scholarly journals Identification of Inflammatory Response-Related Gene Signature Associated With Immune Status and Prognosis of Lung Adenocarcinoma

2021 ◽  
Vol 9 ◽  
Author(s):  
Weijie Zou ◽  
Li Chen ◽  
Wenwen Mao ◽  
Su Hu ◽  
Yuanqing Liu ◽  
...  
Keyword(s):  
High Risk ◽  
Inflammatory Response ◽  
Lung Adenocarcinoma ◽  
Immune Status ◽  
Enrichment Analysis ◽  
Gene Signature ◽  
Gene Set Enrichment Analysis ◽  
Related Gene ◽  
Gene Set Enrichment ◽  
Cox Analysis

Background: Lung adenocarcinoma (LUAD) is an exceedingly diverse disease, making prognostication difficult. Inflammatory responses in the tumor or the tumor microenvironment can alter prognosis in the process of the ongoing cross-talk between the host and the tumor. Nonetheless, Inflammatory response-related genes’ prognostic significance in LUAD, on the other hand, has yet to be determined.Materials and Methods: The clinical data as well as the mRNA expression patterns of LUAD patients were obtained from a public dataset for this investigation. In the TCGA group, a multigene prognostic signature was built utilizing LASSO Cox analysis. Validation was executed on LUAD patients from the GEO cohort. The overall survival (OS) of low- and high-risk cohorts was compared utilizing the Kaplan-Meier analysis. The assessment of independent predictors of OS was carried out utilizing multivariate and univariate Cox analyses. The immune-associated pathway activity and immune cell infiltration score were computed utilizing single-sample gene set enrichment analysis. GO keywords and KEGG pathways were explored utilizing gene set enrichment analysis.Results: LASSO Cox regression analysis was employed to create an inflammatory response-related gene signature model. The high-risk cohort patients exhibited a considerably shorter OS as opposed to those in the low-risk cohort. The prognostic gene signature’s predictive ability was demonstrated using receiver operating characteristic curve analysis. The risk score was found to be an independent predictor of OS using multivariate Cox analysis. The functional analysis illustrated that the immune status and cancer-related pathways for the two-risk cohorts were clearly different. The tumor stage and kind of immune infiltrate were found to be substantially linked with the risk score. Furthermore, the cancer cells’ susceptibility to anti-tumor medication was substantially associated with the prognostic genes expression levels.Conclusion: In LUAD, a new signature made up of 8 inflammatory response-related genes may be utilized to forecast prognosis and influence immunological state. Inhibition of these genes could also be used as a treatment option.

scholarly journals An Inflammatory Response-Related Gene Signature Can Impact the Immune Status and Predict the Prognosis of Hepatocellular Carcinoma

2021 ◽  
Vol 11 ◽  
Author(s):  
Zhuo Lin ◽  
Qian Xu ◽  
Dan Miao ◽  
Fujun Yu
Keyword(s):  
Inflammatory Response ◽  
Immune Status ◽  
Risk Group ◽  
Enrichment Analysis ◽  
Risk Groups ◽  
Gene Signature ◽  
High Risk Group ◽  
Gene Set Enrichment Analysis ◽  
Prognostic Prediction ◽  
Cox Analysis

BackgroundHepatocellular carcinoma (HCC) is a highly heterogeneous disease, which makes the prognostic prediction challenging. As part of the active cross-talk between the tumor and the host, inflammatory response in the tumor or its microenvironment could affect prognosis. However, the prognostic value of inflammatory response-related genes in HCC remains to be further elucidated.MethodsIn this study, the mRNA expression profiles and corresponding clinical data of HCC patients were downloaded from the public database. The least absolute shrinkage and selection operator Cox analysis was utilized to construct a multigene prognostic signature in the TCGA cohort. HCC patients from the ICGC cohort were used for validation. Kaplan Meier analysis was used to compare the overall survival (OS) between high- and low-risk groups. Univariate and multivariate Cox analyses were applied to determine the independent predictors for OS. Single-sample gene set enrichment analysis was utilized to calculate the immune cell infiltration score and immune related pathway activity. Gene set enrichment analysis was implemented to conduct GO terms and KEGG pathways. The qRT-PCR and immunohistochemistry were utilized to perform the mRNA and protein expression of prognostic genes between HCC tissues and normal liver tissues respectively.ResultsAn inflammatory response-related gene signature model was constructed by LASSO Cox regression analysis. Compared with the low-risk group, patients in the high-risk group showed significantly reduced OS. Receiver operating characteristic curve analysis confirmed the predictive capacity of the prognostic gene signature. Multivariate Cox analysis revealed that the risk score was an independent predictor for OS. Functional analysis indicated that immune status was definitely different between two risk groups, and cancer-related pathways were enriched in high-risk group. The risk score was significantly correlated with tumor grade, tumor stage and immune infiltrate types. The expression levels of prognostic genes were significantly correlated with sensitivity of cancer cells to anti-tumor drugs. Furthermore, the expression of prognostic genes showed significant difference between HCC tissues and adjacent non-tumorous tissues in the separate sample cohort.ConclusionA novel signature constructed with eight inflammatory response-related genes can be used for prognostic prediction and impact the immune status in HCC. Moreover, inhibition of these genes may be a therapeutic alternative.

