Forecasting Acute Kidney Injury and Resource Utilization in ICU patients using longitudinal, multimodal models.

Background: Advances in artificial intelligence (AI) have realized the potential of revolutionizing healthcare, such as predicting disease progression via longitudinal inspection of Electronic Health Records (EHRs) and lab tests from patients admitted to Intensive Care Units (ICU). Although substantial literature exists addressing broad subjects, including the prediction of mortality, length-of-stay, and readmission, studies focusing on forecasting Acute Kidney Injury (AKI), specifically dialysis anticipation like Continuous Renal Replacement Therapy (CRRT) are scarce. The technicality of how to implement AI remains elusive. Objective: This study aims to elucidate the important factors and methods that are required to develop effective predictive models of AKI and CRRT for patients admitted to ICU, using EHRs in the Medical Information Mart for Intensive Care (MIMIC) database. Methods: We conducted a comprehensive comparative analysis of established predictive models, considering both time-series measurements and clinical notes from MIMIC-IV databases. Subsequently, we proposed a novel multi-modal model which integrates embeddings of top-performing unimodal models, including Long Short-Term Memory (LSTM) and BioMedBERT, and leverages both unstructured clinical notes and structured time series measurements derived from EHRs to enable the early prediction of AKI and CRRT. Results: Our multimodal model achieved a lead time of at least 12 hours ahead of clinical manifestation, with an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.888 for AKI and 0.997 for CRRT, as well as an Area Under the Precision Recall Curve (AUPRC) of 0.727 for AKI and 0.840 for CRRT, respectively, which significantly outperformed the baseline models. Additionally, we performed a SHapley Additive exPlanation (SHAP) analysis using the expected gradients algorithm, which highlighted important, previously underappreciated predictive features for AKI and CRRT. Conclusion: Our study revealed the importance and the technicality of applying longitudinal, multimodal modeling to improve early prediction of AKI and CRRT, offering insights for timely interventions. The performance and interpretability of our model indicate its potential for further assessment towards clinical applications, to ultimately optimize AKI management and enhance patient outcomes.

Prioritizing genomic variants pathogenicity via DNA, RNA, and protein-level features based on extreme gradient boosting.

Genetic diseases are mostly implicated with genetic variants, including missense, synonymous, non-sense, and copy number variants. These different kinds of variants are indicated to affect phenotypes in various ways from previous studies. It remains essential but challenging to understand the functional consequences of these genetic variants, especially the noncoding ones, due to the lack of corresponding annotations. While many computational methods have been proposed to identify the risk variants. Most of them have only curated DNA-level and protein-level annotations to predict the pathogenicity of the variants, and others have been restricted to missense variants exclusively. In this study, we have curated DNA-, RNA-, and protein-level features to discriminate disease-causing variants in both coding and noncoding regions, where the features of protein sequences and protein structures have been shown essential for analyzing missense variants in coding regions while the features related to RNA-splicing and RBP binding are significant for variants in noncoding regions and synonymous variants in coding regions. Through the integration of these features, we have formulated the Multi-level feature Genomic Variants Predictor (ML-GVP) using the gradient boosting tree. The method has been trained on more than 400,000 variants in the Sherloc-training set from the 6th critical assessment of genome interpretation with superior performance. The method is one of the two best-performing predictors on the blind test in the Sherloc assessment, and is further confirmed by another independent test dataset of de novo variants.

Preliminary exploration of animal models of congenital choledochal cysts.

BACKGROUND: Various animal models have been used to explore the pathogenesis of choledochal cysts (CCs), but with little convincing results. Current surgical techniques can achieve satisfactory outcomes for treatment of CCs. Consequently, recent studies have focused more on clinical issues rather than basic research. Therefore, we need appropriate animal models to further basic research. AIM: To establish an appropriate animal model that may contribute to the investigation of the pathogenesis of CCs. METHODS: Eighty-four specific pathogen-free female Sprague-Dawley rats were randomly allocated to a surgical group, sham surgical group, or control group. A rat model of CC was established by partial ligation of the bile duct. The reliability of the model was confirmed by measurements of serum biochemical indices, morphology of common bile ducts of the rats as well as molecular biology experiments in rat and human tissues. RESULTS: Dilation classified as mild (diameter, ≥ 1 mm to < 3 mm), moderate (≥ 3 mm to < 10 mm), and severe (≥ 10 mm) was observed in 17, 17, and 2 rats in the surgical group, respectively, while no dilation was observed in the control and sham surgical groups. Serum levels of alanine aminotransferase, aspartate aminotransferase, total bilirubin, direct bilirubin, and total bile acids were significantly elevated in the surgical group as compared to the control group 7 d after surgery, while direct bilirubin, total bilirubin, and gamma-glutamyltransferase were further increased 14 d after surgery. Most of the biochemical indices gradually decreased to normal ranges 28 d after surgery. The protein expression trend of signal transducer and activator of transcription 3 in rat model was consistent with the human CC tissues. CONCLUSION: The model of partial ligation of the bile duct of juvenile rats could morphologically simulate the cystic or fusiform CC, which may contribute to investigating the pathogenesis of CC.

