Yan Zeng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Yan Zeng has a total of 116 co-authors. Here are the top co-authors by number of shared publications:
Jun Zheng
Department of Stomatology, Zhanjiang Central Hospital, Guangdong Medical University, Zhanjiang 524037, China
12 shared publicationsJie Yang
Precision Clinical Laboratory, Zhanjiang Central Hospital, Guangdong Medical University Zhanjiang 524037, Guangdong, China
8 shared publicationsJiang Xu
Key Laboratory of Xinjiang Endemic and Ethnic Disease School of Medicine Shihezi University Shihezi China
7 shared publicationsTing Luo
Precision Clinical Laboratory Central People's Hospital of Zhanjiang Zhanjiang, Guangdong China
7 shared publicationsYangyang Pan
Precision Clinical Laboratory, Zhanjiang Central Hospital, Guangdong Medical University, Zhanjiang 524037, China; State Key Laboratory of Military Stomatology & National Clinical Research Center for Oral Diseases & Shaanxi Clinical Research Center for Oral Diseases, School of Stomatology, The Fourth Military Medical University, Xi'an 710032, China
7 shared publicationsFazhan Wang
Shaanxi Energy Institute Xianyang 712000, Shaanxi, China
5 shared publications
Latest Publications
- Open Access
- 1 November 2025
- Published by Taylor & Francis in Journal of Inflammation Research
- Vol. ume 18, 16293-16313
PCK2, a SASP-Associated Gene, Serves as an Independent Prognostic Indicator in Diffuse Large B-Cell Lymphoma
Diffuse large B-cell lymphoma (DLBCL) is characterised by substantial heterogeneity in phenotype and genetics. Recent studies have demonstrated that senescence-associated secretory phenotype (SASP) is both a tumor suppressor and a promoter of tumorigenesis and progression. However, reports on the effects of SASP on DLBCL remain limited. This study aimed to identify the SASP-related indicator of DLBCL, thereby providing new insights into the pathology of DLBCL. Differential analysis and weighted co-expression network analysis (WGCNA) were applied to identify differentially expressed genes (DEGs) and key gene modules of DLBCL. Univariate Cox regression analysis was employed to identify SASP-related genes that serve as independent risk factors for DLBCL prognosis. Overlapped among three methods to obtain the hub gene and explore its potential mechanisms in DLBCL. The association between PCK2 and disease heterogeneity in DLBCL was further analyzed. We constructed a co-expression network centered on PCK2 and validated their expression and prognostic performance. Finally, 30 cases of tumour tissues were utilized to validate the expression of PCK2 in DLBCL patients by immunohistochemistry. In this study, through integrated bioinformatics methods, PCK2 was identified as a SASP-related gene in DLBCL. PCK2 can be regarded as a candidate indicator with good prognostic performance (AUC=0.953, Hazard Ratio (HR) =1.89, 95% CI=1.488–2.399, p<0.001). PCK2 was notably associated with multiple disease characteristics in DLBCL, particularly the immunosuppressive microenvironment and SASP signal. Furthermore, genes exhibiting high correlation with PCK2 demonstrated significant predictive value for DLBCL prognosis. Through immunohistochemistry, it was verified that PCK2 was markedly upregulated in DLBCL compared to normal controls. As a SASP-related gene, PCK2 serve as a candidate indicator providing supplementary information for DLBCL disease monitoring and prognostic assessment.
