Pulmonary Fissure Segmentation in CT Images Using Image Filtering and Machine Learning.

BACKGROUND: Both lung lobe segmentation and lung fissure segmentation are useful in the clinical diagnosis and evaluation of lung disease. It is often of clinical interest to quantify each lobe separately because many diseases are associated with specific lobes. Fissure segmentation is important for a significant proportion of lung lobe segmentation methods, as well as for assessing fissure completeness, since there is an increasing requirement for the quantification of fissure integrity. METHODS: We propose a method for the fully automatic segmentation of pulmonary fissures on lung computed tomography (CT) based on U-Net and PAN models using a Derivative of Stick (DoS) filter for data preprocessing. Model ensembling is also used to improve prediction accuracy. RESULTS: Our method achieved an F1 score of 0.916 for right-lung fissures and 0.933 for left-lung fissures, which are significantly higher than the standalone DoS results (0.724 and 0.666, respectively). We also performed lung lobe segmentation using fissure segmentation. The lobe segmentation algorithm shows results close to those of state-of-the-art methods, with an average Dice score of 0.989. CONCLUSIONS: The proposed method segments pulmonary fissures efficiently and have low memory requirements, which makes it suitable for further research in this field involving rapid experimentation.

Bioassay Protocol Metadata Annotation: Proposed Standards Adoption.

We present a standardized metadata template for assays used in pharmaceutical drug discovery research, according to the FAIR principles. We also describe the use of an automated tool for annotating assays from a variety of sources, including PubChem, commercial assay providers, and the peer-reviewed literature, to this metadata template. Adoption of a standardized metadata template will allow drug discovery scientists to better understand and compare the increasing amounts of assay data becoming available, and will facilitate the use of artificial intelligence tools and other computational methods for analysis and prediction. Since bioassays drive advances in biomedical research, improvements in assay metadata can improve productivity in discovery of new therapeutics, platform technologies, and assay methods.

A Comprehensive Review of Protein Biomarkers for Invasive Lung Cancer.

Invasion and metastasis are important hallmarks of lung cancer, and affect patients' survival. Early diagnostics of metastatic potential are important for treatment management. Recent findings suggest that the transition to an invasive phenotype causes changes in the expression of 700-800 genes. In this context, the biomarkers restricted to the specific type of cancer, like lung cancer, are often overlooked. Some well-known protein biomarkers correlate with the progression of the disease and the immunogenicity of the tumor. Most of these biomarkers are not exclusive to lung cancer because of their significant role in tumorigenesis. The dysregulation of others does not necessarily indicate cell invasiveness, as they play an active role in cell division. Clinical studies of lung cancer use protein biomarkers to assess the invasiveness of cancer cells for therapeutic purposes. However, there is still a need to discover new biomarkers for lung cancer. In the future, minimally invasive techniques, such as blood or saliva analyses, may be sufficient for this purpose. Many researchers suggest unconventional biomarkers, like circulating nucleic acids, exosomal proteins, and autoantibodies. This review paper aims to discuss the advantages and limitations of protein biomarkers of invasiveness in lung cancer, to assess their prognostic value, and propose novel biomarker candidates.

Neoantigen immunogenicity landscapes and evolution of tumor ecosystems during immunotherapy with nivolumab.

Neoantigen immunoediting drives immune checkpoint blockade efficacy, yet the molecular features of neoantigens and how neoantigen immunogenicity shapes treatment response remain poorly understood. To address these questions, 80 patients with non-small cell lung cancer were enrolled in the biomarker cohort of CheckMate 153 (CA209-153), which collected radiographic guided biopsy samples before treatment and during treatment with nivolumab. Early loss of mutations and neoantigens during therapy are both associated with clinical benefit. We examined 1,453 candidate neoantigens, including many of which that had reduced cancer cell fraction after treatment with nivolumab, and identified 196 neopeptides that were recognized by T cells. Mapping these neoantigens to clonal dynamics, evolutionary trajectories and clinical response revealed a strong selection against immunogenic neoantigen-harboring clones. We identified position-specific amino acid and physiochemical features related to immunogenicity and developed an immunogenicity score. Nivolumab-induced microenvironmental evolution in non-small cell lung cancer shared some similarities with melanoma, yet critical differences were apparent. This study provides unprecedented molecular portraits of neoantigen landscapes underlying nivolumab's mechanism of action.

