1
|
Klinkhammer H, Staerk C, Maj C, Krawitz PM, Mayr A. Genetic Prediction Modeling in Large Cohort Studies via Boosting Targeted Loss Functions. Stat Med 2024; 43:5412-5430. [PMID: 39440393 PMCID: PMC11586906 DOI: 10.1002/sim.10249] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2024] [Revised: 09/11/2024] [Accepted: 10/01/2024] [Indexed: 10/25/2024]
Abstract
Polygenic risk scores (PRS) aim to predict a trait from genetic information, relying on common genetic variants with low to medium effect sizes. As genotype data are high-dimensional in nature, it is crucial to develop methods that can be applied to large-scale data (largen $$ n $$ and largep $$ p $$ ). Many PRS tools aggregate univariate summary statistics from genome-wide association studies into a single score. Recent advancements allow simultaneous modeling of variant effects from individual-level genotype data. In this context, we introduced snpboost, an algorithm that applies statistical boosting on individual-level genotype data to estimate PRS via multivariable regression models. By processing variants iteratively in batches, snpboost can deal with large-scale cohort data. Having solved the technical obstacles due to data dimensionality, the methodological scope can now be broadened-focusing on key objectives for the clinical application of PRS. Similar to most methods in this context, snpboost has, so far, been restricted to quantitative and binary traits. Now, we incorporate more advanced alternatives-targeted to the particular aim and outcome. Adapting the loss function extends the snpboost framework to further data situations such as time-to-event and count data. Furthermore, alternative loss functions for continuous outcomes allow us to focus not only on the mean of the conditional distribution but also on other aspects that may be more helpful in the risk stratification of individual patients and can quantify prediction uncertainty, for example, median or quantile regression. This work enhances PRS fitting across multiple model classes previously unfeasible for this data type.
Collapse
Affiliation(s)
- Hannah Klinkhammer
- Institute of Medical Biometry, Informatics and Epidemiology, Medical FacultyUniversity of BonnBonnGermany
- Institute of Genomic Statistics and Bioinformatics, Medical FacultyUniversity of BonnBonnGermany
| | - Christian Staerk
- Institute of Medical Biometry, Informatics and Epidemiology, Medical FacultyUniversity of BonnBonnGermany
- IUF – Leibniz Research Institute for Environmental MedicineDüsseldorfGermany
- Department of StatisticsTU Dortmund UniversityDortmundGermany
| | - Carlo Maj
- Institute of Genomic Statistics and Bioinformatics, Medical FacultyUniversity of BonnBonnGermany
- Center for Human GeneticsPhilipps‐University MarburgMarburgGermany
| | - Peter M. Krawitz
- Institute of Genomic Statistics and Bioinformatics, Medical FacultyUniversity of BonnBonnGermany
| | - Andreas Mayr
- Institute of Medical Biometry, Informatics and Epidemiology, Medical FacultyUniversity of BonnBonnGermany
| |
Collapse
|
2
|
Wu Z, Mo S, Huang Z, Zheng B. Identification of Diagnostically Relevant Biomarkers in Patients with Coronary Artery Disease by Comprehensive Analysis. J Inflamm Res 2024; 17:10495-10513. [PMID: 39654862 PMCID: PMC11627109 DOI: 10.2147/jir.s494438] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/03/2024] [Accepted: 11/28/2024] [Indexed: 12/12/2024] Open
Abstract
Background Peripheral biomarkers are becoming an important method by which to monitor the progression of coronary artery disease (CAD). Not only are they minimally invasive and early detection, but they can also be used for classification and diagnosis of disease as well as prognostic assessment. Currently, this approach is still in the exploratory stage. The purpose of this research is to determine the diagnostic value and therapeutic potential of the endoplasmic reticulum stress (ERS) genes in CAD. Methods The clinical information and RNA sequence data were obtained from the GEO database and subsequently subjected to a series of optimization and visualization processes using various analytical techniques, including WGCNA, LASSO, SVM-RFE feature selection, random forest (RF), and XGBoost, as well as R software and Cytoscape. Finally, immunofluorescence was used to validate the analysis. Results We identify 6 key ERS differentially expressed genes (ERS-DEGs) (UFL1, HSPA1A, ERLIN1, LRRK2, ERN1, SERINC3) for constructing diagnostic models. They showed qualified diagnostic ability as biomarkers of CAD within training dataset (AUC = 0.803) and validation dataset (AUC = 0.776 and 0.797). Association analyses showed that peripheral immune cells, immune checkpoint genes and Human Leukocyte Antigen (HLA) genes had characteristic distributions in CAD and were closely related to specific ERS genes. Meanwhile, we found that HSPA1A may involve the MAPK signaling pathway in CAD. Conclusion We constructed an efficient diagnostic model based on 6 key ERS-DEGs and explored their regulatory networks and effects on the CAD immune microenvironment. UFL1, HSPA1A, ERLIN1, LRRK2, ERN1, SERINC3 are expected to be biomarkers for CAD.
Collapse
Affiliation(s)
- Zimin Wu
- Department of Cardiovascular Surgery Ward, The First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi Zhuang Autonomous Region, 530021, People’s Republic of China
| | - Sisi Mo
- Department of Medical Research, The First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi Zhuang Autonomous Region, 530021, People’s Republic of China
| | - Zuyuan Huang
- Department of Cardiovascular Surgery Ward, The First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi Zhuang Autonomous Region, 530021, People’s Republic of China
| | - Baoshi Zheng
- Department of Cardiovascular Surgery Ward, The First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi Zhuang Autonomous Region, 530021, People’s Republic of China
| |
Collapse
|
3
|
Schmauch B, Elsoukkary SS, Moro A, Raj R, Wehrle CJ, Sasaki K, Calderaro J, Sin-Chan P, Aucejo F, Roberts DE. Combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgery. J Pathol Inform 2024; 15:100360. [PMID: 38292073 PMCID: PMC10825615 DOI: 10.1016/j.jpi.2023.100360] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2023] [Revised: 12/10/2023] [Accepted: 12/23/2023] [Indexed: 02/01/2024] Open
Abstract
Hepatocellular carcinoma (HCC) is among the most common cancers worldwide, and tumor recurrence following liver resection or transplantation is one of the highest contributors to mortality in HCC patients after surgery. Using artificial intelligence (AI), we developed an interdisciplinary model to predict HCC recurrence and patient survival following surgery. We collected whole-slide H&E images, clinical variables, and follow-up data from 300 patients with HCC who underwent transplant and 169 patients who underwent resection at the Cleveland Clinic. A deep learning model was trained to predict recurrence-free survival (RFS) and disease-specific survival (DSS) from the H&E-stained slides. Repeated cross-validation splits were used to compute robust C-index estimates, and the results were compared to those obtained by fitting a Cox proportional hazard model using only clinical variables. While the deep learning model alone was predictive of recurrence and survival among patients in both cohorts, integrating the clinical and histologic models significantly increased the C-index in each cohort. In every subgroup analyzed, we found that a combined clinical and deep learning model better predicted post-surgical outcome in HCC patients compared to either approach independently.
Collapse
Affiliation(s)
| | - Sarah S. Elsoukkary
- Owkin Lab, Owkin, Inc., New York, NY, USA
- Department of Pathology, Cleveland Clinic, Cleveland, OH, USA
| | - Amika Moro
- Department of Surgery, Cleveland Clinic, Cleveland, OH, USA
| | - Roma Raj
- Department of Surgery, Cleveland Clinic, Cleveland, OH, USA
| | | | - Kazunari Sasaki
- Department of Surgery, Stanford University, Palo Alto, CA, USA
| | - Julien Calderaro
- Department of Pathology, Henri Mondor University Hospital, Créteil, France
| | | | | | | |
Collapse
|
4
|
Niu Y, Wang N, Xu Q. Development of an Endoplasmic Reticulum Stress-Related Diagnostic Signature in Polycystic Ovary Syndrome. Reprod Sci 2024:10.1007/s43032-024-01619-3. [PMID: 38955938 DOI: 10.1007/s43032-024-01619-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2023] [Accepted: 06/03/2024] [Indexed: 07/04/2024]
Abstract
Polycystic ovary syndrome (PCOS) is a prevalent endocrine and metabolic disorder in premenopausal women. This investigation was to elucidate the underlying mechanism of endoplasmic reticulum stress (ERS) activation in granulosa cells, which has been implicated in the etiology of PCOS. Differentially expressed genes (DEGs) between PCOS and control groups were integrated with ERS gene lists from databases to identify DE-ERS genes, and functional analyses were performed. Univariate regression analysis and the LASSO method were used to select diagnostic factors, followed by establishing a DE-ERS gene-based diagnostic model. A nomogram model was further generated to predict the risk of PCOS. The correlation between ERS gene expression and immune cell proportion was assessed. A total of 14 DE-ERS genes associated with "protein processing in endoplasmic reticulum", "ferroptosis", and "glycerophospholipid metabolism" were selected as PCOS-related factors. An eight-DE-ERS genes-based diagnostic model was developed and displayed satisfactory performance in the training (Area under curve (AUC) = 0.983) and validation datasets (AUC = 0.802). High risk of PCOS can be accurately predicted, which might contribute to clinical decision-making. Moreover, EDEM1 expression was significantly positively correlated with naive B cell infiltration, while PDIA6 was negatively correlated with neutrophil proportion (P < 0.001). We identified eight novel molecules and developed an ERS gene-based diagnostic model in PCOS, which might provide novel insight for finding biomarkers and treatment methods.
Collapse
Affiliation(s)
- Yanxin Niu
- Department of Obstetrics and Gynaecology, Jinhua People's Hospital, No.267, Danxi East Road, Jinhua, 321000, Zhejiang, P.R. China
| | - Nan Wang
- Department of Obstetrics and Gynaecology, Jinhua People's Hospital, No.267, Danxi East Road, Jinhua, 321000, Zhejiang, P.R. China
| | - Qiulian Xu
- Department of Obstetrics and Gynaecology, Jinhua People's Hospital, No.267, Danxi East Road, Jinhua, 321000, Zhejiang, P.R. China.
| |
Collapse
|
5
|
Shugao H, Yinhang W, Jing Z, Zhanbo Q, Miao D. Action of m6A-related gene signatures on the prognosis and immune microenvironment of colonic adenocarcinoma. Heliyon 2024; 10:e31441. [PMID: 38845921 PMCID: PMC11153101 DOI: 10.1016/j.heliyon.2024.e31441] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2023] [Revised: 05/12/2024] [Accepted: 05/15/2024] [Indexed: 06/09/2024] Open
Abstract
N6-methyladenosine (m6A) modification in human tumor cells exerts considerable influence on crucial processes like tumorigenesis, invasion, metastasis, and immune response. This study aims to comprehensively analyze the impact of m6A-related genes on the prognosis and immune microenvironment (IME) of colonic adenocarcinoma (COAD). Public data sources, predictive algorithms identified m6A-related genes and differential gene expression in COAD. Subtype analysis and assessment of immune cell infiltration patterns were performed using consensus clustering and the CIBERSORT algorithm. The Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis determined gene signatures. Independent prognostic factors were identified using univariate and multivariate Cox proportional hazards models. The findings indicate that 206 prognostic m6A-related DEGs contribute to the m6A regulatory network along with 8 m6A enzymes. Based on the expression levels of these genes, 438 COAD samples from The Cancer Genome Atlas (TCGA) were classified into 3 distinct subtypes, showing marked differences in survival prognosis, clinical characteristics, and immune cell infiltration profiles. Subtype 3 and 2 displayed reduced levels of infiltrating regulatory T cells and M0 macrophages, respectively. A six-gene signature, encompassing KLC3, SLC6A15, AQP7 JMJD7, HOXC6, and CLDN9, was identified and incorporated into a prognostic model. Validation across TCGA and GSE39582 datasets exhibited robust predictive specificity and sensitivity in determining the survival status of COAD patients. Additionally, independent prognostic factors were recognized, and a nomogram model was developed as a prognostic predictor for COAD. In conclusion, the six target genes governed by m6A mechanisms offer substantial potential in predicting COAD outcomes and provide insights into the unique IME profiles associated with various COAD subtypes.
Collapse
Affiliation(s)
- Han Shugao
- Department of Radiology, The Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, China
| | - Wu Yinhang
- Huzhou Central Hospital, Affiliated Central Hospital Huzhou University, Huzhou, China
- Huzhou Central Hospital, Fifth School of Clinical Medicine of Zhejiang Chinese Medical University, Huzhou, China
- Key Laboratory of Multiomics Research and Clinical Transformation of Digestive Cancer of Huzhou, Huzhou, China
| | - Zhuang Jing
- Huzhou Central Hospital, Affiliated Central Hospital Huzhou University, Huzhou, China
- Huzhou Central Hospital, Fifth School of Clinical Medicine of Zhejiang Chinese Medical University, Huzhou, China
- Key Laboratory of Multiomics Research and Clinical Transformation of Digestive Cancer of Huzhou, Huzhou, China
| | - Qu Zhanbo
- Huzhou Central Hospital, Affiliated Central Hospital Huzhou University, Huzhou, China
- Huzhou Central Hospital, Fifth School of Clinical Medicine of Zhejiang Chinese Medical University, Huzhou, China
- Key Laboratory of Multiomics Research and Clinical Transformation of Digestive Cancer of Huzhou, Huzhou, China
| | - Da Miao
- Huzhou Third Municipal Hospital, the Affiliated Hospital of Huzhou University, Huzhou, China
| |
Collapse
|
6
|
Wang CK, Wang TW, Lu CF, Wu YT, Hua MW. Deciphering the Prognostic Efficacy of MRI Radiomics in Nasopharyngeal Carcinoma: A Comprehensive Meta-Analysis. Diagnostics (Basel) 2024; 14:924. [PMID: 38732337 PMCID: PMC11082984 DOI: 10.3390/diagnostics14090924] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/25/2024] [Revised: 04/12/2024] [Accepted: 04/24/2024] [Indexed: 05/13/2024] Open
Abstract
This meta-analysis investigates the prognostic value of MRI-based radiomics in nasopharyngeal carcinoma treatment outcomes, specifically focusing on overall survival (OS) variability. The study protocol was registered with INPLASY (INPLASY202420101). Initially, a systematic review identified 15 relevant studies involving 6243 patients through a comprehensive search across PubMed, Embase, and Web of Science, adhering to PRISMA guidelines. The methodological quality was assessed using the Quality in Prognosis Studies (QUIPS) tool and the Radiomics Quality Score (RQS), highlighting a low risk of bias in most domains. Our analysis revealed a significant average concordance index (c-index) of 72% across studies, indicating the potential of radiomics in clinical prognostication. However, moderate heterogeneity was observed, particularly in OS predictions. Subgroup analyses and meta-regression identified validation methods and radiomics software as significant heterogeneity moderators. Notably, the number of features in the prognosis model correlated positively with its performance. These findings suggest radiomics' promising role in enhancing cancer treatment strategies, though the observed heterogeneity and potential biases call for cautious interpretation and standardization in future research.
Collapse
Affiliation(s)
- Chih-Keng Wang
- School of Medicine, College of Medicine, National Yang-Ming Chiao Tung University, Taipei 112304, Taiwan
- Department of Otolaryngology-Head and Neck Surgery, Taichung Veterans General Hospital, Taichung 407219, Taiwan
| | - Ting-Wei Wang
- School of Medicine, College of Medicine, National Yang-Ming Chiao Tung University, Taipei 112304, Taiwan
- Institute of Biophotonics, National Yang-Ming Chiao Tung University, 155, Sec. 2, Li-Nong St. Beitou Dist., Taipei 112304, Taiwan
| | - Chia-Fung Lu
- Department of Biomedical Imaging and Radiological Sciences, National Yang-Ming Chiao Tung University, Taipei 112304, Taiwan;
| | - Yu-Te Wu
- Institute of Biophotonics, National Yang-Ming Chiao Tung University, 155, Sec. 2, Li-Nong St. Beitou Dist., Taipei 112304, Taiwan
| | - Man-Wei Hua
- Department of Otolaryngology-Head and Neck Surgery, Taichung Veterans General Hospital, Taichung 407219, Taiwan
| |
Collapse
|
7
|
Xiao W, Lai Y, Yang H, Que H. Predictive Role of a Novel Ferroptosis-Related lncRNA Pairs Model in the Prognosis of Papillary Thyroid Carcinoma. Biochem Genet 2024; 62:775-797. [PMID: 37436560 DOI: 10.1007/s10528-023-10447-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2023] [Accepted: 06/29/2023] [Indexed: 07/13/2023]
Abstract
This study aimed to evaluate the potential prognostic value of ferroptosis-related long non-coding RNAs (lncRNAs) in papillary thyroid carcinoma (PTC). Based on The TCGA database, lncRNAs and ferroptosis-related genes with differential expression levels in PTC tumors vs. normal tissues were screened. After the co-expression network construction, ferroptosis-related lncRNAs (FRLs) were screened. Kaplan-Meier analysis was conducted to compare the survival performance of patients with PTC in the high- and low-risk groups. Furthermore, a nomogram was created to enhance PTC prognosis. CIBERSORT was used to investigate the infiltration of various immune cells in high- and low-risk groups. In total, 10 lncRNA pairs with differential expression levels were obtained. There were significant differences in the histological subtype and pathological stage between the high- and low-risk groups, and age (P = 7.39E-13) and FRLM model status (P = 1.09E-04) were identified as independent prognostic factors. Subsequently, the nomogram survival model showed that the predicted one-, three-, and five-year survival rates were similar to the actual one- (c-index = 0.8475), three- (c-index = 0.7964), and five-year (c-index = 0.7555) survival rates. Subjects in the low-risk group had significantly more CD4 + memory T cells and resting myeloid dendritic cells, and subjects in the high-risk group had more plasma B cells and monocytes. The risk assessment model constructed using FRLs showed good predictive value for the prognosis of patients with PTC.