Irisin attenuates type 1 diabetic cardiomyopathy by anti-ferroptosis via SIRT1-mediated deacetylation of p53.

BACKGROUND: Diabetic cardiomyopathy (DCM) is a serious complication in patients with type 1 diabetes mellitus (T1DM), which still lacks adequate therapy. Irisin, a cleavage peptide off fibronectin type III domain-containing 5, has been shown to preserve cardiac function in cardiac ischemia-reperfusion injury. Whether or not irisin plays a cardioprotective role in DCM is not known. METHODS AND RESULTS: T1DM was induced by multiple low-dose intraperitoneal injections of streptozotocin (STZ). Our current study showed that irisin expression/level was lower in the heart and serum of mice with STZ-induced TIDM. Irisin supplementation by intraperitoneal injection improved the impaired cardiac function in mice with DCM, which was ascribed to the inhibition of ferroptosis, because the increased ferroptosis, associated with increased cardiac malondialdehyde (MDA), decreased reduced glutathione (GSH) and protein expressions of solute carrier family 7 member 11 (SLC7A11) and glutathione peroxidase 4 (GPX4), was ameliorated by irisin. In the presence of erastin, a ferroptosis inducer, the irisin-mediated protective effects were blocked. Mechanistically, irisin treatment increased Sirtuin 1 (SIRT1) and decreased p53 K382 acetylation, which decreased p53 protein expression by increasing its degradation, consequently upregulated SLC7A11 and GPX4 expressions. Thus, irisin-mediated reduction in p53 decreases ferroptosis and protects cardiomyocytes against injury due to high glucose. CONCLUSION: This study demonstrated that irisin could improve cardiac function by suppressing ferroptosis in T1DM via the SIRT1-p53-SLC7A11/GPX4 pathway. Irisin may be a therapeutic approach in the management of T1DM-induced cardiomyopathy.

Interpretable Spatial Gradient Analysis for Spatial Transcriptomics Data.

Cellular anatomy and signaling vary across niches, which can induce gradated gene expressions in subpopulations of cells. Such spatial transcriptomic gradient (STG) makes a significant source of intratumor heterogeneity and can influence tumor invasion, progression, and response to treatment. Here we report Local Spatial Gradient Inference (LSGI), a computational framework that systematically identifies spatial locations with prominent, interpretable STGs from spatial transcriptomic (ST) data. To achieve so, LSGI scrutinizes each sliding window employing non-negative matrix factorization (NMF) combined with linear regression. With LSGI, we demonstrated the identification of spatially proximal yet opposite directed pathway gradients in a glioblastoma dataset. We further applied LSGI to 87 tumor ST datasets reported from nine published studies and identified both pan-cancer and tumor-type specific pathways with gradated expression patterns, such as epithelial mesenchymal transition, MHC complex, and hypoxia. The local gradients were further categorized according to their association to tumor-TME (tumor microenvironment) interface, highlighting the pathways related to spatial transcriptional intratumoral heterogeneity. We conclude that LSGI enables highly interpretable STG analysis which can reveal novel insights in tumor biology from the increasingly reported tumor ST datasets.

Self-supervised learning on millions of primary RNA sequences from 72 vertebrates improves sequence-based RNA splicing prediction.