LVI-PathNet: Segmentation-classification pipeline for detection of lymphovascular invasion in whole slide images of lung adenocarcinoma.

Lymphovascular invasion (LVI) in lung cancer is a significant prognostic factor that influences treatment and outcomes, yet its reliable detection is challenging due to interobserver variability. This study aims to develop a deep learning model for LVI detection using whole slide images (WSIs) and evaluate its effectiveness within a pathologist's information system. Experienced pathologists annotated blood vessels and invading tumor cells in 162 WSIs of non-mucinous lung adenocarcinoma sourced from two external and one internal datasets. Two models were trained to segment vessels and identify images with LVI features. DeepLabV3+ model achieved an Intersection-over-Union of 0.8840 and an area under the receiver operating characteristic curve (AUC-ROC) of 0.9869 in vessel segmentation. For LVI classification, the ensemble model achieved a F1-score of 0.9683 and an AUC-ROC of 0.9987. The model demonstrated robustness and was unaffected by variations in staining and image quality. The pilot study showed that pathologists' evaluation time for LVI detecting decreased by an average of 16.95%, and by 21.5% in "hard cases". The model facilitated consistent diagnostic assessments, suggesting potential for broader applications in detecting pathological changes in blood vessels and other lung pathologies.

Devices and Methods for Dosimetry of Personalized Photodynamic Therapy of Tumors: A Review on Recent Trends.

Significance: Despite the widespread use of photodynamic therapy in clinical practice, there is a lack of personalized methods for assessing the sufficiency of photodynamic exposure on tumors, depending on tissue parameters that change during light irradiation. This can lead to different treatment results. Aim: The objective of this article was to conduct a comprehensive review of devices and methods employed for the implicit dosimetric monitoring of personalized photodynamic therapy for tumors. Methods: The review included 88 peer-reviewed research articles published between January 2010 and April 2024 that employed implicit monitoring methods, such as fluorescence imaging and diffuse reflectance spectroscopy. Additionally, it encompassed computer modeling methods that are most often and successfully used in preclinical and clinical practice to predict treatment outcomes. The Internet search engine Google Scholar and the Scopus database were used to search the literature for relevant articles. Results: The review analyzed and compared the results of 88 peer-reviewed research articles presenting various methods of implicit dosimetry during photodynamic therapy. The most prominent wavelengths for PDT are in the visible and near-infrared spectral range such as 405, 630, 660, and 690 nm. Conclusions: The problem of developing an accurate, reliable, and easily implemented dosimetry method for photodynamic therapy remains a current problem, since determining the effective light dose for a specific tumor is a decisive factor in achieving a positive treatment outcome.

Good machine learning practices: Learnings from the modern pharmaceutical discovery enterprise.

Machine Learning (ML) and Artificial Intelligence (AI) have become an integral part of the drug discovery and development value chain. Many teams in the pharmaceutical industry nevertheless report the challenges associated with the timely, cost effective and meaningful delivery of ML and AI powered solutions for their scientists. We sought to better understand what these challenges were and how to overcome them by performing an industry wide assessment of the practices in AI and Machine Learning. Here we report results of the systematic business analysis of the personas in the modern pharmaceutical discovery enterprise in relation to their work with the AI and ML technologies. We identify 23 common business problems that individuals in these roles face when they encounter AI and ML technologies at work, and describe best practices (Good Machine Learning Practices) that address these issues.

Mathematical Modeling of Non-Small-Cell Lung Cancer Biology through the Experimental Data on Cell Composition and Growth of Patient-Derived Organoids.