scholarly journals A New Ferroptosis-Related lncRNA Signature Predicts the Prognosis of Bladder Cancer Patients

2021 ◽  
Vol 9 ◽  
Author(s):  
Mei Chen ◽  
Zhenyu Nie ◽  
Yan Li ◽  
Yuanhui Gao ◽  
Xiaohong Wen ◽  
...  
Keyword(s):  
High Risk ◽  
Immune Status ◽  
Risk Group ◽  
Enrichment Analysis ◽  
Risk Groups ◽  
High Risk Group ◽  
Low Risk ◽  
Gene Set Enrichment Analysis ◽  
Gene Set Enrichment ◽  
Clinicopathological Variables

Background: Ferroptosis is closely related to the occurrence and development of cancer. An increasing number of studies have induced ferroptosis as a treatment strategy for cancer. However, the predictive value of ferroptosis-related lncRNAs in bladder cancer (BC) still need to be further elucidated. The purpose of this study was to construct a predictive signature based on ferroptosis-related long noncoding RNAs (lncRNAs) to predict the prognosis of BC patients.Methods: We downloaded RNA-seq data and the corresponding clinical and prognostic data from The Cancer Genome Atlas (TCGA) database and performed univariate and multivariate Cox regression analyses to obtain ferroptosis-related lncRNAs to construct a predictive signature. The Kaplan-Meier method was used to analyze the overall survival (OS) rate of the high-risk and low-risk groups. Gene set enrichment analysis (GSEA) was performed to explore the functional differences between the high- and low-risk groups. Single-sample gene set enrichment analysis (ssGSEA) was used to explore the relationship between the predictive signature and immune status. Finally, the correlation between the predictive signature and the treatment response of BC patients was analyzed.Results: We constructed a signature composed of nine ferroptosis-related lncRNAs (AL031775.1, AL162586.1, AC034236.2, LINC01004, OCIAD1-AS1, AL136084.3, AP003352.1, Z84484.1, AC022150.2). Compared with the low-risk group, the high-risk group had a worse prognosis. The ferroptosis-related lncRNA signature could independently predict the prognosis of patients with BC. Compared with clinicopathological variables, the ferroptosis-related lncRNA signature has a higher diagnostic efficiency, and the area under the receiver operating characteristic curve was 0.707. When patients were stratified according to different clinicopathological variables, the OS of patients in the high-risk group was shorter than that of those in the low-risk group. GSEA showed that tumor- and immune-related pathways were mainly enriched in the high-risk group. ssGSEA showed that the predictive signature was significantly related to the immune status of BC patients. High-risk patients were more sensitive to anti-PD-1/L1 immunotherapy and the conventional chemotherapy drugs sunitinib, paclitaxel, cisplatin, and docetaxel.Conclusion: The predictive signature can independently predict the prognosis of BC patients, provides a basis for the mechanism of ferroptosis-related lncRNAs in BC and provides clinical treatment guidance for patients with BC.

scholarly journals Systematic Profiling of Invasion-related Genes Signature Predicts Prognostic Features and Identificates Molecular Subtypes of Lung Adenocarcinoma

