Construction of lymph nodes-targeting tumor vaccines by using the principle of DNA base complementary pairing to enhance anti-tumor cellular immune response.

Tumor vaccines, a crucial immunotherapy, have gained growing interest because of their unique capability to initiate precise anti-tumor immune responses and establish enduring immune memory. Injected tumor vaccines passively diffuse to the adjacent draining lymph nodes, where the residing antigen-presenting cells capture and present tumor antigens to T cells. This process represents the initial phase of the immune response to the tumor vaccines and constitutes a pivotal determinant of their effectiveness. Nevertheless, the granularity paradox, arising from the different requirements between the passive targeting delivery of tumor vaccines to lymph nodes and the uptake by antigen-presenting cells, diminishes the efficacy of lymph node-targeting tumor vaccines. This study addressed this challenge by employing a vaccine formulation with a tunable, controlled particle size. Manganese dioxide (MnO2) nanoparticles were synthesized, loaded with ovalbumin (OVA), and modified with A50 or T20 DNA single strands to obtain MnO2/OVA/A50 and MnO2/OVA/T20, respectively. Administering the vaccines sequentially, upon reaching the lymph nodes, the two vaccines converge and simultaneously aggregate into MnO2/OVA/A50-T20 particles through base pairing. This process enhances both vaccine uptake and antigen delivery. In vitro and in vivo studies demonstrated that, the combined vaccine, comprising MnO2/OVA/A50 and MnO2/OVA/T20, exhibited robust immunization effects and remarkable anti-tumor efficacy in the melanoma animal models. The strategy of controlling tumor vaccine size and consequently improving tumor antigen presentation efficiency and vaccine efficacy via the DNA base-pairing principle, provides novel concepts for the development of efficient tumor vaccines.

Chimeric antigen receptor-natural killer cell therapy: current advancements and strategies to overcome challenges.

Chimeric antigen receptor-natural killer (CAR-NK) cell therapy is a novel immunotherapy targeting cancer cells via the generation of chimeric antigen receptors on NK cells which recognize specific cancer antigens. CAR-NK cell therapy is gaining attention nowadays owing to the ability of CAR-NK cells to release potent cytotoxicity against cancer cells without side effects such as cytokine release syndrome (CRS), neurotoxicity and graft-versus-host disease (GvHD). CAR-NK cells do not require antigen priming, thus enabling them to be used as "off-the-shelf" therapy. Nonetheless, CAR-NK cell therapy still possesses several challenges in eliminating cancer cells which reside in hypoxic and immunosuppressive tumor microenvironment. Therefore, this review is envisioned to explore the current advancements and limitations of CAR-NK cell therapy as well as discuss strategies to overcome the challenges faced by CAR-NK cell therapy. This review also aims to dissect the current status of clinical trials on CAR-NK cells and future recommendations for improving the effectiveness and safety of CAR-NK cell therapy.

Gene network-based and ensemble modeling-based selection of tumor-associated antigens with a predicted low risk of tissue damage for targeted immunotherapy.

BACKGROUND: Tumor-associated antigens and their derived peptides constitute an opportunity to design off-the-shelf mainline or adjuvant anti-cancer immunotherapies for a broad array of patients. A performant and rational antigen selection pipeline would lay the foundation for immunotherapy trials with the potential to enhance treatment, tremendously benefiting patients suffering from rare, understudied cancers. METHODS: We present an experimentally validated, data-driven computational pipeline that selects and ranks antigens in a multipronged approach. In addition to minimizing the risk of immune-related adverse events by selecting antigens based on their expression profile in tumor biopsies and healthy tissues, we incorporated a network analysis-derived antigen indispensability index based on computational modeling results, and candidate immunogenicity predictions from a machine learning ensemble model relying on peptide physicochemical characteristics. RESULTS: In a model study of uveal melanoma, Human Leukocyte Antigen (HLA) docking simulations and experimental quantification of the peptide-major histocompatibility complex binding affinities confirmed that our approach discriminates between high-binding and low-binding affinity peptides with a performance similar to that of established methodologies. Blinded validation experiments with autologous T-cells yielded peptide stimulation-induced interferon-γ secretion and cytotoxic activity despite high interdonor variability. Dissecting the score contribution of the tested antigens revealed that peptides with the potential to induce cytotoxicity but unsuitable due to potential tissue damage or instability of expression were properly discarded by the computational pipeline. CONCLUSIONS: In this study, we demonstrate the feasibility of the de novo computational selection of antigens with the capacity to induce an anti-tumor immune response and a predicted low risk of tissue damage. On translation to the clinic, our pipeline supports fast turn-around validation, for example, for adoptive T-cell transfer preparations, in both generalized and personalized antigen-directed immunotherapy settings.