Mathematical models of non-small-cell lung cancer are powerful tools that use clinical and experimental data to describe various aspects of tumorigenesis. The developed algorithms capture phenotypic changes in the tumor and predict changes in tumor behavior, drug resistance, and clinical outcomes of anti-cancer therapy. The aim of this study was to propose a mathematical model that predicts the changes in the cellular composition of patient-derived tumor organoids over time with a perspective of translation of these results to the parental tumor, and therefore to possible clinical course and outcomes for the patient. Using the data on specific biomarkers of cancer cells (PD-L1), tumor-associated macrophages (CD206), natural killer cells (CD8), and fibroblasts (αSMA) as input, we proposed a model that accurately predicts the cellular composition of patient-derived tumor organoids at a desired time point. Combining the obtained results with "omics" approaches will improve our understanding of the nature of non-small-cell lung cancer. Moreover, their implementation into clinical practice will facilitate a decision-making process on treatment strategy and develop a new personalized approach in anti-cancer therapy.

Artificial Intelligence Assists in the Detection of Blood Vessels in Whole Slide Images: Practical Benefits for Oncological Pathology.

The analysis of the microvasculature and the assessment of angiogenesis have significant prognostic value in various diseases, including cancer. The search for invasion into the blood and lymphatic vessels and the assessment of angiogenesis are important aspects of oncological diagnosis. These features determine the prognosis and aggressiveness of the tumor. Traditional manual evaluation methods are time consuming and subject to inter-observer variability. Blood vessel detection is a perfect task for artificial intelligence, which is capable of rapid analyzing thousands of tissue structures in whole slide images. The development of computer vision solutions requires the segmentation of tissue regions, the extraction of features and the training of machine learning models. In this review, we focus on the methodologies employed by researchers to identify blood vessels and vascular invasion across a range of tumor localizations, including breast, lung, colon, brain, renal, pancreatic, gastric and oral cavity cancers. Contemporary models herald a new era of computational pathology in morphological diagnostics.

Characterizing the Immune Microenvironment and Neoantigen Landscape of Hürthle Cell Carcinoma to Identify Potential Immunologic Vulnerabilities.

Hürthle cell carcinoma (HCC) is a rare type of thyroid cancer with high rates of distant metastasis and recurrence. Along with the scarcity of effective systemic therapies for HCC, these factors contribute to poor clinical outcomes. The immunologic features of HCC are poorly defined and response rates with immune checkpoint blockade have not been reported. A more comprehensive understanding of the immune landscape and factors that predict response to checkpoint inhibitors is needed. We performed RNA sequencing on 40 tumors to characterize the neoantigen landscape and immune microenvironment of HCC. We analyzed transcriptomic profiles, tumor-infiltrating immune cell populations, and measures of T-cell activation/dysfunction and correlated these to genetic features such as tumor mutation burden, neoantigen burden, mitochondrial mutations, and LOH from chromosomal uniparental disomy. Finally, immune profiles of patients with recurrence were compared with those of patients without recurrence. HCC tumors exhibited low levels of immune infiltration, with the more aggressive widely invasive phenotype associated with more immune depletion. There was a negative correlation between tumor mutation burden, neoantigen burden, programmed cell death ligand 1 (PD-L1) expression, and the immune infiltration score. HCC tumors that exhibited a global LOH from chromosomal uniparental disomy or haploidization had the lowest level of immune infiltration. HCC tumors that recurred displayed an immune-depleted microenvironment associated with global LOH and aerobic glycolysis. These findings offer new insights into the functional immune landscapes and immune microenvironment of HCC. Our data identify potential immunologic vulnerabilities for these understudied and often fatal cancers. Significance: The immune landscape of HCC is poorly defined and response rates to immunotherapy have not been reported. The authors found the immune microenvironment in HCC to be depleted. This immunosuppression is associated with a global LOH from haploidization and uniparental disomy, resulting in whole chromosome losses across the genome.

