CancerProteome: a resource to functionally decipher the proteome landscape in cancer.

Advancements in mass spectrometry (MS)-based proteomics have greatly facilitated the large-scale quantification of proteins and microproteins, thereby revealing altered signalling pathways across many different cancer types. However, specialized and comprehensive resources are lacking for cancer proteomics. Here, we describe CancerProteome (http://bio-bigdata.hrbmu.edu.cn/CancerProteome), which functionally deciphers and visualizes the proteome landscape in cancer. We manually curated and re-analyzed publicly available MS-based quantification and post-translational modification (PTM) proteomes, including 7406 samples from 21 different cancer types, and also examined protein abundances and PTM levels in 31 120 proteins and 4111 microproteins. Six major analytical modules were developed with a view to describe protein contributions to carcinogenesis using proteome analysis, including conventional analyses of quantitative and the PTM proteome, functional enrichment, protein-protein associations by integrating known interactions with co-expression signatures, drug sensitivity and clinical relevance analyses. Moreover, protein abundances, which correlated with corresponding transcript or PTM levels, were evaluated. CancerProteome is convenient as it allows users to access specific proteins/microproteins of interest using quick searches or query options to generate multiple visualization results. In summary, CancerProteome is an important resource, which functionally deciphers the cancer proteome landscape and provides a novel insight for the identification of tumor protein markers in cancer.

Identification of alternative splicing-derived cancer neoantigens for mRNA vaccine development.

Messenger RNA (mRNA) vaccines have shown great potential for anti-tumor therapy due to the advantages in safety, efficacy and industrial production. However, it remains a challenge to identify suitable cancer neoantigens that can be targeted for mRNA vaccines. Abnormal alternative splicing occurs in a variety of tumors, which may result in the translation of abnormal transcripts into tumor-specific proteins. High-throughput technologies make it possible for systematic characterization of alternative splicing as a source of suitable target neoantigens for mRNA vaccine development. Here, we summarized difficulties and challenges for identifying alternative splicing-derived cancer neoantigens from RNA-seq data and proposed a conceptual framework for designing personalized mRNA vaccines based on alternative splicing-derived cancer neoantigens. In addition, several points were presented to spark further discussion toward improving the identification of alternative splicing-derived cancer neoantigens.

DeepCCI: a deep learning framework for identifying cell-cell interactions from single-cell RNA sequencing data.

MOTIVATION: Cell-cell interactions (CCIs) play critical roles in many biological processes such as cellular differentiation, tissue homeostasis, and immune response. With the rapid development of high throughput single-cell RNA sequencing (scRNA-seq) technologies, it is of high importance to identify CCIs from the ever-increasing scRNA-seq data. However, limited by the algorithmic constraints, current computational methods based on statistical strategies ignore some key latent information contained in scRNA-seq data with high sparsity and heterogeneity. RESULTS: Here, we developed a deep learning framework named DeepCCI to identify meaningful CCIs from scRNA-seq data. Applications of DeepCCI to a wide range of publicly available datasets from diverse technologies and platforms demonstrate its ability to predict significant CCIs accurately and effectively. Powered by the flexible and easy-to-use software, DeepCCI can provide the one-stop solution to discover meaningful intercellular interactions and build CCI networks from scRNA-seq data. AVAILABILITY AND IMPLEMENTATION: The source code of DeepCCI is available online at https://github.com/JiangBioLab/DeepCCI.

DeepST: identifying spatial domains in spatial transcriptomics by deep learning.

Recent advances in spatial transcriptomics (ST) have brought unprecedented opportunities to understand tissue organization and function in spatial context. However, it is still challenging to precisely dissect spatial domains with similar gene expression and histology in situ. Here, we present DeepST, an accurate and universal deep learning framework to identify spatial domains, which performs better than the existing state-of-the-art methods on benchmarking datasets of the human dorsolateral prefrontal cortex. Further testing on a breast cancer ST dataset, we showed that DeepST can dissect spatial domains in cancer tissue at a finer scale. Moreover, DeepST can achieve not only effective batch integration of ST data generated from multiple batches or different technologies, but also expandable capabilities for processing other spatial omics data. Together, our results demonstrate that DeepST has the exceptional capacity for identifying spatial domains, making it a desirable tool to gain novel insights from ST studies.

CeRNASeek: an R package for identification and analysis of ceRNA regulation.

