therapies. In solid tumor models, FLAG CAR T cells, in combination with FLAG-tagged antibodies targeting FAP+ CAFs and Claudin18.2+ tumor cells, enhanced immune cell infiltration and significantly suppressed tumor growth. This dual-targeting strategy disrupted the TME-induced immune suppression, reduced collagen deposition, and boosted T cell activity, resulting in notable tumor growth inhibition and prolonged survival in both subcutaneous and orthotopic pancreatic cancer models.
This CAR T cell platform enables dual targeting of tumor cells and CAFs, overcoming immune suppression in solid tumors. This approach enhances immune activation, reshapes the TME, and provides a promising strategy for improving CAR T cell therapy in solid tumors.
This study was funded by the National Natural Foundation of China (No. 81970632), Guangdong Science and Technology Department (Nos. 2020B1212060018 and 2020B1212030004), Guangdong Basic and Applied Basic Research Foundation 2025A1515011234.
Tumor Immunology: Checkpoints, Prevention, and Treatment (TIPT)