Nivolumab plus ipilimumab in advanced salivary gland cancer: a phase 2 trial.

Salivary gland cancers (SGCs) are rare, aggressive cancers without effective treatments when metastasized. We conducted a phase 2 trial evaluating nivolumab (nivo, anti-PD-1) and ipilimumab (ipi, anti-CTLA-4) in 64 patients with metastatic SGC enrolled in two histology-based cohorts (32 patients each): adenoid cystic carcinoma (ACC; cohort 1) and other SGCs (cohort 2). The primary efficacy endpoint (≥4 objective responses) was met in cohort 2 (5/32, 16%) but not in cohort 1 (2/32, 6%). Treatment safety/tolerability and progression-free survival (PFS) were secondary endpoints. Treatment-related adverse events grade ≥3 occurred in 24 of 64 (38%) patients across both cohorts, and median PFS was 4.4 months (95% confidence interval (CI): 2.4, 8.3) and 2.2 months (95% CI: 1.8, 5.3) for cohorts 1 and 2, respectively. We present whole-exome, RNA and T cell receptor (TCR) sequencing data from pre-treatment and on-treatment tumors and immune cell flow cytometry and TCR sequencing from peripheral blood at serial timepoints. Responding tumors universally demonstrated clonal expansion of pre-existing T cells and mutational contraction. Responding ACCs harbored neoantigens, including fusion-derived neoepitopes, that induced T cell responses ex vivo. This study shows that nivo+ipi has limited efficacy in ACC, albeit with infrequent, exceptional responses, and that it could be promising for non-ACC SGCs, particularly salivary duct carcinomas. ClinicalTrials.gov identifier: NCT03172624 .

Using domain adaptation for classification of healthy and disease conditions from mobile-captured images of standard 12-lead electrocardiograms.

12-lead electrocardiogram (ECG) recordings can be collected in any clinic and the interpretation is performed by a clinician. Modern machine learning tools may make them automatable. However, a large fraction of 12-lead ECG data is still available in printed paper or image only and comes in various formats. To digitize the data, smartphone cameras can be used. Nevertheless, this approach may introduce various artifacts and occlusions into the obtained images. Here we overcome the challenges of automating 12-lead ECG analysis using mobile-captured images and a deep neural network that is trained using a domain adversarial approach. The net achieved an average 0.91 receiver operating characteristic curve on tested images captured by a mobile device. Assessment on image from unseen 12-lead ECG formats that the network was not trained on achieved high accuracy. We further show that the network accuracy can be improved by including a small number of unlabeled samples from unknown formats in the training data. Finally, our models also achieve high accuracy using signals as input rather than images. Using a domain adaptation approach, we successfully classified cardiac conditions on images acquired by a mobile device and showed the generalizability of the classification using various unseen image formats.

Paramagnetism in Microwave-Synthesized Metal-Free Nitrogen-Doped Graphene Quantum Dots.

Nitrogen-doped graphene quantum dots (NGQDs) have gained significant attention due to their various physical and chemical properties; however, there is a gap in the study of NGQDs' magnetic properties. This work adds to the efforts of bridging the gap by demonstrating the room temperature paramagnetism in GQDs doped with Nitrogen up to 3.26 at.%. The focus of this experimental work was to confirm the paramagnetic behavior of metal free NGQDs resulting from the pyridinic N configuration in the GQDs host. Metal-free nitrogen-doped NGQDs were synthesized using glucose and liquid ammonia as precursors by microwave-assisted synthesis. This was followed by dialysis filtration. The morphology, optical, and magnetic properties of the synthesized NGQDs were characterized carefully through atomic force microscopy (AFM), transmission electron microscopy (TEM)), UV-VIS spectroscopy, fluorescence, X-ray photon spectroscopy (XPS), and vibrating sample magnetometer (VSM). The high-resolution TEM analysis of NGQDs showed that the NGQDs have a hexagonal crystalline structure with a lattice fringe of ~0.24 nm of (1120) graphene plane. The N1s peak using XPS was assigned to pyridinic, pyrrolic, graphitic, and oxygenated NGQDs. The magnetic study showed the room-temperature paramagnetic behavior of NGQDs with pyridinic N configuration, which was found to have a magnetization of 20.8 emu/g.