- 1 November 2025
- Published by Taylor & Francis in Journal of Inflammation Research
- Vol. ume 18, 16293-16313
Open AccessPCK2, a SASP-Associated Gene, Serves as an Independent Prognostic Indicator in Diffuse Large B-Cell Lymphoma
Diffuse large B-cell lymphoma (DLBCL) is characterised by substantial heterogeneity in phenotype and genetics. Recent studies have demonstrated that senescence-associated secretory phenotype (SASP) is both a tumor suppressor and a promoter of tumorigenesis and progression. However, reports on the effects of SASP on DLBCL remain limited. This study aimed to identify the SASP-related indicator of DLBCL, thereby providing new insights into the pathology of DLBCL. Differential analysis and weighted co-expression network analysis (WGCNA) were applied to identify differentially expressed genes (DEGs) and key gene modules of DLBCL. Univariate Cox regression analysis was employed to identify SASP-related genes that serve as independent risk factors for DLBCL prognosis. Overlapped among three methods to obtain the hub gene and explore its potential mechanisms in DLBCL. The association between PCK2 and disease heterogeneity in DLBCL was further analyzed. We constructed a co-expression network centered on PCK2 and validated their expression and prognostic performance. Finally, 30 cases of tumour tissues were utilized to validate the expression of PCK2 in DLBCL patients by immunohistochemistry. In this study, through integrated bioinformatics methods, PCK2 was identified as a SASP-related gene in DLBCL. PCK2 can be regarded as a candidate indicator with good prognostic performance (AUC=0.953, Hazard Ratio (HR) =1.89, 95% CI=1.488–2.399, p<0.001). PCK2 was notably associated with multiple disease characteristics in DLBCL, particularly the immunosuppressive microenvironment and SASP signal. Furthermore, genes exhibiting high correlation with PCK2 demonstrated significant predictive value for DLBCL prognosis. Through immunohistochemistry, it was verified that PCK2 was markedly upregulated in DLBCL compared to normal controls. As a SASP-related gene, PCK2 serve as a candidate indicator providing supplementary information for DLBCL disease monitoring and prognostic assessment.
- Open Access
- 22 July 2025
- Published by SAGE Publications in Science Progress
- Vol. 108 (3)
Comprehensive high-throughput sequencing analysis and verification of miRNAs isolated from bronchial epithelial cells undergoing radiation-induced epithelial-mesenchymal transition
Radiation-induced pulmonary fibrosis (RIPF) constitutes a significant complication in radiotherapy for various cancers, often severely limiting its efficacy. Recent studies suggest that epithelial-mesenchymal transition (EMT) plays a vital role in the pathogenesis of RIPF. Elucidating the involvement of microRNAs (miRNAs) in EMT could provide valuable insights into the mechanisms underlying RIPF and potentially reveal therapeutic targets. In this study, twelve dishes of BEAS-2B cells were irradiated with 6 Gy 60 Co γ-rays, and RNA was extracted at 0, 6, and 48 h after irradiation. High-throughput sequencing analysis of miRNA samples revealed miRNA significant changes in the BEAS-2B cells after irradiation, which was verified by RT-PCR. Additionally, the upstream transcription factors (TFs) were predicted through graphene oxide-based analysis. Transcription factors regulate the expression and transcriptional levels of miRNAs, and their functions may be associated with inflammatory or oxidative stress responses. The functional roles of these TFs were characterized through gene ontology (GO) analysis. Overall, we successfully screened and identified a set of miRNAs associated with ionizing radiation-induced EMT in lung epithelial cells and performed predictive identification of their upstream TFs and downstream regulatory target proteins. These data provide a firm foundation for future studies of the mechanism of radiation-induced EMT processes and related changes in biological function.
- 22 July 2025
- Published by SAGE Publications in Science Progress
- Vol. 108 (3)
Open AccessComprehensive high-throughput sequencing analysis and verification of miRNAs isolated from bronchial epithelial cells undergoing radiation-induced epithelial-mesenchymal transition
Radiation-induced pulmonary fibrosis (RIPF) constitutes a significant complication in radiotherapy for various cancers, often severely limiting its efficacy. Recent studies suggest that epithelial-mesenchymal transition (EMT) plays a vital role in the pathogenesis of RIPF. Elucidating the involvement of microRNAs (miRNAs) in EMT could provide valuable insights into the mechanisms underlying RIPF and potentially reveal therapeutic targets. In this study, twelve dishes of BEAS-2B cells were irradiated with 6 Gy 60 Co γ-rays, and RNA was extracted at 0, 6, and 48 h after irradiation. High-throughput sequencing analysis of miRNA samples revealed miRNA significant changes in the BEAS-2B cells after irradiation, which was verified by RT-PCR. Additionally, the upstream transcription factors (TFs) were predicted through graphene oxide-based analysis. Transcription factors regulate the expression and transcriptional levels of miRNAs, and their functions may be associated with inflammatory or oxidative stress responses. The functional roles of these TFs were characterized through gene ontology (GO) analysis. Overall, we successfully screened and identified a set of miRNAs associated with ionizing radiation-induced EMT in lung epithelial cells and performed predictive identification of their upstream TFs and downstream regulatory target proteins. These data provide a firm foundation for future studies of the mechanism of radiation-induced EMT processes and related changes in biological function.