Competitive endogenous RNA (ceRNA) represents a novel layer of gene regulation that controls both physiological and pathological processes. However, there is still lack of computational tools for quickly identifying ceRNA regulation. To address this problem, we presented an R-package, CeRNASeek, which allows identifying and analyzing ceRNA-ceRNA interactions by integration of multiple-omics data. CeRNASeek integrates six widely used computational methods to identify ceRNA-ceRNA interactions, including two global and four context-specific ceRNA regulation prediction methods. In addition, it provides several downstream analyses for predicted ceRNA-ceRNA pairs, including regulatory network analysis, functional annotation and survival analysis. With examples of cancer-related ceRNA prioritization and cancer subtyping, we demonstrate that CeRNASeek is a valuable tool for investigating the function of ceRNAs in complex diseases. In summary, CeRNASeek provides a comprehensive and efficient tool for identifying and analysis of ceRNA regulation. The package is available on the Comprehensive R Archive Network (CRAN) at https://CRAN.R-project.org/package=CeRNASeek.

Comprehensive analysis of partial methylation domains in colorectal cancer based on single-cell methylation profiles.

Epigenetic aberrations have played a significant role in affecting the pathophysiological state of colorectal cancer, and global DNA hypomethylation mainly occurs in partial methylation domains (PMDs). However, the distribution of PMDs in individual cells and the heterogeneity between cells are still unclear. In this study, the DNA methylation profiles of colorectal cancer detected by WGBS and scBS-seq were used to depict PMDs in individual cells for the first time. We found that more than half of the entire genome is covered by PMDs. Three subclasses of PMDS have distinct characteristics, and Gain-PMDs cover a higher proportion of protein coding genes. Gain-PMDs have extensive epigenetic heterogeneity between different cells of the same tumor, and the DNA methylation in cells is affected by the tumor microenvironment. In addition, abnormally elevated promoter methylation in Gain-PMDs may further promote the growth, proliferation and metastasis of tumor cells through silent transcription. The PMDs detected in this study have the potential as epigenetic biomarkers and provide a new insight for colorectal cancer research based on single-cell methylation data.

DLpTCR: an ensemble deep learning framework for predicting immunogenic peptide recognized by T cell receptor.

Accurate prediction of immunogenic peptide recognized by T cell receptor (TCR) can greatly benefit vaccine development and cancer immunotherapy. However, identifying immunogenic peptides accurately is still a huge challenge. Most of the antigen peptides predicted in silico fail to elicit immune responses in vivo without considering TCR as a key factor. This inevitably causes costly and time-consuming experimental validation test for predicted antigens. Therefore, it is necessary to develop novel computational methods for precisely and effectively predicting immunogenic peptide recognized by TCR. Here, we described DLpTCR, a multimodal ensemble deep learning framework for predicting the likelihood of interaction between single/paired chain(s) of TCR and peptide presented by major histocompatibility complex molecules. To investigate the generality and robustness of the proposed model, COVID-19 data and IEDB data were constructed for independent evaluation. The DLpTCR model exhibited high predictive power with area under the curve up to 0.91 on COVID-19 data while predicting the interaction between peptide and single TCR chain. Additionally, the DLpTCR model achieved the overall accuracy of 81.03% on IEDB data while predicting the interaction between peptide and paired TCR chains. The results demonstrate that DLpTCR has the ability to learn general interaction rules and generalize to antigen peptide recognition by TCR. A user-friendly webserver is available at http://jianglab.org.cn/DLpTCR/. Additionally, a stand-alone software package that can be downloaded from https://github.com/jiangBiolab/DLpTCR.

Global characterization of B cell receptor repertoire in COVID-19 patients by single-cell V(D)J sequencing.

The world is facing a pandemic of Corona Virus Disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Adaptive immune responses are essential for SARS-CoV-2 virus clearance. Although a large body of studies have been conducted to investigate the immune mechanism in COVID-19 patients, we still lack a comprehensive understanding of the BCR repertoire in patients. In this study, we used the single-cell V(D)J sequencing to characterize the BCR repertoire across convalescent COVID-19 patients. We observed that the BCR diversity was significantly reduced in disease compared with healthy controls. And BCRs tend to skew toward different V gene segments in COVID-19 and healthy controls. The CDR3 sequences of heavy chain in clonal BCRs in patients were more convergent than that in healthy controls. In addition, we discovered increased IgG and IgA isotypes in the disease, including IgG1, IgG3 and IgA1. In all clonal BCRs, IgG isotypes had the most frequent class switch recombination events and the highest somatic hypermutation rate, especially IgG3. Moreover, we found that an IgG3 cluster from different clonal groups had the same IGHV, IGHJ and CDR3 sequences (IGHV4-4-CARLANTNQFYDSSSYLNAMDVW-IGHJ6). Overall, our study provides a comprehensive characterization of the BCR repertoire in COVID-19 patients, which contributes to the understanding of the mechanism for the immune response to SARS-CoV-2 infection.