Immunotherapy with IL12 and PD1/CTLA4 inhibition is effective in advanced ovarian cancer and associates with reversal of myeloid cell-induced immunosuppression.

The tumor microenvironment (TME) in ovarian cancer (OC) is characterized by immune suppression, due to an abundance of suppressive immune cells populations. To effectively enhance the activity of immune checkpoint inhibition (ICI), there is a need to identify agents that target these immunosuppressive networks while promoting the recruitment of effector T cells into the TME. To this end, we sought to investigate the effect of the immunomodulatory cytokine IL12 alone or in combination with dual-ICI (anti-PD1 + anti-CTLA4) on anti-tumor activity and survival, using the immunocompetent ID8-VEGF murine OC model. Detailed immunophenotyping of peripheral blood, ascites, and tumors revealed that durable treatment responses were associated with reversal of myeloid cell-induced immune suppression, which resulted in enhanced anti-tumor activity by T cells. Single cell transcriptomic analysis further demonstrated striking differences in the phenotype of myeloid cells from mice treated with IL12 in combination with dual-ICI. We also identified marked differences in treated mice that were in remission compared to those whose tumors progressed, further confirming a pivotal role for the modulation of myeloid cell function to allow for response to immunotherapy. These findings provide the scientific basis for the combination of IL12 and ICI to improve clinical response in OC.

Novel Genetic Subtypes of Urothelial Carcinoma With Differential Outcomes on Immune Checkpoint Blockade.

PURPOSE: Immune checkpoint blockade (ICB) therapy has significantly improved clinical outcomes in bladder cancer. Identification of correlates of benefit is critical to select appropriate therapy for individual patients. METHODS: To reveal genetic variables associated with benefit from ICB, we performed whole-exome sequencing on tumor specimens from 88 patients with advanced bladder cancer treated with ICB. RESULTS: We identified several genetic factors that correlated with progression-free and overall survival after ICB therapy including ARID1A mutation, tumor mutational burden, intratumoral heterogeneity, the ratio of nonsynonymous to synonymous mutations in the immunopeptidome (immune dN/dS), and tumor cell purity. In addition, we noted that neutrophil-to-lymphocyte ratio and smoking history were negatively associated with overall survival. These genetic characteristics define four molecular subtypes demonstrating differential sensitivity to ICB. We validated the association of these four subtypes with clinical benefit from ICB in an independent cohort (IMvigor210). Finally, we showed that these molecular subtypes also correlate with outcome, although with distinct relationships, among patients not treated with ICB using The Cancer Genome Atlas (TCGA) bladder cancer cohort. Using parallel RNA sequencing data, the subtypes were also shown to correlate with immune infiltration and inflammation, respectively, in the IMvigor210 and TCGA cohorts. CONCLUSION: Together, our study defines molecular subgroups of bladder cancer that influence benefit from ICB.

Optical spectral diagnostics of the oxygenation level in periodontal tissues and photodynamic therapy using methylene blue in children with cerebral palsy.