- Open Access
Investigation of key miRNAs and Target-mRNA in Kaposi's sarcoma using bioinformatic methods
- 7 February 2024
- Published by Wiley in Oral Diseases
- Vol. 30 (7) , 4266-4277
The effect of c‐Fos on the prognosis, proliferation, and invasion of oral squamous cell carcinoma
Objective: This study aimed to determine the role of c‐Fos in growth and invasion of oral squamous cell carcinoma (OSCC).Methods: Immunohistochemistry was used to assess c‐Fos expression in 94 OSCC tissues and 30 adjacent normal tissues, the correlation between c‐Fos expression and clinicopathological characteristics was examined, and Kaplan–Meier and Cox analysis were used to investigate the role of c‐Fos in predicting the prognosis of OSCC patients. The effects of c‐Fos on the growth and invasion of OSCC were disclosed by overexpression and knockdown of c‐Fos. Furthermore, based on bioinformatics prediction, the effect of miR‐155‐5p on c‐Fos expression was examined, and dual‐luciferase reporter assay system was used to determine whether miR‐155‐5p regulated the transcriptional activity of c‐Fos in OSCC.Results: c‐Fos was markedly increased in OSCC tissues and cells. c‐Fos upregulation indicates a poor prognosis in OSCC patients, and c‐Fos promotes cell proliferation, migration, and invasion in OSCC. miR‐155‐5p could regulate the expression and the transcriptional activity of c‐Fos by directly targeting the c‐Fos 3′‐UTR.Conclusion: This study demonstrated that c‐Fos contributed to the progression of OSCC and may act as a potential target for OSCC therapy, and a potential prognostic biomarker of OSCC.
- 7 February 2024
- Published by Wiley in Oral Diseases
- Vol. 30 (7) , 4266-4277
The effect of c‐Fos on the prognosis, proliferation, and invasion of oral squamous cell carcinoma
Objective: This study aimed to determine the role of c‐Fos in growth and invasion of oral squamous cell carcinoma (OSCC).Methods: Immunohistochemistry was used to assess c‐Fos expression in 94 OSCC tissues and 30 adjacent normal tissues, the correlation between c‐Fos expression and clinicopathological characteristics was examined, and Kaplan–Meier and Cox analysis were used to investigate the role of c‐Fos in predicting the prognosis of OSCC patients. The effects of c‐Fos on the growth and invasion of OSCC were disclosed by overexpression and knockdown of c‐Fos. Furthermore, based on bioinformatics prediction, the effect of miR‐155‐5p on c‐Fos expression was examined, and dual‐luciferase reporter assay system was used to determine whether miR‐155‐5p regulated the transcriptional activity of c‐Fos in OSCC.Results: c‐Fos was markedly increased in OSCC tissues and cells. c‐Fos upregulation indicates a poor prognosis in OSCC patients, and c‐Fos promotes cell proliferation, migration, and invasion in OSCC. miR‐155‐5p could regulate the expression and the transcriptional activity of c‐Fos by directly targeting the c‐Fos 3′‐UTR.Conclusion: This study demonstrated that c‐Fos contributed to the progression of OSCC and may act as a potential target for OSCC therapy, and a potential prognostic biomarker of OSCC.
- 1 January 2024
- Published by e-Century Publishing Corporation in American Journal of Cancer Research
- Vol. 14 (5) , 2408-2423
γ-Synuclein promotes proliferation and inhibits apoptosis of oral squamous cell carcinoma via JAK2/STAT5b signaling pathway
γ-Synuclein (SNCG) has various biological functions associated with tumorigenesis. However, the role of SNCG in oral squamous cell carcinoma (OSCC) remains unknown. In this study, we found that SNCG expression is associated with the malignancy of OSCC. We showed that SNCG promotes cell proliferation and inhibits apoptosis in OSCC. Mechanistically, we demonstrated for the first time, that SNCG interacts with ERK1/2 and promotes its phosphorylation leading to activation of the JAK2/STAT5b signaling pathway. Subsequent experiments with STAT5b interference and ERK1/2 inhibitor treatment reversed the effects of SNCG on OSCC cell proliferation, apoptosis and cell cycle progression. Our findings suggest that SNCG functions as an oncogene in OSCC by targeting the JAK2/STAT5b axis and thus may be a potential new prognostic marker and therapeutic target in OSCC.