Comprehensive analysis of TCR repertoire in COVID-19 using single cell sequencing.

T-cell receptor (TCR) is crucial in T cell-mediated virus clearance. To date, TCR bias has been observed in various diseases. However, studies on the TCR repertoire of COVID-19 patients are lacking. Here, we used single-cell V(D)J sequencing to conduct comparative analyses of TCR repertoire between 12 COVID-19 patients and 6 healthy controls, as well as other virus-infected samples. We observed distinct T cell clonal expansion in COVID-19. Further analysis of VJ gene combination revealed 6 VJ pairs significantly increased, while 139 pairs significantly decreased in COVID-19 patients. When considering the VJ combination of α and ß chains at the same time, the combination with the highest frequency on COVID-19 was TRAV12-2-J27-TRBV7-9-J2-3. Besides, preferential usage of V and J gene segments was also observed in samples infected by different viruses. Our study provides novel insights on TCR in COVID-19, which contribute to our understanding of the immune response induced by SARS-CoV-2.

Krüppel-like Transcription Factor 7 Is a Causal Gene in Autism Development.

BACKGROUND: Autism spectrum disorder (ASD) is a complex neurodevelopmental disease. To date, more than 1000 genes have been shown to be associated with ASD, and only a few of these genes account for more than 1% of autism cases. Klf7 is an important transcription factor of cell proliferation and differentiation in the nervous system, but whether klf7 is involved in autism is unclear. METHODS: We first performed ChIP-seq analysis of klf7 in N2A cells, then performed behavioral tests and RNA-seq in klf7+/- mice, and finally restored mice with adeno-associated virus (AAV)-mediated overexpression of klf7 in klf7+/- mice. RESULTS: Klf7 targeted genes are enriched with ASD genes, and 631 ASD risk genes are also differentially expressed in klf7+/- mice which exhibited the core symptoms of ASD. When klf7 levels were increased in the central nervous system (CNS) in klf7+/- adult mice, deficits in social interaction, repetitive behavior and majority of dysregulated ASD genes were rescued in the adults, suggesting transcriptional regulation. Moreover, knockdown of klf7 in human brain organoids caused dysregulation of 517 ASD risk genes, 344 of which were shared with klf7+/- mice, including some high-confidence ASD genes. CONCLUSIONS: Our findings highlight a klf7 regulation of ASD genes and provide new insights into the pathogenesis of ASD and promising targets for further research on mechanisms and treatments.

Systematic review regulatory principles of non-coding RNAs in cardiovascular diseases.

Cardiovascular diseases (CVDs) continue to be a major cause of morbidity and mortality, and non-coding RNAs (ncRNAs) play critical roles in CVDs. With the recent emergence of high-throughput technologies, including small RNA sequencing, investigations of CVDs have been transformed from candidate-based studies into genome-wide undertakings, and a number of ncRNAs in CVDs were discovered in various studies. A comprehensive review of these ncRNAs would be highly valuable for researchers to get a complete picture of the ncRNAs in CVD. To address these knowledge gaps and clinical needs, in this review, we first discussed dysregulated ncRNAs and their critical roles in cardiovascular development and related diseases. Moreover, we reviewed >28 561 published papers and documented the ncRNA-CVD association benchmarking data sets to summarize the principles of ncRNA regulation in CVDs. This data set included 13 249 curated relationships between 9503 ncRNAs and 139 CVDs in 12 species. Based on this comprehensive resource, we summarized the regulatory principles of dysregulated ncRNAs in CVDs, including the complex associations between ncRNA and CVDs, tissue specificity and ncRNA synergistic regulation. The highlighted principles are that CVD microRNAs (miRNAs) are highly expressed in heart tissue and that they play central roles in miRNA-miRNA functional synergistic network. In addition, CVD-related miRNAs are close to one another in the functional network, indicating the modular characteristic features of CVD miRNAs. We believe that the regulatory principles summarized here will further contribute to our understanding of ncRNA function and dysregulation mechanisms in CVDs.

