|
1
|
Kato M, Nishino J, Nagai M, Rokutan H, Narushima D, Ono H, Hasegawa T, Imoto S, Matsui S, Tsunoda T, Shibata T. Comprehensive analysis of prognosis markers with molecular features derived from pan-cancer whole-genome sequences. Hum Genomics 2025; 19:39. [PMID: 40221813 PMCID: PMC11993945 DOI: 10.1186/s40246-025-00744-7] [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] [Received: 09/30/2024] [Accepted: 03/19/2025] [Indexed: 04/14/2025] Open
Abstract
Cancer prognosis markers are useful for treatment decisions; however, the omics-level landscape is not well understood across multiple cancer types. Pan-Cancer Analysis of Whole Genomes (PCAWG) provides unprecedented access to various types of molecular data, ranging from typical DNA mutations and RNA expressions to more deeply analyzed or whole-genomic features, such as HLA haplotypes and structural variations. We analyzed the PCAWG data of 13 cancer types from 1,514 patients to identify prognosis markers belonging to 17 molecular features in the survival analysis based on the Cox and Lasso regression methods. We found that germline features including HLA haplotypes, neoantigens, and the number of structural variations were associated with overall survival; however, mutational signatures were not. Measuring a few markers provided a sufficient prognostic performance evaluated by c-index for each cancer type. DNA markers demonstrated better or comparable prognostic performance compared to RNA markers in some cancer types. "Universal" markers strongly associated with overall survival across cancer types were not identified. These findings will give insights into the clinical implementation of prognosis markers.
Collapse
Affiliation(s)
- Mamoru Kato
- Division of Bioinformatics, Research Institute, National Cancer Center Japan, Tokyo, Japan.
- CREST, JST, Tokyo, Japan.
| | - Jo Nishino
- Division of Bioinformatics, Research Institute, National Cancer Center Japan, Tokyo, Japan
- CREST, JST, Tokyo, Japan
| | - Momoko Nagai
- Division of Bioinformatics, Research Institute, National Cancer Center Japan, Tokyo, Japan
- CREST, JST, Tokyo, Japan
| | - Hirofumi Rokutan
- Division of Cancer Genomics, Research Institute, National Cancer Center Japan, Tokyo, Japan
| | - Daichi Narushima
- Division of Bioinformatics, Research Institute, National Cancer Center Japan, Tokyo, Japan
| | - Hanako Ono
- Division of Bioinformatics, Research Institute, National Cancer Center Japan, Tokyo, Japan
| | - Takanori Hasegawa
- Division of Health Medical Intelligence, Human Genome Center, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan
| | - Seiya Imoto
- Division of Health Medical Intelligence, Human Genome Center, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan
| | - Shigeyuki Matsui
- CREST, JST, Tokyo, Japan
- Department of Biostatistics, Nagoya University Graduate School of Medicine, Nagoya, Japan
| | - Tatsuhiko Tsunoda
- CREST, JST, Tokyo, Japan
- Laboratory for Medical Science Mathematics, Department of Biological Sciences, School of Science, The University of Tokyo, Tokyo, Japan
- Laboratory for Medical Science Mathematics, RIKEN Center for Integrative Medical Sciences, Yokohama, Japan
| | - Tatsuhiro Shibata
- Division of Cancer Genomics, Research Institute, National Cancer Center Japan, Tokyo, Japan
- Laboratory of Molecular Medicine, Human Genome Center, The Institute of Medical Science, The University of Tokyo, Tokyo, Japan
| |
Collapse
|
|
2
|
Tran D, Nguyen H, Pham VD, Nguyen P, Nguyen Luu H, Minh Phan L, Blair DeStefano C, Jim Yeung SC, Nguyen T. A comprehensive review of cancer survival prediction using multi-omics integration and clinical variables. Brief Bioinform 2025; 26:bbaf150. [PMID: 40221959 PMCID: PMC11994034 DOI: 10.1093/bib/bbaf150] [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] [Received: 10/27/2024] [Revised: 01/29/2025] [Accepted: 03/19/2025] [Indexed: 04/15/2025] Open
Abstract
Cancer is an umbrella term that includes a wide spectrum of disease severity, from those that are malignant, metastatic, and aggressive to benign lesions with very low potential for progression or death. The ability to prognosticate patient outcomes would facilitate management of various malignancies: patients whose cancer is likely to advance quickly would receive necessary treatment that is commensurate with the predicted biology of the disease. Former prognostic models based on clinical variables (age, gender, cancer stage, tumor grade, etc.), though helpful, cannot account for genetic differences, molecular etiology, tumor heterogeneity, and important host biological mechanisms. Therefore, recent prognostic models have shifted toward the integration of complementary information available in both molecular data and clinical variables to better predict patient outcomes: vital status (overall survival), metastasis (metastasis-free survival), and recurrence (progression-free survival). In this article, we review 20 survival prediction approaches that integrate multi-omics and clinical data to predict patient outcomes. We discuss their strategies for modeling survival time (continuous and discrete), the incorporation of molecular measurements and clinical variables into risk models (clinical and multi-omics data), how to cope with censored patient records, the effectiveness of data integration techniques, prediction methodologies, model validation, and assessment metrics. The goal is to inform life scientists of available resources, and to provide a complete review of important building blocks in survival prediction. At the same time, we thoroughly describe the pros and cons of each methodology, and discuss in depth the outstanding challenges that need to be addressed in future method development.
Collapse
Affiliation(s)
- Dao Tran
- Department of Computer Science and Software Engineering, Auburn University, 345 W Magnolia Avenue, Auburn, AL 36849, United States
| | - Ha Nguyen
- Department of Computer Science and Software Engineering, Auburn University, 345 W Magnolia Avenue, Auburn, AL 36849, United States
| | - Van-Dung Pham
- Department of Computer Science and Software Engineering, Auburn University, 345 W Magnolia Avenue, Auburn, AL 36849, United States
| | - Phuong Nguyen
- Department of Computer Science and Software Engineering, Auburn University, 345 W Magnolia Avenue, Auburn, AL 36849, United States
| | - Hung Nguyen Luu
- UPMC Hillman Cancer Center, University of Pittsburgh Medical Center, 5150 Centre Avenue, Pittsburgh, PA 15232, United States
- Department of Epidemiology, School of Public Health, University of Pittsburgh, 130 De Soto Street, Pittsburgh, PA 15261, United States
| | - Liem Minh Phan
- David Grant USAF Medical Center—Clinical Investigation Facility, 60 Medical Group, Defense Health Agency, 101 Bodin Circle, Travis Air Force Base, CA 94535, United States
| | - Christin Blair DeStefano
- Walter Reed National Military Medical Center, Defense Health Agency, 8901 Rockville Pike, Bethesda, MD 20889, United States
| | - Sai-Ching Jim Yeung
- Department of Emergency Medicine, The University of Texas MD Anderson Cancer Center, 1400 Pressler Street, Houston, TX 77030, United States
| | - Tin Nguyen
- Department of Computer Science and Software Engineering, Auburn University, 345 W Magnolia Avenue, Auburn, AL 36849, United States
| |
Collapse
|
|
3
|
Kuras M, Betancourt LH, Hong R, Szadai L, Rodriguez J, Horvatovich P, Pla I, Eriksson J, Szeitz B, Deszcz B, Welinder C, Sugihara Y, Ekedahl H, Baldetorp B, Ingvar C, Lundgren L, Lindberg H, Oskolas H, Horvath Z, Rezeli M, Gil J, Appelqvist R, Kemény LV, Malm J, Sanchez A, Szasz AM, Pawłowski K, Wieslander E, Fenyö D, Nemeth IB, Marko-Varga G. Proteogenomic Profiling of Treatment-Naïve Metastatic Malignant Melanoma. Cancers (Basel) 2025; 17:832. [PMID: 40075679 PMCID: PMC11899103 DOI: 10.3390/cancers17050832] [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: 01/24/2025] [Accepted: 02/12/2025] [Indexed: 03/14/2025] Open
Abstract
BACKGROUND Melanoma is a highly heterogeneous disease, and a deeper molecular classification is essential for improving patient stratification and treatment approaches. Here, we describe the histopathology-driven proteogenomic landscape of 142 treatment-naïve metastatic melanoma samples to uncover molecular subtypes and clinically relevant biomarkers. METHODS We performed an integrative proteogenomic analysis to identify proteomic subtypes, assess the impact of BRAF V600 mutations, and study the molecular profiles and cellular composition of the tumor microenvironment. Clinical and histopathological data were used to support findings related to tissue morphology, disease progression, and patient outcomes. RESULTS Our analysis revealed five distinct proteomic subtypes that integrate immune and stromal microenvironment components and correlate with clinical and histopathological parameters. We demonstrated that BRAF V600-mutated melanomas exhibit biological heterogeneity, where an oncogene-induced senescence-like phenotype is associated with improved survival. This led to a proposed mortality risk-based stratification that may contribute to more personalized treatment strategies. Furthermore, tumor microenvironment composition strongly correlated with disease progression and patient outcomes, highlighting a histopathological connective tissue-to-tumor ratio assessment as a potential decision-making tool. We identified a melanoma-associated SAAV signature linked to extracellular matrix remodeling and SAAV-derived neoantigens as potential targets for anti-tumor immune responses. CONCLUSIONS This study provides a comprehensive stratification of metastatic melanoma, integrating proteogenomic insights with histopathological features. The findings may aid in the development of tailored diagnostic and therapeutic strategies, improving patient management and outcomes.
Collapse
Affiliation(s)
- Magdalena Kuras
- Department of Translational Medicine, Lund University, Skåne University Hospital Malmö, 214 28 Malmö, Sweden; (M.K.); (J.G.); (J.M.); (A.S.); (K.P.)
- Department of Biomedical Engineering, Lund University, 221 00 Lund, Sweden; (P.H.); (I.P.); (J.E.); (Y.S.); (H.L.); (M.R.); (R.A.); (G.M.-V.)
| | - Lazaro Hiram Betancourt
- Department of Translational Medicine, Lund University, Skåne University Hospital Malmö, 214 28 Malmö, Sweden; (M.K.); (J.G.); (J.M.); (A.S.); (K.P.)
- Department of Clinical Sciences Lund, Division of Oncology, Lund University, 221 00 Lund, Sweden; (C.W.); (B.B.); (L.L.); (H.O.)
| | - Runyu Hong
- Institute for Systems Genetics, NYU Grossman School of Medicine, New York, NY 10016, USA; (R.H.); (D.F.)
- Department of Biochemistry and Molecular Pharmacology, NYU Grossman School of Medicine, New York, NY 10016, USA
| | - Leticia Szadai
- Department of Dermatology and Allergology, University of Szeged, 6720 Szeged, Hungary; (L.S.); (I.B.N.)
| | - Jimmy Rodriguez
- Department of Biochemistry and Biophysics, Karolinska Institute, 171 77 Stockholm, Sweden;
| | - Peter Horvatovich
- Department of Biomedical Engineering, Lund University, 221 00 Lund, Sweden; (P.H.); (I.P.); (J.E.); (Y.S.); (H.L.); (M.R.); (R.A.); (G.M.-V.)
- Department of Analytical Biochemistry, Faculty of Science and Engineering, University of Groningen, 9712 CP Groningen, The Netherlands
| | - Indira Pla
- Department of Biomedical Engineering, Lund University, 221 00 Lund, Sweden; (P.H.); (I.P.); (J.E.); (Y.S.); (H.L.); (M.R.); (R.A.); (G.M.-V.)
| | - Jonatan Eriksson
- Department of Biomedical Engineering, Lund University, 221 00 Lund, Sweden; (P.H.); (I.P.); (J.E.); (Y.S.); (H.L.); (M.R.); (R.A.); (G.M.-V.)
| | - Beáta Szeitz
- Division of Oncology, Department of Internal Medicine and Oncology, Semmelweis University, 1085 Budapest, Hungary
| | - Bartłomiej Deszcz
- Department of Biochemistry and Microbiology, Warsaw University of Life Sciences, 02-787 Warsaw, Poland;
| | - Charlotte Welinder
- Department of Clinical Sciences Lund, Division of Oncology, Lund University, 221 00 Lund, Sweden; (C.W.); (B.B.); (L.L.); (H.O.)
| | - Yutaka Sugihara
- Department of Biomedical Engineering, Lund University, 221 00 Lund, Sweden; (P.H.); (I.P.); (J.E.); (Y.S.); (H.L.); (M.R.); (R.A.); (G.M.-V.)
| | - Henrik Ekedahl
- Department of Clinical Sciences Lund, Division of Oncology, Lund University, 221 00 Lund, Sweden; (C.W.); (B.B.); (L.L.); (H.O.)
- SUS University Hospital Lund, 222 42 Lund, Sweden;
| | - Bo Baldetorp
- Department of Clinical Sciences Lund, Division of Oncology, Lund University, 221 00 Lund, Sweden; (C.W.); (B.B.); (L.L.); (H.O.)
| | - Christian Ingvar
- SUS University Hospital Lund, 222 42 Lund, Sweden;
- Department of Surgery, Clinical Sciences, Lund University, SUS, 221 00 Lund, Sweden
| | - Lotta Lundgren
- Department of Clinical Sciences Lund, Division of Oncology, Lund University, 221 00 Lund, Sweden; (C.W.); (B.B.); (L.L.); (H.O.)
- SUS University Hospital Lund, 222 42 Lund, Sweden;
| | - Henrik Lindberg
- Department of Biomedical Engineering, Lund University, 221 00 Lund, Sweden; (P.H.); (I.P.); (J.E.); (Y.S.); (H.L.); (M.R.); (R.A.); (G.M.-V.)
| | - Henriett Oskolas
- Department of Clinical Sciences Lund, Division of Oncology, Lund University, 221 00 Lund, Sweden; (C.W.); (B.B.); (L.L.); (H.O.)
| | - Zsolt Horvath
- Department of Biomedical Engineering, Lund University, 221 00 Lund, Sweden; (P.H.); (I.P.); (J.E.); (Y.S.); (H.L.); (M.R.); (R.A.); (G.M.-V.)
| | - Melinda Rezeli
- Department of Biomedical Engineering, Lund University, 221 00 Lund, Sweden; (P.H.); (I.P.); (J.E.); (Y.S.); (H.L.); (M.R.); (R.A.); (G.M.-V.)
| | - Jeovanis Gil
- Department of Translational Medicine, Lund University, Skåne University Hospital Malmö, 214 28 Malmö, Sweden; (M.K.); (J.G.); (J.M.); (A.S.); (K.P.)
| | - Roger Appelqvist
- Department of Biomedical Engineering, Lund University, 221 00 Lund, Sweden; (P.H.); (I.P.); (J.E.); (Y.S.); (H.L.); (M.R.); (R.A.); (G.M.-V.)
| | - Lajos V. Kemény
- HCEMM-SU Translational Dermatology Research Group, Semmelweis University, 1085 Budapest, Hungary;
- Department of Dermatology, Venereology and Dermatooncology, Faculty of Medicine, Semmelweis University, 1085 Budapest, Hungary
- Department of Physiology, Faculty of Medicine, Semmelweis University, 1085 Budapest, Hungary
- MTA-SE Lendület “Momentum” Dermatology Research Group, Hungarian Academy of Sciences and Semmelweis University, 1085 Budapest, Hungary
| | - Johan Malm
- Department of Translational Medicine, Lund University, Skåne University Hospital Malmö, 214 28 Malmö, Sweden; (M.K.); (J.G.); (J.M.); (A.S.); (K.P.)
| | - Aniel Sanchez
- Department of Translational Medicine, Lund University, Skåne University Hospital Malmö, 214 28 Malmö, Sweden; (M.K.); (J.G.); (J.M.); (A.S.); (K.P.)
| | | | - Krzysztof Pawłowski
- Department of Translational Medicine, Lund University, Skåne University Hospital Malmö, 214 28 Malmö, Sweden; (M.K.); (J.G.); (J.M.); (A.S.); (K.P.)