Language models pretrained by self-supervised learning (SSL) have been widely utilized to study protein sequences, while few models were developed for genomic sequences and were limited to single species. Due to the lack of genomes from different species, these models cannot effectively leverage evolutionary information. In this study, we have developed SpliceBERT, a language model pretrained on primary ribonucleic acids (RNA) sequences from 72 vertebrates by masked language modeling, and applied it to sequence-based modeling of RNA splicing. Pretraining SpliceBERT on diverse species enables effective identification of evolutionarily conserved elements. Meanwhile, the learned hidden states and attention weights can characterize the biological properties of splice sites. As a result, SpliceBERT was shown effective on several downstream tasks: zero-shot prediction of variant effects on splicing, prediction of branchpoints in humans, and cross-species prediction of splice sites. Our study highlighted the importance of pretraining genomic language models on a diverse range of species and suggested that SSL is a promising approach to enhance our understanding of the regulatory logic underlying genomic sequences.

Deciphering cell types by integrating scATAC-seq data with genome sequences.

The single-cell assay for transposase-accessible chromatin using sequencing (scATAC-seq) technology provides insight into gene regulation and epigenetic heterogeneity at single-cell resolution, but cell annotation from scATAC-seq remains challenging due to high dimensionality and extreme sparsity within the data. Existing cell annotation methods mostly focus on the cell peak matrix without fully utilizing the underlying genomic sequence. Here we propose a method, SANGO, for accurate single-cell annotation by integrating genome sequences around the accessibility peaks within scATAC data. The genome sequences of peaks are encoded into low-dimensional embeddings, and then iteratively used to reconstruct the peak statistics of cells through a fully connected network. The learned weights are considered as regulatory modes to represent cells, and utilized to align the query cells and the annotated cells in the reference data through a graph transformer network for cell annotations. SANGO was demonstrated to consistently outperform competing methods on 55 paired scATAC-seq datasets across samples, platforms and tissues. SANGO was also shown to be able to detect unknown tumor cells through attention edge weights learned by the graph transformer. Moreover, from the annotated cells, we found cell-type-specific peaks that provide functional insights/biological signals through expression enrichment analysis, cis-regulatory chromatin interaction analysis and motif enrichment analysis.

A Scalable and Robust Personal Health Management Textile with Multiple Desired Thermal Functions and Electromagnetic Shielding.

The development of functional textiles combining conventional apparel with advanced technologies for personal health management (PHM) has garnered widespread attention. However, the current PHM textiles often achieve multifunctionality by stacking functional modules, leading to poor durability and scalability. Herein, a scalable and robust PHM textile is designed by integrating electrical, radiative, and solar heating, electromagnetic interference (EMI) shielding, and piezoresistive sensing performance onto cotton fabric. This is achieved through an uncomplicated screen-printing process using silver paste. The conductivity of the PHM textile is ≈1.6  ×  104 S m-1, ensuring an electric heating temperature of ≈134 °C with a low voltage of 1.7 V, as well as an EMI shielding effectiveness of ≈56 dB, and human motion monitoring performance. Surprisingly, the radiative/solar heating capability of the PHM textile surpasses that of traditional warm leather. Even after undergoing rigorous physical and chemical treatments, the PHM textile maintains terrific durability. Additionally, the PHM textile possesses maneuverable scalability and comfortable wearability. This innovative work opens up new avenues for the strategic design of PHM textiles and provides an advantageous guarantee of mass production.

Clinical characteristics of choledochal cysts with intrahepatic bile duct dilatations: an observational study.

Purpose: Whether a dilated intrahepatic bile duct (IHBD) has any effect on the prognosis of choledochal cyst (CC) remains controversial. We aimed to summarize the clinical characteristics and prognosis of CC with IHBD dilatation. Methods: One hundred ninety-two children diagnosed with CC were identified, including 127 without IHBD dilatation (group A) and 65 with IHBD dilatation (group B). A retrospective analysis was performed to explore the clinical characteristics and prognosis of CC with IHBD dilatation based on clinical indices, symptoms, and complications. Results: Compared with group A, incidences of jaundice and fever were higher in group B (P = 0.010 and P = 0.033). Preoperative total bilirubin, direct bilirubin, and indirect bilirubin were increased in group B compared to group A (P = 0.005, P < 0.001, and P = 0.014), as were preoperative ALT, AST, γ-GT, and total bile acid (P = 0.006, P = 0.025, P < 0.001, and P = 0.024). The risk of liver fibrosis or cirrhosis was significantly increased for group B compared with group A (P = 0.012) and also occurred earlier in group B (P = 0.006). In the dilated IHBDs, 95.4% (62 of 65) recovered to normal, and more than half of dilated IHBDs (37 of 65) recovered to normal in 1 week. Conclusion: Most IHBDs can recover to normal postoperatively in a short time, and proactive treatment is recommended for CC patients with IHBD dilatation for significant abnormal liver functions.