State of the Art in CAR-T Cell Therapy for Solid Tumors: Is There a Sweeter Future?

Chimeric antigen receptor (CAR)-T cell therapy has proven to be a powerful treatment for hematological malignancies. The situation is very different in the case of solid tumors, for which no CAR-T-based therapy has yet been approved. There are many factors contributing to the absence of response in solid tumors to CAR-T cells, such as the immunosuppressive tumor microenvironment (TME), T cell exhaustion, or the lack of suitable antigen targets, which should have a stable and specific expression on tumor cells. Strategies being developed to improve CAR-T-based therapy for solid tumors include the use of new-generation CARs such as TRUCKs or bi-specific CARs, the combination of CAR therapy with chemo- or radiotherapy, the use of checkpoint inhibitors, and the use of oncolytic viruses. Furthermore, despite the scarcity of targets, a growing number of phase I/II clinical trials are exploring new solid-tumor-associated antigens. Most of these antigens are of a protein nature; however, there is a clear potential in identifying carbohydrate-type antigens associated with tumors, or carbohydrate and proteoglycan antigens that emerge because of aberrant glycosylations occurring in the context of tumor transformation.

CD8+ T cell targeting of tumor antigens presented by HLA-E.

The nonpolymorphic major histocompatibility complex E (MHC-E) molecule is up-regulated on many cancer cells, thus contributing to immune evasion by engaging inhibitory NKG2A/CD94 receptors on NK cells and tumor-infiltrating T cells. To investigate whether MHC-E expression by cancer cells can be targeted for MHC-E-restricted T cell control, we immunized rhesus macaques (RM) with rhesus cytomegalovirus (RhCMV) vectors genetically programmed to elicit MHC-E-restricted CD8+ T cells and to express established tumor-associated antigens (TAAs) including prostatic acidic phosphatase (PAP), Wilms tumor-1 protein, or Mesothelin. T cell responses to all three tumor antigens were comparable to viral antigen-specific responses with respect to frequency, duration, phenotype, epitope density, and MHC restriction. Thus, CMV-vectored cancer vaccines can bypass central tolerance by eliciting T cells to noncanonical epitopes. We further demonstrate that PAP-specific, MHC-E-restricted CD8+ T cells from RhCMV/PAP-immunized RM respond to PAP-expressing HLA-E+ prostate cancer cells, suggesting that the HLA-E/NKG2A immune checkpoint can be exploited for CD8+ T cell-based immunotherapies.

Tumor Antigens beyond the Human Exome.

With the advent of immunotherapeutics, a new era in the combat against cancer has begun. Particularly promising are neo-epitope-targeted therapies as the expression of neo-antigens is tumor-specific. In turn, this allows the selective targeting and killing of cancer cells whilst healthy cells remain largely unaffected. So far, many advances have been made in the development of treatment options which are tailored to the individual neo-epitope repertoire. The next big step is the achievement of efficacious "off-the-shelf" immunotherapies. For this, shared neo-epitopes propose an optimal target. Given the tremendous potential, a thorough understanding of the underlying mechanisms which lead to the formation of neo-antigens is of fundamental importance. Here, we review the various processes which result in the formation of neo-epitopes. Broadly, the origin of neo-epitopes can be categorized into three groups: canonical, noncanonical, and viral neo-epitopes. For the canonical neo-antigens that arise in direct consequence of somatic mutations, we summarize past and recent findings. Beyond that, our main focus is put on the discussion of noncanonical and viral neo-epitopes as we believe that targeting those provides an encouraging perspective to shape the future of cancer immunotherapeutics.

Immunogenic cell death-based cancer vaccines: promising prospect in cancer therapy.