Systematic review of computational methods for identifying miRNA-mediated RNA-RNA crosstalk.

Posttranscriptional crosstalk and communication between RNAs yield large regulatory competing endogenous RNA (ceRNA) networks via shared microRNAs (miRNAs), as well as miRNA synergistic networks. The ceRNA crosstalk represents a novel layer of gene regulation that controls both physiological and pathological processes such as development and complex diseases. The rapidly expanding catalogue of ceRNA regulation has provided evidence for exploitation as a general model to predict the ceRNAs in silico. In this article, we first reviewed the current progress of RNA-RNA crosstalk in human complex diseases. Then, the widely used computational methods for modeling ceRNA-ceRNA interaction networks are further summarized into five types: two types of global ceRNA regulation prediction methods and three types of context-specific prediction methods, which are based on miRNA-messenger RNA regulation alone, or by integrating heterogeneous data, respectively. To provide guidance in the computational prediction of ceRNA-ceRNA interactions, we finally performed a comparative study of different combinations of miRNA-target methods as well as five types of ceRNA identification methods by using literature-curated ceRNA regulation and gene perturbation. The results revealed that integration of different miRNA-target prediction methods and context-specific miRNA/gene expression profiles increased the performance for identifying ceRNA regulation. Moreover, different computational methods were complementary in identifying ceRNA regulation and captured different functional parts of similar pathways. We believe that the application of these computational techniques provides valuable functional insights into ceRNA regulation and is a crucial step for informing subsequent functional validation studies.

Survey of miRNA-miRNA cooperative regulation principles across cancer types.

Cooperative regulation among multiple microRNAs (miRNAs) is a complex type of posttranscriptional regulation in human; however, the global view of the system-level regulatory principles across cancers is still unclear. Here, we investigated miRNA-miRNA cooperative regulatory landscape across 18 cancer types and summarized the regulatory principles of miRNAs. The miRNA-miRNA cooperative pan-cancer network exhibited a scale-free and modular architecture. Cancer types with similar tissue origins had high similarity in cooperative network structure and expression of cooperative miRNA pairs. In addition, cooperative miRNAs showed divergent properties, including higher expression, greater expression variation and a stronger regulatory strength towards targets and were likely to regulate cancer hallmark-related functions. We found a marked rewiring of miRNA-miRNA cooperation between various cancers and revealed conserved and rewired network miRNA hubs. We further identified the common hubs, cancer-specific hubs and other hubs, which tend to target known anticancer drug targets. Finally, miRNA cooperative modules were found to be associated with patient survival in several cancer types. Our study highlights the potential of pan-cancer miRNA-miRNA cooperative regulation as a novel paradigm that may aid in the discovery of tumorigenesis mechanisms and development of anticancer drugs.

Landscape of the long non-coding RNA transcriptome in human heart.

Long non-coding RNAs (lncRNAs) have been revealed to play essential roles in the human cardiovascular system. However, information about their mechanisms is limited, and a comprehensive view of cardiac lncRNAs is lacking from a multiple tissues perspective to date. Here, the landscape of the lncRNA transcriptome in human heart was summarized. We summarized all lncRNA transcripts from publicly available human transcriptome resources (156 heart samples and 210 samples from 29 other tissues) and systematically analysed all annotated and novel lncRNAs expressed in heart. A total of 7485 lncRNAs whose expression was elevated in heart (HE lncRNAs) and 453 lncRNAs expressed in all 30 analysed tissues (EIA lncRNAs) were extracted. Using various bioinformatics resources, methods and tools, the features of these lncRNAs were discussed from various perspectives, including genomic structure, conservation, dynamic variation during heart development, cis-regulation, differential expression in cardiovascular diseases and cancers as well as regulation at transcriptional and post-transcriptional levels. Afterwards, all the features discussed above were integrated into a user-friendly resource named CARDIO-LNCRNAS (http://bio-bigdata.hrbmu.edu.cn/CARDIO-LNCRNAS/ or http://www.bio-bigdata.net/CARDIO-LNCRNAS/). This study represents the first global view of lncRNAs in the human cardiovascular system based on multiple tissues and sheds light on the role of lncRNAs in developments and heart disorders.