Collapse
Affiliation(s)
- Wen Xiao
- Department of Traditional Chinese Surgery, Longhua Hospital, Shanghai University of Traditional Chinese Medicine, Shanghai, 200032, China
| | - Yi Lai
- Department of Head and Neck Surgery, Renji Hospital, School of Medicine, Shanghai Jiaotong University, Shanghai, 200127, China
| | - Haojie Yang
- Department of Coloproctology, Yueyang Hospital of Integrated Traditional Chinese Medicine, Shanghai University of Traditional Chinese Medicine, No.1200, Cailun Road, Shanghai, 200032, China.
| | - Huafa Que
- Department of Traditional Chinese Surgery, Longhua Hospital, Shanghai University of Traditional Chinese Medicine, Shanghai, 200032, China.
| |
Collapse
|
8
|
Yue Q, Han W, Ling Lu Z. Nine-Gene Prognostic Signature Related to Gut Microflora for Predicting the Survival in Gastric Cancer Patients. THE TURKISH JOURNAL OF GASTROENTEROLOGY : THE OFFICIAL JOURNAL OF TURKISH SOCIETY OF GASTROENTEROLOGY 2024; 35:102-111. [PMID: 38454241 PMCID: PMC10895821 DOI: 10.5152/tjg.2024.23063] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Subscribe] [Scholar Register] [Received: 02/27/2023] [Accepted: 04/20/2023] [Indexed: 03/09/2024]
Abstract
BACKGROUND/AIMS The purpose of this study is to screen the feature genes related to gut microflora and explore the role of the genes in predicting the prognosis of patients with gastric cancer. MATERIALS AND METHODS We downloaded the gene profile of gastric cancer from the University of California Santa Cruz, the gut microflora related to gastric cancer from The Cancer Microbiome Atlas. The GSE62254 dataset was downloaded from National Center for Biotechnology Information Gene Expression Omnibus as a validation dataset. A correlation network between differentially expressed genes and gut microflora was constructed using Cytoscape. The optimized prognostic differentially expressed genes were identified through least absolute shrinkage and selection operator (LASSO) algorithm and univariate Cox regression analysis. The risk score model was established and then measured via Kaplan-Meier and area under the curve. Finally, the nomogram model was constructed according to the independent clinical factors, which was evaluated using C-index. RESULTS A total of 754 differentially expressed genes and 8 gut microflora were screened, based on which we successfully constructed the correlation network. We obtained 9 optimized prognostic differentially expressed genes, including HSD17B3, GNG7, CHAD, ARHGAP8, NOX1, YY2, GOLGA8A, DNASE1L3, and ABCA8. Moreover, Kaplan-Meier curves indicated the risk score model correctly predicted the prognosis of gastric cancer in both University of California Santa Cruz and GSE62254 dataset (area under the curve >0.8; area under the curve >0.7). Finally, we constructed the nomogram, in which the C index of 1, 3, and 5 years was 0.824, 0.772, and 0.735 representing that the nomogram was consistent with the actual situation. CONCLUSIONS These results indicate the 9 differentially expressed genes related to gut microflora might predict the survival time of patients with gastric cancer. Both risk signature and nomogram could effectively predict the prognosis for patients with gastric cancer.
Collapse
Affiliation(s)
- Qing Yue
- Department of Oncology, Cancer Center, The First Hospital of Jilin University, Changchun, Jilin, China
| | - Wei Han
- Department of Hepatobiliary and Pancreatic Surgery, General Surgery, The First Hospital of Jilin University, Changchun, Jilin, China
| | - Zi Ling Lu
- Department of Oncology, Cancer Center, The First Hospital of Jilin University, Changchun, Jilin, China
| |
Collapse
|
9
|
Lv L, Huang Y, Li Q, Wu Y, Zheng L. A Comprehensive Prognostic Model for Colon Adenocarcinoma Depending on Nuclear-Mitochondrial-Related Genes. Technol Cancer Res Treat 2024; 23:15330338241258570. [PMID: 38832431 PMCID: PMC11149454 DOI: 10.1177/15330338241258570] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/05/2024] Open
Abstract
Background: Colon adenocarcinoma (COAD) has increasing incidence and is one of the most common malignant tumors. The mitochondria involved in cell energy metabolism, oxygen free radical generation, and cell apoptosis play important roles in tumorigenesis and progression. The relationship between mitochondrial genes and COAD remains largely unknown. Methods: COAD data including 512 samples were set out from the UCSC Xena database. The nuclear mitochondrial-related genes (NMRGs)-related risk prognostic model and prognostic nomogram were constructed, and NMRGs-related gene mutation and the immune environment were analyzed using bioinformatics methods. Then, a liver metastasis model of colorectal cancer was constructed and protein expression was detected using Western blot assay. Results: A prognostic model for COAD was constructed. Comparing the prognostic model dataset and the validation dataset showed considerable correlation in both risk grouping and prognosis. Based on the risk score (RS) model, the samples of the prognostic dataset were divided into high risk group and low risk group. Moreover, pathologic N and T stage and tumor recurrence in the two risk groups were significantly different. The four prognostic factors, including age and pathologic T stage in the nomogram survival model also showed excellent predictive performance. An optimal combination of nine differentially expressed NMRGs was finally obtained, including LARS2, PARS2, ETHE1, LRPPRC, TMEM70, AARS2, ACAD9, VARS2, and ATP8A2. The high-RS group had more inflamed immune features, including T and CD4+ memory cell activation. Besides, mitochondria-associated LRPPRC and LARS2 expression levels were increased in vivo xenograft construction and liver metastases assays. Conclusion: This study established a comprehensive prognostic model for COAD, incorporating nine genes associated with nuclear-mitochondrial functions. This model demonstrates superior predictive performance across four prognostic factors: age, pathological T stage, tumor recurrence, and overall prognosis. It is anticipated to be an effective model for enhancing the prognosis and treatment of COAD.
Collapse
Affiliation(s)
- Lingling Lv
- Department of Traditional Chinese Medicine, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China
| | - Yuqing Huang
- Department of Traditional Chinese Medicine, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China
| | - Qiong Li
- Department of Traditional Chinese Medicine, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China
| | - Yuan Wu
- Department of Traditional Chinese Medicine, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China
| | - Lan Zheng
- Department of Traditional Chinese Medicine, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China
| |
Collapse
|
10
|
Zhao ZY, Cao Y, Wang HL, Liu LY. A risk model based on lncRNA-miRNA-mRNA gene signature for predicting prognosis of patients with bladder cancer. Cancer Biomark 2024; 39:277-287. [PMID: 38306023 DOI: 10.3233/cbm-230216] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/03/2024]
Abstract
OBJECTIVES We aimed to analyze lncRNAs, miRNAs, and mRNA expression profiles of bladder cancer (BC) patients, thereby establishing a gene signature-based risk model for predicting prognosis of patients with BC. METHODS We downloaded the expression data of lncRNAs, miRNAs and mRNA from The Cancer Genome Atlas (TCGA) as training cohort including 19 healthy control samples and 401 BC samples. The differentially expressed RNAs (DERs) were screened using limma package, and the competing endogenous RNAs (ceRNA) regulatory network was constructed and visualized by the cytoscape. Candidate DERs were screened to construct the risk score model and nomogram for predicting the overall survival (OS) time and prognosis of BC patients. The prognostic value was verified using a validation cohort in GSE13507. RESULTS Based on 13 selected. lncRNAs, miRNAs and mRNA screened using L1-penalized algorithm, BC patients were classified into two groups: high-risk group (including 201 patients ) and low risk group (including 200 patients). The high-risk group's OS time ( hazard ratio [HR], 2.160; 95% CI, 1.586 to 2.942; P= 5.678e-07) was poorer than that of low-risk groups' (HR, 1.675; 95% CI, 1.037 to 2.713; P= 3.393 e-02) in the training cohort. The area under curve (AUC) for training and validation datasets were 0.852. Younger patients (age ⩽ 60 years) had an improved OS than the patients with advanced age (age > 60 years) (HR 1.033, 95% CI 1.017 to 1.049; p= 2.544E-05). We built a predictive model based on the TCGA cohort by using nomograms, including clinicopathological factors such as age, recurrence rate, and prognostic score. CONCLUSIONS The risk model based on 13 DERs patterns could well predict the prognosis for patients with BC.
Collapse
|
11
|
Dong L, Wang H, Miao Z, Yu Y, Gai D, Zhang G, Ge L, Shen X. Endoplasmic reticulum stress-related signature predicts prognosis and immune infiltration analysis in acute myeloid leukemia. Hematology 2023; 28:2246268. [PMID: 37589214 DOI: 10.1080/16078454.2023.2246268] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2023] [Accepted: 08/02/2023] [Indexed: 08/18/2023] Open
Abstract
OBJECTIVES To construct an endoplasmic reticulum stress-related prognostic risk score (RS) model to predict prognosis and perform a preliminary analysis of immune infiltration in patients with acute myeloid leukemia (AML). METHODS The whole-genome expression data for AML and endoplasmic reticulum stress (ER stress)-related genes were downloaded from the GEO and GSEA databases, respectively. The samples were divided into death and survival groups, combined with clinical prognosis information. LASSO regression was used to construct a prognostic RS model. The Kaplan-Meier curve method was used to evaluate the association between different risk groups and actual survival prognosis information. A cox regression analysis was used to screen for independent survival prognostic clinical factors and construct a nomogram. CIBERSORT and ssGSEA was used for immune-related analysis. RESULTS Eighteen ER-stress related genes were identified and a comprehensive network was constructed. Further, 5 CC, 8 MF, 17 BP, and 2 KEGG pathways were enriched. Ten optimal DEGs were obtained and a prognostic risk model was constructed. Compared to the low RS group, the OS values of the high RS group were significantly lower. A significant correlation between the different risk groups and the actual prognosis was demonstrated. Ten immune cells with significantly different distributions in different risk groups were screened. KEGG enrichment analysis showed that there were 5 signaling pathways in the high-risk group. CONCLUSIONS The RS model can effectively predict the prognosis and has clinical implications for the prognosis of AML, combined with the correlation between different RS groups and the immune microenvironment.
Collapse
Affiliation(s)
- Lu Dong
- Shanxi Medical University, Taiyuan, People's Republic of China
- Heping Hospital Affiliated to Changzhi Medical College, Changzhi, People's Republic of China
| | - Haili Wang
- Heping Hospital Affiliated to Changzhi Medical College, Changzhi, People's Republic of China
| | - Zefeng Miao
- Heping Hospital Affiliated to Changzhi Medical College, Changzhi, People's Republic of China
| | - Yanhui Yu
- Heping Hospital Affiliated to Changzhi Medical College, Changzhi, People's Republic of China
| | - Dongzheng Gai
- Heping Hospital Affiliated to Changzhi Medical College, Changzhi, People's Republic of China
| | - Guoxiang Zhang
- Heping Hospital Affiliated to Changzhi Medical College, Changzhi, People's Republic of China
| | - Li Ge
- Heping Hospital Affiliated to Changzhi Medical College, Changzhi, People's Republic of China
| | - Xuliang Shen
- Shanxi Medical University, Taiyuan, People's Republic of China
- Heping Hospital Affiliated to Changzhi Medical College, Changzhi, People's Republic of China
| |
Collapse
|
12
|
Liu J, Islam MT, Sang S, Qiu L, Xing L. Biology-aware mutation-based deep learning for outcome prediction of cancer immunotherapy with immune checkpoint inhibitors. NPJ Precis Oncol 2023; 7:117. [PMID: 37932419 PMCID: PMC10628135 DOI: 10.1038/s41698-023-00468-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2023] [Accepted: 10/13/2023] [Indexed: 11/08/2023] Open
Abstract
The response rate of cancer immune checkpoint inhibitors (ICI) varies among patients, making it challenging to pre-determine whether a particular patient will respond to immunotherapy. While gene mutation is critical to the treatment outcome, a framework capable of explicitly incorporating biology knowledge has yet to be established. Here we aim to propose and validate a mutation-based deep learning model for survival analysis on 1571 patients treated with ICI. Our model achieves an average concordance index of 0.59 ± 0.13 across nine types of cancer, compared to the gold standard Cox-PH model (0.52 ± 0.10). The "black box" nature of deep learning is a major concern in healthcare field. This model's interpretability, which results from incorporating the gene pathways and protein interaction (i.e., biology-aware) rather than relying on a 'black box' approach, helps patient stratification and provides insight into novel gene biomarkers, advancing our understanding of ICI treatment.
Collapse
Affiliation(s)
- Junyan Liu
- Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA
| | - Md Tauhidul Islam
- Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA
| | - Shengtian Sang
- Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA
| | - Liang Qiu
- Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA
| | - Lei Xing
- Department of Radiation Oncology, Stanford University, Stanford, CA, 94305, USA.
| |
Collapse
|
13
|
Starke S, Zwanenburg A, Leger K, Lohaus F, Linge A, Kalinauskaite G, Tinhofer I, Guberina N, Guberina M, Balermpas P, von der Grün J, Ganswindt U, Belka C, Peeken JC, Combs SE, Boeke S, Zips D, Richter C, Troost EGC, Krause M, Baumann M, Löck S. Multitask Learning with Convolutional Neural Networks and Vision Transformers Can Improve Outcome Prediction for Head and Neck Cancer Patients. Cancers (Basel) 2023; 15:4897. [PMID: 37835591 PMCID: PMC10571894 DOI: 10.3390/cancers15194897] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2023] [Revised: 09/26/2023] [Accepted: 09/29/2023] [Indexed: 10/15/2023] Open
Abstract
Neural-network-based outcome predictions may enable further treatment personalization of patients with head and neck cancer. The development of neural networks can prove challenging when a limited number of cases is available. Therefore, we investigated whether multitask learning strategies, implemented through the simultaneous optimization of two distinct outcome objectives (multi-outcome) and combined with a tumor segmentation task, can lead to improved performance of convolutional neural networks (CNNs) and vision transformers (ViTs). Model training was conducted on two distinct multicenter datasets for the endpoints loco-regional control (LRC) and progression-free survival (PFS), respectively. The first dataset consisted of pre-treatment computed tomography (CT) imaging for 290 patients and the second dataset contained combined positron emission tomography (PET)/CT data of 224 patients. Discriminative performance was assessed by the concordance index (C-index). Risk stratification was evaluated using log-rank tests. Across both datasets, CNN and ViT model ensembles achieved similar results. Multitask approaches showed favorable performance in most investigations. Multi-outcome CNN models trained with segmentation loss were identified as the optimal strategy across cohorts. On the PET/CT dataset, an ensemble of multi-outcome CNNs trained with segmentation loss achieved the best discrimination (C-index: 0.29, 95% confidence interval (CI): 0.22-0.36) and successfully stratified patients into groups with low and high risk of disease progression (p=0.003). On the CT dataset, ensembles of multi-outcome CNNs and of single-outcome ViTs trained with segmentation loss performed best (C-index: 0.26 and 0.26, CI: 0.18-0.34 and 0.18-0.35, respectively), both with significant risk stratification for LRC in independent validation (p=0.002 and p=0.011). Further validation of the developed multitask-learning models is planned based on a prospective validation study, which has recently completed recruitment.
Collapse
Affiliation(s)
- Sebastian Starke
- Helmholtz-Zentrum Dresden–Rossendorf, Department of Information Services and Computing, 01328 Dresden, Germany
- OncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden–Rossendorf, 01309 Dresden, Germany; (A.Z.); (K.L.); (F.L.); (A.L.); (C.R.); (E.G.C.T.); (M.K.); (M.B.); (S.L.)
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Dresden, 01309 Dresden, Germany
| | - Alex Zwanenburg
- OncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden–Rossendorf, 01309 Dresden, Germany; (A.Z.); (K.L.); (F.L.); (A.L.); (C.R.); (E.G.C.T.); (M.K.); (M.B.); (S.L.)