2021 ◽  
Author(s):  
Ping Yu ◽  
Linlin Tong ◽  
Yujia Song ◽  
Hui Qu ◽  
Ying Chen
Keyword(s):  
Gene Expression ◽  
Lung Adenocarcinoma ◽  
Molecular Subtypes ◽  
Expression Profiles ◽  
Enrichment Analysis ◽  
Gene Signature ◽  
Gene Set Enrichment Analysis ◽  
Normal Tissues ◽  
Tumor Tissues ◽  
Cox Analysis

Abstract Background: Due to the high heterogeneity of lung adenocarcinoma (LUAD), molecular subtype based on gene expression profiles is of great significance for diagnosis, and prognosis prediction in patients with LUAD.Methods: Invasion-related genes were obtained from the CancerSEA database, and LUAD expression profiles were downloaded from The Cancer Genome Atlas. The ConsensusClusterPlus was used to obtain molecular subtypes based on invasion-related genes. The limma software package was used to identify differentially expressed genes (DEGs). A multi-gene risk model was constructed by Lasso-Cox analysis. A nomogram was also constructed based on risk scores and meaningful clinical features.Results: 3 subtypes (C1, C2, C3) based on the expression of invasion-related genes were obtained. C3 had the worst prognosis. A total of 669 DEGs were identified among the subtypes. Pathway enrichment analysis results showed that the DEGs were mainly enriched in the cell cycle, DNA replication, the p53 signaling pathway, and other tumor-related pathways. A 5-gene signature (KRT6A, MELTF, IRX5, MS4A1, CRTAC1) was identified by using Lasso-Cox analysis. The training, validation, and external independent cohorts proved that the model was robust and had better prediction ability than other lung cancer models. The gene expression results showed that the expression levels of MS4A1 and KRT6A in tumor tissues were higher than in normal tissues, while CRTAC1 expression in tumor tissues was lower than in normal tissues. At the same time, the 5 genes were significantly expressed in pan-cancer immune subtypes. Gene set enrichment analysis showed that MS4A1, KRT6A, and CRAT1 genes were both enriched in the HALLMARK_IL2_STAT5_SIGNALING pathway, and IRX5 and MELTF gene were both enriched in the HALLMARK_EPITHELIAL_MESENCHYMAL_TRANSITION pathway. Conclusion: The 5-gene signature prognostic stratification system based on invasion-related genes could be used to assess prognostic risk in patients with LUAD.

A Hypoxia-related LncRNA Signature Predicts Survival of Primary Lower-grade glioma

2021 ◽  
Author(s):  
Yanjia Hu ◽  
Jing Zhang ◽  
Jing Chen
Keyword(s):  
High Risk ◽  
Risk Score ◽  
Cox Regression ◽  
Risk Group ◽  
Enrichment Analysis ◽  
High Risk Group ◽  
Gene Set Enrichment Analysis ◽  
Lower Grade ◽  
Prognostic Signature ◽  
Gene Set Enrichment

Abstract Background Hypoxia-related long non-coding RNAs (lncRNAs) have been proven to play a role in multiple cancers and can serve as prognostic markers. Lower-grade gliomas (LGGs) are characterized by large heterogeneity. Methods This study aimed to construct a hypoxia-related lncRNA signature for predicting the prognosis of LGG patients. Transcriptome and clinical data of LGG patients were obtained from The Cancer Genome Atlas (TCGA) and the Chinese Glioma Genome Atlas (CGGA). LGG cohort in TCGA was chosen as training set and LGG cohorts in CGGA served as validation sets. A prognostic signature consisting of fourteen hypoxia-related lncRNAs was constructed using univariate and LASSO Cox regression. A risk score formula involving the fourteen lncRNAs was developed to calculate the risk score and patients were classified into high- and low-risk groups based on cutoff. Kaplan-Meier survival analysis was used to compare the survival between two groups. Cox regression analysis was used to determine whether risk score was an independent prognostic factor. A nomogram was then constructed based on independent prognostic factors and assessed by C-index and calibration plot. Gene set enrichment analysis and immune cell infiltration analysis were performed to uncover further mechanisms of this lncRNA signature. Results LGG patients with high risk had poorer prognosis than those with low risk in both training and validation sets. Recipient operating characteristic curves showed good performance of the prognostic signature. Univariate and multivariate Cox regression confirmed that the established lncRNA signature was an independent prognostic factor. C-index and calibration plots showed good predictive performance of nomogram. Gene set enrichment analysis showed that genes in the high-risk group were enriched in apoptosis, cell adhesion, pathways in cancer, hypoxia etc. Immune cells were higher in high-risk group. Conclusion The present study showed the value of the 14-lncRNA signature in predicting survival of LGGs and these 14 lncRNAs could be further investigated to reveal more mechanisms involved in gliomas.