- Department of Biochemistry and Microbiology, Warsaw University of Life Sciences, 02-787 Warsaw, Poland;
- Department of Molecular Biology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA
| | - Elisabet Wieslander
- Department of Translational Medicine, Lund University, Skåne University Hospital Malmö, 214 28 Malmö, Sweden; (M.K.); (J.G.); (J.M.); (A.S.); (K.P.)
| | - David Fenyö
- Institute for Systems Genetics, NYU Grossman School of Medicine, New York, NY 10016, USA; (R.H.); (D.F.)
- Department of Biochemistry and Molecular Pharmacology, NYU Grossman School of Medicine, New York, NY 10016, USA
| | - Istvan Balazs Nemeth
- Department of Dermatology and Allergology, University of Szeged, 6720 Szeged, Hungary; (L.S.); (I.B.N.)
| | - György Marko-Varga
- Department of Biomedical Engineering, Lund University, 221 00 Lund, Sweden; (P.H.); (I.P.); (J.E.); (Y.S.); (H.L.); (M.R.); (R.A.); (G.M.-V.)
- Chemical Genomics Global Research Lab, Department of Biotechnology, College of Life Science and Biotechnology, Yonsei University, Seoul 03722, Republic of Korea
- 1st Department of Surgery, Tokyo Medical University, Tokyo 160-8402, Japan
| |
Collapse
|
|
4
|
Zhou Z, Zhang R, Zhou A, Lv J, Chen S, Zou H, Zhang G, Lin T, Wang Z, Zhang Y, Weng S, Han X, Liu Z. Proteomics appending a complementary dimension to precision oncotherapy. Comput Struct Biotechnol J 2024; 23:1725-1739. [PMID: 38689716 PMCID: PMC11058087 DOI: 10.1016/j.csbj.2024.04.044] [Citation(s) in RCA: 5] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2024] [Revised: 04/11/2024] [Accepted: 04/17/2024] [Indexed: 05/02/2024] Open
Abstract
Recent advances in high-throughput proteomic profiling technologies have facilitated the precise quantification of numerous proteins across multiple specimens concurrently. Researchers have the opportunity to comprehensively analyze the molecular signatures in plentiful medical specimens or disease pattern cell lines. Along with advances in data analysis and integration, proteomics data could be efficiently consolidated and employed to recognize precise elementary molecular mechanisms and decode individual biomarkers, guiding the precision treatment of tumors. Herein, we review a broad array of proteomics technologies and the progress and methods for the integration of proteomics data and further discuss how to better merge proteomics in precision medicine and clinical settings.
Collapse
Affiliation(s)
- Zhaokai Zhou
- Department of Interventional Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan 450052, China
- Department of Urology, The First Affiliated Hospital of Zhengzhou University, Henan 450052, China
| | - Ruiqi Zhang
- Department of Interventional Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan 450052, China
| | - Aoyang Zhou
- Department of Interventional Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan 450052, China
| | - Jinxiang Lv
- Department of Gastroenterology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan 450052, China
| | - Shuang Chen
- Center of Reproductive Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan 450052, China
| | - Haijiao Zou
- Center of Reproductive Medicine, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan 450052, China
| | - Ge Zhang
- Department of Cardiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan 450052, China
| | - Ting Lin
- Department of Interventional Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan 450052, China
| | - Zhan Wang
- Department of Urology, The First Affiliated Hospital of Zhengzhou University, Henan 450052, China
| | - Yuyuan Zhang
- Department of Interventional Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan 450052, China
| | - Siyuan Weng
- Department of Interventional Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan 450052, China
| | - Xinwei Han
- Department of Interventional Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan 450052, China
- Interventional Institute of Zhengzhou University, Zhengzhou, Henan 450052, China
- Interventional Treatment and Clinical Research Center of Henan Province, Zhengzhou, Henan 450052, China
| | - Zaoqu Liu
- Department of Interventional Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan 450052, China
- Interventional Institute of Zhengzhou University, Zhengzhou, Henan 450052, China
- Interventional Treatment and Clinical Research Center of Henan Province, Zhengzhou, Henan 450052, China
- Institute of Basic Medical Sciences, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100730, China
| |
Collapse
|
|
5
|
Tolani MA, Zubairu IH, Balarabe K, Awaisu M, Abdullahi M, Adeniji AA, Umar SS, Bello A, Tagawa ST. Barriers and facilitators of the application of precision medicine to the genitourinary cancer care pathway: Perspective from a low- and middle- income country in sub-Saharan Africa. Urol Oncol 2024; 42:411-420. [PMID: 39183140 DOI: 10.1016/j.urolonc.2024.07.014] [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] [Received: 01/19/2024] [Revised: 07/13/2024] [Accepted: 07/19/2024] [Indexed: 08/27/2024]
Abstract
The benefit of the delivery of the right form of cancer care, tailored to the right patient, at the right time is increasingly being recognized in the global oncology community. Information on the role and feasible potential of precision oncology during the management of genitourinary cancer in Nigeria, the most populous country in Africa, is limited. This article, therefore, describes the present application of personalized medicine in Nigeria and its barriers and facilitators. It provided granular details on manpower distribution and epidemiological disparities. It also explored the use of clinical and biological markers for screening and early diagnosis, the application of team science to support genomic profiling, cost-effective approaches for image-based phenotypic precision oncology, the emerging role of molecular imaging, access to clinical trials; and their potential to support data driven diagnosis, treatment decision and care availability in order to address gaps in genitourinary cancer management in the country.
Collapse
Affiliation(s)
- Musliu Adetola Tolani
- College of Medicine, Ahmadu Bello University, Zaria, Nigeria; Division of Urology, Department of Surgery, Ahmadu Bello University Teaching Hospital, Zaria, Nigeria.
| | - Ismail Hadi Zubairu
- College of Medicine, Ahmadu Bello University, Zaria, Nigeria; Honourable Mukhtar Aliyu Betara Centre of Excellence in Oncology, Ahmadu Bello University Teaching Hospital, Zaria, Nigeria
| | - Kabir Balarabe
- College of Medicine, Ahmadu Bello University, Zaria, Nigeria; Department of Pathology, Ahmadu Bello University Teaching Hospital, Zaria, Nigeria
| | - Mudi Awaisu
- College of Medicine, Ahmadu Bello University, Zaria, Nigeria; Division of Urology, Department of Surgery, Ahmadu Bello University Teaching Hospital, Zaria, Nigeria
| | - Mubarak Abdullahi
- College of Medicine, Ahmadu Bello University, Zaria, Nigeria; Department of Radiology, Ahmadu Bello University Teaching Hospital, Zaria, Nigeria
| | | | - Shehu Salihu Umar
- College of Medicine, Ahmadu Bello University, Zaria, Nigeria; Honourable Mukhtar Aliyu Betara Centre of Excellence in Oncology, Ahmadu Bello University Teaching Hospital, Zaria, Nigeria
| | - Ahmad Bello
- College of Medicine, Ahmadu Bello University, Zaria, Nigeria; Division of Urology, Department of Surgery, Ahmadu Bello University Teaching Hospital, Zaria, Nigeria
| | - Scott T Tagawa
- Division of Hematology & Medical Oncology, Weill Cornell Medicine, New York, United States
| |
Collapse
|
|
6
|
Orozco-Castaño C, Mejia-Garcia A, Zambrano Y, Combita AL, Parra-Medina R, Bonilla DA, González A, Odriozola A. Construction of an immune gene expression meta signature to assess the prognostic risk of colorectal cancer patients. ADVANCES IN GENETICS 2024; 112:207-254. [PMID: 39396837 DOI: 10.1016/bs.adgen.2024.08.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/15/2024]
Abstract
Despite recent advancements in colorectal cancer (CRC) treatment, particularly with the introduction of immunotherapy and checkpoint inhibitors, the efficacy of these therapies remains limited to a subset of patients. To address this challenge, our study aimed to develop a prognostic biomarker based on immune-related genes to predict better outcomes in CRC patients and aid in treatment decision-making. We comprehensively analysed immune gene expression signatures associated with CRC prognosis to construct an immune meta-signature with prognostic potential. Utilising data from The Cancer Genome Atlas (TCGA), we employed Cox regression to identify immune-related genes with prognostic significance from multiple studies. Subsequently, we compared the expression levels of immune genes, levels of immune cell infiltration, and various immune-related molecules between high-risk and low-risk patient groups. Functional analysis using Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathway analyses provided insights into the biological pathways associated with the identified prognostic genes. Finally, we validated our findings using a separate CRC cohort from the Gene Expression Omnibus (GEO). Integration of the prognostic genes revealed significant disparities in survival outcomes. Differential expression analysis identified a set of immune-associated genes, which were further refined using LASSO penalisation and Cox regression. Univariate Cox regression analyses confirmed the autonomy of the gene signature as a prognostic indicator for CRC patient survival. Our risk prediction model effectively stratified CRC patients based on their prognosis, with the high-risk group showing enrichment in pro-oncogenic terms and pathways. Immune infiltration analysis revealed an augmented presence of certain immunosuppressive subsets in the high-risk group. Finally, we validated the performance of our prognostic model by applying the risk score equation to a different CRC patient dataset, confirming its prognostic potential in this new cohort. Overall, our study presents a novel immune-related gene signature with promising implications for predicting cancer progression and prognosis, thereby enabling more personalised management strategies for CRC patients.
Collapse
Affiliation(s)
- Carlos Orozco-Castaño
- Grupo de Investigación en Biología del Cáncer, Instituto Nacional de Cancerología (INC), Bogotá, Colombia; Grupo de Apoyo y Seguimiento para la Investigación GASPI, Instituto Nacional de Cancerología (INC), Bogotá, Colombia.
| | - Alejandro Mejia-Garcia
- Department of Human Genetics, McGill University, Montreal, QC, Canada, McGill University, Genome Centre, Montreal, QC, Canada
| | - Yina Zambrano
- Grupo de Investigación en Biología del Cáncer, Instituto Nacional de Cancerología (INC), Bogotá, Colombia
| | - Alba Lucia Combita
- Grupo de Investigación en Biología del Cáncer, Instituto Nacional de Cancerología (INC), Bogotá, Colombia; Grupo de Apoyo y Seguimiento para la Investigación GASPI, Instituto Nacional de Cancerología (INC), Bogotá, Colombia; Departamento de Microbiología, Facultad de Medicina, Universidad Nacional de Colombia, Bogotá, Colombia
| | - Rafael Parra-Medina
- Research Institute, Fundación Universitaria de Ciencias de la Salud-FUCS, Bogotá, Colombia; Department of Pathology, Instituto Nacional de Cancerología, Electronic address, Bogotá, Colombia
| | - Diego A Bonilla
- Research Division, Dynamical Business & Science Society - DBSS International SAS, Bogotá, Colombia; Hologenomics Research Group, Department of Genetics, Physical Anthropology, and Animal Physiology, University of the Basque Country, Spain
| | - Adriana González
- Hologenomics Research Group, Department of Genetics, Physical Anthropology, and Animal Physiology, University of the Basque Country, Spain
| | - Adrián Odriozola
- Hologenomics Research Group, Department of Genetics, Physical Anthropology, and Animal Physiology, University of the Basque Country, Spain
| |
Collapse
|
|
7
|
Su D, Xiong Y, Wang S, Wei H, Ke J, Li H, Wang T, Zuo Y, Yang L. Structural deep clustering network for stratification of breast cancer patients through integration of somatic mutation profiles. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 242:107808. [PMID: 37716222 DOI: 10.1016/j.cmpb.2023.107808] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/14/2023] [Revised: 08/15/2023] [Accepted: 09/10/2023] [Indexed: 09/18/2023]
Abstract
BACKGROUND AND OBJECTIVE Breast cancer is among of the most malignant tumor that occurs in women and is one of the leading causes of death from gynecologic malignancy worldwide. The high degree of heterogeneity that characterizes breast cancer makes it challenging to devise effective therapeutic strategies. Accumulating evidence highlights the crucial role of stratifying breast cancer patients into clinically significant subtypes to achieve better prognoses and treatments. The structural deep clustering network is a graph convolutional network-based clustering algorithm that integrates structural information and has achieved state-of-the-art performance in various applications. METHODS In this study, we employed structural deep clustering network to integrate somatic mutation profiles for stratifying 2526 breast cancer patients from the Memorial Sloan Kettering Cancer Center into two clinically differentiable subtypes. RESULTS Breast cancer patients in cluster 1 exhibited better prognosis than breast cancer patients in cluster 2, and the difference between them was statistically significant. The immunogenomic landscape further demonstrated that cluster 1 was associated with remarkable infiltration of the tumor infiltrating lymphocytes. The clustering subtype could be used to evaluate the therapeutic benefit of immunotherapy and chemotherapy in breast cancer patients. Furthermore, our approach effectively classified patients from eight different cancer types, demonstrating its generalizability. CONCLUSIONS Our study represents a step towards a generic methodology for classifying cancer patients using only somatic mutation data and structural deep clustering network approaches. Employing structural deep clustering network to identify breast cancer subtypes is promising and can inform the development of more accurate and personalized therapies.
Collapse
Affiliation(s)
- Dongqing Su
- College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, 150081, China
| | - Yuqiang Xiong
- College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, 150081, China
| | - Shiyuan Wang
- College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, 150081, China
| | - Haodong Wei
- College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, 150081, China
| | - Jiawei Ke
- College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, 150081, China
| | - Honghao Li
- College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, 150081, China
| | - Tao Wang
- College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, 150081, China
| | - Yongchun Zuo
- The State Key Laboratory of Reproductive Regulation and Breeding of Grassland Livestock, College of Life Sciences, Inner Mongolia University, Hohhot, 010070, China; Digital College, Inner Mongolia Intelligent Union Big Data Academy, Inner Mongolia Wesure Date Technology Co., Ltd. Hohhot, 010010, China; Inner Mongolia International Mongolian Hospital, Hohhot 010065, China
| | - Lei Yang
- College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, 150081, China.
| |
Collapse
|
|
8
|
Zhang Z, Wei Z, Zhao L, Gu C, Meng Y. Assessing the clinical utility of multi-omics data for predicting serous ovarian cancer prognosis. J OBSTET GYNAECOL 2023; 43:2171778. [PMID: 36803381 DOI: 10.1080/01443615.2023.2171778] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/23/2023]
Abstract
Ovarian cancer (OC) is characterised by heterogeneity that complicates the prediction of patient survival and treatment outcomes. Here, we conducted analyses to predict the prognosis of patients from the Genomic Data Commons database and validated the predictions by fivefold cross-validation and by using an independent dataset in the International Cancer Genome Consortium database. We analysed the somatic DNA mutation, mRNA expression, DNA methylation, and microRNA expression data of 1203 samples from 599 serous ovarian cancer (SOC) patients. We found that principal component transformation (PCT) improved the predictive performance of the survival and therapeutic models. Deep learning algorithms also showed better predictive power than the decision tree (DT) and random forest (RF). Furthermore, we identified a series of molecular features and pathways that are associated with patient survival and treatment outcomes. Our study provides perspective on building reliable prognostic and therapeutic strategies and further illuminates the molecular mechanisms of SOC.Impact statementWhat is already known on this subject? Recent studies have focussed on predicting cancer outcomes based on omics data. But the limitation is the performance of single-platform genomic analyses or the small numbers of genomic analyses.What do the results of this study add? We analysed multi-omics data, found that principal component transformation (PCT) significantly improved the predictive performance of the survival and therapeutic models. Deep learning algorithms also showed better predictive power than did decision tree (DT) and random forest (RF). Furthermore, we identified a series of molecular features and pathways that are associated with patient survival and treatment outcomes.What are the implications of these findings for clinical practice and/or further research? Our study provides perspective on how to build reliable prognostic and therapeutic strategies and further illuminates the molecular mechanisms of SOC for future studies.