Label-aware distance mitigates temporal and spatial variability for clustering and visualization of single-cell gene expression data.

Clustering and visualization are essential parts of single-cell gene expression data analysis. The Euclidean distance used in most distance-based methods is not optimal. The batch effect, i.e., the variability among samples gathered from different times, tissues, and patients, introduces large between-group distance and obscures the true identities of cells. To solve this problem, we introduce Label-Aware Distance (LAD), a metric using temporal/spatial locality of the batch effect to control for such factors. We validate LAD on simulated data as well as apply it to a mouse retina development dataset and a lung dataset. We also found the utility of our approach in understanding the progression of the Coronavirus Disease 2019 (COVID-19). LAD provides better cell embedding than state-of-the-art batch correction methods on longitudinal datasets. It can be used in distance-based clustering and visualization methods to combine the power of multiple samples to help make biological findings.

Transcriptional and phenotypic heterogeneity underpinning venetoclax resistance in AML.

The venetoclax BCL2 inhibitor in combination with hypomethylating agents represents a cornerstone of induction therapy for older AML patients, unfit for intensive chemotherapy. Like other targeted therapies, venetoclax-based therapies suffer from innate and acquired resistance. While several mechanisms of resistance have been identified, the heterogeneity of resistance mechanism across patient populations is poorly understood. Here we utilized integrative analysis of transcriptomic and ex-vivo drug response data in AML patients to identify four transcriptionally distinct VEN resistant clusters (VR_C1-4), with distinct phenotypic, genetic and drug response patterns. VR_C1 was characterized by enrichment for differentiated monocytic- and cDC-like blasts, transcriptional activation of PI3K-AKT-mTOR signaling axis, and energy metabolism pathways. They showed sensitivity to mTOR and CDK inhibition. VR_C2 was enriched for NRAS mutations and associated with distinctive transcriptional suppression of HOX expression. VR_C3 was characterized by enrichment for TP53 mutations and higher infiltration by cytotoxic T cells. This cluster showed transcriptional expression of erythroid markers, suggesting tumor cells mimicking erythroid differentiation, activation of JAK-STAT signaling, and sensitivity to JAK inhibition, which in a subset of cases synergized with venetoclax. VR_C4 shared transcriptional similarities with venetoclax-sensitive patients, with modest over-expression of interferon signaling. They were also characterized by high rates of DNMT3A mutations. Finally, we projected venetoclax-resistance states onto single cells profiled from a patient who relapsed under venetoclax therapy capturing multiple resistance states in the tumor and shifts in their abundance under venetoclax selection, suggesting that single tumors may consist of cells mimicking multiple VR_Cs contributing to intra-tumor heterogeneity. Taken together, our results provide a strategy to evaluate inter- and intra-tumor heterogeneity of venetoclax resistance mechanisms and provide insights into approaches to navigate further management of patients who failed therapy with BCL2 inhibitors.

Absorbed Bioactive Compounds Replicate Guanxin II-Induced Endothelium-Associated in/ex vivo Vasodilation.

OBJECTIVE: To develop an interference-free and rapid method to elucidate Guanxin II (GX II)'s representative vasodilator absorbed bioactive compounds (ABCs) among enormous phytochemicals. METHODS: The contents of ferulic acid, tanshinol, and hydroxysafflor yellow A (FTA) in GX II/rat serum after the oral administration of GX II (30 g/kg) were detected using ultra-performance liquid chromatography-mass spectrometry. Totally 18 rats were randomly assigned to the control group (0.9% normal saline), GX II (30 g/kg) and FTA (5, 28 and 77 mg/kg) by random number table method. Diastolic coronary flow velocity-time integral (VTI), i.e., coronary flow or coronary flow-mediated dilation (CFMD), and endothelium-intact vascular tension of isolated aortic rings were measured. After 12 h of exposure to blank medium or 0.5 mmol/L H2O2, endothelial cells (ECs) were treated with post-dose GX II of supernatant from deproteinized serum (PGSDS, 300 µL PGSDS per 1 mL of culture medium) or FTA (237, 1539, and 1510 mg/mL) for 10 min as control, H2O2, PGSDS and FTA groups. Nitric oxide (NO), vascular endothelial growth factor (VEGF), endothelin-1 (ET-1), superoxide dismutase (SOD), malondialdehyde (MDA) and phosphorylated phosphoinositide 3 kinase (p-PI3K), phosphorylated protein kinase B (p-AKT), phosphorylated endothelial nitric oxide synthase (p-eNOS) were analyzed. PGSDS was developed as a GX II proxy of ex vivo herbal crude extracts. RESULTS: PGSDS effectively eliminates false responses caused by crude GX II preparations. When doses equaled the contents in GX II/its post-dose serum, FTA accounted for 98.17% of GX II -added CFMD and 92.99% of PGSDS-reduced vascular tension. In ECs, FTA/PGSDS was found to have significant antioxidant (lower MDA and higher SOD, P<0.01) and endothelial function-protective (lower VEGF, ET-1, P<0.01) effects. The increases in aortic relaxation, endothelial NO levels and phosphorylated PI3K/Akt/eNOS protein induced by FTA/PGSDS were markedly abolished by NG-nitro-L-arginine methyl ester (L-NA, eNOS inhibitor) and wortmannin (PI3K/AKT inhibitor), respectively, indicating an endothelium-dependent vasodilation via the PI3K/AKT-eNOS pathway (P<0.01). CONCLUSION: This study provides a strategy for rapidly and precisely elucidating GX II's representative in/ex vivo cardioprotective absorbed bioactive compounds (ABCs)-FTA, suggesting its potential in advancing precision ethnomedicine.