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Dresden, 01309 Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany: German Cancer Research Center (DKFZ), Heidelberg, Germany; Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany, and; Helmholtz Association/Helmholtz-Zentrum Dresden–Rossendorf (HZDR), 01307 Dresden, Germany
| | - Karoline Leger
- OncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden–Rossendorf, 01309 Dresden, Germany; (A.Z.); (K.L.); (F.L.); (A.L.); (C.R.); (E.G.C.T.); (M.K.); (M.B.); (S.L.)
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Dresden, 01309 Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany: German Cancer Research Center (DKFZ), Heidelberg, Germany; Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany, and; Helmholtz Association/Helmholtz-Zentrum Dresden–Rossendorf (HZDR), 01307 Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, 01309 Dresden, Germany
| | - Fabian Lohaus
- OncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden–Rossendorf, 01309 Dresden, Germany; (A.Z.); (K.L.); (F.L.); (A.L.); (C.R.); (E.G.C.T.); (M.K.); (M.B.); (S.L.)
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Dresden, 01309 Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany: German Cancer Research Center (DKFZ), Heidelberg, Germany; Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany, and; Helmholtz Association/Helmholtz-Zentrum Dresden–Rossendorf (HZDR), 01307 Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, 01309 Dresden, Germany
| | - Annett Linge
- OncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden–Rossendorf, 01309 Dresden, Germany; (A.Z.); (K.L.); (F.L.); (A.L.); (C.R.); (E.G.C.T.); (M.K.); (M.B.); (S.L.)
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Dresden, 01309 Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany: German Cancer Research Center (DKFZ), Heidelberg, Germany; Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany, and; Helmholtz Association/Helmholtz-Zentrum Dresden–Rossendorf (HZDR), 01307 Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, 01309 Dresden, Germany
| | - Goda Kalinauskaite
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Berlin, 10117 Berlin, Germany; (G.K.); (I.T.)
- Department of Radiooncology and Radiotherapy, Charité University Hospital, 10117 Berlin, Germany
| | - Inge Tinhofer
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Berlin, 10117 Berlin, Germany; (G.K.); (I.T.)
- Department of Radiooncology and Radiotherapy, Charité University Hospital, 10117 Berlin, Germany
| | - Nika Guberina
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Essen, 45147 Essen, Germany (M.G.)
- Department of Radiotherapy, Medical Faculty, University of Duisburg-Essen, 45147 Essen, Germany
| | - Maja Guberina
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Essen, 45147 Essen, Germany (M.G.)
- Department of Radiotherapy, Medical Faculty, University of Duisburg-Essen, 45147 Essen, Germany
| | - Panagiotis Balermpas
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Frankfurt, 60596 Frankfurt, Germany; (P.B.); (J.v.d.G.)
- Department of Radiotherapy and Oncology, Goethe-University Frankfurt, 60596 Frankfurt, Germany
| | - Jens von der Grün
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Frankfurt, 60596 Frankfurt, Germany; (P.B.); (J.v.d.G.)
- Department of Radiotherapy and Oncology, Goethe-University Frankfurt, 60596 Frankfurt, Germany
| | - Ute Ganswindt
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Munich, 80336 Munich, Germany; (U.G.); (C.B.); (J.C.P.); (S.E.C.)
- Department of Radiation Oncology, Ludwig-Maximilians-Universität, 80336 Munich, Germany
- Clinical Cooperation Group, Personalized Radiotherapy in Head and Neck Cancer, Helmholtz Zentrum Munich, 85764 Neuherberg, Germany
- Department of Radiation Oncology, Medical University of Innsbruck, Anichstraße 35, A-6020 Innsbruck, Austria
| | - Claus Belka
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Munich, 80336 Munich, Germany; (U.G.); (C.B.); (J.C.P.); (S.E.C.)
- Department of Radiation Oncology, Ludwig-Maximilians-Universität, 80336 Munich, Germany
- Clinical Cooperation Group, Personalized Radiotherapy in Head and Neck Cancer, Helmholtz Zentrum Munich, 85764 Neuherberg, Germany
| | - Jan C. Peeken
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Munich, 80336 Munich, Germany; (U.G.); (C.B.); (J.C.P.); (S.E.C.)
- Department of Radiation Oncology, Technische Universität München, 81675 Munich, Germany
- Institute of Radiation Medicine (IRM), Helmholtz Zentrum München, 85764 Neuherberg, Germany
| | - Stephanie E. Combs
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Munich, 80336 Munich, Germany; (U.G.); (C.B.); (J.C.P.); (S.E.C.)
- Department of Radiation Oncology, Technische Universität München, 81675 Munich, Germany
- Institute of Radiation Medicine (IRM), Helmholtz Zentrum München, 85764 Neuherberg, Germany
| | - Simon Boeke
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Tübingen, 72076 Tübingen, Germany; (S.B.); (D.Z.)
- Department of Radiation Oncology, Faculty of Medicine and University Hospital Tübingen, Eberhard Karls Universität Tübingen, 72076 Tübingen, Germany
| | - Daniel Zips
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Tübingen, 72076 Tübingen, Germany; (S.B.); (D.Z.)
- Department of Radiation Oncology, Faculty of Medicine and University Hospital Tübingen, Eberhard Karls Universität Tübingen, 72076 Tübingen, Germany
| | - Christian Richter
- OncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden–Rossendorf, 01309 Dresden, Germany; (A.Z.); (K.L.); (F.L.); (A.L.); (C.R.); (E.G.C.T.); (M.K.); (M.B.); (S.L.)
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Dresden, 01309 Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, 01309 Dresden, Germany
- Helmholtz-Zentrum Dresden–Rossendorf, Institute of Radiooncology—OncoRay, 01328 Dresden, Germany
| | - Esther G. C. Troost
- OncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden–Rossendorf, 01309 Dresden, Germany; (A.Z.); (K.L.); (F.L.); (A.L.); (C.R.); (E.G.C.T.); (M.K.); (M.B.); (S.L.)
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Dresden, 01309 Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany: German Cancer Research Center (DKFZ), Heidelberg, Germany; Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany, and; Helmholtz Association/Helmholtz-Zentrum Dresden–Rossendorf (HZDR), 01307 Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, 01309 Dresden, Germany
- Helmholtz-Zentrum Dresden–Rossendorf, Institute of Radiooncology—OncoRay, 01328 Dresden, Germany
| | - Mechthild Krause
- OncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden–Rossendorf, 01309 Dresden, Germany; (A.Z.); (K.L.); (F.L.); (A.L.); (C.R.); (E.G.C.T.); (M.K.); (M.B.); (S.L.)
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Dresden, 01309 Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany: German Cancer Research Center (DKFZ), Heidelberg, Germany; Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany, and; Helmholtz Association/Helmholtz-Zentrum Dresden–Rossendorf (HZDR), 01307 Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, 01309 Dresden, Germany
- Helmholtz-Zentrum Dresden–Rossendorf, Institute of Radiooncology—OncoRay, 01328 Dresden, Germany
| | - Michael Baumann
- OncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden–Rossendorf, 01309 Dresden, Germany; (A.Z.); (K.L.); (F.L.); (A.L.); (C.R.); (E.G.C.T.); (M.K.); (M.B.); (S.L.)
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, 01309 Dresden, Germany
- German Cancer Research Center (DKFZ), Division Radiooncology/Radiobiology, 69120 Heidelberg, Germany
- German Cancer Consortium (DKTK), Core Center DKFZ, 69120 Heidelberg, Germany
| | - Steffen Löck
- OncoRay—National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden–Rossendorf, 01309 Dresden, Germany; (A.Z.); (K.L.); (F.L.); (A.L.); (C.R.); (E.G.C.T.); (M.K.); (M.B.); (S.L.)
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) Partner Site Dresden, 01309 Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, 01309 Dresden, Germany
| |
Collapse
|
14
|
Meng X, Zou T. Clinical applications of graph neural networks in computational histopathology: A review. Comput Biol Med 2023; 164:107201. [PMID: 37517325 DOI: 10.1016/j.compbiomed.2023.107201] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2023] [Revised: 06/10/2023] [Accepted: 06/19/2023] [Indexed: 08/01/2023]
Abstract
Pathological examination is the optimal approach for diagnosing cancer, and with the advancement of digital imaging technologies, it has spurred the emergence of computational histopathology. The objective of computational histopathology is to assist in clinical tasks through image processing and analysis techniques. In the early stages, the technique involved analyzing histopathology images by extracting mathematical features, but the performance of these models was unsatisfactory. With the development of artificial intelligence (AI) technologies, traditional machine learning methods were applied in this field. Although the performance of the models improved, there were issues such as poor model generalization and tedious manual feature extraction. Subsequently, the introduction of deep learning techniques effectively addressed these problems. However, models based on traditional convolutional architectures could not adequately capture the contextual information and deep biological features in histopathology images. Due to the special structure of graphs, they are highly suitable for feature extraction in tissue histopathology images and have achieved promising performance in numerous studies. In this article, we review existing graph-based methods in computational histopathology and propose a novel and more comprehensive graph construction approach. Additionally, we categorize the methods and techniques in computational histopathology according to different learning paradigms. We summarize the common clinical applications of graph-based methods in computational histopathology. Furthermore, we discuss the core concepts in this field and highlight the current challenges and future research directions.
Collapse
Affiliation(s)
- Xiangyan Meng
- Xi'an Technological University, Xi'an, Shaanxi, 710021, China.
| | - Tonghui Zou
- Xi'an Technological University, Xi'an, Shaanxi, 710021, China.
| |
Collapse
|
15
|
Wang TW, Hsu MS, Lin YH, Chiu HY, Chao HS, Liao CY, Lu CF, Wu YT, Huang JW, Chen YM. Application of Radiomics in Prognosing Lung Cancer Treated with Epidermal Growth Factor Receptor Tyrosine Kinase Inhibitors: A Systematic Review and Meta-Analysis. Cancers (Basel) 2023; 15:3542. [PMID: 37509204 PMCID: PMC10377421 DOI: 10.3390/cancers15143542] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/11/2023] [Revised: 07/01/2023] [Accepted: 07/06/2023] [Indexed: 07/30/2023] Open
Abstract
In the context of non-small cell lung cancer (NSCLC) patients treated with EGFR tyrosine kinase inhibitors (TKIs), this research evaluated the prognostic value of CT-based radiomics. A comprehensive systematic review and meta-analysis of studies up to April 2023, which included 3111 patients, was conducted. We utilized the Quality in Prognosis Studies (QUIPS) tool and radiomics quality scoring (RQS) system to assess the quality of the included studies. Our analysis revealed a pooled hazard ratio for progression-free survival of 2.80 (95% confidence interval: 1.87-4.19), suggesting that patients with certain radiomics features had a significantly higher risk of disease progression. Additionally, we calculated the pooled Harrell's concordance index and area under the curve (AUC) values of 0.71 and 0.73, respectively, indicating good predictive performance of radiomics. Despite these promising results, further studies with consistent and robust protocols are needed to confirm the prognostic role of radiomics in NSCLC.
Collapse
Affiliation(s)
- Ting-Wei Wang
- School of Medicine, National Yang Ming Chiao Tung University, Taipei 112, Taiwan
- Institute of Biophotonics, National Yang Ming Chiao Tung University, Taipei 112, Taiwan
| | - Ming-Sheng Hsu
- School of Medicine, National Yang Ming Chiao Tung University, Taipei 112, Taiwan
| | - Yi-Hui Lin
- Department of Radiation Oncology, Taichung Veterans General Hospital, Taichung 407, Taiwan
| | - Hwa-Yen Chiu
- School of Medicine, National Yang Ming Chiao Tung University, Taipei 112, Taiwan
- Institute of Biophotonics, National Yang Ming Chiao Tung University, Taipei 112, Taiwan
- Department of Chest Medicine, Taipei Veterans General Hospital, Taipei 112, Taiwan
| | - Heng-Sheng Chao
- School of Medicine, National Yang Ming Chiao Tung University, Taipei 112, Taiwan
- Institute of Biomedical Informatics, National Yang Ming Chiao Tung University, Taipei 112, Taiwan
| | - Chien-Yi Liao
- Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei 112, Taiwan
| | - Chia-Feng Lu
- Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei 112, Taiwan
| | - Yu-Te Wu
- Institute of Biophotonics, National Yang Ming Chiao Tung University, Taipei 112, Taiwan
| | - Jing-Wen Huang
- Department of Radiation Oncology, Taichung Veterans General Hospital, Taichung 407, Taiwan
| | - Yuh-Min Chen
- School of Medicine, National Yang Ming Chiao Tung University, Taipei 112, Taiwan
- Department of Chest Medicine, Taipei Veterans General Hospital, Taipei 112, Taiwan
| |
Collapse
|
16
|
Zhao Y, Gao J, Fan Y, Xu H, Wang Y, Yao P. A risk score model based on endoplasmic reticulum stress related genes for predicting prognostic value of osteosarcoma. BMC Musculoskelet Disord 2023; 24:519. [PMID: 37353812 DOI: 10.1186/s12891-023-06629-x] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/23/2022] [Accepted: 06/12/2023] [Indexed: 06/25/2023] Open
Abstract
BACKGROUND We aimed to establish an osteosarcoma prognosis prediction model based on a signature of endoplasmic reticulum stress-related genes. METHODS Differentially expressed genes (DEGs) between osteosarcoma with and without metastasis from The Cancer Genome Atlas (TCGA) database were mapped to ERS genes retrieved from Gene Set Enrichment Analysis to select endoplasmic reticulum stress-related DEGs. Subsequently, we constructed a risk score model based on survival-related endoplasmic reticulum stress DEGs and a nomogram of independent survival prognostic factors. Based on the median risk score, we stratified the samples into high- and low-risk groups. The ability of the model was assessed by Kaplan-Meier, receiver operating characteristic curve, and functional analyses. Additionally, the expression of the identified prognostic endoplasmic reticulum stress-related DEGs was verified using real-time quantitative PCR (RT-qPCR). RESULTS In total, 41 endoplasmic reticulum stress-related DEGs were identified in patients with osteosarcoma with metastasis. A risk score model consisting of six prognostic endoplasmic reticulum stress-related DEGs (ATP2A3, ERMP1, FBXO6, ITPR1, NFE2L2, and USP13) was established, and the Kaplan-Meier and receiver operating characteristic curves validated their performance in the training and validation datasets. Age, tumor metastasis, and the risk score model were demonstrated to be independent prognostic clinical factors for osteosarcoma and were used to establish a nomogram survival model. The nomogram model showed similar performance of one, three, and five year-survival rate to the actual survival rates. Nine immune cell types in the high-risk group were found to be significantly different from those in the low-risk group. These survival-related genes were significantly enriched in nine Kyoto Encyclopedia of Genes and Genomes pathways, including cell adhesion molecule cascades, and chemokine signaling pathways. Further, RT-qPCR results demonstrated that the consistency rate of bioinformatics analysis was approximately 83.33%, suggesting the relatively high reliability of the bioinformatics analysis. CONCLUSION We established an osteosarcoma prediction model based on six prognostic endoplasmic reticulum stress-related DEGs that could be helpful in directing personalized treatment.
Collapse
Affiliation(s)
- Yong Zhao
- Department of Orthopaedic Surgery, Shengzhou People's Hospital (the First Affiliated Hospital of Zhejiang University Shengzhou Branch), Shaoxing, 312400, Zhejiang, China.
| | - Jijian Gao
- Department of Orthopaedic Surgery, Shengzhou People's Hospital (the First Affiliated Hospital of Zhejiang University Shengzhou Branch), Shaoxing, 312400, Zhejiang, China
| | - Yong Fan
- Department of Orthopaedic Surgery, Shengzhou People's Hospital (the First Affiliated Hospital of Zhejiang University Shengzhou Branch), Shaoxing, 312400, Zhejiang, China
| | - Hongyu Xu
- Department of Orthopaedic Surgery, Shengzhou People's Hospital (the First Affiliated Hospital of Zhejiang University Shengzhou Branch), Shaoxing, 312400, Zhejiang, China
| | - Yun Wang
- Department of Orthopaedic Surgery, Shengzhou People's Hospital (the First Affiliated Hospital of Zhejiang University Shengzhou Branch), Shaoxing, 312400, Zhejiang, China
| | - Pengjie Yao
- Department of Orthopaedic Surgery, Shengzhou People's Hospital (the First Affiliated Hospital of Zhejiang University Shengzhou Branch), Shaoxing, 312400, Zhejiang, China
| |
Collapse
|
17
|
Liao CM, Su CT, Huang HC, Lin CM. Improved Survival Analyses Based on Characterized Time-Dependent Covariates to Predict Individual Chronic Kidney Disease Progression. Biomedicines 2023; 11:1664. [PMID: 37371759 DOI: 10.3390/biomedicines11061664] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2023] [Revised: 06/01/2023] [Accepted: 06/05/2023] [Indexed: 06/29/2023] Open
Abstract
Kidney diseases can cause severe morbidity, mortality, and health burden. Determining the risk factors associated with kidney damage and deterioration has become a priority for the prevention and treatment of kidney disease. This study followed 497 patients with stage 3-5 chronic kidney disease (CKD) who were treated at the ward of Taipei Veterans General Hospital from January 2006 to 2019 in Taiwan. The patients underwent 3-year-long follow-up sessions for clinical measurements, which occurred every 3 months. Three time-dependent survival models, namely the Cox proportional hazard model (Cox PHM), random survival forest (RSF), and an artificial neural network (ANN), were used to process patient demographics and laboratory data for predicting progression to renal failure, and important features for optimal prediction were evaluated. The individual prediction of CKD progression was validated using the Kaplan-Meier estimation method, based on patients' true outcomes during and beyond the study period. The results showed that the average concordance indexes for the cross-validation of the Cox PHM, ANN, and RSF models were 0.71, 0.72, and 0.89, respectively. RSF had the best predictive performances for CKD patients within the 3 years of follow-up sessions, with a sensitivity of 0.79 and specificity of 0.88. Creatinine, age, estimated glomerular filtration rate, and urine protein to creatinine ratio were useful factors for predicting the progression of CKD patients in the RSF model. These results may be helpful for instantaneous risk prediction at each follow-up session for CKD patients.