- 1 January 2024
- Published by e-Century Publishing Corporation in American Journal of Cancer Research
- Vol. 14 (5) , 2408-2423
γ-Synuclein promotes proliferation and inhibits apoptosis of oral squamous cell carcinoma via JAK2/STAT5b signaling pathway
γ-Synuclein (SNCG) has various biological functions associated with tumorigenesis. However, the role of SNCG in oral squamous cell carcinoma (OSCC) remains unknown. In this study, we found that SNCG expression is associated with the malignancy of OSCC. We showed that SNCG promotes cell proliferation and inhibits apoptosis in OSCC. Mechanistically, we demonstrated for the first time, that SNCG interacts with ERK1/2 and promotes its phosphorylation leading to activation of the JAK2/STAT5b signaling pathway. Subsequent experiments with STAT5b interference and ERK1/2 inhibitor treatment reversed the effects of SNCG on OSCC cell proliferation, apoptosis and cell cycle progression. Our findings suggest that SNCG functions as an oncogene in OSCC by targeting the JAK2/STAT5b axis and thus may be a potential new prognostic marker and therapeutic target in OSCC.
- Open Access
- 1 January 2024
- Published by Ivyspring International Publisher in Journal of Cancer
- Vol. 15 (6) , 1593-1602
A Potential biomarker for the early diagnosis of OSCC: saliva and serum PrPC
Background: Oral squamous cell carcinoma (OSCC) is frequently diagnosed at an advanced stage, and the high mortality of patients is mainly due to the delay of diagnosis. Cellular prion protein (PrPC) contributes to the occurrence and development of many malignant tumors. However, little has been known about the clinical and diagnostic value of PrPC in OSCC. This study investigated the levels of PrPC in the saliva and serum of patients with OSCC, OPMD and control group and their diagnostic value.
- 1 January 2024
- Published by Ivyspring International Publisher in Journal of Cancer
- Vol. 15 (6) , 1593-1602
Open AccessA Potential biomarker for the early diagnosis of OSCC: saliva and serum PrPC
Background: Oral squamous cell carcinoma (OSCC) is frequently diagnosed at an advanced stage, and the high mortality of patients is mainly due to the delay of diagnosis. Cellular prion protein (PrPC) contributes to the occurrence and development of many malignant tumors. However, little has been known about the clinical and diagnostic value of PrPC in OSCC. This study investigated the levels of PrPC in the saliva and serum of patients with OSCC, OPMD and control group and their diagnostic value.
- Open Access
- 26 May 2023
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 9 (21) , eadg1778
Neuropilin 1 is an entry receptor for KSHV infection of mesenchymal stem cell through TGFBR1/2-mediated macropinocytosis
Kaposi’s sarcoma–associated herpesvirus (KSHV) has been implicated in the pathogenesis of Kaposi’s sarcoma (KS) and other malignancies. The cellular origin of KS has been suggested to be either mesenchymal stem cells (MSCs) or endothelial cells. However, receptor(s) for KSHV to infect MSCs remains unknown. By combining bioinformatics analysis and shRNA screening, we identify neuropilin 1 (NRP1) as an entry receptor for KSHV infection of MSCs. Functionally, NRP1 knockout and overexpression in MSCs significantly reduce and promote, respectively, KSHV infection. Mechanistically, NRP1 facilitated the binding and internalization of KSHV by interacting with KSHV glycoprotein B (gB), which was blocked by soluble NRP1 protein. Furthermore, NRP1 interacts with TGF-β receptor type 2 (TGFBR2) through their respective cytoplasmic domains and thus activates the TGFBR1/2 complex, which facilitates the macropinocytosis-mediated KSHV internalization via the small GTPases Cdc42 and Rac1. Together, these findings implicate that KSHV has evolved a strategy to invade MSCs by harnessing NRP1 and TGF-beta receptors to stimulate macropinocytosis.