Collapse
Affiliation(s)
- Zhe Zhang
- Department of Obstetrics and Gynecology, Seventh Medical Center of Chinese, PLA General Hospital, Beijing, P.R. China
| | - Zhiyao Wei
- Department of Obstetrics and Gynecology, Seventh Medical Center of Chinese, PLA General Hospital, Beijing, P.R. China
| | - Luyang Zhao
- Department of Obstetrics and Gynecology, Seventh Medical Center of Chinese, PLA General Hospital, Beijing, P.R. China
| | - Chenglei Gu
- Department of Obstetrics and Gynecology, Seventh Medical Center of Chinese, PLA General Hospital, Beijing, P.R. China
| | - Yuanguang Meng
- Department of Obstetrics and Gynecology, Seventh Medical Center of Chinese, PLA General Hospital, Beijing, P.R. China
| |
Collapse
|
|
9
|
Yuan D, Zhu H, Wang T, Zhang Y, Zheng X, Qu Y. Development and validation of an individualized gene expression-based signature to predict overall survival of patients with high-grade serous ovarian carcinoma. Eur J Med Res 2023; 28:465. [PMID: 37884970 PMCID: PMC10604403 DOI: 10.1186/s40001-023-01376-0] [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] [Received: 03/23/2023] [Accepted: 09/18/2023] [Indexed: 10/28/2023] Open
Abstract
BACKGROUND High-grade serious ovarian carcinoma (HGSOC) is a subtype of ovarian cancer with a different prognosis attributable to genetic heterogeneity. The prognosis of patients with advanced HGSOC requires prediction by genetic markers. This study systematically analyzed gene expression profile data to establish a genetic marker for predicting HGSOC prognosis. METHODS The RNA-seq data set and information on clinical follow-up of HGSOC were retrieved from Gene Expression Omnibus (GEO) database, and the data were standardized by DESeq2 as a training set. On the other hand, HGSOC RNA sequence data and information on clinical follow-up were retrieved from The Cancer Genome Atlas (TCGA) as a test set. Additionally, ovarian cancer microarray data set was obtained from GEO as the external validation set. Prognostic genes were screened from the training set, and characteristic selection was performed using the least absolute shrinkage and selection operator (LASSO) with 80% re-sampling for 5000 times. Genes with a frequency of more than 2000 were selected as robust biomarkers. Finally, a gene-related prognostic model was validated in both the test and GEO validation sets. RESULTS A total of 148 genes were found to be significantly correlated with HGSOC prognosis. The expression profile of these genes could stratify HGSOC prognosis and they were enriched to multiple tumor-related regulatory pathways such as tyrosine metabolism and AMPK signaling pathway. AKR1B10 and ANGPT4 were obtained after 5000-time re-sampling by LASSO regression. AKR1B10 was associated with the metastasis and progression of several tumors. In this study, Cox regression analysis was performed to create a 2-gene signature as an independent prognostic factor for HGSOC, which has the ability to stratify risk samples in all three data sets (p < 0.05). The Gene Set Enrichment Analysis (GSEA) discovered abnormally active REGULATION_OF_AUTOPHAGY and OLFACTORY_TRANSDUCTION pathways in the high-risk group samples. CONCLUSION This study resulted in the creation of a 2-gene molecular prognostic classifier that distinguished clinical features and was a promising novel prognostic tool for assessing the prognosis of HGSOC. RiskScore was a novel prognostic model which might be effective in guiding accurate prognosis of HGSOC.
Collapse
Affiliation(s)
- Dandan Yuan
- Department of Obstertrics and Gynecology, The Second Affiliated Hospital of Harbin Medical University, Harbin, 150086, China
| | - Hong Zhu
- Department of Gynecological Oncology, Renji Hospital Affiliated to Medical College of Shanghai Jiaotong University, Shanghai, 200000, China
| | - Ting Wang
- Department of Hepatological Surgery, The Third Affiliated Hospital of Harbin Medical University, Harbin, 150001, China
| | - Yang Zhang
- Department of Obstertrics and Gynecology, The Second Affiliated Hospital of Harbin Medical University, Harbin, 150086, China
| | - Xin Zheng
- Department of Gynecology, The First Hospital of Jiaxing City, Jiaxing, 314000, China
| | - Yanjun Qu
- Department of Obstertrics and Gynecology, The First Affiliated Hospital of Harbin Medical University, Harbin, 150001, China.
| |
Collapse
|
|
10
|
Kalocsay M, Berberich MJ, Everley RA, Nariya MK, Chung M, Gaudio B, Victor C, Bradshaw GA, Eisert RJ, Hafner M, Sorger PK, Mills CE, Subramanian K. Proteomic profiling across breast cancer cell lines and models. Sci Data 2023; 10:514. [PMID: 37542042 PMCID: PMC10403526 DOI: 10.1038/s41597-023-02355-0] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/11/2021] [Accepted: 07/03/2023] [Indexed: 08/06/2023] Open
Abstract
We performed quantitative proteomics on 60 human-derived breast cancer cell line models to a depth of ~13,000 proteins. The resulting high-throughput datasets were assessed for quality and reproducibility. We used the datasets to identify and characterize the subtypes of breast cancer and showed that they conform to known transcriptional subtypes, revealing that molecular subtypes are preserved even in under-sampled protein feature sets. All datasets are freely available as public resources on the LINCS portal. We anticipate that these datasets, either in isolation or in combination with complimentary measurements such as genomics, transcriptomics and phosphoproteomics, can be mined for the purpose of predicting drug response, informing cell line specific context in models of signalling pathways, and identifying markers of sensitivity or resistance to therapeutics.
Collapse
Affiliation(s)
- Marian Kalocsay
- Laboratory of Systems Pharmacology, Program in Therapeutic Science, Harvard Medical School, Boston, MA, 02115, USA
- Department of Experimental Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, 77030, USA
| | - Matthew J Berberich
- Laboratory of Systems Pharmacology, Program in Therapeutic Science, Harvard Medical School, Boston, MA, 02115, USA
| | - Robert A Everley
- Laboratory of Systems Pharmacology, Program in Therapeutic Science, Harvard Medical School, Boston, MA, 02115, USA
| | - Maulik K Nariya
- Laboratory of Systems Pharmacology, Program in Therapeutic Science, Harvard Medical School, Boston, MA, 02115, USA
- IGBMC, Strasbourg, Grand Est, France
| | - Mirra Chung
- Laboratory of Systems Pharmacology, Program in Therapeutic Science, Harvard Medical School, Boston, MA, 02115, USA
| | - Benjamin Gaudio
- Laboratory of Systems Pharmacology, Program in Therapeutic Science, Harvard Medical School, Boston, MA, 02115, USA
| | - Chiara Victor
- Laboratory of Systems Pharmacology, Program in Therapeutic Science, Harvard Medical School, Boston, MA, 02115, USA
| | - Gary A Bradshaw
- Laboratory of Systems Pharmacology, Program in Therapeutic Science, Harvard Medical School, Boston, MA, 02115, USA
| | - Robyn J Eisert
- Laboratory of Systems Pharmacology, Program in Therapeutic Science, Harvard Medical School, Boston, MA, 02115, USA
| | - Marc Hafner
- Laboratory of Systems Pharmacology, Program in Therapeutic Science, Harvard Medical School, Boston, MA, 02115, USA
- Department of Oncology Bioinformatics, Genentech, Inc., South San Francisco, CA, 94080, USA
| | - Peter K Sorger
- Laboratory of Systems Pharmacology, Program in Therapeutic Science, Harvard Medical School, Boston, MA, 02115, USA.
| | - Caitlin E Mills
- Laboratory of Systems Pharmacology, Program in Therapeutic Science, Harvard Medical School, Boston, MA, 02115, USA.
| | - Kartik Subramanian
- Laboratory of Systems Pharmacology, Program in Therapeutic Science, Harvard Medical School, Boston, MA, 02115, USA.
- Bristol Myers Squibb, Cambridge, MA, 02142, USA.
| |
Collapse
|
|
11
|
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
|
|
12
|
Hou X, Ma B, Liu M, Zhao Y, Chai B, Pan J, Wang P, Li D, Liu S, Song F. The transcriptional risk scores for kidney renal clear cell carcinoma using XGBoost and multiple omics data. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2023; 20:11676-11687. [PMID: 37501415 DOI: 10.3934/mbe.2023519] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/29/2023]
Abstract
Most kidney cancers are kidney renal clear cell carcinoma (KIRC) that is a main cause of cancer-related deaths. Polygenic risk score (PRS) is a weighted linear combination of phenotypic related alleles on the genome that can be used to assess KIRC risk. However, standalone SNP data as input to the PRS model may not provide satisfactory result. Therefore, Transcriptional risk scores (TRS) based on multi-omics data and machine learning models were proposed to assess the risk of KIRC. First, we collected four types of multi-omics data (DNA methylation, miRNA, mRNA and lncRNA) of KIRC patients from the TCGA database. Subsequently, a novel TRS method utilizing multiple omics data and XGBoost model was developed. Finally, we performed prevalence analysis and prognosis prediction to evaluate the utility of the TRS generated by our method. Our TRS methods exhibited better predictive performance than the linear models and other machine learning models. Furthermore, the prediction accuracy of combined TRS model was higher than that of single-omics TRS model. The KM curves showed that TRS was a valid prognostic indicator for cancer staging. Our proposed method extended the current definition of TRS from standalone SNP data to multi-omics data and was superior to the linear models and other machine learning models, which may provide a useful implement for diagnostic and prognostic prediction of KIRC.
Collapse
Affiliation(s)
- Xiaoyu Hou
- School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China
| | - Baoshan Ma
- School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China
| | - Ming Liu
- Physical Department of Science and Technology, Dalian University, Dalian 116622, China
| | - Yuxuan Zhao
- School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China
| | - Bingjie Chai
- School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China
| | - Jianqiao Pan
- School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China
| | - Pengcheng Wang
- Department of Mechanical Engineering, University of Houston, Houston 77204, USA
| | - Di Li
- Department of Neuro Intervention, Dalian Medical University affiliated Dalian Municipal Central Hospital, Dalian 116033, China
| | - Shuxin Liu
- Department of Nephrology, Dalian Medical University affiliated Dalian Municipal Central Hospital, Dalian 116033, China
| | - Fengju Song
- Department of Epidemiology and Biostatistics, Key Laboratory of Molecular Cancer Epidemiology, Tianjin, National Clinical Research Center of Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin 300060, China
| |
Collapse
|
|
13
|
Fan L, Sowmya A, Meijering E, Song Y. Cancer Survival Prediction From Whole Slide Images With Self-Supervised Learning and Slide Consistency. IEEE TRANSACTIONS ON MEDICAL IMAGING 2023; 42:1401-1412. [PMID: 37015696 DOI: 10.1109/tmi.2022.3228275] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/04/2023]
Abstract
Histopathological Whole Slide Images (WSIs) at giga-pixel resolution are the gold standard for cancer analysis and prognosis. Due to the scarcity of pixel- or patch-level annotations of WSIs, many existing methods attempt to predict survival outcomes based on a three-stage strategy that includes patch selection, patch-level feature extraction and aggregation. However, the patch features are usually extracted by using truncated models (e.g. ResNet) pretrained on ImageNet without fine-tuning on WSI tasks, and the aggregation stage does not consider the many-to-one relationship between multiple WSIs and the patient. In this paper, we propose a novel survival prediction framework that consists of patch sampling, feature extraction and patient-level survival prediction. Specifically, we employ two kinds of self-supervised learning methods, i.e. colorization and cross-channel, as pretext tasks to train convnet-based models that are tailored for extracting features from WSIs. Then, at the patient-level survival prediction we explicitly aggregate features from multiple WSIs, using consistency and contrastive losses to normalize slide-level features at the patient level. We conduct extensive experiments on three large-scale datasets: TCGA-GBM, TCGA-LUSC and NLST. Experimental results demonstrate the effectiveness of our proposed framework, as it achieves state-of-the-art performance in comparison with previous studies, with concordance index of 0.670, 0.679 and 0.711 on TCGA-GBM, TCGA-LUSC and NLST, respectively.
Collapse
|
|
14
|
Hédou J, Marić I, Bellan G, Einhaus J, Gaudillière DK, Ladant FX, Verdonk F, Stelzer IA, Feyaerts D, Tsai AS, Ganio EA, Sabayev M, Gillard J, Bonham TA, Sato M, Diop M, Angst MS, Stevenson D, Aghaeepour N, Montanari A, Gaudillière B. Stabl: sparse and reliable biomarker discovery in predictive modeling of high-dimensional omic data. RESEARCH SQUARE 2023:rs.3.rs-2609859. [PMID: 36909508 PMCID: PMC10002850 DOI: 10.21203/rs.3.rs-2609859/v1] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/06/2023]
Abstract
High-content omic technologies coupled with sparsity-promoting regularization methods (SRM) have transformed the biomarker discovery process. However, the translation of computational results into a clinical use-case scenario remains challenging. A rate-limiting step is the rigorous selection of reliable biomarker candidates among a host of biological features included in multivariate models. We propose Stabl, a machine learning framework that unifies the biomarker discovery process with multivariate predictive modeling of clinical outcomes by selecting a sparse and reliable set of biomarkers. Evaluation of Stabl on synthetic datasets and four independent clinical studies demonstrates improved biomarker sparsity and reliability compared to commonly used SRMs at similar predictive performance. Stabl readily extends to double- and triple-omics integration tasks and identifies a sparser and more reliable set of biomarkers than those selected by state-of-the-art early- and late-fusion SRMs, thereby facilitating the biological interpretation and clinical translation of complex multi-omic predictive models. The complete package for Stabl is available online at https://github.com/gregbellan/Stabl.
Collapse
Affiliation(s)
- Julien Hédou
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
| | - Ivana Marić
- Department of Pediatrics, Stanford University, Stanford, CA
| | | | - Jakob Einhaus
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
- Department of Pathology and Neuropathology, University Hospital and Comprehensive Cancer Center Tübingen, Tübingen, Germany
| | - Dyani K. Gaudillière
- Division of Plastic and Reconstructive Surgery, Department of Surgery, Stanford University, Stanford, CA
| | | | - Franck Verdonk
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
- Sorbonne University, GRC 29, AP-HP, DMU DREAM, Department of Anesthesiology and Intensive Care, Hôpital Saint-Antoine, Assistance Publique-Hôpitaux de Paris; Paris, France
| | - Ina A. Stelzer
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
| | - Dorien Feyaerts
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
| | - Amy S. Tsai
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
| | - Edward A. Ganio
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
| | - Maximilian Sabayev
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
| | - Joshua Gillard
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
| | - Thomas A. Bonham
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
| | - Masaki Sato
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
| | - Maïgane Diop
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
| | - Martin S. Angst
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
| | | | - Nima Aghaeepour
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
- Department of Pediatrics, Stanford University, Stanford, CA
- Department of Biomedical Data Science, Stanford University, Stanford, CA
| | - Andrea Montanari
- Department of Statistics, Stanford University, Stanford, CA
- Department of Electrical Engineering, Stanford University, Stanford, CA
| | - Brice Gaudillière
- Department of Anesthesiology, Perioperative & Pain Medicine, Stanford University, Stanford, CA
- Department of Pediatrics, Stanford University, Stanford, CA
| |
Collapse
|
|
15
|
Carrion J, Nandakumar R, Shi X, Gu H, Kim Y, Raskind WH, Peter B, Dinu V. A data-fusion approach to identifying developmental dyslexia from multi-omics datasets. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.02.27.530280. [PMID: 36909570 PMCID: PMC10002702 DOI: 10.1101/2023.02.27.530280] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/06/2023]
Abstract
This exploratory study tested and validated the use of data fusion and machine learning techniques to probe high-throughput omics and clinical data with a goal of exploring the etiology of developmental dyslexia. Developmental dyslexia is the leading learning disability in school aged children affecting roughly 5-10% of the US population. The complex biological and neurological phenotype of this life altering disability complicates its diagnosis. Phenome, exome, and metabolome data was collected allowing us to fully explore this system from a behavioral, cellular, and molecular point of view. This study provides a proof of concept showing that data fusion and ensemble learning techniques can outperform traditional machine learning techniques when provided small and complex multi-omics and clinical datasets. Heterogenous stacking classifiers consisting of single-omic experts/models achieved an accuracy of 86%, F1 score of 0.89, and AUC value of 0.83. Ensemble methods also provided a ranked list of important features that suggests exome single nucleotide polymorphisms found in the thalamus and cerebellum could be potential biomarkers for developmental dyslexia and heavily influenced the classification of DD within our machine learning models.