Alternative splicing associated with cancer stemness in kidney renal clear cell carcinoma.

BACKGROUD: Cancer stemness is associated with metastases in kidney renal clear cell carcinoma (KIRC) and negatively correlates with immune infiltrates. Recent stemness evaluation methods based on the absolute expression have been proposed to reveal the relationship between stemness and cancer. However, we found that existing methods do not perform well in assessing the stemness of KIRC patients, and they overlooked the impact of alternative splicing. Alternative splicing not only progresses during the differentiation of stem cells, but also changes during the acquisition of the stemness features of cancer stem cells. There is an urgent need for a new method to predict KIRC-specific stemness more accurately, so as to provide help in selecting treatment options. METHODS: The corresponding RNA-Seq data were obtained from the The Cancer Genome Atlas (TCGA) data portal. We also downloaded stem cell RNA sequence data from the Progenitor Cell Biology Consortium (PCBC) Synapse Portal. Independent validation sets with large sample size and common clinic pathological characteristics were obtained from the Gene Expression Omnibus (GEO) database. we constructed a KIRC-specific stemness prediction model using an algorithm called one-class logistic regression based on the expression and alternative splicing data to predict stemness indices of KIRC patients, and the model was externally validated. We identify stemness-associated alternative splicing events (SASEs) by analyzing different alternative splicing event between high- and low- stemness groups. Univariate Cox and multivariable logistic regression analysisw as carried out to detect the prognosis-related SASEs respectively. The area under curve (AUC) of receiver operating characteristic (ROC) was performed to evaluate the predictive values of our model. RESULTS: Here, we constructed a KIRC-specific stemness prediction model with an AUC of 0.968,and to provide a user-friendly interface of our model for KIRC stemness analysis, we have developed KIRC Stemness Calculator and Visualization (KSCV), hosted on the Shiny server, can most easily be accessed via web browser and the url https://jiang-lab.shinyapps.io/kscv/ . When applied to 605 KIRC patients, our stemness indices had a higher correlation with the gender, smoking history and metastasis of the patients than the previous stemness indices, and revealed intratumor heterogeneity at the stemness level. We identified 77 novel SASEs by dividing patients into high- and low- stemness groups with significantly different outcome and they had significant correlations with expression of 17 experimentally validated splicing factors. Both univariate and multivariate survival analysis demonstrated that SASEs closely correlated with the overall survival of patients. CONCLUSIONS: Basing on the stemness indices, we found that not only immune infiltration but also alternative splicing events showed significant different at the stemness level. More importantly, we highlight the critical role of these differential alternative splicing events in poor prognosis, and we believe in the potential for their further translation into targets for immunotherapy.

FACER: comprehensive molecular and functional characterization of epigenetic chromatin regulators.

Epigenetic alterations, a well-recognized cancer hallmark, are driven by chromatin regulators (CRs). However, little is known about the extent of CR deregulation in cancer, and less is known about their common and specialized roles across various cancers. Here, we performed genome-wide analyses and constructed molecular signatures and network profiles of functional CRs in over 10 000 tumors across 33 cancer types. By integration of DNA mutation, genome-wide methylation, transcriptional/post-transcriptional regulation, and protein interaction networks with clinical outcomes, we identified CRs associated with cancer subtypes and clinical prognosis as potential oncogenic drivers. Comparative network analysis revealed principles of CR regulatory specificity and functionality. In addition, we identified common and specific CRs by assessing their prevalence across cancer types. Common CRs tend to be histone modifiers and chromatin remodelers with fundamental roles, whereas specialized CRs are involved in context-dependent functions. Finally, we have made a user-friendly web interface-FACER (Functional Atlas of Chromatin Epigenetic Regulators) available for exploring clinically relevant CRs for the development of CR biomarkers and therapeutic targets. Our integrative analysis reveals specific determinants of CRs across cancer types and presents a resource for investigating disease-associated CRs.

LncMAP: Pan-cancer atlas of long noncoding RNA-mediated transcriptional network perturbations.