Tumor immunotherapy is a promising approach for addressing the limitations of conventional tumor treatments, such as chemotherapy and radiotherapy, which often have side effects and fail to prevent recurrence and metastasis. However, the effectiveness and sustainability of immune activation in tumor immunotherapy remain challenging. Tumor immunogenic cell death, characterized by the release of immunogenic substances, damage associated molecular patterns (DAMPs), and tumor associated antigens, from dying tumor cells (DTCs), offers a potential solution. By enhancing the immunogenicity of DTCs through the inclusion of more immunogenic antigens and stimulating factors, immunogenic cell death (ICD) based cancer vaccines can be developed as a powerful tool for immunotherapy. Integrating ICD nanoinducers into conventional treatments like chemotherapy, photodynamic therapy, photothermal therapy, sonodynamic therapy, and radiotherapy presents a novel strategy to enhance treatment efficacy and potentially improve patient outcomes. Preclinical research has identified numerous potential ICD inducers. However, effectively translating these findings into clinically relevant applications remains a critical challenge. This review aims to contribute to this endeavor by providing valuable insights into the in vitro preparation of ICD-based cancer vaccines. We explored established tools for ICD induction, followed by an exploration of personalized ICD induction strategies and vaccine designs. By sharing this knowledge, we hope to stimulate further development and advancement in the field of ICD-based cancer vaccines.

Evaluation of the antitumor effect of neoantigen peptide vaccines derived from the translatome of lung cancer.

Emerging evidence suggests that tumor-specific neoantigens are ideal targets for cancer immunotherapy. However, how to predict tumor neoantigens based on translatome data remains obscure. Through the extraction of ribosome-nascent chain complexes (RNCs) from LLC cells, followed by RNC-mRNA extraction, RNC-mRNA sequencing, and comprehensive bioinformatic analysis, we successfully identified proteins undergoing translatome and exhibiting mutations in the cells. Subsequently, novel antigens identification was analyzed by the interaction between their high affinity and the Major Histocompatibility Complex (MHC). Neoantigens immunogenicity was analyzed by enzyme-linked immunospot assay (ELISpot). Finally, in vivo experiments in mice were conducted to evaluate the antitumor effects of translatome-derived neoantigen peptides on lung cancer. The results showed that ten neoantigen peptides were identified and synthesized by translatome data from LLC cells; 8 out of the 10 neoantigens had strong immunogenicity. The neoantigen peptide vaccine group exhibited significant tumor growth inhibition effect. In conclusion, neoantigen peptide vaccine derived from the translatome of lung cancer exhibited significant tumor growth inhibition effect.

Exploring dendritic cell subtypes in cancer immunotherapy: unraveling the role of mature regulatory dendritic cells.

Dendritic cells (DCs) possess a specialized function in presenting antigens and play pivotal roles in both innate and adaptive immune responses. Their ability to cross-present antigens from tumor cells to naïve T cells is instrumental in generating specific T-cell-mediated antitumor responses, crucial for controlling tumor growth and preventing tumor cell dissemination. However, within a tumor immune microenvironment (TIME), the functions of DCs can be significantly compromised. This review focuses on the profile, function, and activation of DCs, leveraging recent studies that reveal insights into their phenotype acquisition, transcriptional state, and functional programs through single-cell RNA sequence (scRNA-seq) analysis. Additionally, the therapeutic potential of DC-mediated tumor antigen sensing in priming antitumor immunity is discussed.

Predictability of B cell clonal persistence and immunosurveillance in breast cancer.

B cells and T cells are important components of the adaptive immune system and mediate anticancer immunity. The T cell landscape in cancer is well characterized, but the contribution of B cells to anticancer immunosurveillance is less well explored. Here we show an integrative analysis of the B cell and T cell receptor repertoire from individuals with metastatic breast cancer and individuals with early breast cancer during neoadjuvant therapy. Using immune receptor, RNA and whole-exome sequencing, we show that both B cell and T cell responses seem to coevolve with the metastatic cancer genomes and mirror tumor mutational and neoantigen architecture. B cell clones associated with metastatic immunosurveillance and temporal persistence were more expanded and distinct from site-specific clones. B cell clonal immunosurveillance and temporal persistence are predictable from the clonal structure, with higher-centrality B cell antigen receptors more likely to be detected across multiple metastases or across time. This predictability was generalizable across other immune-mediated disorders. This work lays a foundation for prioritizing antibody sequences for therapeutic targeting in cancer.

Engineered Bacteriophage-Based In Situ Vaccine Remodels a Tumor Microenvironment and Elicits Potent Antitumor Immunity.