Collapse
Affiliation(s)
- Jackson Carrion
- College of Health Solutions, Arizona State University, Phoenix, AZ 85004
| | - Rohit Nandakumar
- College of Health Solutions, Arizona State University, Phoenix, AZ 85004
| | - Xiaojian Shi
- College of Health Solutions, Arizona State University, Phoenix, AZ 85004
- Cellular and Molecular Physiology Department, Yale School of Medicine, New Haven, CT 06510
| | - Haiwei Gu
- College of Health Solutions, Arizona State University, Phoenix, AZ 85004
- Center for Translational Science, Florida International University, Port St. Lucie, FL 34987
| | - Yookyung Kim
- College of Health Solutions, Arizona State University, Phoenix, AZ 85004
| | - Wendy H Raskind
- Department of Medicine/Medical Genetics, University of Washington, Seattle, WA 98105
| | - Beate Peter
- College of Health Solutions, Arizona State University, Phoenix, AZ 85004
| | - Valentin Dinu
- College of Health Solutions, Arizona State University, Phoenix, AZ 85004
| |
Collapse
|
|
16
|
An Integrative Analysis of Nasopharyngeal Carcinoma Genomes Unraveled Unique Processes Driving a Viral-Positive Cancer. Cancers (Basel) 2023; 15:cancers15041243. [PMID: 36831585 PMCID: PMC9953764 DOI: 10.3390/cancers15041243] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2023] [Revised: 02/03/2023] [Accepted: 02/13/2023] [Indexed: 02/18/2023] Open
Abstract
As one of few viral-positive cancers, nasopharyngeal carcinoma (NPC) is extremely rare across the world but very frequent in several regions of the world, including Southern China (known as the Cantonese cancer). Even though several genomic studies have been conducted for NPC, their sample sizes are relatively small and systematic comparison with other cancer types has not been explored. In this study, we collected four-hundred-thirty-one samples from six previous studies and provided the first integrative analysis of NPC genomes. Combining several statistical methods for detecting driver genes, we identified 25 novel drivers for NPC, including ATG14 and NLRC5. Many of these novel drivers are enriched in several important pathways, such as autophagy and immunity. By comparing NPC with many other cancer types, we found NPC is a unique cancer type in which a high proportion of patients (45.2%) do not have any known driver mutations (termed as "missing driver events") but have a preponderance of deletion events, including chromosome 3p deletion. Through signature analysis, we identified many known and novel signatures, including single-base signatures (n = 12), double-base signatures (n = 1), indel signatures (n = 9) and copy number signatures (n = 8). Many of these new signatures are involved in DNA repair and have unknown etiology and genome instability, implying an unprecedented dynamic mutational process possibly driven by complex interactions between viral and host genomes. By combining clinical, molecular and intra-tumor heterogeneity features, we constructed the first integrative survival model for NPC, providing a strong basis for patient prognosis and stratification. Taken together, we have performed one of the first integrative analyses of NPC genomes and brought unique genomic insights into tumorigenesis of a viral-driven cancer.
Collapse
|
|
17
|
Li L, Liang Y, Shao M, Lu S, Liao S, Ouyang D. Self-supervised learning-based Multi-Scale feature Fusion Network for survival analysis from whole slide images. Comput Biol Med 2023; 153:106482. [PMID: 36586231 DOI: 10.1016/j.compbiomed.2022.106482] [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: 10/23/2022] [Revised: 12/16/2022] [Accepted: 12/25/2022] [Indexed: 12/29/2022]
Abstract
Understanding prognosis and mortality is critical for evaluating the treatment plan of patients. Advances in digital pathology and deep learning techniques have made it practical to perform survival analysis in whole slide images (WSIs). Current methods are usually based on a multi-stage framework which includes patch sampling, feature extraction and prediction. However, the random patch sampling strategy is highly unstable and prone to sampling non-ROI. Feature extraction typically relies on hand-crafted features or convolutional neural networks (CNNs) pre-trained on ImageNet, while the artificial error or domain gaps may affect the survival prediction performance. Besides, the limited information representation of local sampling patches will create a bottleneck limitation on the effectiveness of prediction. To address the above challenges, we propose a novel patch sampling strategy based on image information entropy and construct a Multi-Scale feature Fusion Network (MSFN) based on self-supervised feature extractor. Specifically, we adopt image information entropy as a criterion to select representative sampling patches, thereby avoiding the noise interference caused by random to blank regions. Meanwhile, we pretrain the feature extractor utilizing self-supervised learning mechanism to improve the efficiency of feature extraction. Furthermore, a global-local feature fusion prediction network based on the attention mechanism is constructed to improve the survival prediction effect of WSIs with comprehensive multi-scale information representation. The proposed method is validated by adequate experiments and achieves competitive results on both of the most popular WSIs survival analysis datasets, TCGA-GBM and TCGA-LUSC. Code and trained models are made available at: https://github.com/Mercuriiio/MSFN.
Collapse
Affiliation(s)
- Le Li
- Faculty of Innovation Engineering, Macau University of Science and Technology, 999078, Macao Special Administrative Region of China.
| | - Yong Liang
- Peng Cheng Laboratory, Shenzhen, 518055, China.
| | - Mingwen Shao
- College of Computer Science and Technology, China University of Petroleum, Qingdao 266580, China.
| | - Shanghui Lu
- Faculty of Innovation Engineering, Macau University of Science and Technology, 999078, Macao Special Administrative Region of China.
| | - Shuilin Liao
- Faculty of Innovation Engineering, Macau University of Science and Technology, 999078, Macao Special Administrative Region of China.
| | - Dong Ouyang
- Faculty of Innovation Engineering, Macau University of Science and Technology, 999078, Macao Special Administrative Region of China.
| |
Collapse
|
|
18
|
Tarfeen N, Nisa KU, Ali S, Yatoo AM, Shah AM, Sabba A, Maqbool R, Ahmad MB. Utility of proteomics and phosphoproteomics in the tailored medication of cancer. Proteomics 2023. [DOI: 10.1016/b978-0-323-95072-5.00006-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/01/2023]
|
|
19
|
Huang L, Long JP, Irajizad E, Doecke JD, Do KA, Ha MJ. A unified mediation analysis framework for integrative cancer proteogenomics with clinical outcomes. Bioinformatics 2023; 39:6989623. [PMID: 36648331 PMCID: PMC9879726 DOI: 10.1093/bioinformatics/btad023] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2022] [Revised: 11/18/2022] [Accepted: 01/16/2023] [Indexed: 01/18/2023] Open
Abstract
MOTIVATION Multilevel molecular profiling of tumors and the integrative analysis with clinical outcomes have enabled a deeper characterization of cancer treatment. Mediation analysis has emerged as a promising statistical tool to identify and quantify the intermediate mechanisms by which a gene affects an outcome. However, existing methods lack a unified approach to handle various types of outcome variables, making them unsuitable for high-throughput molecular profiling data with highly interconnected variables. RESULTS We develop a general mediation analysis framework for proteogenomic data that include multiple exposures, multivariate mediators on various scales of effects as appropriate for continuous, binary and survival outcomes. Our estimation method avoids imposing constraints on model parameters such as the rare disease assumption, while accommodating multiple exposures and high-dimensional mediators. We compare our approach to other methods in extensive simulation studies at a range of sample sizes, disease prevalence and number of false mediators. Using kidney renal clear cell carcinoma proteogenomic data, we identify genes that are mediated by proteins and the underlying mechanisms on various survival outcomes that capture short- and long-term disease-specific clinical characteristics. AVAILABILITY AND IMPLEMENTATION Software is made available in an R package (https://github.com/longjp/mediateR). SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Licai Huang
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | | | - Ehsan Irajizad
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - James D Doecke
- CSIRO, Royal Brisbane and Women’s Hospital, Brisbane, Australia
| | - Kim-Anh Do
- Department of Biostatistics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Min Jin Ha
- To whom correspondence should be addressed.
| |
Collapse
|
|
20
|
Curti N, Levi G, Giampieri E, Castellani G, Remondini D. A network approach for low dimensional signatures from high throughput data. Sci Rep 2022; 12:22253. [PMID: 36564421 PMCID: PMC9789141 DOI: 10.1038/s41598-022-25549-9] [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: 06/14/2022] [Accepted: 11/30/2022] [Indexed: 12/24/2022] Open
Abstract
One of the main objectives of high-throughput genomics studies is to obtain a low-dimensional set of observables-a signature-for sample classification purposes (diagnosis, prognosis, stratification). Biological data, such as gene or protein expression, are commonly characterized by an up/down regulation behavior, for which discriminant-based methods could perform with high accuracy and easy interpretability. To obtain the most out of these methods features selection is even more critical, but it is known to be a NP-hard problem, and thus most feature selection approaches focuses on one feature at the time (k-best, Sequential Feature Selection, recursive feature elimination). We propose DNetPRO, Discriminant Analysis with Network PROcessing, a supervised network-based signature identification method. This method implements a network-based heuristic to generate one or more signatures out of the best performing feature pairs. The algorithm is easily scalable, allowing efficient computing for high number of observables ([Formula: see text]-[Formula: see text]). We show applications on real high-throughput genomic datasets in which our method outperforms existing results, or is compatible with them but with a smaller number of selected features. Moreover, the geometrical simplicity of the resulting class-separation surfaces allows a clearer interpretation of the obtained signatures in comparison to nonlinear classification models.
Collapse
Affiliation(s)
- Nico Curti
- grid.6292.f0000 0004 1757 1758Department of Physics and Astronomy, University of Bologna, Bologna, Italy ,grid.470193.80000 0004 8343 7610INFN Bologna, Bologna, Italy
| | - Giuseppe Levi
- grid.6292.f0000 0004 1757 1758Department of Physics and Astronomy, University of Bologna, Bologna, Italy ,grid.470193.80000 0004 8343 7610INFN Bologna, Bologna, Italy
| | - Enrico Giampieri
- grid.470193.80000 0004 8343 7610INFN Bologna, Bologna, Italy ,grid.6292.f0000 0004 1757 1758Department of Experimental, Diagnostic and Specialty Medicine, University of Bologna, Bologna, Italy
| | - Gastone Castellani
- grid.470193.80000 0004 8343 7610INFN Bologna, Bologna, Italy ,grid.6292.f0000 0004 1757 1758Department of Experimental, Diagnostic and Specialty Medicine, University of Bologna, Bologna, Italy
| | - Daniel Remondini
- grid.6292.f0000 0004 1757 1758Department of Physics and Astronomy, University of Bologna, Bologna, Italy ,grid.470193.80000 0004 8343 7610INFN Bologna, Bologna, Italy
| |
Collapse
|
|
21
|
Synthesizing genome regulation data with vote-counting. Trends Genet 2022; 38:1208-1216. [PMID: 35817619 DOI: 10.1016/j.tig.2022.06.012] [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: 03/28/2022] [Revised: 05/31/2022] [Accepted: 06/16/2022] [Indexed: 01/24/2023]
Abstract
The increasing availability of high-throughput datasets allows amalgamating research information across a large body of genome regulation studies. Given the recent success of meta-analyses on transcriptional regulators, epigenetic marks, and enhancer:gene associations, we expect that such surveys will continue to provide novel and reproducible insights. However, meta-analyses are severely hampered by the diversity of available data, concurring protocols, an eclectic amount of bioinformatics tools, and myriads of conceivable parameter combinations. Such factors can easily bar life scientists from synthesizing omics data and substantially curb their interpretability. Despite statistical challenges of the method, we would like to emphasize the advantages of joining data from different sources through vote-counting and showcase examples that achieve a simple but highly intuitive data integration.
Collapse
|
|
22
|
Weaver C, Bin Satter K, Richardson KP, Tran LKH, Tran PMH, Purohit S. Diagnostic and Prognostic Biomarkers in Renal Clear Cell Carcinoma. Biomedicines 2022; 10:biomedicines10112953. [PMID: 36428521 PMCID: PMC9687861 DOI: 10.3390/biomedicines10112953] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/27/2022] [Revised: 11/14/2022] [Accepted: 11/15/2022] [Indexed: 11/19/2022] Open
Abstract
Renal clear cell carcinoma (ccRCC) comprises over 75% of all renal tumors and arises in the epithelial cells of the proximal convoluted tubule. Molecularly ccRCC is characterized by copy number alterations (CNAs) such as the loss of chromosome 3p and VHL inactivation. Additional driver mutations (SETD2, PBRM1, BAP1, and others) promote genomic instability and tumor cell metastasis through the dysregulation of various metabolic and immune-response pathways. Many researchers identified mutation, gene expression, and proteomic signatures for early diagnosis and prognostics for ccRCC. Despite a tremendous influx of data regarding DNA alterations, gene expression, and protein expression, the incorporation of these analyses for diagnosis and prognosis of RCC into the clinical application has not been implemented yet. In this review, we focused on the molecular changes associated with ccRCC development, along with gene expression and protein signatures, to emphasize the utilization of these molecular profiles in clinical practice. These findings, in the context of machine learning and precision medicine, may help to overcome some of the barriers encountered for implementing molecular profiles of tumors into the diagnosis and treatment of ccRCC.