- 26 May 2023
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 9 (21) , eadg1778
Open AccessNeuropilin 1 is an entry receptor for KSHV infection of mesenchymal stem cell through TGFBR1/2-mediated macropinocytosis
Kaposi’s sarcoma–associated herpesvirus (KSHV) has been implicated in the pathogenesis of Kaposi’s sarcoma (KS) and other malignancies. The cellular origin of KS has been suggested to be either mesenchymal stem cells (MSCs) or endothelial cells. However, receptor(s) for KSHV to infect MSCs remains unknown. By combining bioinformatics analysis and shRNA screening, we identify neuropilin 1 (NRP1) as an entry receptor for KSHV infection of MSCs. Functionally, NRP1 knockout and overexpression in MSCs significantly reduce and promote, respectively, KSHV infection. Mechanistically, NRP1 facilitated the binding and internalization of KSHV by interacting with KSHV glycoprotein B (gB), which was blocked by soluble NRP1 protein. Furthermore, NRP1 interacts with TGF-β receptor type 2 (TGFBR2) through their respective cytoplasmic domains and thus activates the TGFBR1/2 complex, which facilitates the macropinocytosis-mediated KSHV internalization via the small GTPases Cdc42 and Rac1. Together, these findings implicate that KSHV has evolved a strategy to invade MSCs by harnessing NRP1 and TGF-beta receptors to stimulate macropinocytosis.
- 3 November 2022
- Published by Wiley in Journal of Medical Virology
- Vol. 95 (1) , e28255
LANA regulates miR‐155/GATA3 signaling axis by enhancing c‐Jun/c‐Fos interaction to promote the proliferation and migration of KSHV‐infected cells
Kaposi's sarcoma (KS) is the second most common tumor in people infected with human immunodeficiency virus worldwide, but its pathogenesis is still unclear. In this study, we discovered that the expression of GATA‐binding protein 3 (GATA3) was lowly expressed in KS tissues and KSHV‐infected cells, while microRNA‐155 (miR‐155) was highly expressed in KS serum and KSHV‐infected cells. miR‐155 promoted the proliferation, migration and invasion of KSHV infection by targeting GATA3. Further, The KSHV‐encoded protein, the Latency associated nuclear antigen (LANA), promotes the proliferation, migration and invasion of KSHV‐infected cells by regulating the miR‐155/GATA3 axis. Regarding the molecular mechanism, c‐Jun and c‐Fos interact to form a complex. LANA upregulates the expression of c‐Jun and c‐Fos and enhances the formation of c‐Jun/c‐Fos complex. The complex binds to the −95∼−100 bp site of miR‐155 promoter and transcriptionally activates miR‐155. All in all, LANA enhances the c‐Jun/c‐Fos interaction, resulting in enhanced transcriptional regulation of miR‐155 by the c‐Jun/c‐Fos complex, thereby downregulating GATA3 and promoting the proliferation, migration and invasion of KSHV‐infected cells. The discovery of LANA/c‐Jun/c‐Fos/miR‐155/GATA3 further refines the pathogenesis of KS, potentially opening a new avenue for developing effective drugs against KS.
- 3 November 2022
- Published by Wiley in Journal of Medical Virology
- Vol. 95 (1) , e28255
LANA regulates miR‐155/GATA3 signaling axis by enhancing c‐Jun/c‐Fos interaction to promote the proliferation and migration of KSHV‐infected cells
Kaposi's sarcoma (KS) is the second most common tumor in people infected with human immunodeficiency virus worldwide, but its pathogenesis is still unclear. In this study, we discovered that the expression of GATA‐binding protein 3 (GATA3) was lowly expressed in KS tissues and KSHV‐infected cells, while microRNA‐155 (miR‐155) was highly expressed in KS serum and KSHV‐infected cells. miR‐155 promoted the proliferation, migration and invasion of KSHV infection by targeting GATA3. Further, The KSHV‐encoded protein, the Latency associated nuclear antigen (LANA), promotes the proliferation, migration and invasion of KSHV‐infected cells by regulating the miR‐155/GATA3 axis. Regarding the molecular mechanism, c‐Jun and c‐Fos interact to form a complex. LANA upregulates the expression of c‐Jun and c‐Fos and enhances the formation of c‐Jun/c‐Fos complex. The complex binds to the −95∼−100 bp site of miR‐155 promoter and transcriptionally activates miR‐155. All in all, LANA enhances the c‐Jun/c‐Fos interaction, resulting in enhanced transcriptional regulation of miR‐155 by the c‐Jun/c‐Fos complex, thereby downregulating GATA3 and promoting the proliferation, migration and invasion of KSHV‐infected cells. The discovery of LANA/c‐Jun/c‐Fos/miR‐155/GATA3 further refines the pathogenesis of KS, potentially opening a new avenue for developing effective drugs against KS.