In situ vaccines (ISVs) utilize the localized delivery of chemotherapeutic agents or radiotherapy to stimulate the release of endogenous antigens from tumors, thereby eliciting systemic and persistent immune activation. Recently, a bioinspired ISV strategy has attracted tremendous attention due to its features such as an immune adjuvant effect and genetic plasticity. M13 bacteriophages are natural nanomaterials with intrinsic immunogenicity, genetic flexibility, and cost-effectiveness for large-scale production, demonstrating the potential for application in cancer vaccines. In this study, we propose an ISV based on the engineered M13 bacteriophage targeting CD40 (M13CD40) for dendritic cell (DC)-targeted immune stimulation, named H-GM-M13CD40. We induce immunogenic cell death and release tumor antigens through local delivery of (S)-10-hydroxycamptothecin (HCPT), followed by intratumoral injection of granulocyte-macrophage colony stimulating factor (GM-CSF) and M13CD40 to enhance DC recruitment and activation. We demonstrate that this ISV strategy can result in significant accumulation and activation of DCs at the tumor site, reversing the immunosuppressive tumor microenvironment. In addition, H-GM-M13CD40 can synergize with the PD-1 blockade and induce abscopal effects in cold tumor models. Overall, our study verifies the immunogenicity of the engineered M13CD40 bacteriophage and provides a proof of concept that the engineered M13CD40 phage can function as an adjuvant for ISVs.

RNA aggregates harness the danger response for potent cancer immunotherapy.

Cancer immunotherapy remains limited by poor antigenicity and a regulatory tumor microenvironment (TME). Here, we create "onion-like" multi-lamellar RNA lipid particle aggregates (LPAs) to substantially enhance the payload packaging and immunogenicity of tumor mRNA antigens. Unlike current mRNA vaccine designs that rely on payload packaging into nanoparticle cores for Toll-like receptor engagement in immune cells, systemically administered RNA-LPAs activate RIG-I in stromal cells, eliciting massive cytokine/chemokine response and dendritic cell/lymphocyte trafficking that provokes cancer immunogenicity and mediates rejection of both early- and late-stage murine tumor models. In client-owned canines with terminal gliomas, RNA-LPAs improved survivorship and reprogrammed the TME, which became "hot" within days of a single infusion. In a first-in-human trial, RNA-LPAs elicited rapid cytokine/chemokine release, immune activation/trafficking, tissue-confirmed pseudoprogression, and glioma-specific immune responses in glioblastoma patients. These data support RNA-LPAs as a new technology that simultaneously reprograms the TME while eliciting rapid and enduring cancer immunotherapy.

Tumor-Derived Antigenic Peptides as Potential Cancer Vaccines.

Peptide antigens derived from tumors have been observed to elicit protective immune responses, categorized as either tumor-associated antigens (TAAs) or tumor-specific antigens (TSAs). Subunit cancer vaccines incorporating these antigens have shown promise in inducing protective immune responses, leading to cancer prevention or eradication. Over recent years, peptide-based cancer vaccines have gained popularity as a treatment modality and are often combined with other forms of cancer therapy. Several clinical trials have explored the safety and efficacy of peptide-based cancer vaccines, with promising outcomes. Advancements in techniques such as whole-exome sequencing, next-generation sequencing, and in silico methods have facilitated the identification of antigens, making it increasingly feasible. Furthermore, the development of novel delivery methods and a deeper understanding of tumor immune evasion mechanisms have heightened the interest in these vaccines among researchers. This article provides an overview of novel insights regarding advancements in the field of peptide-based vaccines as a promising therapeutic avenue for cancer treatment. It summarizes existing computational methods for tumor neoantigen prediction, ongoing clinical trials involving peptide-based cancer vaccines, and recent studies on human vaccination experiments.

Liposome Nanomedicine Based on Tumor Cell Lysate Mitigates the Progression of Lynch Syndrome-Associated Colon Cancer.