Collapse
Affiliation(s)
- Chaston Weaver
- Center for Biotechnology and Genomic Medicine, Medical College of Georgia, Augusta University, 1120 15th St., Augusta, GA 30912, USA
| | - Khaled Bin Satter
- Center for Biotechnology and Genomic Medicine, Medical College of Georgia, Augusta University, 1120 15th St., Augusta, GA 30912, USA
| | - Katherine P. Richardson
- Center for Biotechnology and Genomic Medicine, Medical College of Georgia, Augusta University, 1120 15th St., Augusta, GA 30912, USA
- Department of Interdisciplinary Health Science, College of Allied Health Sciences, Augusta University, 1120 15th St., Augusta, GA 30912, USA
| | - Lynn K. H. Tran
- Department of Urology, Baylor College of Medicine, Houston, TX 76798, USA
| | - Paul M. H. Tran
- Department of Internal Medicine, Yale School of Medicine, Yale University, New Haven, CT 06510, USA
| | - Sharad Purohit
- Center for Biotechnology and Genomic Medicine, Medical College of Georgia, Augusta University, 1120 15th St., Augusta, GA 30912, USA
- Department of Interdisciplinary Health Science, College of Allied Health Sciences, Augusta University, 1120 15th St., Augusta, GA 30912, USA
- Department of Undergraduate Health Professionals, College of Allied Health Sciences, Augusta University, 1120 15th St., Augusta, GA 30912, USA
- Department of Obstetrics and Gynecology, Medical College of Georgia, Augusta University, 1120 15th St., Augusta, GA 30912, USA
- Correspondence:
| |
Collapse
|
|
23
|
Li L, Li J, Jia J, He H, Li M, Yan X, Yu Q, Guo H, Wang H, Lv Z, Sun H, Liao G, Cui J. Clonal evolution characteristics and reduced dimension prognostic model for non-metastatic metachronous bilateral breast cancer. Front Oncol 2022; 12:963884. [PMID: 36249030 PMCID: PMC9559188 DOI: 10.3389/fonc.2022.963884] [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: 06/08/2022] [Accepted: 08/31/2022] [Indexed: 11/13/2022] Open
Abstract
BACKGROUND How to evaluate the prognosis and develop overall treatment strategies of metachronous bilateral breast cancer (MBBC) remains confused in clinical. Here, we investigated the correlation between clonal evolution and clinical characteristics of MBBC; we aim to establish a novel prognostic model in these patients. METHODS The data from Surveillance, Epidemiology, and End Results (SEER) database and the First Hospital of Jilin University were analyzed for breast cancer-specific cumulative mortality (BCCM) by competing risk model. Meanwhile, whole-exome sequencing was applied for 10 lesions acquired at spatial-temporal distinct regions of five patients from our own hospital to reconstruct clonal evolutionary characteristics of MBBC. Then, dimensional-reduction (DR) cumulative incidence function (CIF) curves of MBBC features were established on different point in diagnostic interval time, to build a novel DR nomogram. RESULTS Significant heterogeneity in genome and clinical features of MBBC was widespread. The mutational diversity of contralateral BC (CBC) was significantly higher than that in primary BC (PBC), and the most effective prognostic MATH ratio was significantly correlated with interval time (R 2 = 0.85, p< 0.05). In SEER cohort study (n = 13,304), the interval time was not only significantly affected the BCCM by multivariate analysis (p< 0.000) but determined the weight of clinical features (T/N stage, grade and ER status) on PBC and CBC in prognostic evaluation. Thus, clinical parameters after DR based on interval time were incorporated into the nomogram for prognostic predicting BCCM. Concordance index was 0.773 (95% CI, 0.769-0.776) in training cohort (n = 8,869), and 0.819 (95% CI, 0.813-0.826) in validation cohort (n = 4,435). CONCLUSIONS Bilateral heterogeneous characteristics and interval time were determinant prognostic factors of MBBC. The DR prognostic nomogram may help clinicians in prognostic evaluation and decision making.
Collapse
Affiliation(s)
- Lingyu Li
- Cancer Center, The First Hospital of Jilin University, Changchun, China
| | - Jiaxuan Li
- Cancer Center, The First Hospital of Jilin University, Changchun, China
| | - Jiwei Jia
- School of Mathematics, Jilin University, Changchun, China
- National Applied Mathematical Center (Jilin), Changchun, China
| | - Hua He
- Cancer Center, The First Hospital of Jilin University, Changchun, China
| | - Mingyang Li
- College of Electronic Science and Engineering, Jilin University, Changchun, China
| | - Xu Yan
- Cancer Center, The First Hospital of Jilin University, Changchun, China
| | - Qing Yu
- Department of Translational Medicine, Geneplus-Beijing, Beijing, China
| | - Hanfei Guo
- Cancer Center, The First Hospital of Jilin University, Changchun, China
| | - Hong Wang
- Cancer Center, The First Hospital of Jilin University, Changchun, China
| | - Zheng Lv
- Cancer Center, The First Hospital of Jilin University, Changchun, China
| | - Haishuang Sun
- Cancer Center, The First Hospital of Jilin University, Changchun, China
| | - Guidong Liao
- School of Mathematics, Jilin University, Changchun, China
| | - Jiuwei Cui
- Cancer Center, The First Hospital of Jilin University, Changchun, China
| |
Collapse
|
|
24
|
Ding DY, Li S, Narasimhan B, Tibshirani R. Cooperative learning for multiview analysis. Proc Natl Acad Sci U S A 2022; 119:e2202113119. [PMID: 36095183 PMCID: PMC9499553 DOI: 10.1073/pnas.2202113119] [Citation(s) in RCA: 28] [Impact Index Per Article: 9.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2022] [Accepted: 08/09/2022] [Indexed: 11/18/2022] Open
Abstract
We propose a method for supervised learning with multiple sets of features ("views"). The multiview problem is especially important in biology and medicine, where "-omics" data, such as genomics, proteomics, and radiomics, are measured on a common set of samples. "Cooperative learning" combines the usual squared-error loss of predictions with an "agreement" penalty to encourage the predictions from different data views to agree. By varying the weight of the agreement penalty, we get a continuum of solutions that include the well-known early and late fusion approaches. Cooperative learning chooses the degree of agreement (or fusion) in an adaptive manner, using a validation set or cross-validation to estimate test set prediction error. One version of our fitting procedure is modular, where one can choose different fitting mechanisms (e.g., lasso, random forests, boosting, or neural networks) appropriate for different data views. In the setting of cooperative regularized linear regression, the method combines the lasso penalty with the agreement penalty, yielding feature sparsity. The method can be especially powerful when the different data views share some underlying relationship in their signals that can be exploited to boost the signals. We show that cooperative learning achieves higher predictive accuracy on simulated data and real multiomics examples of labor-onset prediction. By leveraging aligned signals and allowing flexible fitting mechanisms for different modalities, cooperative learning offers a powerful approach to multiomics data fusion.
Collapse
Affiliation(s)
- Daisy Yi Ding
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305
| | - Shuangning Li
- Department of Statistics, Stanford University, Stanford, CA 94305
| | - Balasubramanian Narasimhan
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305
- Department of Statistics, Stanford University, Stanford, CA 94305
| | - Robert Tibshirani
- Department of Biomedical Data Science, Stanford University, Stanford, CA 94305
- Department of Statistics, Stanford University, Stanford, CA 94305
| |
Collapse
|
|
25
|
Pan J, Ma B, Hou X, Li C, Xiong T, Gong Y, Song F. The construction of transcriptional risk scores for breast cancer based on lightGBM and multiple omics data. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2022; 19:12353-12370. [PMID: 36654001 DOI: 10.3934/mbe.2022576] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/17/2023]
Abstract
BACKGROUND Polygenic risk score (PRS) can evaluate the individual-level genetic risk of breast cancer. However, standalone single nucleotide polymorphisms (SNP) data used for PRS may not provide satisfactory prediction accuracy. Additionally, current PRS models based on linear regression have insufficient power to leverage non-linear effects from thousands of associated SNPs. Here, we proposed a transcriptional risk score (TRS) based on multiple omics data to estimate the risk of breast cancer. METHODS The multiple omics data and clinical data of breast invasive carcinoma (BRCA) were collected from the cancer genome atlas (TCGA) and the gene expression omnibus (GEO). First, we developed a novel TRS model for BRCA utilizing single omic data and LightGBM algorithm. Subsequently, we built a combination model of TRS derived from each omic data to further improve the prediction accuracy. Finally, we performed association analysis and prognosis prediction to evaluate the utility of the TRS generated by our method. RESULTS The proposed TRS model achieved better predictive performance than the linear models and other ML methods in single omic dataset. An independent validation dataset also verified the effectiveness of our model. Moreover, the combination of the TRS can efficiently strengthen prediction accuracy. The analysis of prevalence and the associations of the TRS with phenotypes including case-control and cancer stage indicated that the risk of breast cancer increases with the increases of TRS. The survival analysis also suggested that TRS for the cancer stage is an effective prognostic metric of breast cancer patients. CONCLUSIONS Our proposed TRS model expanded the current definition of PRS from standalone SNP data to multiple omics data and outperformed the linear models, which may provide a powerful tool for diagnostic and prognostic prediction of breast cancer.
Collapse
Affiliation(s)
- Jianqiao Pan
- Department of Epidemiology and Biostatistics, Key Laboratory of Molecular Cancer Epidemiology, Tianjin, National Clinical Research Center of Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin 300060, China
- School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China
| | - Baoshan Ma
- School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China
| | - Xiaoyu Hou
- School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China
| | - Chongyang Li
- School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China
| | - Tong Xiong
- School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China
| | - Yi Gong
- School of Information Science and Technology, Dalian Maritime University, Dalian 116026, China
| | - Fengju Song
- Department of Epidemiology and Biostatistics, Key Laboratory of Molecular Cancer Epidemiology, Tianjin, National Clinical Research Center of Cancer, Tianjin Medical University Cancer Institute and Hospital, Tianjin 300060, China
| |
Collapse
|
|
26
|
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
|
|
27
|
Khouja HI, Ashankyty IM, Bajrai LH, Kumar PKP, Kamal MA, Firoz A, Mobashir M. Multi-staged gene expression profiling reveals potential genes and the critical pathways in kidney cancer. Sci Rep 2022; 12:7240. [PMID: 35508649 PMCID: PMC9065671 DOI: 10.1038/s41598-022-11143-6] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2021] [Accepted: 10/11/2021] [Indexed: 02/05/2023] Open
Abstract
Cancer is among the highly complex disease and renal cell carcinoma is the sixth-leading cause of cancer death. In order to understand complex diseases such as cancer, diabetes and kidney diseases, high-throughput data are generated at large scale and it has helped in the research and diagnostic advancement. However, to unravel the meaningful information from such large datasets for comprehensive and minute understanding of cell phenotypes and disease pathophysiology remains a trivial challenge and also the molecular events leading to disease onset and progression are not well understood. With this goal, we have collected gene expression datasets from publicly available dataset which are for two different stages (I and II) for renal cell carcinoma and furthermore, the TCGA and cBioPortal database have been utilized for clinical relevance understanding. In this work, we have applied computational approach to unravel the differentially expressed genes, their networks for the enriched pathways. Based on our results, we conclude that among the most dominantly altered pathways for renal cell carcinoma, are PI3K-Akt, Foxo, endocytosis, MAPK, Tight junction, cytokine-cytokine receptor interaction pathways and the major source of alteration for these pathways are MAP3K13, CHAF1A, FDX1, ARHGAP26, ITGBL1, C10orf118, MTO1, LAMP2, STAMBP, DLC1, NSMAF, YY1, TPGS2, SCARB2, PRSS23, SYNJ1, CNPPD1, PPP2R5E. In terms of clinical significance, there are large number of differentially expressed genes which appears to be playing critical roles in survival.
Collapse
Affiliation(s)
- Hamed Ishaq Khouja
- Department of Medical Laboratory Technology, Faculty of Applied Medical Sciences, King Abdulaziz University, Jeddah, Saudi Arabia.
| | - Ibraheem Mohammed Ashankyty
- Department of Medical Laboratory Technology, Faculty of Applied Medical Sciences, King Abdulaziz University, Jeddah, Saudi Arabia
| | - Leena Hussein Bajrai
- Special Infectious Agents Unit-BSL3, King Fahad Medical Research Center, King Abdulaziz University, Jeddah, Saudi Arabia
- Biochemistry Department, Sciences College, King Abdulaziz University, Jeddah, Saudi Arabia
| | - P K Praveen Kumar
- Department of Biotechnology, Sri Venkateswara College of Engineering, Sriperumbudur, 602105, India
| | - Mohammad Amjad Kamal
- West China School of Nursing/Institutes for Systems Genetics, Frontiers Science Center for Disease-Related Molecular Network, West China Hospital, Sichuan University, Chengdu, 610041, Sichuan, China
- King Fahd Medical Research Center, King Abdulaziz University, P. O. Box 80216, Jeddah, 21589, Saudi Arabia
- Enzymoics, Novel Global Community Educational Foundation, 7 Peterlee Place, Hebersham, NSW, 2770, Australia
| | - Ahmad Firoz
- Department of Biological Sciences, Faculty of Science, King Abdulaziz University, Jeddah, Kingdom of Saudi Arabia
| | - Mohammad Mobashir
- SciLifeLab, Department of Oncology and Pathology, Karolinska Institutet, Box 1031, 171 21, Stockholm, Sweden.
| |
Collapse
|
|
28
|
Adnan N, Zand M, Huang THM, Ruan J. Construction and Evaluation of Robust Interpretation Models for Breast Cancer Metastasis Prediction. IEEE/ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2022; 19:1344-1353. [PMID: 34662279 PMCID: PMC9254332 DOI: 10.1109/tcbb.2021.3120673] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/05/2023]
Abstract
Interpretability of machine learning (ML) models represents the extent to which a model's decision-making process can be understood by model developers and/or end users. Transcriptomics-based cancer prognosis models, for example, while achieving good accuracy, are usually hard to interpret, due to the high-dimensional feature space and the complexity of models. As interpretability is critical for the transparency and fairness of ML models, several algorithms have been proposed to improve the interpretability of arbitrary classifiers. However, evaluation of these algorithms often requires substantial domain knowledge. Here, we propose a breast cancer metastasis prediction model using a very small number of biologically interpretable features, and a simple yet novel model interpretation approach that can provide personalized interpretations. In addition, we contributed, to the best of our knowledge, the first method to quantitatively compare different interpretation algorithms. Experimental results show that our model not only achieved competitive prediction accuracy, but also higher inter-classifier interpretation consistency than state-of-the-art interpretation methods. Importantly, our interpretation results can improve the generalizability of the prediction models. Overall, this work provides several novel ideas to construct and evaluate interpretable ML models that can be valuable to both the cancer machine learning community and related application domains.
Collapse
|
|
29
|
Systematic illumination of druggable genes in cancer genomes. Cell Rep 2022; 38:110400. [PMID: 35196490 PMCID: PMC8919705 DOI: 10.1016/j.celrep.2022.110400] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2021] [Revised: 09/12/2021] [Accepted: 01/26/2022] [Indexed: 01/15/2023] Open
Abstract
By combining 6 druggable genome resources, we identify 6,083 genes as potential druggable genes (PDGs). We characterize their expression, recurrent genomic alterations, cancer dependencies, and therapeutic potentials by integrating genome, functionome, and druggome profiles across cancers. 81.5% of PDGs are reliably expressed in major adult cancers, 46.9% show selective expression patterns, and 39.1% exhibit at least one recurrent genomic alteration. We annotate a total of 784 PDGs as dependent genes for cancer cell growth. We further quantify 16 cancer-related features and estimate a PDG cancer drug target score (PCDT score). PDGs with higher PCDT scores are significantly enriched for genes encoding kinases and histone modification enzymes. Importantly, we find that a considerable portion of high PCDT score PDGs are understudied genes, providing unexplored opportunities for drug development in oncology. By integrating the druggable genome and the cancer genome, our study thus generates a comprehensive blueprint of potential druggable genes across cancers. Jiang et al. generate a comprehensive blueprint of potential druggable genes (PDGs) across cancers by a systematic integration of the druggable genome and the cancer genome. This resource is publicly available to the cancer research community in The Cancer Druggable Gene Atlas (TCDA) through the Functional Cancer Genome data portal.