Collapse
Affiliation(s)
- Chen-Mao Liao
- Department of Applied Statistics and Information Science, Ming Chuan University, Taoyuan 333, Taiwan
| | - Chuan-Tsung Su
- Department of Healthcare Information and Management, Ming Chuan University, Taoyuan 333, Taiwan
| | - Hao-Che Huang
- Department of Applied Statistics and Information Science, Ming Chuan University, Taoyuan 333, Taiwan
| | - Chih-Ming Lin
- Department of Healthcare Information and Management, Ming Chuan University, Taoyuan 333, Taiwan
| |
Collapse
|
18
|
Di D, Zou C, Feng Y, Zhou H, Ji R, Dai Q, Gao Y. Generating Hypergraph-Based High-Order Representations of Whole-Slide Histopathological Images for Survival Prediction. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023; 45:5800-5815. [PMID: 36155478 DOI: 10.1109/tpami.2022.3209652] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/06/2023]
Abstract
Patient survival prediction based on gigapixel whole-slide histopathological images (WSIs) has become increasingly prevalent in recent years. A key challenge of this task is achieving an informative survival-specific global representation from those WSIs with highly complicated data correlation. This article proposes a multi-hypergraph based learning framework, called "HGSurvNet," to tackle this challenge. HGSurvNet achieves an effective high-order global representation of WSIs via multilateral correlation modeling in multiple spaces and a general hypergraph convolution network. It has the ability to alleviate over-fitting issues caused by the lack of training data by using a new convolution structure called hypergraph max-mask convolution. Extensive validation experiments were conducted on three widely-used carcinoma datasets: Lung Squamous Cell Carcinoma (LUSC), Glioblastoma Multiforme (GBM), and National Lung Screening Trial (NLST). Quantitative analysis demonstrated that the proposed method consistently outperforms state-of-the-art methods, coupled with the Bayesian Concordance Readjust loss. We also demonstrate the individual effectiveness of each module of the proposed framework and its application potential for pathology diagnosis and reporting empowered by its interpretability potential.
Collapse
|
19
|
Liu Y, Gao Z, Peng C, Jiang X. Construction of a 10-gene prognostic score model of predicting recurrence for laryngeal cancer. Eur J Med Res 2022; 27:249. [DOI: 10.1186/s40001-022-00829-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2021] [Accepted: 09/26/2022] [Indexed: 11/15/2022] Open
Abstract
AbstractWe constructed a prognostic score (PS) model to predict the recurrence risk in patients previously diagnosed with laryngeal cancer (LC). Here the training dataset, consisting of 82 LC samples, was downloaded from The Cancer Genome Atlas (TCGA). The PS model then divided the LC samples into high- and low-risk groups, which predicted well the survival time of LC in three datasets (TCGA dataset: AUC = 0.899; GSE27020: AUC = 0.719; and GSE25727: AUC = 0.662). Therefore, the PS model based on the 10 genes and its nomogram is proposed to help predict the recurrence risk in patients with LC.
Collapse
|
20
|
Sonabend R, Bender A, Vollmer S. Avoiding C-hacking when evaluating survival distribution predictions with discrimination measures. Bioinformatics 2022; 38:4178-4184. [PMID: 35818973 PMCID: PMC9438958 DOI: 10.1093/bioinformatics/btac451] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2022] [Revised: 06/17/2022] [Accepted: 07/11/2022] [Indexed: 12/24/2022] Open
Abstract
MOTIVATION In this article, we consider how to evaluate survival distribution predictions with measures of discrimination. This is non-trivial as discrimination measures are the most commonly used in survival analysis and yet there is no clear method to derive a risk prediction from a distribution prediction. We survey methods proposed in literature and software and consider their respective advantages and disadvantages. RESULTS Whilst distributions are frequently evaluated by discrimination measures, we find that the method for doing so is rarely described in the literature and often leads to unfair comparisons or 'C-hacking'. We demonstrate by example how simple it can be to manipulate results and use this to argue for better reporting guidelines and transparency in the literature. We recommend that machine learning survival analysis software implements clear transformations between distribution and risk predictions in order to allow more transparent and accessible model evaluation. AVAILABILITY AND IMPLEMENTATION The code used in the final experiment is available at https://github.com/RaphaelS1/distribution_discrimination.
Collapse
Affiliation(s)
| | - Andreas Bender
- Department of Statistics, LMU Munich, 80539 Bavaria, Germany
| | - Sebastian Vollmer
- Department of Computer Science, Technische Universität Kaiserslautern, 67663 Kaiserslautern, Germany,Data Science and its Application, Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI), 67663 Kaiserslautern, Germany,Mathematics Institute, University of Warwick, CV4 7AL Coventry, UK
| |
Collapse
|
21
|
Liu Y, Li A, Liu J, Meng G, Wang M. TSDLPP: A Novel Two-Stage Deep Learning Framework For Prognosis Prediction Based on Whole Slide Histopathological Images. IEEE/ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2022; 19:2523-2532. [PMID: 33989155 DOI: 10.1109/tcbb.2021.3080295] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
Recently, digital pathology image-based prognosis prediction has become a hot topic in healthcare research to make early decisions on therapy and improve the treatment quality of patients. Therefore, there has been a recent surge of interest in designing deep learning method solving the problem of prognosis prediction with digital pathology images. However, whole slide histopathological images (WSIs) based prognosis prediction is still a challenge due to the large size of pathological images, the heterogeneity of tumors and the high cost of region of interests (ROIs) labeling. In this study, we design a novel two-stage deep learning framework for prognosis prediction (TSDLPP) based on WSIs. Our proposed framework consists of two-stage paradigms: 1) training tissue decomposition network (TDNet) to divide WSIs into cancerous and non-cancerous regions, 2) integrating general prognosis-related densely connected CNN (GPR-DCCNN) and morphology-specific prognosis-related densely connected CNNs (MSPR-DCCNNs) to extract different level features of pathological images. In the end, we apply TSDLPP to the prognosis prediction of breast cancer using The Cancer Genome Atlas (TCGA) datasets. Experiment results demonstrate that TSDLPP obtains superior performance of prognosis prediction compared with the existing state-of-arts methods.
Collapse
|
22
|
Meng M, Gu B, Bi L, Song S, Feng DD, Kim J. DeepMTS: Deep Multi-task Learning for Survival Prediction in Patients With Advanced Nasopharyngeal Carcinoma Using Pretreatment PET/CT. IEEE J Biomed Health Inform 2022; 26:4497-4507. [PMID: 35696469 DOI: 10.1109/jbhi.2022.3181791] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
Nasopharyngeal Carcinoma (NPC) is a malignant epithelial cancer arising from the nasopharynx. Survival prediction is a major concern for NPC patients, as it provides early prognostic information to plan treatments. Recently, deep survival models based on deep learning have demonstrated the potential to outperform traditional radiomics-based survival prediction models. Deep survival models usually use image patches covering the whole target regions (e.g., nasopharynx for NPC) or containing only segmented tumor regions as the input. However, the models using the whole target regions will also include non-relevant background information, while the models using segmented tumor regions will disregard potentially prognostic information existing out of primary tumors (e.g., local lymph node metastasis and adjacent tissue invasion). In this study, we propose a 3D end-to-end Deep Multi-Task Survival model (DeepMTS) for joint survival prediction and tumor segmentation in advanced NPC from pretreatment PET/CT. Our novelty is the introduction of a hard-sharing segmentation backbone to guide the extraction of local features related to the primary tumors, which reduces the interference from non-relevant background information. In addition, we also introduce a cascaded survival network to capture the prognostic information existing out of primary tumors and further leverage the global tumor information (e.g., tumor size, shape, and locations) derived from the segmentation backbone. Our experiments with two clinical datasets demonstrate that our DeepMTS can consistently outperform traditional radiomics-based survival prediction models and existing deep survival models.
Collapse
|
23
|
Gong Y, Wu S, Dong S, Chen S, Cai G, Bao K, Yang H, Jiao Y. Development of a prognostic metabolic signature in stomach adenocarcinoma. Clin Transl Oncol 2022; 24:1615-1630. [PMID: 35355155 DOI: 10.1007/s12094-022-02809-8] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/15/2021] [Accepted: 02/19/2022] [Indexed: 02/07/2023]
Abstract
PURPOSE The growth and aggressiveness of Stomach adenocarcinoma (STAD) is significantly affected by basic metabolic changes. This study aimed to identify metabolic gene prognostic signatures in STAD. METHODS An integrative analysis of datasets from the Cancer Genome Atlas and Gene Expression Omnibus was performed. A metabolic gene prognostic signature was developed using univariable Cox regression and Kaplan-Meier survival analysis. A nomogram model was developed to predict the prognosis of STAD patients. Finally, Gene Set Enrichment Analysis (GESA) was used to explore the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways significantly associated with the risk grouping. RESULTS A total of 327 metabolism-related differentially expressed genes were identified. Three subtypes of STAD were identified and nine immune cell types, including memory B cell, resting and activated CD4+ memory T cells, were significantly different among the three subgroups. A risk score model including nine survival-related genes which could separate high-risk patients from low-risk patients was developed. The prognosis of STAD patients likely benefited from lower expression levels of genes, including ABCG4, ABCA6, GPX8, KYNU, ST8SIA5, and CYP19A1. Age, radiation therapy, tumor recurrence, and risk score model status were found to be independent risk factors for STAD and were used for developing a nomogram. Nine KEGG pathways, including spliceosome, pentose phosphate pathway, and citrate TCA cycle were significantly enriched in GESA. CONCLUSION We propose a metabolic gene signature and a nomogram for STAD which might be used for predicting the survival of STAD patients and exploring prognostic markers.
Collapse
Affiliation(s)
- Yu Gong
- Department of Gastrointestinal Surgery, The Affiliated Changzhou No.2 People's Hospital of Nanjing Medical University, 68 GeHu Road, Changzhou, 213000, Jiangsu, China
| | - Siyuan Wu
- Department of Hepato-Biliary-Pancreatic Surgery, The Affiliated Changzhou No.2 People's Hospital of Nanjing Medical University, Changzhou, 213000, China
| | - Sen Dong
- Bengbu Medical University, Benbu, 233000, China
| | - Shuai Chen
- Nanjing Medical University, Jiangsu, 213000, China
| | - Gengdi Cai
- Dalian Medical University, Dalian, 116000, China
| | - Kun Bao
- Dalian Medical University, Dalian, 116000, China
| | - Haojun Yang
- Department of Gastrointestinal Surgery, The Affiliated Changzhou No.2 People's Hospital of Nanjing Medical University, 68 GeHu Road, Changzhou, 213000, Jiangsu, China
| | - Yuwen Jiao
- Department of Gastrointestinal Surgery, The Affiliated Changzhou No.2 People's Hospital of Nanjing Medical University, 68 GeHu Road, Changzhou, 213000, Jiangsu, China.
| |
Collapse
|
24
|
Magnetic Resonance Imaging-Based Radiomics for the Prediction of Progression-Free Survival in Patients with Nasopharyngeal Carcinoma: A Systematic Review and Meta-Analysis. Cancers (Basel) 2022; 14:cancers14030653. [PMID: 35158921 PMCID: PMC8833585 DOI: 10.3390/cancers14030653] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2021] [Revised: 01/21/2022] [Accepted: 01/26/2022] [Indexed: 02/04/2023] Open
Abstract
Simple Summary More than 70% of patients with nasopharyngeal carcinoma (NPC) present with a locoregionally advanced state. Although the initial staging of NPC is primarily based on TNM staging, there is currently no well-established prognostic marker for NPC. Recently, radiomics has received considerable research attention as a potential prognostic biomarker for NPC. The aim of this systematic review and meta-analysis was to comprehensively evaluate the prognostic value of pretreatment magnetic resonance imaging (MRI)-based radiomics for NPC. The analyzed radiomic models demonstrated modest prognostic values, with a pooled mean estimated Harrell’s concordance index (C index) of 0.762. The prognostic models developed using more than eight radiomic features had significantly higher C-indices than those developed using fewer features. Our findings provide evidence that MRI-based radiomics may have a modest prognostic role in the treatment of NPC. However, more consistent study protocols are needed to verify the generalizability of radiomics. Abstract Advanced non-metastatic nasopharyngeal carcinoma (NPC) has variable treatment outcomes. However, there are no prognostic biomarkers for identifying high-risk patients with NPC. The aim of this systematic review and meta-analysis was to comprehensively assess the prognostic value of magnetic resonance imaging (MRI)-based radiomics for untreated NPC. The PubMed-Medline and EMBASE databases were searched for relevant articles published up to 12 August 2021. The Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) checklist was used to determine the qualities of the selected studies. Random-effects modeling was used to calculate the pooled estimates of Harrell’s concordance index (C-index) for progression-free survival (PFS). Between-study heterogeneity was evaluated using Higgins’ inconsistency index (I2). Among the studies reported in the 57 articles screened, 10 with 3458 patients were eligible for qualitative and quantitative data syntheses. The mean adherence rate to the TRIPOD checklist was 68.6 ± 7.1%. The pooled estimate of the C-index was 0.762 (95% confidence interval, 0.687–0.837). Substantial between-study heterogeneity was observed (I2 = 89.2%). Overall, MRI-based radiomics shows good prognostic performance in predicting the PFS of patients with untreated NPC. However, more consistent and robust study protocols are necessary to validate the prognostic role of radiomics for NPC.
Collapse
|
25
|
Ran X, Luo J, Zuo C, Huang Y, Sui Y, Cen J, Tang S. Developing metabolic gene signatures to predict intrahepatic cholangiocarcinoma prognosis and mining a miRNA regulatory network. J Clin Lab Anal 2021; 36:e24107. [PMID: 34871464 PMCID: PMC8761474 DOI: 10.1002/jcla.24107] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2021] [Revised: 10/14/2021] [Accepted: 10/25/2021] [Indexed: 11/10/2022] Open
Abstract
Background Metabolic disturbance is closely correlated with intrahepatic cholangiocarcinoma (IHCC), and we aimed to identify metabolic gene marker for the prognosis of IHCC. Methods We obtained expression and clinical data from 141 patients with IHCC from public databases. Prognostic metabolic genes were selected using univariate Cox regression analysis. Unsupervised cluster analysis was applied to identify IHCC subtypes, and CIBERSORT was used for immune infiltration analysis of different subtypes. Then, the metabolic gene signature was screened using multivariate Cox regression analysis and the LASSO algorithm. The prognostic potential and regulatory network of the metabolic gene signature were further investigated. Results We screened 228 prognosis‐related metabolic genes. Based on their expression levels, IHCC samples were divided into two subtypes, which showed significant differences in survival and immune cell infiltration. After LASSO analysis, eight metabolic genes including CYP19A1, SCD5, ACOT8, SRD5A3, MOGAT2, PFKFB3, PPARGC1B, and RPL17 were identified as the optimal genes for the prognosis signature. The prognostic model had excellent predictive abilities, with areas under the receiver‐operating characteristic curves over 0.8. A nomogram model was also established based on two independent prognostic clinical factors (pathologic stage and prognostic model), and the generated calibration curves and c‐indexes determined its excellent accuracy and discriminative ability to predict 1‐ and 5‐year survival status (c‐indexes>0.7). Finally, we found that miR‐26a‐5p, miR‐27a‐3p, and miR‐27b‐3p were the upstream regulators that mediate the involvement of gene signatures in metabolic pathways. Conclusion We developed eight metabolic gene signatures to predict IHCC prognosis and proposed potential upstream regulatory axes of gene signatures.