Dental diseases occur in children with cerebral palsy three times higher than in healthy children. Low values of the unstimulated salivation rate (<0.3 ml per minute), pH and buffer capacity, changes in enzyme activity and sialic acid concentration, as well as increased saliva osmolarity and total protein concentration, which indicates impaired hydration, are the factors in the development of a gingiva disease in case of cerebral palsy. This leads to increased bacterial agglutination and the formation of acquired pellicle and biofilm, leading to the formation of dental plaque. There is a tendency toward an increase in the concentration of hemoglobin and a decrease in the degree of hemoglobin oxygenation, as well as an increase in the generation of reactive oxygen and nitrogen species. Photodynamic therapy (PDT) with the use of photosensitizer methylene blue improves blood circulation and the degree of oxygenation in periodontal tissues, as well as eliminates a bacterial biofilm. Analysis of back diffuse reflection spectra makes it possible to conduct non-invasive monitoring determine tissue areas with a low level of hemoglobin oxygenation for precision photodynamic exposure. Aim: To improve the effectiveness of phototheranostics methods using, namely PDT with simultaneous optical-spectral control, for the treatment of gingivitis in children with complex dental and somatic status (cerebral palsy). Methods: The study involved 15 children (6-18 y.o.) with various forms of cerebral palsy, in particular, spastic diplegia and atonic-astatic form and with gingivitis. The degree of hemoglobin oxygenation was measured in tissues before PDT and on the 12th day. PDT was performed using laser radiation (λ = 660 nm) with a power density of 150 mW/cm2 with a five-minute application of 0.01% MB. The total light dose was 45 ± 15 J/cm2. For statistical evaluation of the results, a paired Student's t-test was used. Results: The paper presents the results of phototheranostics using methylene blue in children with cerebral palsy. An increase in the level of hemoglobin oxygenation from 50 to 67% (p < 0.001) and a decrease in blood volume in the microcirculatory bed of periodontal tissues were shown. Conclusion: Photodynamic therapy methods with application of methylene blue make it possible to assess the state of the gingival mucosa tissue diseases objectively in real time, and to provide effective targeted therapy for gingivitis in children with cerebral palsy. There is a prospect that they can become widely used clinical methods.

Activation of enzymatic ethanol oxidation by ATP hydrolysis energy transferred to ADH1A enzyme molecule over Müller cell intermediate filaments.

Presently exciton activation of enzymatic oxidation of ethanol by human alcohol dehydrogenase (ADH) 1A enzyme is reported. The ADH1A enzyme was activated by infrared (IR) excitons transferred over Müller cell (MC) intermediate filaments (IFs). These IR excitons were generated by energy liberated upon enzymatic ATP hydrolysis and transferred to IFs. Also, the emission spectrum was recorded of the electronically excited ADH1A…NAD+…EtOH complexes obtained by energy transfer from IR excitons that traveled along IFs. These results support the hypothesis that ATP hydrolysis energy may be transmitted in vivo in the form of IR excitons, over the network of IFs, both within and between cells.

KDM6A Loss Triggers an Epigenetic Switch That Disrupts Urothelial Differentiation and Drives Cell Proliferation in Bladder Cancer.

Disruption of KDM6A, a histone lysine demethylase, is one of the most common somatic alternations in bladder cancer. Insights into how KDM6A mutations affect the epigenetic landscape to promote carcinogenesis could help reveal potential new treatment approaches. Here, we demonstrated that KDM6A loss triggers an epigenetic switch that disrupts urothelial differentiation and induces a neoplastic state characterized by increased cell proliferation. In bladder cancer cells with intact KDM6A, FOXA1 interacted with KDM6A to activate genes instructing urothelial differentiation. KDM6A-deficient cells displayed simultaneous loss of FOXA1 target binding and genome-wide redistribution of the bZIP transcription factor ATF3, which in turn repressed FOXA1-target genes and activated cell-cycle progression genes. Importantly, ATF3 depletion reversed the cell proliferation phenotype induced by KDM6A deficiency. These data establish that KDM6A loss engenders an epigenetic state that drives tumor growth in an ATF3-dependent manner, creating a potentially targetable molecular vulnerability. SIGNIFICANCE: A gain-of-function epigenetic switch that disrupts differentiation is triggered by inactivating KDM6A mutations in bladder cancer and can serve as a potential target for novel therapies.

Comparison of EMT-Related and Multi-Drug Resistant Gene Expression, Extracellular Matrix Production, and Drug Sensitivity in NSCLC Spheroids Generated by Scaffold-Free and Scaffold-Based Methods.