Treatment with immune checkpoint inhibitors (ICIs) has shown efficacy in some patients with Lynch syndrome-associated colon cancer, but some patients still do not benefit from it. In this study, we adopted a combination strategy of tumor vaccines and ICIs to maximize the benefits of immunotherapy. Here, we obtained tumor-antigen-containing cell lysate (TCL) by lysing MC38Mlh1 KD cells and prepared liposome nanoparticles (Lipo-PEG) with a typical spherical morphology by thin-film hydration. Anti-PD-L1 was coupled to the liposome surface by the amidation reaction. As observed, anti-PD-L1/TCL@Lipo-PEG was not significantly toxic to mouse intestinal epithelial cells (MODE-K) in the safe concentration range and did not cause hemolysis of mouse red blood cells. In addition, anti-PD-L1/TCL@Lipo-PEG reduced immune escape from colon cancer cells (MC38Mlh1 KD) by the anti-PD-L1 antibody, restored the killing function of CD8+ T cells, and targeted more tumor antigens to bone marrow-derived dendritic cells (BMDCs), which also expressed PD-L1, to stimulate BMDC antigen presentation. In syngeneic transplanted Lynch syndrome-associated colon cancer mice, the combination of anti-PD-L1 and TCL provided better cancer suppression than monoimmunotherapy, and the cancer suppression effect of anti-PD-L1/TCL@Lipo-PEG treatment was even better than that of the free drug. Meanwhile anti-PD-L1/TCL@Lipo-PEG enhanced the immunosuppressive tumor microenvironment. In vivo fluorescence imaging and H&E staining showed that the nanomedicine was mainly retained in the tumor site and had no significant toxic side effects on other major organs. The anti-PD-L1/TCL@Lipo-PEG prepared in this study has high efficacy and good biosafety in alleviating the progression of Lynch syndrome-associated colon cancer, and it is expected to be a therapeutic candidate for Lynch syndrome-associated colon cancer.

Car T Cells in Solid Tumors: Overcoming Obstacles.

Chimeric antigen receptor T cell (CAR T cell) therapy has emerged as a prominent adoptive cell therapy and a therapeutic approach of great interest in the fight against cancer. This approach has shown notorious efficacy in refractory hematological neoplasm, which has bolstered its exploration in the field of solid cancers. However, successfully managing solid tumors presents considerable intrinsic challenges, which include the necessity of guiding the modified cells toward the tumoral region, assuring their penetration and survival in adverse microenvironments, and addressing the complexity of identifying the specific antigens for each type of cancer. This review focuses on outlining the challenges faced by CAR T cell therapy when used in the treatment of solid tumors, as well as presenting optimizations and emergent approaches directed at improving its efficacy in this particular context. From precise localization to the modulation of the tumoral microenvironment and the adaptation of antigen recognition strategies, diverse pathways will be examined to overcome the current limitations and buttress the therapeutic potential of CAR T cells in the fight against solid tumors.

NeoAgDT: optimization of personal neoantigen vaccine composition by digital twin simulation of a cancer cell population.

MOTIVATION: Neoantigen vaccines make use of tumor-specific mutations to enable the patient's immune system to recognize and eliminate cancer. Selecting vaccine elements, however, is a complex task which needs to take into account not only the underlying antigen presentation pathway but also tumor heterogeneity. RESULTS: Here, we present NeoAgDT, a two-step approach consisting of: (i) simulating individual cancer cells to create a digital twin of the patient's tumor cell population and (ii) optimizing the vaccine composition by integer linear programming based on this digital twin. NeoAgDT shows improved selection of experimentally validated neoantigens over ranking-based approaches in a study of seven patients. AVAILABILITY AND IMPLEMENTATION: The NeoAgDT code is published on Github: https://github.com/nec-research/neoagdt.

The phosphatase inhibitor LB-100 creates neoantigens in colon cancer cells through perturbation of mRNA splicing.

Perturbation of protein phosphorylation represents an attractive approach to cancer treatment. Besides kinase inhibitors, protein phosphatase inhibitors have been shown to have anti-cancer activity. A prime example is the small molecule LB-100, an inhibitor of protein phosphatases 2A/5 (PP2A/PP5), enzymes that affect cellular physiology. LB-100 has proven effective in pre-clinical models in combination with immunotherapy, but the molecular underpinnings of this synergy remain understood poorly. We report here a sensitivity of the mRNA splicing machinery to phosphorylation changes in response to LB-100 in colorectal adenocarcinoma. We observe enrichment for differentially phosphorylated sites within cancer-critical splicing nodes of U2 snRNP, SRSF and hnRNP proteins. Altered phosphorylation endows LB-100-treated colorectal adenocarcinoma cells with differential splicing patterns. In PP2A-inhibited cells, over 1000 events of exon skipping and intron retention affect regulators of genomic integrity. Finally, we show that LB-100-evoked alternative splicing leads to neoantigens that are presented by MHC class 1 at the cell surface. Our findings provide a potential explanation for the pre-clinical and clinical observations that LB-100 sensitizes cancer cells to immune checkpoint blockade.