Collapse
Affiliation(s)
- Xun Ran
- Department of hepatobiliary surgery, The affiliated hospital of Guizhou medical university, Guiyang, Guizhou Province, China
| | - Jun Luo
- Department of hepatobiliary surgery, The affiliated hospital of Guizhou medical university, Guiyang, Guizhou Province, China
| | - Chaohai Zuo
- Department of Hepatobiliary Surgery, Jiangmen Central Hospital, Jiangmen, Guangdong Province, China
| | - YongYe Huang
- Digestive center area two, Guangzhou Panyu Central Hospital, Guangzhou, China
| | - Yi Sui
- IVD Medical Marketing Department, 3D Medicine Inc., Shanghai, China
| | - JunHua Cen
- Hepatobiliary Surgery Department, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong, China
| | - Shengli Tang
- Hepatopancreatobiliary surgery, Zhongnan hospital of Wuhan university, Wuhan, Hubei, China
| |
Collapse
|
26
|
Tsai YT, Hsu CM, Chang GH, Tsai MS, Lee YC, Huang EI, Lai CH, Fang KH. Advanced Lung Cancer Inflammation Index Predicts Survival Outcomes of Patients With Oral Cavity Cancer Following Curative Surgery. Front Oncol 2021; 11:609314. [PMID: 34660250 PMCID: PMC8514840 DOI: 10.3389/fonc.2021.609314] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2020] [Accepted: 09/13/2021] [Indexed: 12/13/2022] Open
Abstract
Aim The aim of our study was to investigate the prognostic value of preoperative advanced lung cancer inflammation index (ALI) and to establish prognostic nomograms for the prediction of survival outcomes in patients with oral cavity squamous cell carcinoma (OSCC). Materials and Methods A total of 372 patients who received primary curative surgery for OSCC during 2008–2017 at a tertiary referral center were enrolled. We used the receiver operating characteristic curve to determine the optimal cutoff point of ALI. Through a Cox proportional hazards model and Kaplan–Meier analysis, we elucidated the ALI–overall survival (OS) and ALI–disease-free survival (DFS) associations. Prognostic nomograms based on ALI and the results of multivariate analysis were created to predict the OS and DFS. We used the concordance indices (C-indices) and calibration plots to assess the discriminatory and predictive ability. Results The results revealed that the ALI cutoff was 33.6, and 105 and 267 patients had ALI values of <33.6 and ≥33.6, respectively. ALI < 33.6 significantly indicated lower OS (44.0% vs. 80.1%, p < 0.001) and DFS (33.6% vs. 62.8%; p < 0.001). In multivariate analysis, ALI < 33.6 was independently associated with poor OS and DFS (both p < 0.001). The C-indices of established nomograms were 0.773 and 0.674 for OS and DFS, respectively; moreover, the calibration plots revealed good consistency between nomogram-predicted and actual observed OS and DFS. Conclusion ALI is a promising prognostic biomarker in patients undergoing primary surgery for OSCC; moreover, ALI-based nomograms may be a useful prognostic tool for individualized OS and DFS estimations.
Collapse
Affiliation(s)
- Yao-Te Tsai
- Department of Otolaryngology-Head and Neck Surgery, Chang Gung Memorial Hospital, Chiayi, Taiwan
| | - Cheng-Ming Hsu
- Department of Otolaryngology-Head and Neck Surgery, Chang Gung Memorial Hospital, Chiayi, Taiwan.,Department of Medicine, College of Medicine, Chang Gung University, Taoyuan, Taiwan
| | - Geng-He Chang
- Department of Otolaryngology-Head and Neck Surgery, Chang Gung Memorial Hospital, Chiayi, Taiwan
| | - Ming-Shao Tsai
- Department of Otolaryngology-Head and Neck Surgery, Chang Gung Memorial Hospital, Chiayi, Taiwan
| | - Yi-Chan Lee
- Department of Otolaryngology-Head and Neck Surgery, Chang Gung Memorial Hospital, Keelung, Taiwan
| | - Ethan I Huang
- Department of Otolaryngology-Head and Neck Surgery, Chang Gung Memorial Hospital, Chiayi, Taiwan.,Department of Medicine, College of Medicine, Chang Gung University, Taoyuan, Taiwan
| | - Chia-Hsuan Lai
- Department of Radiation Oncology, Chang Gung Memorial Hospital, Chiayi, Taiwan
| | - Ku-Hao Fang
- Department of Otolaryngology-Head and Neck Surgery, Chang Gung Memorial Hospital, Taoyuan, Taiwan
| |
Collapse
|
27
|
Kuruc F, Binder H, Hess M. Stratified neural networks in a time-to-event setting. Brief Bioinform 2021; 23:6377517. [PMID: 34585236 DOI: 10.1093/bib/bbab392] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2021] [Revised: 08/25/2021] [Accepted: 08/30/2021] [Indexed: 12/28/2022] Open
Abstract
Deep neural networks are frequently employed to predict survival conditional on omics-type biomarkers, e.g., by employing the partial likelihood of Cox proportional hazards model as loss function. Due to the generally limited number of observations in clinical studies, combining different data sets has been proposed to improve learning of network parameters. However, if baseline hazards differ between the studies, the assumptions of Cox proportional hazards model are violated. Based on high dimensional transcriptome profiles from different tumor entities, we demonstrate how using a stratified partial likelihood as loss function allows for accounting for the different baseline hazards in a deep learning framework. Additionally, we compare the partial likelihood with the ranking loss, which is frequently employed as loss function in machine learning approaches due to its seemingly simplicity. Using RNA-seq data from the Cancer Genome Atlas (TCGA) we show that use of stratified loss functions leads to an overall better discriminatory power and lower prediction error compared to their non-stratified counterparts. We investigate which genes are identified to have the greatest marginal impact on prediction of survival when using different loss functions. We find that while similar genes are identified, in particular known prognostic genes receive higher importance from stratified loss functions. Taken together, pooling data from different sources for improved parameter learning of deep neural networks benefits largely from employing stratified loss functions that consider potentially varying baseline hazards. For easy application, we provide PyTorch code for stratified loss functions and an explanatory Jupyter notebook in a GitHub repository.
Collapse
Affiliation(s)
- Fabrizio Kuruc
- Institute of Medical Biometry and Statistics, Faculty of Medicine and Medical Center - University of Freiburg, Germany
| | - Harald Binder
- Institute of Medical Biometry and Statistics, Faculty of Medicine and Medical Center - University of Freiburg, Germany
| | - Moritz Hess
- Institute of Medical Biometry and Statistics, Faculty of Medicine and Medical Center - University of Freiburg, Germany
| |
Collapse
|
28
|
Yang QF, Wu D, Wang J, Ba L, Tian C, Liu YT, Hu Y, Liu L. Development and validation of an individualized immune prognostic model in stage I-III lung squamous cell carcinoma. Sci Rep 2021; 11:12727. [PMID: 34135424 PMCID: PMC8209222 DOI: 10.1038/s41598-021-92115-0] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2021] [Accepted: 06/03/2021] [Indexed: 02/05/2023] Open
Abstract
Lung squamous cell carcinoma (LUSC) possesses a poor prognosis even for stages I-III resected patients. Reliable prognostic biomarkers that can stratify and predict clinical outcomes for stage I-III resected LUSC patients are urgently needed. Based on gene expression of LUSC tissue samples from five public datasets, consisting of 687 cases, we developed an immune-related prognostic model (IPM) according to immune genes from ImmPort database. Then, we comprehensively analyzed the immune microenvironment and mutation burden that are significantly associated with this model. According to the IPM, patients were stratified into high- and low-risk groups with markedly distinct survival benefits. We found that patients with high immune risk possessed a higher proportion of immunosuppressive cells such as macrophages M0, and presented higher expression of CD47, CD73, SIRPA, and TIM-3. Moreover, When further stratified based on the tumor mutation burden (TMB) and risk score, patients with high TMB and low immune risk had a remarkable prolonged overall survival compared to patients with low TMB and high immune risk. Finally, a nomogram combing the IPM with clinical factors was established to provide a more precise evaluation of prognosis. The proposed immune relevant model is a promising biomarker for predicting overall survival in stage I-III LUSC. Thus, it may shed light on identifying patient subset at high risk of adverse prognosis from an immunological perspective.
Collapse
Affiliation(s)
- Qi-Fan Yang
- grid.33199.310000 0004 0368 7223Cancer Center, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022 China
| | - Di Wu
- grid.33199.310000 0004 0368 7223Cancer Center, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022 China
| | - Jian Wang
- grid.33199.310000 0004 0368 7223Cancer Center, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022 China
| | - Li Ba
- grid.33199.310000 0004 0368 7223Department of Ultrasound, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022 China
| | - Chen Tian
- grid.33199.310000 0004 0368 7223Cancer Center, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022 China
| | - Yu-Ting Liu
- grid.33199.310000 0004 0368 7223Cancer Center, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022 China
| | - Yue Hu
- grid.33199.310000 0004 0368 7223Cancer Center, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022 China
| | - Li Liu
- grid.33199.310000 0004 0368 7223Cancer Center, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430022 China
| |
Collapse
|
29
|
Zhang M, Liang M, Chen S, Tan N, Li Y, Xiao Y. Novel physiologic nomogram discriminates symptom outcome in patients with erosive esophagitis. Esophagus 2021; 18:407-415. [PMID: 33156447 DOI: 10.1007/s10388-020-00793-y] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/07/2020] [Accepted: 10/23/2020] [Indexed: 02/03/2023]
Abstract
BACKGROUND AND AIM Most of patients with erosive esophagitis (EE) are of LA grade A&B with low reflux burden, therefore require further esophageal function tests (EFTs). One-third of them respond poorly to pump proton inhibitor (PPI) treatment. The aim was to establish and validate a physiologic nomogram to discriminate symptom outcome to PPI treatment in patients with EE. METHODS A total of 79 EE patients with heartburn who underwent EFTs and received PPI therapy were randomly assigned into a training set (n = 55) and a validation set (n = 24). Clinical data including physiologic parameters from EFTs were collected. Significant factors for the positive symptomatic outcome were identified using logistic regression analysis. Physiologic signature was developed using the least absolute shrinkage and selection operator algorithm. The nomogram was established by combining significant factors and physiologic signature, and its performance was evaluated and validated in the training and validation set. The clinical value of the nomogram was measured by decision curve analysis. RESULTS Significant factors for positive symptomatic response to PPI treatment were identified as follows: acid exposure time, total number of reflux episodes, and two novel metrics including mean nocturnal baseline impedance and post-reflux swallow-induced peristaltic wave index. The nomogram which incorporated both significant factors and physiologic signature demonstrated good performance in the training and validation sets [C-index: 0.938 (95% CI 0.882-0.995); 0.839 (95% CI 0.678-0.995), respectively]. Decision curves showed significant clinical usefulness. CONCLUSION The first physiologic nomogram was developed to discriminate the individualized response to PPI therapy among EE patients.
Collapse
Affiliation(s)
- Mengyu Zhang
- Department of Gastroenterology, The First Affiliated Hospital of Sun Yat-sen University, 58 Zhongshan II Road, Guangzhou, 510080, Guangdong Province, China
| | - Mengya Liang
- Department of Cardiac Surgery, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, 510080, China
| | - Songfeng Chen
- Department of Gastroenterology, The First Affiliated Hospital of Sun Yat-sen University, 58 Zhongshan II Road, Guangzhou, 510080, Guangdong Province, China
| | - Niandi Tan
- Department of Gastroenterology, The First Affiliated Hospital of Sun Yat-sen University, 58 Zhongshan II Road, Guangzhou, 510080, Guangdong Province, China
| | - Yuwen Li
- Department of Gastroenterology, The First Affiliated Hospital of Sun Yat-sen University, 58 Zhongshan II Road, Guangzhou, 510080, Guangdong Province, China
| | - Yinglian Xiao
- Department of Gastroenterology, The First Affiliated Hospital of Sun Yat-sen University, 58 Zhongshan II Road, Guangzhou, 510080, Guangdong Province, China.
| |
Collapse
|
30
|
Aastha, Huang P, Liu Y. DeepCompete : A deep learning approach to competing risks in continuous time domain. AMIA ... ANNUAL SYMPOSIUM PROCEEDINGS. AMIA SYMPOSIUM 2021; 2020:177-186. [PMID: 33936389 PMCID: PMC8075516] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
An increasing number of people survive longer ages leading to a growing population of people 65 years of age or older. A large percentage of this population is afflicted with multiple acute diseases (multi-morbidity). Clinicians need new tools to quantify the relative risk of an adverse event due to each competing disease and prioritize treatment among various diseases affecting a patient. Currently available deep learning survival analysis models have limited ability to incorporate multiple risks. Also, deep learning survival analysis models in current literature work predominantly in the discrete-time domain, while all biochemical processes continuously happen in the body. In this work, we introduce a novel architecture for a continuous-time deep learning model to combat these two issues, DeepCompete, aimed at survival analysis for competing risks. Our model learns the risk of each disease in an entirely data-driven fashion without making strong assumptions about the underlying stochastic processes. Further, we demonstrate that our model has superior results compared to state of the art continuous-time statistical models for survival analysis.
Collapse
Affiliation(s)
- Aastha
- University of Southern California, Los Angeles, California, USA
| | - Pengyu Huang
- University of Southern California, Los Angeles, California, USA
| | - Yan Liu
- University of Southern California, Los Angeles, California, USA
| |
Collapse
|
31
|
Jing B, Deng Y, Zhang T, Hou D, Li B, Qiang M, Liu K, Ke L, Li T, Sun Y, Lv X, Li C. Deep learning for risk prediction in patients with nasopharyngeal carcinoma using multi-parametric MRIs. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2020; 197:105684. [PMID: 32781421 DOI: 10.1016/j.cmpb.2020.105684] [Citation(s) in RCA: 26] [Impact Index Per Article: 5.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/06/2019] [Accepted: 07/28/2020] [Indexed: 06/11/2023]
Abstract
BACKGROUND Magnetic resonance images (MRI) is the main diagnostic tool for risk stratification and treatment decision in nasopharyngeal carcinoma (NPC). However, the holistic feature information of multi-parametric MRIs has not been fully exploited by clinicians to accurately evaluate patients. OBJECTIVE To help clinicians fully utilize the missed information to regroup patients, we built an end-to-end deep learning model to extract feature information from multi-parametric MRIs for predicting and stratifying the risk scores of NPC patients. METHODS In this paper, we proposed an end-to-end multi-modality deep survival network (MDSN) to precisely predict the risk of disease progression of NPC patients. Extending from 3D dense net, this proposed MDSN extracted deep representation from multi-parametric MRIs (T1w, T2w, and T1c). Moreover, deep features and clinical stages were integrated through MDSN to more accurately predict the overall risk score (ORS) of individual NPC patient. RESULT A total of 1,417 individuals treated between January 2012 and December 2014 were included for training and validating the end-to-end MDSN. Results were then tested in a retrospective cohort of 429 patients included in the same institution. The C-index of the proposed method with or without clinical stages was 0.672 and 0.651 on the test set, respectively, which was higher than the that of the stage grouping (0.610). CONCLUSIONS The C-index of the model which integrated clinical stages with deep features is 0.062 higher than that of stage grouping alone (0.672 vs 0.610). We conclude that features extracted from multi-parametric MRIs based on MDSN can well assist the clinical stages in regrouping patients.