Estrogen Receptor Mutations as Novel Targets for Immunotherapy in Metastatic Estrogen Receptor-positive Breast Cancer.

Estrogen receptor-positive (ER+) breast cancer is not considered immunogenic and, to date, has been proven resistant to immunotherapy. Endocrine therapy remains the cornerstone of treatment for ER+ breast cancers. However, constitutively activating mutations in the estrogen receptor alpha (ESR1) gene can emerge during treatment, rendering tumors resistant to endocrine therapy. Although these mutations represent a pathway of resistance, they also represent a potential source of neoepitopes that can be targeted by immunotherapy. In this study, we investigated ESR1 mutations as novel targets for breast cancer immunotherapy. Using machine learning algorithms, we identified ESR1-derived peptides predicted to form stable complexes with HLA-A*0201. We then validated the binding affinity and stability of the top predicted peptides through in vitro binding and dissociation assays and showed that these peptides bind HLA-A*0201 with high affinity and stability. Using tetramer assays, we confirmed the presence and expansion potential of antigen-specific CTLs from healthy female donors. Finally, using in vitro cytotoxicity assays, we showed the lysis of peptide-pulsed targets and breast cancer cells expressing common ESR1 mutations by expanded antigen-specific CTLs. Ultimately, we identified five peptides derived from the three most common ESR1 mutations (D538G, Y537S, and E380Q) and their associated wild-type peptides, which were the most immunogenic. Overall, these data confirm the immunogenicity of epitopes derived from ESR1 and highlight the potential of these peptides to be targeted by novel immunotherapy strategies. SIGNIFICANCE: Estrogen receptor (ESR1) mutations have emerged as a key factor in endocrine therapy resistance. We identified and validated five novel, immunogenic ESR1-derived peptides that could be targeted through vaccine-based immunotherapy.

Enhancing surgical outcomes of posterior iliac bone harvesting through a pivotal modification.

Traditionally, patients are positioned in the prone position to access the donor site during the posterior iliac bone graft harvesting procedure. However, this well-established method is associated with complications such as pressure injuries, displacement of the endotracheal tube and intravenous catheter, and blindness. Moreover, the process of turning patients 180° between the supine and prone positions is both laborious and time consuming. However, no updates have been made in the approaches published in the literature to counteract these problems. Therefore, to overcome these challenges and improve patient outcomes, we proposed a pivotal modification: change prone position to the lateral decubitus position. This approach allowed us to effectively avoid the aforementioned complications. In addition, this modification offered significant advantages, including ease of implementation and timesaving benefits. The article presented results of the modification and a comprehensive evaluation of clinical and anesthetic considerations comparing the two methods.

Safety, efficacy and determinants of response of allogeneic CD19-specific CAR-NK cells in CD19+ B cell tumors: a phase 1/2 trial.