scholarly journals DPYSL2 as potential diagnostic and prognostic biomarker linked to immune infiltration in lung adenocarcinoma

2021 ◽  
Vol 19 (1) ◽  
Author(s):  
Yang-Jie Wu ◽  
Ai-Tao Nai ◽  
Gui-Cheng He ◽  
Fei Xiao ◽  
Zhi-Min Li ◽  
...  
Keyword(s):  
Lung Adenocarcinoma ◽  
Roc Curve ◽  
Enrichment Analysis ◽  
Gene Set Enrichment Analysis ◽  
List Type ◽  
Gene Set Enrichment ◽  
Gene Set ◽  
Normal Tissues ◽  
Kaplan Meier ◽  
Kaplan Meier Plotter

Abstract Background Dihydropyrimidinase like 2 (DPYSL2) has been linked to tumor metastasis. However, the function of DPSY2L in lung adenocarcinoma (LUAD) is yet to be explored. Methods Herein, we assessed DPYSL2 expression in various tumor types via online databases such as Oncomine and Tumor Immune Estimation Resource (TIMER). Further, we verified the low protein and mRNA expressions of DPYSL2 in LUAD via the ULCAN, The TCGA and GEPIA databases. We applied the ROC curve to examine the role of DPYSL2 in diagnosis. The prognostic significance of DPYSL2 was established through the Kaplan–Meier plotter and the Cox analyses (univariate and multivariate). TIMER was used to explore DPYSL2 expression and its connection to immune infiltrated cells. Through Gene Set Enrichment Analysis, the possible mechanism of DPYSL2 in LUAD was investigated. Results In this study, database analysis revealed lower DPYSL2 expression in LUAD than in normal tissues. The ROC curve suggested that expression of DPYSL2 had high diagnostic efficiency in LUAD. The DPYSL2 expression had an association with the survival time of LUAD patients in the Kaplan–Meier plotter and the Cox analyses. The results from TIMER depicted a markedly positive correlation of DPYSL2 expression with immune cells infiltrated in LUAD, such as macrophages, dendritic cells, CD4+ T cells, and neutrophils. Additionally, many gene markers for the immune system had similar positive correlations in the TIMER analysis. In Gene Set Enrichment Analysis, six immune-related signaling pathways were associated with DPYSL2. Conclusions In summary, DPYSL2 is a novel biomarker with diagnostic and prognostic potential for LUAD as well as an immunotherapy target. Highlights Expression of DPYSL2 was considerably lower in LUAD than in normal tissues. Investigation of multiple databases showed a high diagnostic value of DPYSL2 in LUAD. DPYSL2 can independently predict the LUAD outcomes. Immune-related mechanisms may be potential ways for DPYSL2 to play a role in LUAD.

scholarly journals An immune-related lncRNA signature as a prognostic immunotherapy target for colon cancer

2020 ◽  
Author(s):  
Bin Wu ◽  
Yi Yao ◽  
Yi Dong ◽  
Si Qi Yang ◽  
Deng Jing Zhou ◽  
...  
Keyword(s):  
Colon Cancer ◽  
High Risk ◽  
Risk Score ◽  
Enrichment Analysis ◽  
Risk Groups ◽  
Low Risk ◽  
Gene Set Enrichment Analysis ◽  
Risk Scores ◽  
Gene Set Enrichment ◽  
Immunotherapy Target