Programming peptide-oligonucleotide nano-assembly for engineering of neoantigen vaccine with potent immunogenicity.

Background: Neoantigen nanovaccine has been recognized as a promising treatment modality for personalized cancer immunotherapy. However, most current nanovaccines are carrier-dependent and the manufacturing process is complicated, resulting in potential safety concerns and suboptimal codelivery of neoantigens and adjuvants to antigen-presenting cells (APCs). Methods: Here we report a facile and general methodology for nanoassembly of peptide and oligonucleotide by programming neoantigen peptide with a short cationic module at N-terminus to prepare nanovaccine. The programmed peptide can co-assemble with CpG oligonucleotide (TLR9 agonist) into monodispersed nanostructures without the introduction of artificial carrier. Results: We demonstrate that the engineered nanovaccine promoted the codelivery of neoantigen peptides and adjuvants to lymph node-residing APCs and instigated potent neoantigen-specific T-cell responses, eliciting neoantigen-specific antitumor immune responses with negligible systemic toxicity. Furthermore, the antitumor T-cell immunity is profoundly potentiated when combined with anti-PD-1 therapy, leading to significant inhibition or even complete regression of established melanoma and MC-38 colon tumors. Conclusions: Collectively, this work demonstrates the feasibility and effectiveness of personalized cancer nanovaccine preparation with high immunogenicity and good biosafety by programming neoantigen peptide for nanoassembly with oligonucleotides without the aid of artificial carrier.

State-Of-The-Art Advancements on Cancer Vaccines and Biomarkers.

The origins of cancer vaccines date back to the 1800s. Since then, there have been significant efforts to generate vaccines against solid and hematologic malignancies using a variety of platforms. To date, these efforts have generally been met with minimal success. However, in the era of improved methods and technological advancements, supported by compelling preclinical and clinical data, a wave of renewed interest in the field offers the promise of discovering field-changing paradigms in the management of established and resected disease using cancer vaccines. These include novel approaches to personalized neoantigen vaccine development, as well as innovative immune-modulatory vaccines (IMVs) that facilitate activation of antiregulatory T cells to limit immunosuppression caused by regulatory immune cells. This article will introduce some of the limitations that have affected cancer vaccine development over the past several decades, followed by an introduction to the latest advancements in neoantigen vaccine and IMV therapy, and then conclude with a discussion of some of the newest technologies and progress that are occurring across the cancer vaccine space. Cancer vaccines are among the most promising frontiers for breakthrough innovations and strategies poised to make a measurable impact in the ongoing fight against cancer.

Sa-TTCA: An SVM-based approach for tumor T-cell antigen classification using features extracted from biological sequencing and natural language processing.

Accurately predicting tumor T-cell antigen (TTCA) sequences is a crucial task in the development of cancer vaccines and immunotherapies. TTCAs derived from tumor cells, are presented to immune cells (T cells) through major histocompatibility complex (MHC), via the recognition of specific portions of their structure known as epitopes. More specifically, MHC class I introduces TTCAs to T-cell receptors (TCR) which are located on the surface of CD8+ T cells. However, TTCA sequences are varied and lead to struggles in vaccine design. Recently, Machine learning (ML) models have been developed to predict TTCA sequences which could aid in fast and correct TTCA identification. During the construction of the TTCA predictor, the peptide encoding strategy is an important step. Previous studies have used biological descriptors for encoding TTCA sequences. However, there have been no studies that use natural language processing (NLP), a potential approach for this purpose. As sentences have their own words with diverse properties, biological sequences also hold unique characteristics that reflect evolutionary information, physicochemical values, and structural information. We hypothesized that NLP methods would benefit the prediction of TTCA. To develop a new identifying TTCA model, we first constructed a based model with widely used ML algorithms and extracted features from biological descriptors. Then, to improve our model performance, we added extracted features from biological language models (BLMs) based on NLP methods. Besides, we conducted feature selection by using Chi-square and Pearson Correlation Coefficient techniques. Then, SMOTE, Up-sampling, and Near-Miss were used to treat unbalanced data. Finally, we optimized Sa-TTCA by the SVM algorithm to the four most effective feature groups. The best performance of Sa-TTCA showed a competitive balanced accuracy of 87.5% on a training set, and 72.0% on an independent testing set. Our results suggest that integrating biological descriptors with natural language processing has the potential to improve the precision of predicting protein/peptide functionality, which could be beneficial for developing cancer vaccines.