Collapse
Affiliation(s)
- Bingzhong Jing
- Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou 510060, China; Department of Information, Sun Yat-Sen University Cancer Centre, Guangzhou 510060, China
| | - Yishu Deng
- Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou 510060, China; Department of Information, Sun Yat-Sen University Cancer Centre, Guangzhou 510060, China
| | - Tao Zhang
- Guangzhou Deepaint intelligence Tenchnology Co.Ltd., Guangzhou 510060, China
| | - Dan Hou
- Guangzhou Deepaint intelligence Tenchnology Co.Ltd., Guangzhou 510060, China
| | - Bin Li
- Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou 510060, China; Department of Information, Sun Yat-Sen University Cancer Centre, Guangzhou 510060, China
| | - Mengyun Qiang
- Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou 510060, China; Department of Nasopharyngeal Carcinoma, Sun Yat-Sen University Cancer Centre, Guangzhou 510060, China
| | - Kuiyuan Liu
- Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou 510060, China; Department of Nasopharyngeal Carcinoma, Sun Yat-Sen University Cancer Centre, Guangzhou 510060, China
| | - Liangru Ke
- Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou 510060, China; Department of Radiology, Sun Yat-Sen University Cancer Centre, Guangzhou 510060, China
| | - Taihe Li
- Shenzhen Annet Information System Co.LTD., Guangzhou 510060, China
| | - Ying Sun
- Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou 510060, China; Department of Radiotherapy, Sun Yat-Sen University Cancer Centre, Guangzhou 510060, China
| | - Xing Lv
- Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou 510060, China; Department of Nasopharyngeal Carcinoma, Sun Yat-Sen University Cancer Centre, Guangzhou 510060, China.
| | - Chaofeng Li
- Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in South China, Collaborative Innovation Center for Cancer Medicine, Guangzhou 510060, China; Department of Information, Sun Yat-Sen University Cancer Centre, Guangzhou 510060, China.
| |
Collapse
|
32
|
Kothari G, Korte J, Lehrer EJ, Zaorsky NG, Lazarakis S, Kron T, Hardcastle N, Siva S. A systematic review and meta-analysis of the prognostic value of radiomics based models in non-small cell lung cancer treated with curative radiotherapy. Radiother Oncol 2020; 155:188-203. [PMID: 33096167 DOI: 10.1016/j.radonc.2020.10.023] [Citation(s) in RCA: 34] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2020] [Revised: 10/14/2020] [Accepted: 10/15/2020] [Indexed: 12/16/2022]
Abstract
BACKGROUND AND PURPOSE Radiomics allows extraction of quantifiable features from imaging. This study performs a systematic review and meta-analysis of the performance of radiomics based prognostic models in non-small cell lung cancer (NSCLC). MATERIALS AND METHODS A literature review was performed following PRISMA guidelines. Medline, EMBASE and Cochrane databases were searched for articles investigating radiomics features predictive of overall survival (OS) in NSCLC treated with curative intent radiotherapy. A random-effects meta-analysis of Harrell's Concordance Index (C-index) was performed on the performance of radiomics models. RESULTS Of the 2746 articles retrieved, 40 studies of 55 datasets and 6223 patients were eligible for inclusion in the systematic review. There was significant heterogeneity in the methodology for feature selection and model development. Twelve datasets reported the C-index of radiomics based models in predicting OS and were included in the meta-analysis. The C-index random effects estimate was 0.57 (95% CI 0.53-0.62). There was significant heterogeneity (I2 = 70.3%). CONCLUSIONS Based on this review, radiomics based models for lung cancer have to date demonstrated modest prognostic capabilities. Future research should consider using standardised radiomics features, robust feature selection and model development, and deep learning techniques, absolving the need for pre-defined features, to improve imaging-based models.
Collapse
Affiliation(s)
- Gargi Kothari
- Department of Radiation Oncology, Peter MacCallum Cancer Centre, Melbourne, Australia; Sir Peter MacCallum Department of Oncology, University of Melbourne, Peter MacCallum Cancer Centre, Melbourne, Australia.
| | - James Korte
- Department of Physical Sciences, Peter MacCallum Cancer Centre, Melbourne, Australia; Department of Biomedical Engineering, School of Engineering, University of Melbourne, Melbourne, Australia
| | - Eric J Lehrer
- Department of Radiation Oncology, Icahn School of Medicine at Mount Sinai, New York, USA
| | - Nicholas G Zaorsky
- Department of Radiation Oncology, Penn State Cancer Institute, Hershey, USA; Department of Public Health Sciences, Penn State College of Medicine, Hershey, USA
| | - Smaro Lazarakis
- Health Sciences Library, Peter MacCallum Cancer Centre, Parkville, Australia
| | - Tomas Kron
- Sir Peter MacCallum Department of Oncology, University of Melbourne, Peter MacCallum Cancer Centre, Melbourne, Australia; Department of Physical Sciences, Peter MacCallum Cancer Centre, Melbourne, Australia; Centre for Medical Radiation Physics, University of Wollongong, Wollongong, Australia
| | - Nicholas Hardcastle
- Department of Physical Sciences, Peter MacCallum Cancer Centre, Melbourne, Australia; Centre for Medical Radiation Physics, University of Wollongong, Wollongong, Australia
| | - Shankar Siva
- Department of Radiation Oncology, Peter MacCallum Cancer Centre, Melbourne, Australia; Sir Peter MacCallum Department of Oncology, University of Melbourne, Peter MacCallum Cancer Centre, Melbourne, Australia
| |
Collapse
|
33
|
Jin LP, Liu T, Meng FQ, Tai JD. Prognosis prediction model based on competing endogenous RNAs for recurrence of colon adenocarcinoma. BMC Cancer 2020; 20:968. [PMID: 33028275 PMCID: PMC7541229 DOI: 10.1186/s12885-020-07163-y] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2020] [Accepted: 07/10/2020] [Indexed: 01/05/2023] Open
Abstract
BACKGROUND Colon adenocarcinoma (COAD) patients who develop recurrence have poor prognosis. Our study aimed to establish effective prognosis prediction model based on competing endogenous RNAs (ceRNAs) for recurrence of COAD. METHODS COAD expression profilings downloaded from The Cancer Genome Atlas (TCGA) were used as training dataset, and expression profilings of GSE29623 retrieved from Gene Expression Omnibus (GEO) were set as validation dataset. Differentially expressed RNAs (DERs) between non-recurrent and recurrent specimens in training dataset were screened, and optimum prognostic signature DERs were revealed to establish prognostic score (PS) model. Kaplan-Meier survival analysis was conducted for PS model, and GEO dataset was used for validation. Prognosis prediction efficiencies were evaluated by area under curve (AUC) and C-index. Meanwhile, ceRNA regulatory network was constructed by using signature mRNAs, lncRNAs and miRNAs. RESULTS We identified 562 DERs including 42 lncRNAs, 36 miRNAs, and 484 mRNAs. PS prediction model, consisting of 17 optimum prognostic signature DERs, showed that high risk group had significantly poorer prognosis (5-year AUC = 0.951, C-index = 0.788), which also validated in GSE29623. Prognosis prediction model incorporating multi-RNAs with pathologic distant metastasis (M) and pathologic primary tumor (T) (5-year AUC = 0.969, C-index = 0.812) had better efficiency than clinical prognosis prediction model (5-year AUC = 0.712, C-index = 0.680). In the constructed ceRNA regulatory network, lncRNA NCBP2-AS1 could interact with hsa-miR-34c and hsa-miR-363, and lncRNA LINC00115 could interact with hsa-miR-363 and hsa-miR-4709. SIX4, GRAP, NKAIN4, MMAA, and ERVMER34-1 are regulated by hsa-miR-4709. CONCLUSION Prognosis prediction model incorporating multi-RNAs with pathologic M and pathologic T may have great value in COAD prognosis prediction.
Collapse
Affiliation(s)
- Li Peng Jin
- Department of Colorectal & Anal Surgery, First Hospital Bethune of Jilin University, No. 71, Xinmin Street, Chaoyang District, Changchun, 130000 Jilin China
| | - Tao Liu
- Department of Colorectal & Anal Surgery, First Hospital Bethune of Jilin University, No. 71, Xinmin Street, Chaoyang District, Changchun, 130000 Jilin China
| | - Fan Qi Meng
- Department of Colorectal & Anal Surgery, First Hospital Bethune of Jilin University, No. 71, Xinmin Street, Chaoyang District, Changchun, 130000 Jilin China
| | - Jian Dong Tai
- Department of Colorectal & Anal Surgery, First Hospital Bethune of Jilin University, No. 71, Xinmin Street, Chaoyang District, Changchun, 130000 Jilin China
| |
Collapse
|
34
|
Yao J, Zhu X, Jonnagaddala J, Hawkins N, Huang J. Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks. Med Image Anal 2020; 65:101789. [DOI: 10.1016/j.media.2020.101789] [Citation(s) in RCA: 80] [Impact Index Per Article: 16.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2019] [Revised: 06/29/2020] [Accepted: 07/16/2020] [Indexed: 01/25/2023]
|
35
|
Starke S, Leger S, Zwanenburg A, Leger K, Lohaus F, Linge A, Schreiber A, Kalinauskaite G, Tinhofer I, Guberina N, Guberina M, Balermpas P, von der Grün J, Ganswindt U, Belka C, Peeken JC, Combs SE, Boeke S, Zips D, Richter C, Troost EGC, Krause M, Baumann M, Löck S. 2D and 3D convolutional neural networks for outcome modelling of locally advanced head and neck squamous cell carcinoma. Sci Rep 2020; 10:15625. [PMID: 32973220 PMCID: PMC7518264 DOI: 10.1038/s41598-020-70542-9] [Citation(s) in RCA: 29] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2020] [Accepted: 07/20/2020] [Indexed: 12/14/2022] Open
Abstract
For treatment individualisation of patients with locally advanced head and neck squamous cell carcinoma (HNSCC) treated with primary radiochemotherapy, we explored the capabilities of different deep learning approaches for predicting loco-regional tumour control (LRC) from treatment-planning computed tomography images. Based on multicentre cohorts for exploration (206 patients) and independent validation (85 patients), multiple deep learning strategies including training of 3D- and 2D-convolutional neural networks (CNN) from scratch, transfer learning and extraction of deep autoencoder features were assessed and compared to a clinical model. Analyses were based on Cox proportional hazards regression and model performances were assessed by the concordance index (C-index) and the model's ability to stratify patients based on predicted hazards of LRC. Among all models, an ensemble of 3D-CNNs achieved the best performance (C-index 0.31) with a significant association to LRC on the independent validation cohort. It performed better than the clinical model including the tumour volume (C-index 0.39). Significant differences in LRC were observed between patient groups at low or high risk of tumour recurrence as predicted by the model ([Formula: see text]). This 3D-CNN ensemble will be further evaluated in a currently ongoing prospective validation study once follow-up is complete.
Collapse
Affiliation(s)
- Sebastian Starke
- Helmholtz-Zentrum Dresden - Rossendorf, Department of Information Services and Computing, Dresden, Germany.
- OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany.
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany.
| | - Stefan Leger
- OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany
| | - Alex Zwanenburg
- OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany
| | - Karoline Leger
- OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
| | - Fabian Lohaus
- OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
| | - Annett Linge
- OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
| | - Andreas Schreiber
- Department of Radiotherapy, Hospital Dresden-Friedrichstadt, Dresden, Germany
| | - Goda Kalinauskaite
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Berlin, Berlin, Germany
- Department of Radiooncology and Radiotherapy, Charité University Hospital, Berlin, Germany
| | - Inge Tinhofer
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Berlin, Berlin, Germany
- Department of Radiooncology and Radiotherapy, Charité University Hospital, Berlin, Germany
| | - Nika Guberina
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Essen, Essen, Germany
- Department of Radiotherapy, Medical Faculty, University of Duisburg-Essen, Essen, Germany
| | - Maja Guberina
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Essen, Essen, Germany
- Department of Radiotherapy, Medical Faculty, University of Duisburg-Essen, Essen, Germany
| | - Panagiotis Balermpas
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Frankfurt, Frankfurt, Germany
- Department of Radiotherapy and Oncology, Goethe-University Frankfurt, Frankfurt, Germany
| | - Jens von der Grün
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Frankfurt, Frankfurt, Germany
- Department of Radiotherapy and Oncology, Goethe-University Frankfurt, Frankfurt, Germany
| | - Ute Ganswindt
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Munich, Munich, Germany
- Department of Radiation Oncology, Ludwig-Maximilians-Universität, Munich, Germany
- Clinical Cooperation Group, Personalized Radiotherapy in Head and Neck Cancer, Helmholtz Zentrum, Munich, Germany
- Department of Radiation Oncology, Medical University of Innsbruck, Anichstraße 35, 6020, Innsbruck, Austria
| | - Claus Belka
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Munich, Munich, Germany
- Department of Radiation Oncology, Ludwig-Maximilians-Universität, Munich, Germany
- Clinical Cooperation Group, Personalized Radiotherapy in Head and Neck Cancer, Helmholtz Zentrum, Munich, Germany
| | - Jan C Peeken
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Munich, Munich, Germany
- Department of Radiation Oncology, Technische Universität München, Munich, Germany
- Institute of Radiation Medicine (IRM), Helmholtz Zentrum München, Neuherberg, Germany
| | - Stephanie E Combs
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Munich, Munich, Germany
- Department of Radiation Oncology, Technische Universität München, Munich, Germany
- Institute of Radiation Medicine (IRM), Helmholtz Zentrum München, Neuherberg, Germany
| | - Simon Boeke
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Tübingen, Tübingen, Germany
- Department of Radiation Oncology, Faculty of Medicine and University Hospital Tübingen, Eberhard Karls Universität Tübingen, Tübingen, Germany
| | - Daniel Zips
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Tübingen, Tübingen, Germany
- Department of Radiation Oncology, Faculty of Medicine and University Hospital Tübingen, Eberhard Karls Universität Tübingen, Tübingen, Germany
| | - Christian Richter
- OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
- Helmholtz-Zentrum Dresden - Rossendorf, Institute of Radiooncology - OncoRay, Dresden, Germany
| | - Esther G C Troost
- OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
- Helmholtz-Zentrum Dresden - Rossendorf, Institute of Radiooncology - OncoRay, Dresden, Germany
| | - Mechthild Krause
- OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
- Helmholtz-Zentrum Dresden - Rossendorf, Institute of Radiooncology - OncoRay, Dresden, Germany
| | - Michael Baumann
- OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany
- National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
- Helmholtz-Zentrum Dresden - Rossendorf, Institute of Radiooncology - OncoRay, Dresden, Germany
- German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Steffen Löck
- OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
- German Cancer Research Center (DKFZ), Heidelberg and German Cancer Consortium (DKTK) partner site Dresden, Dresden, Germany
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
| |
Collapse
|
36
|
Yan Y, Lin J, Zhang M, Liu H, Zhou Q, Chen R, Wen K, Wang J, Xiao Z, Mao K. A Novel Staging System to Forecast the Cancer-Specific Survival of Patients With Resected Gallbladder Cancer. Front Oncol 2020; 10:1281. [PMID: 32850391 PMCID: PMC7399135 DOI: 10.3389/fonc.2020.01281] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2019] [Accepted: 06/19/2020] [Indexed: 12/16/2022] Open
Abstract
Objective: Gallbladder cancer (GBC) is one of the most aggressive malignant tumors, and there is no effective and convenient method for predicting cancer-specific survival (CSS). We aim to develop a novel nomogram staging system based on the positive lymph node ratio (pLNR) for GBC patients. Methods:A total of 1,356 patients enrolled in the study. We evaluated the prognostic value of the pLNR and built a prognostic nomogram staging system based on the pLNR in the training cohort. The concordance index and calibration plots were used to evaluate model discrimination. The predictive accuracy and clinical value of the nomograms were measured by decision curve analysis (DCA). The CSS nomogram was further validated in an internal validation cohort. Results:The pLNR was an independent prognostic factor for CSS based on Cox regression analyses. A prognostic nomogram that combined T classification, pLNR, M classification, histologic grade, live metastasis, and tumor size was formulated with a c-index of 0.763 (95% CI, 0.728–0.798), while the c-indexes for the staging system of AJCC 8th, 7th, and 6th for CSS prediction were 0.718, 0.718, and 0.717, respectively. The calibration curves showed perfect agreement. The DCA showed that the nomogram provided substantial clinical value. The nomogram (the AUCs for 1, 3, and 5 years were 0.693, 0.716, and 0.726, respectively,) showed high prognostic accuracy. Conclusion:We have developed a formulated nomogram staging system based on the pLNR that allows more accurate individualized predictions of CSS for resected GBC patients than the AJCC staging systems.
Collapse
Affiliation(s)
- Yongcong Yan
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Jianhong Lin
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Mengyu Zhang
- Department of Gastroenterology and Hepatology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Haohan Liu
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Qianlei Zhou
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Ruibin Chen
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Kai Wen
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Jie Wang
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Zhiyu Xiao
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Kai Mao
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| |
Collapse
|
37
|
Meier A, Nekolla K, Hewitt LC, Earle S, Yoshikawa T, Oshima T, Miyagi Y, Huss R, Schmidt G, Grabsch HI. Hypothesis-free deep survival learning applied to the tumour microenvironment in gastric cancer. JOURNAL OF PATHOLOGY CLINICAL RESEARCH 2020; 6:273-282. [PMID: 32592447 PMCID: PMC7578283 DOI: 10.1002/cjp2.170] [Citation(s) in RCA: 17] [Impact Index Per Article: 3.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/05/2019] [Revised: 04/14/2020] [Accepted: 04/20/2020] [Indexed: 02/06/2023]
Abstract
The biological complexity reflected in histology images requires advanced approaches for unbiased prognostication. Machine learning and particularly deep learning methods are increasingly applied in the field of digital pathology. In this study, we propose new ways to predict risk for cancer‐specific death from digital images of immunohistochemically (IHC) stained tissue microarrays (TMAs). Specifically, we evaluated a cohort of 248 gastric cancer patients using convolutional neural networks (CNNs) in an end‐to‐end weakly supervised scheme independent of subjective pathologist input. To account for the time‐to‐event characteristic of the outcome data, we developed new survival models to guide the network training. In addition to the standard H&E staining, we investigated the prognostic value of a panel of immune cell markers (CD8, CD20, CD68) and a proliferation marker (Ki67). Our CNN‐derived risk scores provided additional prognostic value when compared to the gold standard prognostic tool TNM stage. The CNN‐derived risk scores were also shown to be superior when systematically compared to cell density measurements or a CNN score derived from binary 5‐year survival classification, which ignores time‐to‐event. To better understand the underlying biological mechanisms, we qualitatively investigated risk heat maps for each marker which visualised the network output. We identified patterns of biological interest that were related to low risk of cancer‐specific death such as the presence of B‐cell predominated clusters and Ki67 positive sub‐regions and showed that the corresponding risk scores had prognostic value in multivariate Cox regression analyses (Ki67&CD20 risks: hazard ratio (HR) = 1.47, 95% confidence interval (CI) = 1.15–1.89, p = 0.002; CD20&CD68 risks: HR = 1.33, 95% CI = 1.07–1.67, p = 0.009). Our study demonstrates the potential additional value that deep learning in combination with a panel of IHC markers can bring to the field of precision oncology.