Abstract Background：We aimed to investigate an immune-related long non-coding RNA (lncRNA) signature that may be exploited as a potential immunotherapy target in colon cancer. Materials and methods: Colon cancer samples from The Cancer Genome Atlas (TCGA) containing available clinical information and complete genomic mRNA expression data were used in our study. We then constructed immune-related lncRNA co-expression networks to identify the most promising immune-related lncRNAs. According to the risk score developed from screened immune-related lncRNAs, the high-risk and low-risk groups were separated on the basis of the median risk score, which served as the cutoff value. An overall survival analysis was then performed to confirm that the risk score developed from screened immune-related lncRNAs could predict colon cancer prognosis. The prediction reliability was further evaluated in the independent prognostic analysis and receiver operating characteristic curve (ROC). A principal component analysis (PCA) and gene set enrichment analysis (GSEA) were performed for functional annotation. Results: Information for a total of 514 patients was included in our study. After multiplex analysis, 12 immune-related lncRNAs were confirmed as a signature to evaluate the risk scores for each patient with cancer. Patients in the low-risk group exhibited a longer overall survival (OS) than those in the high-risk group. Additionally, the risk scores were an independent factor, and the Area Under Curve (AUC) of ROC for accuracy prediction was 0.726. Moreover, the low-risk and high-risk groups displayed different immune statuses based on principal components and gene set enrichment analysis.Conclusions: Our study suggested that the signature consisting of 12 immune-related lncRNAs can provide an accessible approach to measuring the prognosis of colon cancer and may serve as a valuable antitumor immunotherapy.

scholarly journals A Starvation-Based 9-mRNA Signature Correlates With Prognosis in Patients With Hepatocellular Carcinoma

2021 ◽  
Vol 11 ◽  
Author(s):  
Dengliang Lei ◽  
Yue Chen ◽  
Yang Zhou ◽  
Gangli Hu ◽  
Fang Luo
Keyword(s):  
Hepatocellular Carcinoma ◽  
High Risk ◽  
Liver Cancer ◽  
Cancer Patients ◽  
Enrichment Analysis ◽  
Clinical Information ◽  
Cancer Genome ◽  
Gene Set Enrichment Analysis ◽  
Biological Processes ◽  
Gene Set Enrichment

BackgroundHepatocellular carcinoma (HCC) is one of the world’s most prevalent and lethal cancers. Notably, the microenvironment of tumor starvation is closely related to cancer malignancy. Our study constructed a signature of starvation-related genes to predict the prognosis of liver cancer patients.MethodsThe mRNA expression matrix and corresponding clinical information of HCC patients were obtained from the International Cancer Genome Consortium (ICGC) and The Cancer Genome Atlas (TCGA). Gene set enrichment analysis (GSEA) was used to distinguish different genes in the hunger metabolism gene in liver cancer and adjacent tissues. Gene Set Enrichment Analysis (GSEA) was used to identify biological differences between high- and low-risk samples. Univariate and multivariate analyses were used to construct prognostic models for hunger-related genes. Kaplan-Meier (KM) and receiver-operating characteristic (ROC) were used to assess the model accuracy. The model and relevant clinical information were used to construct a nomogram, protein expression was detected by western blot (WB), and transwell assay was used to evaluate the invasive and metastatic ability of cells.ResultsFirst, we used univariate analysis to identify 35 prognostic genes, which were further demonstrated to be associated with starvation metabolism through Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO). We then used multivariate analysis to build a model with nine genes. Finally, we divided the sample into low- and high-risk groups according to the median of the risk score. KM can be used to conclude that the prognosis of high- and low-risk samples is significantly different, and the prognosis of high-risk samples is worse. The prognostic accuracy of the 9-mRNA signature was also tested in the validation data set. GSEA was used to identify typical pathways and biological processes related to 9-mRNA, cell cycle, hypoxia, p53 pathway, and PI3K/AKT/mTOR pathway, as well as biological processes related to the model. As evidenced by WB, EIF2S1 expression was increased after starvation. Overall, EIF2S1 plays an important role in the invasion and metastasis of liver cancer.ConclusionsThe 9-mRNA model can serve as an accurate signature to predict the prognosis of liver cancer patients. However, its mechanism of action warrants further investigation.

scholarly journals Establishment of Immune-related Gene Pair Signature to Predict Lung Adenocarcinoma Prognosis

2020 ◽  
Vol 29 ◽  
pp. 096368972097713
Author(s):  
Xueping Jiang ◽  
Yanping Gao ◽  
Nannan Zhang ◽  
Cheng Yuan ◽  
Yuan Luo ◽  
...  
Keyword(s):  
High Risk ◽  
Lung Adenocarcinoma ◽  
Gene Pair ◽  
Risk Group ◽  
High Risk Group ◽  
Gene Set Enrichment Analysis ◽  
M2 Macrophage ◽  
Related Gene ◽  
Immune Related Gene ◽  
Potential Biomarker