Collapse
|
|
30
|
Wang S, Wang S, Zhang X, Meng D, Xia Q, Xie S, Shen S, Yu B, Hu J, Liu H, Yan W. Comprehensive analysis of prognosis-related alternative splicing events in ovarian cancer. RNA Biol 2022; 19:1007-1018. [PMID: 35980273 PMCID: PMC9397453 DOI: 10.1080/15476286.2022.2113148] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022] Open
Abstract
Ovarian cancer (OV) is characterized by high incidence and poor prognosis. Increasing evidence indicates that aberrant alternative splicing (AS) events are associated with the pathogenesis of cancer. We examined prognosis-related alternative splicing events and constructed a clinically applicable model to predict patients’ outcomes. Public database including The Cancer Genome Atlas (TCGA), TCGA SpliceSeq, and the Genomics of Drug Sensitivity in Cancer databases were used to detect the AS expression, immune cell infiltration and IC50. The prognosis-related AS model was constructed and validated by using Cox regression, LASSO regression, C-index, calibration plots, and ROC curves. A total of eight AS events (including FLT3LG|50942|AP) were selected to establish the prognosis-related AS model. Compared with high-risk group, low-risk group had a better outcome (P = 1.794e-06), was more sensitive to paclitaxel (P = 0.022), and higher proportions of plasma cells. We explored the upstream regulatory mechanisms of prognosis-related AS and found that two splicing factor and 156 tag single nucleotide polymorphisms may be involved in the regulation of prognosis-related AS. In order to assess patient prognosis more comprehensively, we constructed a clinically applicable model combining risk score and clinicopathological features, and the 1 -, and 3-year AUCs of the clinically applicable model were 0.812, and 0.726, which were 7.5% and 3.3% higher than that of the risk score. We constructed a prognostic signature for OV patients and comprehensively analysed the regulatory characteristics of the prognostic AS events in OV.
Collapse
Affiliation(s)
| | - Shiyuan Wang
- Key Laboratory of Environmental Medicine Engineering, Ministry of Education, School of Public Health, Southeast University, Nanjing, Jiangsu, China
| | - Xing Zhang
- Key Laboratory of Environmental Medicine Engineering, Ministry of Education, School of Public Health, Southeast University, Nanjing, Jiangsu, China
| | - Dan Meng
- Key Laboratory of Environmental Medicine Engineering, Ministry of Education, School of Public Health, Southeast University, Nanjing, Jiangsu, China
| | - Qianqian Xia
- Key Laboratory of Environmental Medicine Engineering, Ministry of Education, School of Public Health, Southeast University, Nanjing, Jiangsu, China
| | - Shuqian Xie
- Key Laboratory of Environmental Medicine Engineering, Ministry of Education, School of Public Health, Southeast University, Nanjing, Jiangsu, China
| | - Siyuan Shen
- Key Laboratory of Environmental Medicine Engineering, Ministry of Education, School of Public Health, Southeast University, Nanjing, Jiangsu, China
| | - Bingjia Yu
- Key Laboratory of Environmental Medicine Engineering, Ministry of Education, School of Public Health, Southeast University, Nanjing, Jiangsu, China
| | - Jing Hu
- Key Laboratory of Environmental Medicine Engineering, Ministry of Education, School of Public Health, Southeast University, Nanjing, Jiangsu, China
| | - Haohan Liu
- Key Laboratory of Environmental Medicine Engineering, Ministry of Education, School of Public Health, Southeast University, Nanjing, Jiangsu, China
| | - Wenjing Yan
- Key Laboratory of Environmental Medicine Engineering, Ministry of Education, School of Public Health, Southeast University, Nanjing, Jiangsu, China
| |
Collapse
|
|
31
|
Network Approaches for Precision Oncology. ADVANCES IN EXPERIMENTAL MEDICINE AND BIOLOGY 2022; 1361:199-213. [DOI: 10.1007/978-3-030-91836-1_11] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|
|
32
|
Jiang J, Yuan J, Hu Z, Xu M, Zhang Y, Long M, Fan Y, Montone K, Tanyi JL, Tavana O, Chan HM, Zhang L, Hu X. Systematic pan-cancer characterization of nuclear receptors identifies potential cancer biomarkers and therapeutic targets. Cancer Res 2021; 82:46-59. [PMID: 34750098 DOI: 10.1158/0008-5472.can-20-3458] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2020] [Revised: 02/15/2021] [Accepted: 11/02/2021] [Indexed: 11/16/2022]
Abstract
The nuclear receptor (NR) superfamily is one of the major druggable gene families, representing targets of approximately 13.5% of approved drugs. Certain NRs, such as estrogen receptor and androgen receptor, have been well demonstrated to be functionally involved in cancer and serve as informative biomarkers and therapeutic targets in oncology. However, the spectrum of NR dysregulation across cancers remains to be comprehensively characterized. Through computational integration of genetic, genomic, and pharmacologic profiles, we characterized the expression, recurrent genomic alterations, and cancer dependency of NRs at a large scale across primary tumor specimens and cancer cell lines. Expression levels of NRs were highly cancer-type specific and globally downregulated in tumors compared to corresponding normal tissue. Although the majority of NRs showed copy number losses in cancer, both recurrent focal gains and losses were identified in select NRs. Recurrent mutations and transcript fusions of NRs were observed in a small portion of cancers, serving as actionable genomic alterations. Analysis of large-scale CRISPR and RNAi screening datasets identified 10 NRs as strongly selective essential genes for cancer cell growth. In a subpopulation of tumor cells, growth dependencies correlated significantly with expression or genomic alterations. Overall, our comprehensive characterization of NRs across cancers may facilitate the identification and prioritization of potential biomarkers and therapeutic targets, as well as the selection of patients for precision cancer treatment.
Collapse
Affiliation(s)
| | - Jiao Yuan
- Ob and Gyn, University of Pennsylvania
| | - Zhongyi Hu
- Department of Obstetrics and Gynecology, University of Pennsylvania
| | - Mu Xu
- Department of Obstetrics and Gynecology, University of Pennsylvania
| | | | - Meixiao Long
- Comprehensive Cancer Center, The Ohio State University
| | - Yi Fan
- Radiation Oncology, University of Pennsylvania
| | | | | | | | - Ho Man Chan
- Bioscience, Research and Early Development, Oncology R&D, AstraZeneca (United States)
| | - Lin Zhang
- Department of Obstetrics and Gynecology, University of Pennsylvania
| | | |
Collapse
|
|
33
|
Shi K, Lin W, Zhao XM. Identifying Molecular Biomarkers for Diseases With Machine Learning Based on Integrative Omics. IEEE/ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2021; 18:2514-2525. [PMID: 32305934 DOI: 10.1109/tcbb.2020.2986387] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
Molecular biomarkers are certain molecules or set of molecules that can be of help for diagnosis or prognosis of diseases or disorders. In the past decades, thanks to the advances in high-throughput technologies, a huge amount of molecular 'omics' data, e.g., transcriptomics and proteomics, have been accumulated. The availability of these omics data makes it possible to screen biomarkers for diseases or disorders. Accordingly, a number of computational approaches have been developed to identify biomarkers by exploring the omics data. In this review, we present a comprehensive survey on the recent progress of identification of molecular biomarkers with machine learning approaches. Specifically, we categorize the machine learning approaches into supervised, un-supervised and recommendation approaches, where the biomarkers including single genes, gene sets and small gene networks. In addition, we further discuss potential problems underlying bio-medical data that may pose challenges for machine learning, and provide possible directions for future biomarker identification.
Collapse
|
|
34
|
Desmet C, Cook DJ. Recent Developments in Privacy-Preserving Mining of Clinical Data. ACM/IMS TRANSACTIONS ON DATA SCIENCE 2021; 2:28. [PMID: 35018368 PMCID: PMC8746818 DOI: 10.1145/3447774] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/01/2020] [Accepted: 01/01/2021] [Indexed: 06/14/2023]
Abstract
With the dramatic increases in both the capability to collect personal data and the capability to analyze large amounts of data, increasingly sophisticated and personal insights are being drawn. These insights are valuable for clinical applications but also open up possibilities for identification and abuse of personal information. In this paper, we survey recent research on classical methods of privacy-preserving data mining. Looking at dominant techniques and recent innovations to them, we examine the applicability of these methods to the privacy-preserving analysis of clinical data. We also discuss promising directions for future research in this area.
Collapse
|
|
35
|
Isaev K, Jiang L, Wu S, Lee CA, Watters V, Fort V, Tsai R, Coutinho FJ, Hussein SMI, Zhang J, Wu J, Dirks PB, Schramek D, Reimand J. Pan-cancer analysis of non-coding transcripts reveals the prognostic onco-lncRNA HOXA10-AS in gliomas. Cell Rep 2021; 37:109873. [PMID: 34686327 DOI: 10.1016/j.celrep.2021.109873] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2019] [Revised: 07/21/2021] [Accepted: 09/29/2021] [Indexed: 12/12/2022] Open
Abstract
Long non-coding RNAs (lncRNAs) are increasingly recognized as functional units in cancer and powerful biomarkers; however, most remain uncharacterized. Here, we analyze 5,592 prognostic lncRNAs in 9,446 cancers of 30 types using machine learning. We identify 166 lncRNAs whose expression correlates with survival and improves the accuracy of common clinical variables, molecular features, and cancer subtypes. Prognostic lncRNAs are often characterized by switch-like expression patterns. In low-grade gliomas, HOXA10-AS activation is a robust marker of poor prognosis that complements IDH1/2 mutations, as validated in another retrospective cohort, and correlates with developmental pathways in tumor transcriptomes. Loss- and gain-of-function studies in patient-derived glioma cells, organoids, and xenograft models identify HOXA10-AS as a potent onco-lncRNA that regulates cell proliferation, contact inhibition, invasion, Hippo signaling, and mitotic and neuro-developmental pathways. Our study underscores the pan-cancer potential of the non-coding transcriptome for identifying biomarkers and regulators of cancer progression.
Collapse
Affiliation(s)
- Keren Isaev
- Ontario Institute for Cancer Research, Toronto, ON, Canada; Department of Medical Biophysics, University of Toronto, Toronto, ON, Canada
| | - Lingyan Jiang
- Lunenfeld-Tanenbaum Research Institute, Mount Sinai Hospital, Toronto, ON, Canada
| | - Shuai Wu
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China; Shanghai Clinical Medical Center of Neurosurgery, Shanghai, China; Shanghai Key Laboratory of Brain Function and Restoration and Neural Regeneration, Shanghai, China
| | - Christian A Lee
- Ontario Institute for Cancer Research, Toronto, ON, Canada; Department of Medical Biophysics, University of Toronto, Toronto, ON, Canada
| | - Valérie Watters
- Cancer Research Center, Université Laval, Quebec City, QC, Canada; CHU of Québec-Université Laval Research Center, Oncology Division, Quebec City, QC, Canada
| | - Victoire Fort
- Cancer Research Center, Université Laval, Quebec City, QC, Canada; CHU of Québec-Université Laval Research Center, Oncology Division, Quebec City, QC, Canada
| | - Ricky Tsai
- Lunenfeld-Tanenbaum Research Institute, Mount Sinai Hospital, Toronto, ON, Canada
| | | | - Samer M I Hussein
- Cancer Research Center, Université Laval, Quebec City, QC, Canada; CHU of Québec-Université Laval Research Center, Oncology Division, Quebec City, QC, Canada
| | - Jie Zhang
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China; Shanghai Clinical Medical Center of Neurosurgery, Shanghai, China; Shanghai Key Laboratory of Brain Function and Restoration and Neural Regeneration, Shanghai, China
| | - Jinsong Wu
- Department of Neurosurgery, Huashan Hospital, Shanghai Medical College, Fudan University, Shanghai, China; Neurosurgical Institute of Fudan University, Shanghai, China; Shanghai Clinical Medical Center of Neurosurgery, Shanghai, China; Shanghai Key Laboratory of Brain Function and Restoration and Neural Regeneration, Shanghai, China
| | - Peter B Dirks
- SickKids Research Institute, Toronto, ON, Canada; Department of Molecular Genetics, University of Toronto, Toronto, ON, Canada
| | - Daniel Schramek
- Lunenfeld-Tanenbaum Research Institute, Mount Sinai Hospital, Toronto, ON, Canada; Department of Molecular Genetics, University of Toronto, Toronto, ON, Canada.
| | - Jüri Reimand
- Ontario Institute for Cancer Research, Toronto, ON, Canada; Department of Medical Biophysics, University of Toronto, Toronto, ON, Canada; Department of Molecular Genetics, University of Toronto, Toronto, ON, Canada.
| |
Collapse
|
|
36
|
Hajian M, Esmaeili A, Talebi A. Comparative evaluation of BMI-1 proto-oncogene expression in normal tissue, adenoma and papillary carcinoma of human thyroid in pathology samples. BMC Res Notes 2021; 14:369. [PMID: 34551814 PMCID: PMC8456638 DOI: 10.1186/s13104-021-05771-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/17/2021] [Accepted: 09/01/2021] [Indexed: 11/14/2022] Open
Abstract
Objective Papillary Thyroid carcinoma accounts for more than 60% of adult thyroid carcinomas. Finding a helpful marker is vital to determine the correct treatment approach. The present study was aimed to evaluate the expression of the B cell-specific Moloney murine leukemia virus integration site 1 (BMI-1) gene in papillary carcinoma, adenoma, and adjacent healthy thyroid tissues. Pathology blocks of thyroid tissues at the pathology department of patients who have undergone thyroid surgery between 2015 and 2019 were examined; papillary carcinoma, adenoma, and healthy tissues were selected and sectioned. Total RNA was extracted, and the relative expression level of the BMI-1 gene was examined using the Real-Time qPCR method. Results In the papillary and adenoma tissues, BMI-1 was overexpressed (1.047-fold and 1.042-fold) in comparison to healthy tissues (p < 0.05 for both comparisons). However, no statistically significant differences were observed between adenoma and papillary carcinoma tissues regarding BMI-1 gene expression. This study demonstrated a new biomarker for thyroid malignancies and found that the mRNA levels of the BMI-1 gene were higher in tumor tissues compared with healthy tissues. Further studies are needed to evaluate the BMI1 gene expression in other thyroid cancers.
Collapse
Affiliation(s)
- Mohadeseh Hajian
- Department of Pathology, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran
| | - Abolghasem Esmaeili
- Department of Cell and Molecular Biology, University of Isfahan, Isfahan, Iran.
| | - Ardeshir Talebi
- Department of Pathology, School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran
| |
Collapse
|
|
37
|
Miranda SP, Baião FA, Fleck JL, Piccolo SR. Predicting drug sensitivity of cancer cells based on DNA methylation levels. PLoS One 2021; 16:e0238757. [PMID: 34506489 PMCID: PMC8432830 DOI: 10.1371/journal.pone.0238757] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/21/2020] [Accepted: 06/28/2021] [Indexed: 01/22/2023] Open
Abstract
Cancer cell lines, which are cell cultures derived from tumor samples, represent one of the least expensive and most studied preclinical models for drug development. Accurately predicting drug responses for a given cell line based on molecular features may help to optimize drug-development pipelines and explain mechanisms behind treatment responses. In this study, we focus on DNA methylation profiles as one type of molecular feature that is known to drive tumorigenesis and modulate treatment responses. Using genome-wide, DNA methylation profiles from 987 cell lines in the Genomics of Drug Sensitivity in Cancer database, we used machine-learning algorithms to evaluate the potential to predict cytotoxic responses for eight anti-cancer drugs. We compared the performance of five classification algorithms and four regression algorithms representing diverse methodologies, including tree-, probability-, kernel-, ensemble-, and distance-based approaches. We artificially subsampled the data to varying degrees, aiming to understand whether training based on relatively extreme outcomes would yield improved performance. When using classification or regression algorithms to predict discrete or continuous responses, respectively, we consistently observed excellent predictive performance when the training and test sets consisted of cell-line data. Classification algorithms performed best when we trained the models using cell lines with relatively extreme drug-response values, attaining area-under-the-receiver-operating-characteristic-curve values as high as 0.97. The regression algorithms performed best when we trained the models using the full range of drug-response values, although this depended on the performance metrics we used. Finally, we used patient data from The Cancer Genome Atlas to evaluate the feasibility of classifying clinical responses for human tumors based on models derived from cell lines. Generally, the algorithms were unable to identify patterns that predicted patient responses reliably; however, predictions by the Random Forests algorithm were significantly correlated with Temozolomide responses for low-grade gliomas.