Collapse
Affiliation(s)
- Armin Meier
- Image Data Sciences, Definiens GmbH, Munich, Germany
| | | | - Lindsay C Hewitt
- Department of Pathology, GROW School for Oncology and Developmental Biology, Maastricht University Medical Center+, Maastricht, The Netherlands
| | - Sophie Earle
- Division of Pathology and Data Analytics, Leeds Institute of Medical Research at St. James's , University of Leeds, Leeds, UK
| | - Takaki Yoshikawa
- Department of Gastric Surgery, National Cancer Center Hospital, Tokyo, Japan
| | - Takashi Oshima
- Department of Gastrointestinal Surgery, Kanagawa Cancer Center Hospital, Yokohama, Japan
| | - Yohei Miyagi
- Molecular Pathology and Genetics Division, Kanagawa Cancer Center Research Institute, Yokohama, Japan
| | - Ralf Huss
- Institute of Pathology and Molecular Diagnostic, University Hospital Augsburg, Augsburg, Germany
| | | | - Heike I Grabsch
- Department of Pathology, GROW School for Oncology and Developmental Biology, Maastricht University Medical Center+, Maastricht, The Netherlands.,Division of Pathology and Data Analytics, Leeds Institute of Medical Research at St. James's , University of Leeds, Leeds, UK
| |
Collapse
|
38
|
A potential prognostic prediction model of colon adenocarcinoma with recurrence based on prognostic lncRNA signatures. Hum Genomics 2020; 14:24. [PMID: 32522293 PMCID: PMC7288433 DOI: 10.1186/s40246-020-00270-8] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2019] [Accepted: 05/13/2020] [Indexed: 12/18/2022] Open
Abstract
BACKGROUND Colon adenocarcinoma (COAD) is one of the common gastrointestinal malignant diseases, with high mortality rate and poor prognosis due to delayed diagnosis. This study aimed to construct a prognostic prediction model for patients with colon adenocarcinoma (COAD) recurrence. METHODS Differently expressed RNAs (DERs) between recurrence and non-recurrence COAD samples were identified based on expression profile data from the NCBI Gene Expression Omnibus (GEO) repository and The Cancer Genome Atlas (TCGA) database. Then, recurrent COAD discriminating classifier was established using SMV-RFE algorithm, and receiver operating characteristic curve was used to assess the predictive power of classifier. Furthermore, the prognostic prediction model was constructed based on univariate and multivariate Cox regression analysis, and Kaplan-Meier survival curve analysis was used to estimate this model. Furthermore, the co-expression network of DElncRNAs and DEmRNAs was constructed followed by GO and KEGG pathway enrichment analysis. RESULTS A total of 54 optimized signature DElncRNAs were screened and SMV classifier was constructed, which presented a high accuracy to distinguish recurrence and non-recurrence COAD samples. Furthermore, six independent prognostic lncRNAs signatures (LINC00852, ZNF667-AS1, FOXP1-IT1, LINC01560, TAF1A-AS1, and LINC00174) in COAD patients with recurrence were screened, and the prognostic prediction model for recurrent COAD was constructed, which possessed a relative satisfying predicted ability both in the training dataset and validation dataset. Furthermore, the DEmRNAs in the co-expression network were mainly enriched in glycan biosynthesis, cardiac muscle contraction, and colorectal cancer. CONCLUSIONS Our study revealed that six lncRNA signatures acted as an independent prognostic biomarker for patients with COAD recurrence.
Collapse
|
39
|
Wu G, Zhang M. A novel risk score model based on eight genes and a nomogram for predicting overall survival of patients with osteosarcoma. BMC Cancer 2020; 20:456. [PMID: 32448271 PMCID: PMC7245838 DOI: 10.1186/s12885-020-06741-4] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2019] [Accepted: 03/12/2020] [Indexed: 12/19/2022] Open
Abstract
BACKGROUND This study aims to identify a predictive model to predict survival outcomes of osteosarcoma (OS) patients. METHODS A RNA sequencing dataset (the training set) and a microarray dataset (the validation set) were obtained from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) database, respectively. Differentially expressed genes (DEGs) between metastatic and non-metastatic OS samples were identified in training set. Prognosis-related DEGs were screened and optimized by support vector machine (SVM) recursive feature elimination. A SVM classifier was built to classify metastatic and non-metastatic OS samples. Independent prognosic genes were extracted by multivariate regression analysis to build a risk score model followed by performance evaluation in two datasets by Kaplan-Meier (KM) analysis. Independent clinical prognostic indicators were identified followed by nomogram analysis. Finally, functional analyses of survival-related genes were conducted. RESULT Totally, 345 DEGs and 45 prognosis-related genes were screened. A SVM classifier could distinguish metastatic and non-metastatic OS samples. An eight-gene signature was an independent prognostic marker and used for constructing a risk score model. The risk score model could separate OS samples into high and low risk groups in two datasets (training set: log-rank p < 0.01, C-index = 0.805; validation set: log-rank p < 0.01, C-index = 0.797). Tumor metastasis and RS model status were independent prognostic factors and nomogram model exhibited accurate survival prediction for OS. Additionally, functional analyses of survival-related genes indicated they were closely associated with immune responses and cytokine-cytokine receptor interaction pathway. CONCLUSION An eight-gene predictive model and nomogram were developed to predict OS prognosis.
Collapse
Affiliation(s)
- Guangzhi Wu
- Departments of Hand Surgery, The Third Hospital of Jilin University, Changchun, Jilin Province China
| | - Minglei Zhang
- Departments of Orthopedics, The Third Hospital of Jilin University, Changchun, Jilin Province China
| |
Collapse
|
40
|
Huang Z, Johnson TS, Han Z, Helm B, Cao S, Zhang C, Salama P, Rizkalla M, Yu CY, Cheng J, Xiang S, Zhan X, Zhang J, Huang K. Deep learning-based cancer survival prognosis from RNA-seq data: approaches and evaluations. BMC Med Genomics 2020; 13:41. [PMID: 32241264 PMCID: PMC7118823 DOI: 10.1186/s12920-020-0686-1] [Citation(s) in RCA: 26] [Impact Index Per Article: 5.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022] Open
Abstract
BACKGROUND Recent advances in kernel-based Deep Learning models have introduced a new era in medical research. Originally designed for pattern recognition and image processing, Deep Learning models are now applied to survival prognosis of cancer patients. Specifically, Deep Learning versions of the Cox proportional hazards models are trained with transcriptomic data to predict survival outcomes in cancer patients. METHODS In this study, a broad analysis was performed on TCGA cancers using a variety of Deep Learning-based models, including Cox-nnet, DeepSurv, and a method proposed by our group named AECOX (AutoEncoder with Cox regression network). Concordance index and p-value of the log-rank test are used to evaluate the model performances. RESULTS All models show competitive results across 12 cancer types. The last hidden layers of the Deep Learning approaches are lower dimensional representations of the input data that can be used for feature reduction and visualization. Furthermore, the prognosis performances reveal a negative correlation between model accuracy, overall survival time statistics, and tumor mutation burden (TMB), suggesting an association among overall survival time, TMB, and prognosis prediction accuracy. CONCLUSIONS Deep Learning based algorithms demonstrate superior performances than traditional machine learning based models. The cancer prognosis results measured in concordance index are indistinguishable across models while are highly variable across cancers. These findings shedding some light into the relationships between patient characteristics and survival learnability on a pan-cancer level.
Collapse
Affiliation(s)
- Zhi Huang
- School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, 47907, USA.,Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.,Department of Electrical and Computer Engineering, Indiana University - Purdue University Indianapolis, Indianapolis, IN, 46202, USA
| | - Travis S Johnson
- Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.,Department of Biomedical Informatics, The Ohio State University, Columbus, OH, 43210, USA
| | - Zhi Han
- Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
| | - Bryan Helm
- Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
| | - Sha Cao
- Department of Medical and Molecular Genetics, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
| | - Chi Zhang
- Department of Electrical and Computer Engineering, Indiana University - Purdue University Indianapolis, Indianapolis, IN, 46202, USA.,Department of Medical and Molecular Genetics, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
| | - Paul Salama
- Department of Electrical and Computer Engineering, Indiana University - Purdue University Indianapolis, Indianapolis, IN, 46202, USA
| | - Maher Rizkalla
- Department of Electrical and Computer Engineering, Indiana University - Purdue University Indianapolis, Indianapolis, IN, 46202, USA
| | - Christina Y Yu
- Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.,Department of Biomedical Informatics, The Ohio State University, Columbus, OH, 43210, USA
| | - Jun Cheng
- Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.,National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, 518060, China
| | - Shunian Xiang
- Department of Medical and Molecular Genetics, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.,Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University, Shenzhen, 518060, China
| | - Xiaohui Zhan
- Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, 46202, USA.,Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University, Shenzhen, 518060, China
| | - Jie Zhang
- Department of Medical and Molecular Genetics, Indiana University School of Medicine, Indianapolis, IN, 46202, USA
| | - Kun Huang
- Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, 46202, USA. .,Department of Electrical and Computer Engineering, Indiana University - Purdue University Indianapolis, Indianapolis, IN, 46202, USA.
| |
Collapse
|
41
|
Xu Z, Sun Y, Xu T, Shi Y, Liang L, Liu P, Ge J. MGUS Predicts Worse Prognosis in Patients with Coronary Artery Disease. J Cardiovasc Transl Res 2020; 13:806-812. [PMID: 31900894 PMCID: PMC7541390 DOI: 10.1007/s12265-019-09950-w] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/28/2019] [Accepted: 12/11/2019] [Indexed: 11/29/2022]
Abstract
We performed a retrospective cohort study to analyze all 87 CAD patients with MGUS and 178 CAD patients without MGUS admitted in Zhongshan Hospital Fudan University from 2015 to 2017. Patients were followed up via regular patient visits or telephone, and the median follow-up period was 2.9 years. The end point of follow-up was the occurrence of major adverse cardiac events (MACE). CAD patients with MGUS had a higher risk of MACE than those without MGUS (log-rank P = 0.0015). After adjustment for other markers in the stepwise Cox regression model, MGUS was still related to the increasing risk of MACE incident (P = 0.002, HR = 2.308). Then, we constructed the nomogram based on the Cox regression model, and the concordance index (C-index) was 0.667. Hence, MGUS might be added into the risk model of CAD.
Collapse
Affiliation(s)
- Zhao Xu
- Department of Hematology, Zhongshan Hospital Fudan University, 180 Fenglin Road, Shanghai, 200032, China
| | - Yifeng Sun
- Department of Hematology, Zhongshan Hospital Fudan University, 180 Fenglin Road, Shanghai, 200032, China
| | - Tianhong Xu
- Department of Hematology, Zhongshan Hospital Fudan University, 180 Fenglin Road, Shanghai, 200032, China
| | - Yidan Shi
- Department of Statistics and Actuarial Science, University of Waterloo, Waterloo, Canada
| | - Lifan Liang
- Department of Hematology, Zhongshan Hospital Fudan University, 180 Fenglin Road, Shanghai, 200032, China
| | - Peng Liu
- Department of Hematology, Zhongshan Hospital Fudan University, 180 Fenglin Road, Shanghai, 200032, China.
| | - Junbo Ge
- Department of Cardiology, Shanghai Institute of Cardiovascular Diseases, Zhongshan Hospital Fudan University, Shanghai, China
| |
Collapse
|
42
|
Yi B, Tang C, Tao Y, Zhao Z. Definition of a novel vascular invasion-associated multi-gene signature for predicting survival in patients with hepatocellular carcinoma. Oncol Lett 2020; 19:147-158. [PMID: 31897125 PMCID: PMC6923904 DOI: 10.3892/ol.2019.11072] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/05/2019] [Accepted: 09/11/2019] [Indexed: 12/12/2022] Open
Abstract
The aim of the present study was to identify a vascular invasion-associated gene signature for predicting prognosis in patients with hepatocellular carcinoma (HCC). Using RNA-sequencing data of 292 HCC samples from The Cancer Genome Atlas (TCGA), the present study screened differentially expressed genes (DEGs) between patients with and without vascular invasion. Feature genes were selected from the DEGs by support vector machine (SVM)-based recursive feature elimination (RFE-SVM) algorithm to build a classifier. A multi-gene signature was selected by L1 penalized (LASSO) Cox proportional hazards (PH) regression model from the feature genes selected by the RFE-SVM to develop a prognostic scoring model. TCGA set was defined as the training set and was divided by the gene signature into a high-risk group and a low-risk group. Involvement of the DEGs between the two risk groups in pathways was also investigated. The presence and absence of vascular invasion between patients of training set was 175 DEGs. A classification model of 42 genes performed well in differentiating patients with and without vascular invasion on the training set and the validation set. A 14-gene prognostic model was built that could divide the training set or the validation set into two risk groups with significantly different survival outcomes. A total of 762 DEGs in the two risk groups of the training set were revealed to be significantly associated with a number of signaling pathways. The present study provided a 42-gene classifier for predicting vascular invasion, and identified a vascular invasion-associated 14-gene signature for predicting prognosis in patients with HCC. Several genes and pathways in HCC development are characterized and may be potential therapeutic targets for this type of cancer.
Collapse
Affiliation(s)
- Bo Yi
- Department of Hepatobiliary Surgery, Zhu Zhou Central Hospital, Zhuzhou, Hunan 412007, P.R. China
| | - Caixi Tang
- Department of Hepatobiliary Surgery, Zhu Zhou Central Hospital, Zhuzhou, Hunan 412007, P.R. China
| | - Yin Tao
- Department of Hepatobiliary Surgery, Zhu Zhou Central Hospital, Zhuzhou, Hunan 412007, P.R. China
| | - Zhijian Zhao
- Department of Hepatobiliary Surgery, Zhu Zhou Central Hospital, Zhuzhou, Hunan 412007, P.R. China
| |
Collapse
|
43
|
Yan Y, Zhou Q, Zhang M, Liu H, Lin J, Liu Q, Shi B, Wen K, Chen R, Wang J, Mao K, Xiao Z. Integrated Nomograms for Preoperative Prediction of Microvascular Invasion and Lymph Node Metastasis Risk in Hepatocellular Carcinoma Patients. Ann Surg Oncol 2019; 27:1361-1371. [PMID: 31773517 DOI: 10.1245/s10434-019-08071-7] [Citation(s) in RCA: 13] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2019] [Indexed: 12/24/2022]
Abstract
BACKGROUND The aim of the present work is to develop and validate accurate preoperative nomograms to predict microvascular invasion (MVI) and lymph node metastasis (LNM) in hepatocellular carcinoma. PATIENTS AND METHODS A total of 268 patients with resected hepatocellular carcinoma (HCC) were divided into a training set (n = 180), in an earlier period, and a validation set (n = 88), thereafter. Risk factors for MVI and LNM were assessed based on logistic regression. Blood signatures were established using the least absolute shrinkage and selection operator algorithm. Nomograms were constructed by combining risk factors and blood signatures. Performance was evaluated using the training set and validated using the validation set. The clinical values of the nomograms were measured by decision curve analysis. RESULTS The risk factors for MVI were hepatitis B virus (HBV) DNA loading, portal hypertension, Barcelona liver clinic (BCLC) stage, and three computerized tomography (CT) imaging features, namely tumor number, size, and encapsulation, while only BCLC stage, Child-Pugh classification, and tumor encapsulation were associated with LNM. The nomogram incorporating both risk factors and blood signatures achieved better performance in predicting MVI in the training and validation sets (C-indexes of 0.828 and 0.804) than the LNM nomogram (C-indexes of 0.765 and 0.717). Calibration curves also demonstrated a good fit. The decision curves indicate significant clinical usefulness. CONCLUSIONS The novel validated nomograms for HCC patients presented herein are noninvasive preoperative tools that can effectively predict the individualized risk of MVI and LNM, and this predictive power can aid doctors in explaining the illness for patient counseling.