Tumor microenvironment (TME) has critical impacts on the pathogenesis of lung adenocarcinoma (LUAD). However, the molecular mechanism of TME effects on the prognosis of LUAD patients remains unclear. Our study aimed to establish an immune-related gene pair (IRGP) model for prognosis prediction and internal mechanism investigation. Based on 702 TME-related differentially expressed genes (DEGs) extracted from The Cancer Genome Atlas (TCGA) training cohort using the ESTIMATE algorithm, a 10-IRGP signature was established to predict LUAD patient prognosis. Gene Ontology and Kyoto Encyclopedia of Genes and Genomes analyses showed that DEGs were significantly associated with tumor immune response. In both TCGA training and Gene Expression Omnibus validation datasets, the risk score was an independent prognostic factor for LUAD patients using Lasso-Cox analysis, and patients in the high-risk group had poorer prognosis than those in the low-risk one. In the high-risk group, M2 macrophage and neutrophil infiltrations were higher, while the levels of T cell follicular helpers were significantly lower. The gene set enrichment analysis results showed that DNA repair signaling pathways were involved. In summary, we established an IRGP signature as a potential biomarker to predict the prognosis of LUAD patients.

scholarly journals Establishment and Validation of a Novel Metabolism-related Gene Signature for Predicting Overall Survival of Patients with Breast Cancer

2021 ◽  
Author(s):  
Jian Li ◽  
Yang Liu ◽  
Fei Liu ◽  
Qiang Tian ◽  
Baojiang Li ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Cox Regression ◽  
Treatment Strategies ◽  
Enrichment Analysis ◽  
Risk Groups ◽  
Gene Signature ◽  
Gene Set Enrichment Analysis ◽  
Current Status ◽  
Lasso Regression ◽  
Related Gene

Abstract It is well known that Breast cancer is a heterogeneous disease.Although the current recurrence and mortality rate have been greatly improved, many people still suffer relapse and metastasis.Metabolic reprograming is currently considered to be a new hallmark of cancer.Therefore,in this study, we comprehensively analyzed the prognostic effect of metabolic-related gene signatures in breast cancer and its relationship with the immune microenvironment.We constructed a novel metabolic-related gene signature containing 6 genes to distinguish between high and low risk groups by univariate Cox regression and least absolute shrinkage and selection operator (LASSO) regression, and validated its robustness and accuracy through multiple databases.The metabolic gene signature may be an independent risk factor for BC both in the training and the testing set,the nomogram has a moderately accurate performance,and the C index was 0.757 and 0.728 respectively.The signature can reveal metabolic characteristics based on gene set enrichment analysis and at the same time monitor the status of TME.This gene signature can be used as a promising independent prognostic marker for BC patients, and can indicate the current status of TME, providing more clues for exploring new diagnostic and treatment strategies.

scholarly journals Learning interpretable cellular and gene signature embeddings from single-cell transcriptomic data

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Yifan Zhao ◽  
Huiyu Cai ◽  
Zuobai Zhang ◽  
Jian Tang ◽  
Yue Li
Keyword(s):  
Single Cell ◽  
Large Scale ◽  
Topic Model ◽  
Enrichment Analysis ◽  
Gene Signature ◽  
Gene Set Enrichment Analysis ◽  
Learning Performance ◽  
Cell Type ◽  
Gene Set Enrichment ◽  
Gene Sets

AbstractThe advent of single-cell RNA sequencing (scRNA-seq) technologies has revolutionized transcriptomic studies. However, large-scale integrative analysis of scRNA-seq data remains a challenge largely due to unwanted batch effects and the limited transferabilty, interpretability, and scalability of the existing computational methods. We present single-cell Embedded Topic Model (scETM). Our key contribution is the utilization of a transferable neural-network-based encoder while having an interpretable linear decoder via a matrix tri-factorization. In particular, scETM simultaneously learns an encoder network to infer cell type mixture and a set of highly interpretable gene embeddings, topic embeddings, and batch-effect linear intercepts from multiple scRNA-seq datasets. scETM is scalable to over 106 cells and confers remarkable cross-tissue and cross-species zero-shot transfer-learning performance. Using gene set enrichment analysis, we find that scETM-learned topics are enriched in biologically meaningful and disease-related pathways. Lastly, scETM enables the incorporation of known gene sets into the gene embeddings, thereby directly learning the associations between pathways and topics via the topic embeddings.

Sign in / Sign up

Export Citation Format

Share Document