There is a pressing need for allogeneic chimeric antigen receptor (CAR)-immune cell therapies that are safe, effective and affordable. We conducted a phase 1/2 trial of cord blood-derived natural killer (NK) cells expressing anti-CD19 chimeric antigen receptor and interleukin-15 (CAR19/IL-15) in 37 patients with CD19+ B cell malignancies. The primary objectives were safety and efficacy, defined as day 30 overall response (OR). Secondary objectives included day 100 response, progression-free survival, overall survival and CAR19/IL-15 NK cell persistence. No notable toxicities such as cytokine release syndrome, neurotoxicity or graft-versus-host disease were observed. The day 30 and day 100 OR rates were 48.6% for both. The 1-year overall survival and progression-free survival were 68% and 32%, respectively. Patients who achieved OR had higher levels and longer persistence of CAR-NK cells. Receiving CAR-NK cells from a cord blood unit (CBU) with nucleated red blood cells ≤ 8 × 107 and a collection-to-cryopreservation time ≤ 24 h was the most significant predictor for superior outcome. NK cells from these optimal CBUs were highly functional and enriched in effector-related genes. In contrast, NK cells from suboptimal CBUs had upregulation of inflammation, hypoxia and cellular stress programs. Finally, using multiple mouse models, we confirmed the superior antitumor activity of CAR/IL-15 NK cells from optimal CBUs in vivo. These findings uncover new features of CAR-NK cell biology and underscore the importance of donor selection for allogeneic cell therapies. ClinicalTrials.gov identifier: NCT03056339 .

Graph autoencoder with mirror temporal convolutional networks for traffic anomaly detection.

Traffic time series anomaly detection has been intensively studied for years because of its potential applications in intelligent transportation. However, classical traffic anomaly detection methods often overlook the evolving dynamic associations between road network nodes, which leads to challenges in capturing the long-term temporal correlations, spatial characteristics, and abnormal node behaviors in datasets with high periodicity and trends, such as morning peak travel periods. In this paper, we propose a mirror temporal graph autoencoder (MTGAE) framework to explore anomalies and capture unseen nodes and the spatiotemporal correlation between nodes in the traffic network. Specifically, we propose the mirror temporal convolutional module to enhance feature extraction capabilities and capture hidden node-to-node features in the traffic network. Morever, we propose the graph convolutional gate recurrent unit cell (GCGRU CELL) module. This module uses Gaussian kernel functions to map data into a high-dimensional space, and enables the identification of anomalous information and potential anomalies within the complex interdependencies of the traffic network, based on prior knowledge and input data. We compared our work with several other advanced deep-learning anomaly detection models. Experimental results on the NYC dataset illustrate that our model works best compared to other models for traffic anomaly detection.

Neoantigen Cancer Vaccines and Different Immune Checkpoint Therapies Each Utilize Both Converging and Distinct Mechanisms that in Combination Enable Synergistic Therapeutic Efficacy.

The goal of therapeutic cancer vaccines and immune checkpoint therapy (ICT) is to eliminate cancer by expanding and/or sustaining T cells with anti-tumor capabilities. However, whether cancer vaccines and ICT enhance anti-tumor immunity by distinct or overlapping mechanisms remains unclear. Here, we compared effective therapeutic tumor-specific mutant neoantigen (NeoAg) cancer vaccines with anti-CTLA-4 and/or anti-PD-1 ICT in preclinical models. Both NeoAg vaccines and ICT induce expansion of intratumoral NeoAg-specific CD8 T cells, though the degree of expansion and acquisition of effector activity was much more substantial following NeoAg vaccination. Further, we found that NeoAg vaccines are particularly adept at inducing proliferating and stem-like NeoAg-specific CD8 T cells. Single cell T cell receptor (TCR) sequencing revealed that TCR clonotype expansion and diversity of NeoAg-specific CD8 T cells relates to their phenotype and functional state associated with specific immunotherapies employed. Effective NeoAg vaccines and ICT required both CD8 and CD4 T cells. While NeoAg vaccines and anti-PD-1 affected the CD4 T cell compartment, it was to less of an extent than observed with anti-CTLA-4, which notably induced ICOS+Bhlhe40+ Th1-like CD4 T cells and, when combined with anti-PD-1, a small subset of Th2-like CD4 T cells. Although effective NeoAg vaccines or ICT expanded intratumoral M1-like iNOS+ macrophages, NeoAg vaccines expanded rather than suppressed (as observed with ICT) M2-like CX3CR1+CD206+ macrophages, associated with the vaccine adjuvant. Further, combining NeoAg vaccination with ICT induced superior efficacy compared to either therapy in isolation, highlighting the utility of combining these modalities to eliminate cancer.