Collapse
Affiliation(s)
- Sofia P. Miranda
- Department of Industrial Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, Rio de Janeiro, Brazil
| | - Fernanda A. Baião
- Department of Industrial Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, Rio de Janeiro, Brazil
| | - Julia L. Fleck
- Mines Saint-Etienne, Univ Clermont Auvergne, CNRS, UMR 6158 LIMOS, Centre CIS, Saint-Etienne, France
| | - Stephen R. Piccolo
- Department of Biology, Brigham Young University, Provo, Utah, United States of America
| |
Collapse
|
|
38
|
Hassanzadeh HR, Wang MD. An Integrated Deep Network for Cancer Survival Prediction Using Omics Data. Front Big Data 2021; 4:568352. [PMID: 34337396 PMCID: PMC8322661 DOI: 10.3389/fdata.2021.568352] [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: 06/01/2020] [Accepted: 06/01/2021] [Indexed: 12/22/2022] Open
Abstract
As a highly sophisticated disease that humanity faces, cancer is known to be associated with dysregulation of cellular mechanisms in different levels, which demands novel paradigms to capture informative features from different omics modalities in an integrated way. Successful stratification of patients with respect to their molecular profiles is a key step in precision medicine and in tailoring personalized treatment for critically ill patients. In this article, we use an integrated deep belief network to differentiate high-risk cancer patients from the low-risk ones in terms of the overall survival. Our study analyzes RNA, miRNA, and methylation molecular data modalities from both labeled and unlabeled samples to predict cancer survival and subsequently to provide risk stratification. To assess the robustness of our novel integrative analytics, we utilize datasets of three cancer types with 836 patients and show that our approach outperforms the most successful supervised and semi-supervised classification techniques applied to the same cancer prediction problems. In addition, despite the preconception that deep learning techniques require large size datasets for proper training, we have illustrated that our model can achieve better results for moderately sized cancer datasets.
Collapse
Affiliation(s)
- Hamid Reza Hassanzadeh
- School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA, United States
| | - May D. Wang
- Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, United States
| |
Collapse
|
|
39
|
Huang H, Fu J, Zhang L, Xu J, Li D, Onwuka JU, Zhang D, Zhao L, Sun S, Zhu L, Zheng T, Jia C, Cui B, Zhao Y. Integrative Analysis of Identifying Methylation-Driven Genes Signature Predicts Prognosis in Colorectal Carcinoma. Front Oncol 2021; 11:629860. [PMID: 34178621 PMCID: PMC8231008 DOI: 10.3389/fonc.2021.629860] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/16/2020] [Accepted: 05/24/2021] [Indexed: 01/20/2023] Open
Abstract
Background Aberrant DNA methylation is a critical regulator of gene expression and plays a crucial role in the occurrence, progression, and prognosis of colorectal cancer (CRC). We aimed to identify methylation-driven genes by integrative epigenetic and transcriptomic analysis to predict the prognosis of CRC patients. Methods Methylation-driven genes were selected for CRC using a MethylMix algorithm and LASSO regression screening strategy, and were further used to construct a prognostic risk-assessment model. The Cancer Genome Atlas (TCGA) database was obtained as the training set for both the screening of methylation-driven genes and the effect of genes signature on CRC prognosis. Then, the prognostic genes signature was validated in three independent expression arrays of CRC data from Gene Expression Omnibus (GEO). Results We identified 143 methylation-driven genes, of which the combination of BATF, PHYHIPL, RBP1, and PNPLA4 expression levels was screened as a better prognostic model with the best area under the curve (AUC) (AUC = 0.876). Compared with patients in the low-risk group, CRC patients in the high-risk group had significantly poorer overall survival in the training set (HR = 2.184, 95% CI: 1.404–3.396, P < 0.001). Similar results were observed in the validation set. Moreover, VanderWeele’s mediation analysis indicated that the effect of methylation on prognosis was mediated by the levels of their expression (HRindirect = 1.473, P = 0.001, Proportion mediated, 69.10%). Conclusions We identified a four-gene prognostic signature by integrative analysis and developed a risk-assessment model that is significantly associated with patients’ survival. Methylation-driven genes might be a potential prognostic signature for CRC patients.
Collapse
Affiliation(s)
- Hao Huang
- Department of Epidemiology, Public Health School of Harbin Medical University, Harbin, China
| | - Jinming Fu
- Department of Epidemiology, Public Health School of Harbin Medical University, Harbin, China
| | - Lei Zhang
- Department of Epidemiology, Public Health School of Harbin Medical University, Harbin, China
| | - Jing Xu
- Department of Epidemiology, Public Health School of Harbin Medical University, Harbin, China
| | - Dapeng Li
- Department of Epidemiology, Public Health School of Harbin Medical University, Harbin, China
| | - Justina Ucheojor Onwuka
- Department of Epidemiology, Public Health School of Harbin Medical University, Harbin, China
| | - Ding Zhang
- Department of Epidemiology, Public Health School of Harbin Medical University, Harbin, China
| | - Liyuan Zhao
- Department of Epidemiology, Public Health School of Harbin Medical University, Harbin, China
| | - Simin Sun
- Department of Epidemiology, Public Health School of Harbin Medical University, Harbin, China
| | - Lin Zhu
- Department of Epidemiology, Public Health School of Harbin Medical University, Harbin, China
| | - Ting Zheng
- Department of Epidemiology, Public Health School of Harbin Medical University, Harbin, China
| | - Chenyang Jia
- Department of Epidemiology, Public Health School of Harbin Medical University, Harbin, China
| | - Binbin Cui
- Department of Colorectal Surgery, The Third Hospital of Harbin Medical University, Harbin, China
| | - Yashuang Zhao
- Department of Epidemiology, Public Health School of Harbin Medical University, Harbin, China
| |
Collapse
|
|
40
|
Kuru Hİ, Buyukozkan M, Tastan O. PRER: A patient representation with pairwise relative expression of proteins on biological networks. PLoS Comput Biol 2021; 17:e1008998. [PMID: 34038408 PMCID: PMC8238204 DOI: 10.1371/journal.pcbi.1008998] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2020] [Revised: 06/28/2021] [Accepted: 04/23/2021] [Indexed: 11/19/2022] Open
Abstract
Changes in protein and gene expression levels are often used as features in predictive modeling such as survival prediction. A common strategy to aggregate information contained in individual proteins is to integrate the expression levels with the biological networks. In this work, we propose a novel patient representation where we integrate proteins’ expression levels with the protein-protein interaction (PPI) networks: Patient representation with PRER (Pairwise Relative Expressions with Random walks). PRER captures the dysregulation patterns of proteins based on the neighborhood of a protein in the PPI network. Specifically, PRER computes a feature vector for a patient by comparing the source protein’s expression level with other proteins’ levels that are within its neighborhood. The neighborhood of the source protein is derived by biased random-walk strategy on the network. We test PRER’s performance in survival prediction task in 10 different cancers using random forest survival models. PRER yields a statistically significant predictive performance in 9 out of 10 cancers when compared to the same model trained with features based on individual protein expressions. Furthermore, we identified the pairs of proteins that their interactions are predictive of patient survival but their individual expression levels are not. The set of identified relations provides a valuable collection of protein biomarkers with high prognostic value. PRER can be used for other complex diseases and prediction tasks that use molecular expression profiles as input. PRER is freely available at: https://github.com/hikuru/PRER. Cancer remains to be one of the most prevalent and challenging diseases to treat. Cancer is a complex disease with several disrupted molecular mechanisms at play. The protein expression level is a fundamental indicator of how the molecular mechanisms are altered in each tumor. Predicting patient survival based on the changes is essential for understanding the cancer mechanisms and arriving at patient-specific treatment plans. For this task, existing machine learning models are used, such as random survival forest, which requires a feature-based representation of each patient based on her tumors. Most of these models use the individual molecular quantities of the tumors. However, cancer is a complex disease in which molecular mechanisms are dysregulated in various ways. In this work, we present a new patient representation scheme in which we integrate each tumor’s protein expression levels with their neighboring proteins’ expression levels in a protein-protein interaction network to capture patient-specific dysregulation patterns. Our results suggest that proteins’ relative expressions are more predictive than their individual expressions. We also analyze which of the protein interactions are more predictive of patient survival. The identified set of important protein interactions can be potentially used for cancer prognosis.
Collapse
Affiliation(s)
| | | | - Oznur Tastan
- Faculty of Natural Sciences and Engineering, Sabanci University, Istanbul, Turkey
- * E-mail:
| |
Collapse
|
|
41
|
Kuksin M, Morel D, Aglave M, Danlos FX, Marabelle A, Zinovyev A, Gautheret D, Verlingue L. Applications of single-cell and bulk RNA sequencing in onco-immunology. Eur J Cancer 2021; 149:193-210. [PMID: 33866228 DOI: 10.1016/j.ejca.2021.03.005] [Citation(s) in RCA: 83] [Impact Index Per Article: 20.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2020] [Revised: 02/26/2021] [Accepted: 03/04/2021] [Indexed: 02/08/2023]
Abstract
The rising interest for precise characterization of the tumour immune contexture has recently brought forward the high potential of RNA sequencing (RNA-seq) in identifying molecular mechanisms engaged in the response to immunotherapy. In this review, we provide an overview of the major principles of single-cell and conventional (bulk) RNA-seq applied to onco-immunology. We describe standard preprocessing and statistical analyses of data obtained from such techniques and highlight some computational challenges relative to the sequencing of individual cells. We notably provide examples of gene expression analyses such as differential expression analysis, dimensionality reduction, clustering and enrichment analysis. Additionally, we used public data sets to exemplify how deconvolution algorithms can identify and quantify multiple immune subpopulations from either bulk or single-cell RNA-seq. We give examples of machine and deep learning models used to predict patient outcomes and treatment effect from high-dimensional data. Finally, we balance the strengths and weaknesses of single-cell and bulk RNA-seq regarding their applications in the clinic.
Collapse
Affiliation(s)
- Maria Kuksin
- ENS de Lyon, 15 Parvis René Descartes, 69007, Lyon, France; Département d'Innovations Thérapeutiques et Essais Précoces (DITEP), Gustave Roussy Cancer Campus, 114 rue Edouard Vaillant, 94800, Villejuif, France
| | - Daphné Morel
- Département d'Innovations Thérapeutiques et Essais Précoces (DITEP), Gustave Roussy Cancer Campus, 114 rue Edouard Vaillant, 94800, Villejuif, France; Département de Radiothérapie, Gustave Roussy Cancer Campus, Gustave Roussy, 114 rue Edouard Vaillant, 94800, Villejuif, France; INSERM UMR1030, Molecular Radiotherapy and Therapeutic Innovations, Gustave Roussy, 114 rue Edouard Vaillant, 94800, Villejuif, France
| | - Marine Aglave
- INSERM US23, CNRS UMS 3655, Gustave Roussy Cancer Campus, 114 rue Edouard Vaillant, 94800, Villejuif, France
| | | | - Aurélien Marabelle
- Département d'Innovations Thérapeutiques et Essais Précoces (DITEP), Gustave Roussy Cancer Campus, 114 rue Edouard Vaillant, 94800, Villejuif, France; INSERM U1015, Gustave Roussy, Université Paris Saclay, France
| | - Andrei Zinovyev
- Institut Curie, PSL Research University, F-75005, Paris, France; INSERM, U900, F-75005, Paris, France; MINES ParisTech, PSL Research University, CBIO-Centre for Computational Biology, F-75006, Paris, France; Laboratory of Advanced Methods for High-dimensional Data Analysis, Lobachevsky University, 603000, Nizhny Novgorod, Russia
| | - Daniel Gautheret
- Institute for Integrative Biology of the Cell, UMR 9198, CEA, CNRS, Université Paris-Saclay, Gif-Sur-Yvette, France; IHU PRISM, Gustave Roussy Cancer Campus, Gustave Roussy, 114 Rue Edouard Vaillant, 94800, Villejuif, France; Université Paris-Saclay, France
| | - Loïc Verlingue
- Département d'Innovations Thérapeutiques et Essais Précoces (DITEP), Gustave Roussy Cancer Campus, 114 rue Edouard Vaillant, 94800, Villejuif, France; INSERM UMR1030, Molecular Radiotherapy and Therapeutic Innovations, Gustave Roussy, 114 rue Edouard Vaillant, 94800, Villejuif, France; Institut Curie, PSL Research University, F-75005, Paris, France; Université Paris-Saclay, France.
| |
Collapse
|
|
42
|
Georgopoulou D, Callari M, Rueda OM, Shea A, Martin A, Giovannetti A, Qosaj F, Dariush A, Chin SF, Carnevalli LS, Provenzano E, Greenwood W, Lerda G, Esmaeilishirazifard E, O'Reilly M, Serra V, Bressan D, Mills GB, Ali HR, Cosulich SS, Hannon GJ, Bruna A, Caldas C. Landscapes of cellular phenotypic diversity in breast cancer xenografts and their impact on drug response. Nat Commun 2021; 12:1998. [PMID: 33790302 PMCID: PMC8012607 DOI: 10.1038/s41467-021-22303-z] [Citation(s) in RCA: 39] [Impact Index Per Article: 9.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2020] [Accepted: 02/26/2021] [Indexed: 02/01/2023] Open
Abstract
The heterogeneity of breast cancer plays a major role in drug response and resistance and has been extensively characterized at the genomic level. Here, a single-cell breast cancer mass cytometry (BCMC) panel is optimized to identify cell phenotypes and their oncogenic signalling states in a biobank of patient-derived tumour xenograft (PDTX) models representing the diversity of human breast cancer. The BCMC panel identifies 13 cellular phenotypes (11 human and 2 murine), associated with both breast cancer subtypes and specific genomic features. Pre-treatment cellular phenotypic composition is a determinant of response to anticancer therapies. Single-cell profiling also reveals drug-induced cellular phenotypic dynamics, unravelling previously unnoticed intra-tumour response diversity. The comprehensive view of the landscapes of cellular phenotypic heterogeneity in PDTXs uncovered by the BCMC panel, which is mirrored in primary human tumours, has profound implications for understanding and predicting therapy response and resistance.
Collapse
Affiliation(s)
- Dimitra Georgopoulou
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
| | - Maurizio Callari
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
| | - Oscar M Rueda
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
| | - Abigail Shea
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
| | - Alistair Martin
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
| | - Agnese Giovannetti
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
- Laboratory of Clinical Genomics, Fondazione IRCCS Casa Sollievo della Sofferenza, San Giovanni Rotondo, Italy
| | - Fatime Qosaj
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
| | - Ali Dariush
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
- Institute of Astronomy, University of Cambridge, Cambridge, UK
| | - Suet-Feung Chin
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
| | | | - Elena Provenzano
- Breast Cancer Programme, CRUK Cambridge Centre, Cambridge, UK
- Cambridge Breast Cancer Research Unit, NIHR Cambridge Biomedical Research Centre and Cambridge Experimental Cancer Medicine Centre, Cambridge University Hospitals NHS Foundation Trust, Cambridge, UK
| | - Wendy Greenwood
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
| | - Giulia Lerda
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
| | - Elham Esmaeilishirazifard
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
- Bioscience, Oncology, Early Oncology R&D, AstraZeneca, Cambridge, UK
| | - Martin O'Reilly
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
| | - Violeta Serra
- Experimental Therapeutics Group, Vall d'Hebron Institut d'Oncologia, Barcelona, Spain
| | - Dario Bressan
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
| | - Gordon B Mills
- Cell, Development and Cancer Biology, Knight Cancer Institute, Oregon Health & Sciences University, Portland, OR, USA
| | - H Raza Ali
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
| | - Sabina S Cosulich
- Bioscience, Oncology, Early Oncology R&D, AstraZeneca, Cambridge, UK
| | - Gregory J Hannon
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
| | - Alejandra Bruna
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK
| | - Carlos Caldas
- Cancer Research UK Cambridge Institute and Department of Oncology, Li Ka Shing Centre, University of Cambridge, Cambridge, UK.