Collapse
Affiliation(s)
- Yongcong Yan
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,RNA Biomedical Institute, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Qianlei Zhou
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,RNA Biomedical Institute, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Mengyu Zhang
- Department of Gastroenterology and Hepatology, The First Affiliated Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Haohan Liu
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,RNA Biomedical Institute, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Jianhong Lin
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,RNA Biomedical Institute, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Qinghua Liu
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,RNA Biomedical Institute, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Bingchao Shi
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,RNA Biomedical Institute, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Kai Wen
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,RNA Biomedical Institute, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Ruibin Chen
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.,RNA Biomedical Institute, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Jie Wang
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China
| | - Kai Mao
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.
| | - Zhiyu Xiao
- Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China.
| |
Collapse
|
44
|
Mubeen S, Hoyt CT, Gemünd A, Hofmann-Apitius M, Fröhlich H, Domingo-Fernández D. The Impact of Pathway Database Choice on Statistical Enrichment Analysis and Predictive Modeling. Front Genet 2019; 10:1203. [PMID: 31824580 PMCID: PMC6883970 DOI: 10.3389/fgene.2019.01203] [Citation(s) in RCA: 55] [Impact Index Per Article: 9.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2019] [Accepted: 10/30/2019] [Indexed: 02/04/2023] Open
Abstract
Pathway-centric approaches are widely used to interpret and contextualize -omics data. However, databases contain different representations of the same biological pathway, which may lead to different results of statistical enrichment analysis and predictive models in the context of precision medicine. We have performed an in-depth benchmarking of the impact of pathway database choice on statistical enrichment analysis and predictive modeling. We analyzed five cancer datasets using three major pathway databases and developed an approach to merge several databases into a single integrative one: MPath. Our results show that equivalent pathways from different databases yield disparate results in statistical enrichment analysis. Moreover, we observed a significant dataset-dependent impact on the performance of machine learning models on different prediction tasks. In some cases, MPath significantly improved prediction performance and also reduced the variance of prediction performances. Furthermore, MPath yielded more consistent and biologically plausible results in statistical enrichment analyses. In summary, this benchmarking study demonstrates that pathway database choice can influence the results of statistical enrichment analysis and predictive modeling. Therefore, we recommend the use of multiple pathway databases or integrative ones.
Collapse
Affiliation(s)
- Sarah Mubeen
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
| | - Charles Tapley Hoyt
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
| | - André Gemünd
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany
| | - Martin Hofmann-Apitius
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
| | - Holger Fröhlich
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
| | - Daniel Domingo-Fernández
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
| |
Collapse
|
45
|
Cao XH, Han C, Glass LM, Kindman A, Obradovic Z. Time-to-event estimation by re-defining time. J Biomed Inform 2019; 100:103326. [PMID: 31678589 DOI: 10.1016/j.jbi.2019.103326] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2019] [Revised: 09/05/2019] [Accepted: 10/28/2019] [Indexed: 11/26/2022]
Abstract
The primary goal of a time-to-event estimation model is to accurately infer the occurrence time of a target event. Most existing studies focus on developing new models to effectively utilize the information in the censored observations. In this paper, we propose a model to tackle the time-to-event estimation problem from a completely different perspective. Our model relaxes a fundamental constraint that the target variable, time, is a univariate number which satisfies a partial order. Instead, the proposed model interprets each event occurrence time as a time concept with a vector representation. We hypothesize that the model will be more accurate and interpretable by capturing (1) the relationships between features and time concept vectors and (2) the relationships among time concept vectors. We also propose a scalable framework to simultaneously learn the model parameters and time concept vectors. Rigorous experiments and analysis have been conducted in medical event prediction task on seven gene expression datasets. The results demonstrate the efficiency and effectiveness of the proposed model. Furthermore, similarity information among time concept vectors helped in identifying time regimes, thus leading to a potential knowledge discovery related to the human cancer considered in our experiments.
Collapse
Affiliation(s)
- Xi Hang Cao
- Center for Data Analytics and Biomedical Informatics, Temple University, 386 SERC, 1925 N. 12th St., Philadelphia, PA 19122, USA.
| | - Chao Han
- Center for Data Analytics and Biomedical Informatics, Temple University, 386 SERC, 1925 N. 12th St., Philadelphia, PA 19122, USA.
| | | | | | - Zoran Obradovic
- Center for Data Analytics and Biomedical Informatics, Temple University, 386 SERC, 1925 N. 12th St., Philadelphia, PA 19122, USA.
| |
Collapse
|
46
|
Forghani R, Savadjiev P, Chatterjee A, Muthukrishnan N, Reinhold C, Forghani B. Radiomics and Artificial Intelligence for Biomarker and Prediction Model Development in Oncology. Comput Struct Biotechnol J 2019; 17:995-1008. [PMID: 31388413 PMCID: PMC6667772 DOI: 10.1016/j.csbj.2019.07.001] [Citation(s) in RCA: 110] [Impact Index Per Article: 18.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2019] [Revised: 07/06/2019] [Accepted: 07/07/2019] [Indexed: 12/14/2022] Open
Abstract
Unlabelled Image.
Collapse
Affiliation(s)
- Reza Forghani
- Department of Radiology, McGill University, 1650 Cedar Avenue, Montreal, Quebec H3G 1A4, Canada.,Department of Radiology and Research, Institute of the McGill University Health Centre, 1001 Decarie Blvd, Montreal H4A 3J1, Quebec, Canada.,Segal Cancer Centre, Lady Davis Institute for Medical Research, Jewish General Hospital, 3755 Cote Ste-Catherine Road, Montreal, Quebec H3T 1E2, Canada.,Gerald Bronfman Department of Oncology, McGill University, Suite 720, 5100 Maisonneuve Blvd West, Montreal, Quebec H4A3T2, Canada.,Department of Otolaryngology, Head and Neck Surgery, Royal Victoria Hospital, McGill University Health Centre, 1001 boul. Decarie Blvd, Montreal, Quebec H3A 3J1, Canada
| | - Peter Savadjiev
- Department of Radiology, McGill University, 1650 Cedar Avenue, Montreal, Quebec H3G 1A4, Canada.,Department of Computer Science, McGill University, 3480 University St, Montreal, Quebec H3A 0E9, Canada
| | - Avishek Chatterjee
- Medical Physics Unit, Cedars Cancer Centre, McGill University Health Centre, 1001 Decarie Blvd, Montreal, Quebec H4A 3J1, Canada
| | - Nikesh Muthukrishnan
- Department of Radiology and Research, Institute of the McGill University Health Centre, 1001 Decarie Blvd, Montreal H4A 3J1, Quebec, Canada.,Segal Cancer Centre, Lady Davis Institute for Medical Research, Jewish General Hospital, 3755 Cote Ste-Catherine Road, Montreal, Quebec H3T 1E2, Canada
| | - Caroline Reinhold
- Department of Radiology, McGill University, 1650 Cedar Avenue, Montreal, Quebec H3G 1A4, Canada.,Department of Radiology and Research, Institute of the McGill University Health Centre, 1001 Decarie Blvd, Montreal H4A 3J1, Quebec, Canada
| | - Behzad Forghani
- Department of Radiology, McGill University, 1650 Cedar Avenue, Montreal, Quebec H3G 1A4, Canada.,Gerald Bronfman Department of Oncology, McGill University, Suite 720, 5100 Maisonneuve Blvd West, Montreal, Quebec H4A3T2, Canada
| |
Collapse
|
47
|
Tang W, Putluri V, Ambati CR, Dorsey TH, Putluri N, Ambs S. Liver- and Microbiome-derived Bile Acids Accumulate in Human Breast Tumors and Inhibit Growth and Improve Patient Survival. Clin Cancer Res 2019; 25:5972-5983. [PMID: 31296531 DOI: 10.1158/1078-0432.ccr-19-0094] [Citation(s) in RCA: 29] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2019] [Revised: 05/24/2019] [Accepted: 07/08/2019] [Indexed: 01/08/2023]
Abstract
PURPOSE Metabolomics is a discovery tool for novel associations of metabolites with disease. Here, we interrogated the metabolome of human breast tumors to describe metabolites whose accumulation affects tumor biology. EXPERIMENTAL DESIGN We applied large-scale metabolomics followed by absolute quantification and machine learning-based feature selection using LASSO to identify metabolites that show a robust association with tumor biology and disease outcome. Key observations were validated with the analysis of an independent dataset and cell culture experiments. RESULTS LASSO-based feature selection revealed an association of tumor glycochenodeoxycholate levels with improved breast cancer survival, which was confirmed using a Cox proportional hazards model. Absolute quantification of four bile acids, including glycochenodeoxycholate and microbiome-derived deoxycholate, corroborated the accumulation of bile acids in breast tumors. Levels of glycochenodeoxycholate and other bile acids showed an inverse association with the proliferation score in tumors and the expression of cell-cycle and G2-M checkpoint genes, which was corroborated with cell culture experiments. Moreover, tumor levels of these bile acids markedly correlated with metabolites in the steroid metabolism pathway and increased expression of key genes in this pathway, suggesting that bile acids may interfere with hormonal pathways in the breast. Finally, a proteome analysis identified the complement and coagulation cascade as being upregulated in glycochenodeoxycholate-high tumors. CONCLUSIONS We describe the unexpected accumulation of liver- and microbiome-derived bile acids in breast tumors. Tumors with increased bile acids show decreased proliferation, thus fall into a good prognosis category, and exhibit significant changes in steroid metabolism.
Collapse
Affiliation(s)
- Wei Tang
- Laboratory of Human Carcinogenesis, Center for Cancer Research (CCR), NCI, NIH, Bethesda, Maryland
| | - Vasanta Putluri
- Department of Molecular and Cellular Biology, Verna and Marrs McLean Department of Biochemistry and Alkek Center for Molecular Discovery, Baylor College of Medicine, Houston, Texas
| | - Chandrashekar R Ambati
- Department of Molecular and Cellular Biology, Verna and Marrs McLean Department of Biochemistry and Alkek Center for Molecular Discovery, Baylor College of Medicine, Houston, Texas
| | - Tiffany H Dorsey
- Laboratory of Human Carcinogenesis, Center for Cancer Research (CCR), NCI, NIH, Bethesda, Maryland
| | - Nagireddy Putluri
- Department of Molecular and Cellular Biology, Verna and Marrs McLean Department of Biochemistry and Alkek Center for Molecular Discovery, Baylor College of Medicine, Houston, Texas.
| | - Stefan Ambs
- Laboratory of Human Carcinogenesis, Center for Cancer Research (CCR), NCI, NIH, Bethesda, Maryland.
| |
Collapse
|
48
|
Zhang A, Li A, He J, Wang M. LSCDFS-MKL: A multiple kernel based method for lung squamous cell carcinomas disease-free survival prediction with pathological and genomic data. J Biomed Inform 2019; 94:103194. [PMID: 31048071 DOI: 10.1016/j.jbi.2019.103194] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2018] [Revised: 04/14/2019] [Accepted: 04/29/2019] [Indexed: 11/18/2022]
Abstract
Lung squamous cell carcinoma (SCC) is a fatal disease in both male and female, for which current treatments are inadequate. Surgical resection is regarded as the cornerstone of treatment for patients with lung SCC, but even for the same stage patients, the wide spectrum of disease-free survival (DFS) times exits. Therefore, how to improve the DFS prediction performance of lung SCC becomes one major research area. In this study, we proposed a novel method called LSCDFS-MKL, which was on the basis of multiple kernel learning to predict DFS of lung SCC. In LSCDFS-MKL, we first efficiently integrated pathological images and genomic data (copy number aberration, gene expression, protein expression) from lung SCC. The results of LSCDFS-MKL between different types of data show that the features extracted from pathological images play an important role in DFS prediction of lung SCC. Then we compared our method LSCDFS-MKL with other existing methods and performance analysis indicates that LSCDFS-MKL has a significantly better performance than other prediction methods. After that, we applied the proposed method on different stage stratums and the performance demonstrates that LSCDFS-MKL remains efficient in DFS prediction of lung SCC patients. Finally, we performed LSCDFS-MKL on an independent validation dataset and the accuracy of DFS prediction achieves 100%, which is promising.
Collapse
Affiliation(s)
- Aoshuang Zhang
- School of Information Science and Technology, University of Science and Technology of China, 443 Huangshan Road, Hefei 230027, China.
| | - Ao Li
- School of Information Science and Technology, University of Science and Technology of China, 443 Huangshan Road, Hefei 230027, China; Research Centers for Biomedical Engineering, University of Science and Technology of China, 443 Huangshan Road, Hefei 230027, China.
| | - Jie He
- Department of Pathology, The First Affiliated Hospital of University of Science and Technology of China, Hefei 230031, China; Department of Pathology, Anhui Provincial Cancer Hospital, Hefei 230031, China.
| | - Minghui Wang
- School of Information Science and Technology, University of Science and Technology of China, 443 Huangshan Road, Hefei 230027, China; Research Centers for Biomedical Engineering, University of Science and Technology of China, 443 Huangshan Road, Hefei 230027, China.
| |
Collapse
|
49
|
Xiao Z, Yan Y, Zhou Q, Liu H, Huang P, Zhou Q, Lai C, Zhang J, Wang J, Mao K. Development and external validation of prognostic nomograms in hepatocellular carcinoma patients: a population based study. Cancer Manag Res 2019; 11:2691-2708. [PMID: 31118768 PMCID: PMC6489568 DOI: 10.2147/cmar.s191287] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2018] [Accepted: 02/25/2019] [Indexed: 12/14/2022] Open
Abstract
Background: We attempted to construct and validate novel nomograms to predict overall survival (OS) and cancer-specific survival (CSS) in patients with hepatocellular carcinoma (HCC). Methods: Models were established using a discovery set (n=10,262) obtained from the Surveillance, Epidemiology, and End Results (SEER) database. Based on univariate and multivariate Cox regression analyses, we identified independent risk factors for OS and CSS. Concordance indexes (c-indexes) and calibration plots were used to evaluate model discrimination. The predictive accuracy and clinical values of the nomograms were measured by decision curve analysis (DCA). Results: Our OS nomogram with a c-index of 0.753 (95% confidence interval (CI), 0.745–0.761) was based on age, sex, race, marital status, histological grade, TNM stage, tumor size, and surgery performed, and it performed better than TNM stage. Our CSS nomogram had a c-index of 0.748 (95% CI, 0.740–0.756). The calibration curves fit well. DCA showed that the two nomograms provided substantial clinical value. Internal validation produced c-indexes of 0.758 and 0.752 for OS and CSS, respectively, while external validation in the Sun Yat-sen Memorial Hospital (SYMH) cohort produced a c-indexes of 0.702 and 0.686 for OS and CSS, respectively. Conclusions: We have developed nomograms that enable more accurate individualized predictions of OS and CSS to help doctors better formulate individual treatment and follow-up management strategies.
Collapse
Affiliation(s)
- Zhiyu Xiao
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China.,Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China
| | - Yongcong Yan
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China.,Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China
| | - Qianlei Zhou
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China.,Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China
| | - Haohan Liu
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China.,Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China
| | - Pinbo Huang
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China.,Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China
| | - Qiming Zhou
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China.,Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China
| | - Changliang Lai
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China.,Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China
| | - Jianlong Zhang
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China.,Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China
| | - Jie Wang
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China.,Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China
| | - Kai Mao
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China.,Department of Hepatobiliary Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou 510120, People's Republic of China
| |
Collapse
|
50
|
Mubeen S, Hoyt CT, Gemünd A, Hofmann-Apitius M, Fröhlich H, Domingo-Fernández D. The Impact of Pathway Database Choice on Statistical Enrichment Analysis and Predictive Modeling. Front Genet 2019. [PMID: 31824580 DOI: 10.3389/fgene.2019.01203/bibtex] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/06/2023] Open
Abstract
Pathway-centric approaches are widely used to interpret and contextualize -omics data. However, databases contain different representations of the same biological pathway, which may lead to different results of statistical enrichment analysis and predictive models in the context of precision medicine. We have performed an in-depth benchmarking of the impact of pathway database choice on statistical enrichment analysis and predictive modeling. We analyzed five cancer datasets using three major pathway databases and developed an approach to merge several databases into a single integrative one: MPath. Our results show that equivalent pathways from different databases yield disparate results in statistical enrichment analysis. Moreover, we observed a significant dataset-dependent impact on the performance of machine learning models on different prediction tasks. In some cases, MPath significantly improved prediction performance and also reduced the variance of prediction performances. Furthermore, MPath yielded more consistent and biologically plausible results in statistical enrichment analyses. In summary, this benchmarking study demonstrates that pathway database choice can influence the results of statistical enrichment analysis and predictive modeling. Therefore, we recommend the use of multiple pathway databases or integrative ones.
Collapse
Affiliation(s)
- Sarah Mubeen
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
| | - Charles Tapley Hoyt
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
| | - André Gemünd
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany
| | - Martin Hofmann-Apitius
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
| | - Holger Fröhlich
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
| | - Daniel Domingo-Fernández
- Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing (SCAI), Sankt Augustin, Germany
- Bonn-Aachen International Center for IT, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
| |
Collapse
|