Multicellular 3D tumor models are becoming a powerful tool for testing of novel drug products and personalized anticancer therapy. Tumor spheroids, a commonly used 3D multicellular tumor model, more closely reproduce the tumor microenvironment than conventional 2D cell cultures. It should be noted that spheroids can be produced using different techniques, which can be subdivided into scaffold-free (SF) and scaffold-based (SB) methods. However, it remains unclear, to what extent spheroid properties depend on the method of their generation. In this study, we aimed to carry out a head-to-head comparison of drug sensitivity and molecular expression profile in SF and SB spheroids along with a monolayer (2D) cell culture. Here, we produced non-small cell lung cancer (NSCLC) spheroids based on human lung adenocarcinoma cell line A549. Drug sensitivity analysis of the tested cell cultures to five different chemotherapeutics resulted in IC50 (A549-SB) > IC50 (A549-SF) > IC50 (A549-2D) trend. It was found that SF and SB A549 spheroids displayed elevated expression levels of epithelial-to-mesenchymal transition (EMT) markers and proteins associated with drug resistance compared with the monolayer A549 cell culture. Enhanced drug resistance of A549-SB spheroids can be a result of larger diameters and elevated deposition of extracellular matrix (ECM) that impairs drug penetration into spheroids. Thus, the choice of the spheroid production method can influence the properties of the generated 3D cell culture and their drug resistance. This fact should be considered for correct interpretation of drug testing results.

Transcriptional and functional analyses of neoantigen-specific CD4 T cells during a profound response to anti-PD-L1 in metastatic Merkel cell carcinoma.

BACKGROUND: Merkel cell carcinoma (MCC) often responds to PD-1 pathway blockade, regardless of tumor-viral status (~80% of cases driven by the Merkel cell polyomavirus (MCPyV)). Prior studies have characterized tumor-specific T cell responses to MCPyV, which have typically been CD8, but little is known about the T cell response to UV-induced neoantigens. METHODS: A patient in her mid-50s with virus-negative (VN) MCC developed large liver metastases after a brief initial response to chemotherapy. She received anti-PD-L1 (avelumab) and had a partial response within 4 weeks. Whole exome sequencing (WES) was performed to determine potential neoantigen peptides. Characterization of peripheral blood neoantigen T cell responses was evaluated via interferon-gamma (IFNγ) ELISpot, flow cytometry and single-cell RNA sequencing. Tumor-resident T cells were characterized by multiplexed immunohistochemistry. RESULTS: WES identified 1027 tumor-specific somatic mutations, similar to the published average of 1121 for VN-MCCs. Peptide prediction with a binding cut-off of ≤100 nM resulted in 77 peptides that were synthesized for T cell assays. Although peptides were predicted based on class I HLAs, we identified circulating CD4 T cells targeting 5 of 77 neoantigens. In contrast, no neoantigen-specific CD8 T cell responses were detected. Neoantigen-specific CD4 T cells were undetectable in blood before anti-PD-L1 therapy but became readily detectible shortly after starting therapy. T cells produced robust IFNγ when stimulated by neoantigen (mutant) peptides but not by the normal (wild-type) peptides. Single cell RNAseq showed neoantigen-reactive T cells expressed the Th1-associated transcription factor (T-bet) and associated cytokines. These CD4 T cells did not significantly exhibit cytotoxicity or non-Th1 markers. Within the pretreatment tumor, resident CD4 T cells were also Th1-skewed and expressed T-bet. CONCLUSIONS: We identified and characterized tumor-specific Th1-skewed CD4 T cells targeting multiple neoantigens in a patient who experienced a profound and durable partial response to anti-PD-L1 therapy. To our knowledge, this is the first report of neoantigen-specific T cell responses in MCC. Although CD4 and CD8 T cells recognizing viral tumor antigens are often detectible in virus-positive MCC, only CD4 T cells recognizing neoantigens were detected in this patient. These findings suggest that CD4 T cells can play an important role in the response to anti-PD-(L)1 therapy.