Gene regulatory network perturbations contribute to the development and progression of cancer, however, molecular determinants that mediate transcriptional perturbations remain a fundamental challenge for cancer biology. We show that transcriptional perturbations are widely mediated by long noncoding RNAs (lncRNAs) via integration of genome-wide transcriptional regulation with paired lncRNA and gene expression profiles. Systematic construction of an LncRNA Modulator Atlas in Pan-cancer (LncMAP) reveals distinct types of lncRNA regulatory molecules, which are expressed in multiple tissues, exhibit higher conservation. Strikingly, cancers with similar tissue origin share lncRNA modulators which perturb the regulation of cell cycle and immune response-related functions. Furthermore, we identified a large number of pan-cancer lncRNA modulators with potential clinical significance, which are differentially expressed in cancer or are strongly correlated with drug sensitivity across cell lines. Further stratification of cancer patients based on lncRNA-mediated transcriptional perturbations identifies subtypes with distinct survival rates. Finally, we made a user-friendly web interface available for exploring lncRNA-mediated transcriptional perturbations across cancer types. Our study provides a systems-level dissection of lncRNA-mediated regulatory perturbations in cancer, and also presents a valuable tool and resource for investigating the function of lncRNAs in cancer.

Methods for Identification of Protein-RNA Interaction.

The importance of RNA-protein interactions in regulation of mRNA and non-coding RNA function is increasingly appreciated. With the development of next generation high-throughput sequencing technologies, a variety of methods have been proposed to comprehensively identify RNA-protein interactions. In this chapter, we discussed the traditional and state-of-the-art technologies that were used to study RNA-protein interaction, including experimental and computational methods. To help highlight the biological significance of RNA-protein interaction in complex diseases, online resources on RNA-protein interactions were briefly discussed. Finally, we discussed the interaction among noncoding RNAs (such as long noncoding RNAs and microRNAs) and proteins, as well as the dysregulation of RNA-protein interaction in complex diseases. These summarization will ultimately provide a more complete picture for understanding of the function of RNA-protein interactions, including how these interaction assembled and how they modulate cellular function in complex diseases.

Functional requirement of alternative splicing in epithelial-mesenchymal transition of pancreatic circulating tumor.

Circulating tumor cells (CTCs) that undergo epithelial-to-mesenchymal transition (EMT) can provide valuable information regarding metastasis and potential therapies. However, current studies on the EMT overlook alternative splicing. Here, we used single-cell full-length transcriptome data and mRNA sequencing of CTCs to identify stage-specific alternative splicing of partial EMT and mesenchymal states during pancreatic cancer metastasis. We classified definitive tumor and normal epithelial cells via genetic aberrations and demonstrated dynamic changes in the epithelial-mesenchymal continuum in both epithelial cancer cells and CTCs. We provide the landscape of alternative splicing in CTCs at different stages of EMT, uncovering cell-type-specific splicing patterns and splicing events in cell surface proteins suitable for therapies. We show that MBNL1 governs cell fate through alternative splicing independently of changes in gene expression and affects the splicing pattern during EMT. We found a high frequency of events that contained multiple premature termination codons and were enriched with C and G nucleotides in close proximity, which influence the likelihood of stop codon readthrough and expand the range of potential therapeutic targets. Our study provides insights into the EMT transcriptome's dynamic changes and identifies potential diagnostic and therapeutic targets in pancreatic cancer.

The Deep Learning Framework iCanTCR Enables Early Cancer Detection Using the T-cell Receptor Repertoire in Peripheral Blood.

T cells recognize tumor antigens and initiate an anticancer immune response in the very early stages of tumor development, and the antigen specificity of T cells is determined by the T-cell receptor (TCR). Therefore, monitoring changes in the TCR repertoire in peripheral blood may offer a strategy to detect various cancers at a relatively early stage. Here, we developed the deep learning framework iCanTCR to identify patients with cancer based on the TCR repertoire. The iCanTCR framework uses TCRß sequences from an individual as an input and outputs the predicted cancer probability. The model was trained on over 2,000 publicly available TCR repertoires from 11 types of cancer and healthy controls. Analysis of several additional publicly available datasets validated the ability of iCanTCR to distinguish patients with cancer from noncancer individuals and demonstrated the capability of iCanTCR for the accurate classification of multiple cancers. Importantly, iCanTCR precisely identified individuals with early-stage cancer with an AUC of 86%. Altogether, this work provides a liquid biopsy approach to capture immune signals from peripheral blood for noninvasive cancer diagnosis. SIGNIFICANCE: Development of a deep learning-based method for multicancer detection using the TCR repertoire in the peripheral blood establishes the potential of evaluating circulating immune signals for noninvasive early cancer detection.