- Open Access
- 20 October 2022
- Published by Wiley in BioMed Research International
- Vol. 2022 (1) , 5170261
A Breast Cancer Prediction Model Based on a Panel from Circulating Exosomal miRNAs
Breast cancer (BC) has been a serious threat to women’s health. Exosomes contain a variety of biomolecules, which is an excellent choice as disease diagnostic markers, but whether it could be applied as a noninvasive biomarker for BC diagnosis demands to be additional studied. In this study, we aimed at creating a predictive model and reveal the value of plasma exosomal miRNA (exo‐miRNA) in early diagnosis of BC. Firstly, exosomes isolated from plasma were identified by Nanoparticle Tracking Analysis (NTA), Transmission Electron Microscope (TEM), and Western Blot. miRNA expression in plasma samples from 56 BC patients and 40 normal controls was analyzed by high‐throughput sequencing. miRNAs with strong correlation characteristics were selected by Lasso logistic regression. Then, we built the training set and test set, evaluated the Lasso regression accuracy, and evaluated the performance of different models in the training set and test set. Finally, GO analysis, KEGG, and Reactome pathway enrichment analysis were used to understand the biological significance of 16 characteristic miRNAs. The successful separation of exosomes in serum was identified by NTA, TEM, and Western Blot. The training set data matrix containing 1962 miRNAs was obtained by sequencing for model construction, and 16 strongly correlated miRNAs were selected by Lasso logistic regression. The accuracy of Lasso regression in training set and test set were 97.22% and 95.83%, respectively. We built different models and evaluated the performance of each model in the training set and test set. The results showed that the AUC values of Lasso, SVM, GBDT, and Random Forest model in the training set were 1, and the AUC values in the test set were 0.979, 0.936, 0.971, and 0.979, respectively. Bioinformatics analysis showed that 16 signature miRNAs were significantly enriched in cancer‐related pathways such as herpes simplex virus 1 infection, TGF‐β signaling, and Toll‐like receptor family. The results of this study suggest that the 16 characteristic miRNAs screened from plasma exosomes can be used as a group of biomarkers, and the prediction model constructed based on this set of markers is expected to be used in the early diagnosis of BC.
- 20 October 2022
- Published by Wiley in BioMed Research International
- Vol. 2022 (1) , 5170261
Open AccessA Breast Cancer Prediction Model Based on a Panel from Circulating Exosomal miRNAs
Breast cancer (BC) has been a serious threat to women’s health. Exosomes contain a variety of biomolecules, which is an excellent choice as disease diagnostic markers, but whether it could be applied as a noninvasive biomarker for BC diagnosis demands to be additional studied. In this study, we aimed at creating a predictive model and reveal the value of plasma exosomal miRNA (exo‐miRNA) in early diagnosis of BC. Firstly, exosomes isolated from plasma were identified by Nanoparticle Tracking Analysis (NTA), Transmission Electron Microscope (TEM), and Western Blot. miRNA expression in plasma samples from 56 BC patients and 40 normal controls was analyzed by high‐throughput sequencing. miRNAs with strong correlation characteristics were selected by Lasso logistic regression. Then, we built the training set and test set, evaluated the Lasso regression accuracy, and evaluated the performance of different models in the training set and test set. Finally, GO analysis, KEGG, and Reactome pathway enrichment analysis were used to understand the biological significance of 16 characteristic miRNAs. The successful separation of exosomes in serum was identified by NTA, TEM, and Western Blot. The training set data matrix containing 1962 miRNAs was obtained by sequencing for model construction, and 16 strongly correlated miRNAs were selected by Lasso logistic regression. The accuracy of Lasso regression in training set and test set were 97.22% and 95.83%, respectively. We built different models and evaluated the performance of each model in the training set and test set. The results showed that the AUC values of Lasso, SVM, GBDT, and Random Forest model in the training set were 1, and the AUC values in the test set were 0.979, 0.936, 0.971, and 0.979, respectively. Bioinformatics analysis showed that 16 signature miRNAs were significantly enriched in cancer‐related pathways such as herpes simplex virus 1 infection, TGF‐β signaling, and Toll‐like receptor family. The results of this study suggest that the 16 characteristic miRNAs screened from plasma exosomes can be used as a group of biomarkers, and the prediction model constructed based on this set of markers is expected to be used in the early diagnosis of BC.