- Breast Cancer Programme, CRUK Cambridge Centre, Cambridge, UK.
- Cambridge Breast Cancer Research Unit, NIHR Cambridge Biomedical Research Centre and Cambridge Experimental Cancer Medicine Centre, Cambridge University Hospitals NHS Foundation Trust, Cambridge, UK.
| |
Collapse
|
|
43
|
Identification of hepatocellular carcinoma prognostic markers based on 10-immune gene signature. Biosci Rep 2021; 40:226069. [PMID: 32789471 PMCID: PMC7457228 DOI: 10.1042/bsr20200894] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2020] [Revised: 07/14/2020] [Accepted: 08/05/2020] [Indexed: 12/13/2022] Open
Abstract
Background: Due to the heterogeneity of hepatocellular carcinoma (HCC), hepatocelluarin-associated differentially expressed genes were analyzed by bioinformatics methods to screen the molecular markers for HCC prognosis and potential molecular targets for immunotherapy. Methods: RNA-seq data and clinical follow-up data of HCC were downloaded from The Cancer Genome Atlas (TCGA) database. Multivariate Cox analysis and Lasso regression were used to identify robust immunity-related genes. Finally, a risk prognosis model of immune gene pairs was established and verified by clinical features, test set and Gene Expression Omnibus (GEO) external validation set. Results: A total of 536 immune-related gene (IRGs) were significantly associated with the prognosis of patients with HCC. Ten robust IRGs were finally obtained and a prognostic risk prediction model was constructed by feature selection of Lasso. The risk score of each sample is calculated based on the risk model and is divided into high risk group (Risk-H) and low risk group (Risk-L). Risk models enable risk stratification of samples in training sets, test sets, external validation sets, staging and subtypes. The area under the curve (AUC) in the training set and the test set were all >0.67, and there were significant overall suvival (OS) differences between the Risk-H and Risk-L samples. Compared with the published four models, the traditional clinical features of Grade, Stage and Gender, the model performed better on the risk prediction of HCC prognosis. Conclusion: The present study constructed 10-gene signature as a novel prognostic marker for predicting survival in patients with HCC.
Collapse
|
|
44
|
Mass-spectrometry-based proteomic correlates of grade and stage reveal pathways and kinases associated with aggressive human cancers. Oncogene 2021; 40:2081-2095. [PMID: 33627787 PMCID: PMC7981264 DOI: 10.1038/s41388-021-01681-0] [Citation(s) in RCA: 29] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2020] [Revised: 01/11/2021] [Accepted: 01/25/2021] [Indexed: 01/30/2023]
Abstract
Proteomic signatures associated with clinical measures of more aggressive cancers could yield molecular clues as to disease drivers. Here, utilizing the Clinical Proteomic Tumor Analysis Consortium (CPTAC) mass-spectrometry-based proteomics datasets, we defined differentially expressed proteins and mRNAs associated with higher grade or higher stage, for each of seven cancer types (breast, colon, lung adenocarcinoma, clear cell renal, ovarian, uterine, and pediatric glioma), representing 794 patients. Widespread differential patterns of total proteins and phosphoproteins involved some common patterns shared between different cancer types. More proteins were associated with higher grade than higher stage. Most proteomic signatures predicted patient survival in independent transcriptomic datasets. The proteomic grade signatures, in particular, involved DNA copy number alterations. Pathways of interest were enriched within the grade-associated proteins across multiple cancer types, including pathways of altered metabolism, Warburg-like effects, and translation factors. Proteomic grade correlations identified protein kinases having functional impact in vitro in uterine endometrial cancer cells, including MAP3K2, MASTL, and TTK. The protein-level grade and stage associations for all proteins profiled-along with corresponding information on phosphorylation, pathways, mRNA expression, and copy alterations-represent a resource for identifying new potential targets. Proteomic analyses are often concordant with corresponding transcriptomic analyses, but with notable exceptions.
Collapse
|
|
45
|
Li R, Wang G, Wu Z, Lu H, Li G, Sun Q, Cai M. Identification of 6 gene markers for survival prediction in osteosarcoma cases based on multi-omics analysis. Exp Biol Med (Maywood) 2021; 246:1512-1523. [PMID: 33563042 DOI: 10.1177/1535370221992015] [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] [Indexed: 11/16/2022] Open
Abstract
Multiple-omics sequencing information with high-throughput has laid a solid foundation to identify genes associated with cancer prognostic process. Multiomics information study is capable of revealing the cancer occurring and developing system according to several aspects. Currently, the prognosis of osteosarcoma is still poor, so a genetic marker is needed for predicting the clinically related overall survival result. First, Office of Cancer Genomics (OCG Target) provided RNASeq, copy amount variations information, and clinically related follow-up data. Genes associated with prognostic process and genes exhibiting copy amount difference were screened in the training group, and the mentioned genes were integrated for feature selection with least absolute shrinkage and selection operator (Lasso). Eventually, effective biomarkers received the screening process. Lastly, this study built and demonstrated one gene-associated prognosis mode according to the set of the test and gene expression omnibus validation set; 512 prognosis-related genes (P < 0.01), 336 copies of amplified genes (P < 0.05), and 36 copies of deleted genes (P < 0.05) were obtained, and those genes of the mentioned genomic variants display close associations with tumor occurring and developing mechanisms. This study generated 10 genes for candidates through the integration of genomic variant genes as well as prognosis-related genes. Six typical genes (i.e. MYC, CHIC2, CCDC152, LYL1, GPR142, and MMP27) were obtained by Lasso feature selection and stepwise multivariate regression study, many of which are reported to show a relationship to tumor progressing process. The authors conducted Cox regression study for building 6-gene sign, i.e. one single prognosis-related element, in terms of cases carrying osteosarcoma. In addition, the samples were able to be risk stratified in the training group, test set, and externally validating set. The AUC of five-year survival according to the training group and validation set reached over 0.85, with superior predictive performance as opposed to the existing researches. Here, 6-gene sign was built to be new prognosis-related marking elements for assessing osteosarcoma cases' surviving state.
Collapse
Affiliation(s)
- Runmin Li
- Department of Orthopaedics, Shanghai Tenth People's Hospital, Tongji University, School of Medicine, Shanghai 200072, China
| | - Guosheng Wang
- Institute of Translational Medicine, Zhejiang University School of Medicine, Hangzhou 310029, China
| | - ZhouJie Wu
- Department of Orthopaedics, Shanghai Tenth People's Hospital, Tongji University, School of Medicine, Shanghai 200072, China
| | - HuaGuang Lu
- Department of Orthopaedics, Shanghai Tenth People's Hospital, Tongji University, School of Medicine, Shanghai 200072, China
| | - Gen Li
- Department of Orthopaedics, Shanghai Tenth People's Hospital, Tongji University, School of Medicine, Shanghai 200072, China
| | - Qi Sun
- Department of Orthopaedics, Shanghai Tenth People's Hospital, Tongji University, School of Medicine, Shanghai 200072, China
| | - Ming Cai
- Department of Orthopaedics, Shanghai Tenth People's Hospital, Tongji University, School of Medicine, Shanghai 200072, China
| |
Collapse
|
|
46
|
He Z, Zhang J, Yuan X, Zhang Y. Integrating Somatic Mutations for Breast Cancer Survival Prediction Using Machine Learning Methods. Front Genet 2021; 11:632901. [PMID: 33537063 PMCID: PMC7848170 DOI: 10.3389/fgene.2020.632901] [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: 11/24/2020] [Accepted: 12/30/2020] [Indexed: 12/13/2022] Open
Abstract
Breast cancer is the most common malignancy in women, and because it has a high mortality rate, it is urgent to develop computational methods to increase the accuracy of breast cancer survival predictive models. Although multi-omics data such as gene expression have been extensively used in recent studies, the accurate prognosis of breast cancer remains a challenge. Somatic mutations are another important and promising data source for studying cancer development, and its effect on the prognosis of breast cancer remains to be further explored. Meanwhile, these omics datasets are high-dimensional and redundant. Therefore, we adopted multiple kernel learning (MKL) to efficiently integrate somatic mutation to currently molecular data including gene expression, copy number variation (CNV), methylation, and protein expression data for the prediction of breast cancer survival. Before integration, the maximum relevance minimum redundancy (mRMR) feature selection method was utilized to select features that present high relevance to survival and low redundancy among themselves for each type of data. The experimental results demonstrated that the proposed method achieved the most optimal performance and there was a remarkable improvement in the prediction performance when somatic mutations were included, indicating that somatic mutations are critical for improving breast cancer survival predictions. Moreover, mRMR was superior to other feature selection methods used in previous studies. Furthermore, MKL outperformed the other traditional classifiers in multi-omics data integration. Our analysis indicated that through employing promising omics data such as somatic mutations and harnessing the power of proper feature selection methods and effective integration frameworks, the breast cancer survival predictive accuracy can be further increased, thereby providing a more optimal clinical diagnosis and more effective treatment for breast cancer patients.
Collapse
Affiliation(s)
- Zongzhen He
- School of Computer Science and Technology, Xidian University, Xi'an, China
| | - Junying Zhang
- School of Computer Science and Technology, Xidian University, Xi'an, China
| | - Xiguo Yuan
- School of Computer Science and Technology, Xidian University, Xi'an, China
| | - Yuanyuan Zhang
- School of Information and Control Engineering, Qingdao University of Technology, Qingdao, China
| |
Collapse
|
|
47
|
Badea L, Stănescu E. Identifying transcriptomic correlates of histology using deep learning. PLoS One 2020; 15:e0242858. [PMID: 33237966 PMCID: PMC7688140 DOI: 10.1371/journal.pone.0242858] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/10/2020] [Accepted: 11/11/2020] [Indexed: 12/18/2022] Open
Abstract
Linking phenotypes to specific gene expression profiles is an extremely important problem in biology, which has been approached mainly by correlation methods or, more fundamentally, by studying the effects of gene perturbations. However, genome-wide perturbations involve extensive experimental efforts, which may be prohibitive for certain organisms. On the other hand, the characterization of the various phenotypes frequently requires an expert's subjective interpretation, such as a histopathologist's description of tissue slide images in terms of complex visual features (e.g. 'acinar structures'). In this paper, we use Deep Learning to eliminate the inherent subjective nature of these visual histological features and link them to genomic data, thus establishing a more precisely quantifiable correlation between transcriptomes and phenotypes. Using a dataset of whole slide images with matching gene expression data from 39 normal tissue types, we first developed a Deep Learning tissue classifier with an accuracy of 94%. Then we searched for genes whose expression correlates with features inferred by the classifier and demonstrate that Deep Learning can automatically derive visual (phenotypical) features that are well correlated with the transcriptome and therefore biologically interpretable. As we are particularly concerned with interpretability and explainability of the inferred histological models, we also develop visualizations of the inferred features and compare them with gene expression patterns determined by immunohistochemistry. This can be viewed as a first step toward bridging the gap between the level of genes and the cellular organization of tissues.
Collapse
Affiliation(s)
- Liviu Badea
- Artificial Intelligence and Bioinformatics Group, National Institute for Research and Development in Informatics, Bucharest, Romania
| | - Emil Stănescu
- Artificial Intelligence and Bioinformatics Group, National Institute for Research and Development in Informatics, Bucharest, Romania
| |
Collapse
|
|
48
|
Roshanaei G, Safari M, Faradmal J, Abbasi M, Khazaei S. Factors affecting the survival of patients with colorectal cancer using random survival forest. J Gastrointest Cancer 2020; 53:64-71. [PMID: 33174117 DOI: 10.1007/s12029-020-00544-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 10/28/2020] [Indexed: 11/26/2022]
Abstract
PURPOSE Colorectal cancer is one of the most common cancers and the leading cause of cancer death in Iran. This study aimed to develop and validate a random survival forest (RSF) to identify important risk factors on mortality in colorectal patients based on their demographic and clinical-related variables. METHODS In this retrospective cohort study, the information of 317 patients with colorectal cancer who were referred to Imam Khomeini Clinic of Hamadan during the years of 2002 to 2017 were examined. Patient survival was calculated from the time of diagnosis to death. In the present study, the RSF model was used to identify factors affecting patient survival. Also, the results of the RSF model were compared with the Cox model. The data were analyzed using R software (version 3.6.1) and survival packages. RESULTS One-, 2-, 3-, 4-, 5-, and 10-year survival rates of included patients were 81.4%, 63%, 57%, 52%, 45%, and 34%, respectively, and the median survival was obtained to be 53 months. The number of 150 patients was died at this time period. The four most important predictors of survival included metastasis to other organs, WBC count, disease stage, and number of lymphomas involved. RSF method predicted survival better than the conventional Cox proportional hazard model. CONCLUSION We found that metastasis to other organs, WBC count, disease stage, and number of lymphomas involved were the most four most important predictors of low survival for colorectal cancer patients.
Collapse
Affiliation(s)
- Ghodratollah Roshanaei
- Department of Biostatistics, School of Public Health, Modeling of Noncommunicable Diseases Research Canter, Hamadan University of Medical Sciences, Hamadan, Iran
| | - Malihe Safari
- Department of Biostatistics, School of Public Health, Modeling of Noncommunicable Diseases Research Canter, Hamadan University of Medical Sciences, Hamadan, Iran
| | - Javad Faradmal
- Department of Biostatistics, School of Public Health, Modeling of Noncommunicable Diseases Research Canter, Hamadan University of Medical Sciences, Hamadan, Iran
| | - Mohammad Abbasi
- Department of Internal Medicine, School of Medicine, Hamadan University of Medical Sciences, Hamadan, Iran
| | - Salman Khazaei
- Research Center for Health Sciences, Hamadan University of Medical Sciences, Hamadan, Iran.
| |
Collapse
|
|
49
|
Shi M, Sheng Z, Tang H. Prognostic outcome prediction by semi-supervised least squares classification. Brief Bioinform 2020; 22:5935498. [PMID: 33094318 DOI: 10.1093/bib/bbaa249] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2020] [Revised: 09/04/2020] [Accepted: 09/04/2020] [Indexed: 11/13/2022] Open
Abstract
Although great progress has been made in prognostic outcome prediction, small sample size remains a challenge in obtaining accurate and robust classifiers. We proposed the Rescaled linear square Regression based Least Squares Learning (RRLSL), a jointly developed semi-supervised feature selection and classifier, for predicting prognostic outcome of cancer patients. RRLSL used the least square regression to identify the scale factors and then rank the features in available multiple types of molecular data. We applied the unlabeled multiple molecular data in conjunction with the labeled data to develop a similarity graph. RRLSL produced the constraint with kernel functions to bridge the gap between label information and geometry information from messenger RNA and microRNA expression profiling. Importantly, this semi-supervised model proposed the least squares learning with L2 regularization to develop a semi-supervised classifier. RRLSL suggested the performance improvement in the prognostic outcome prediction and successfully discriminated between the recurrent patients and non-recurrent ones. We also demonstrated that RRLSL improved the accuracy and Area Under the Precision Recall Curve (AUPRC) as compared to the baseline semi-supervised methods. RRLSL is available for a stand-alone software package (https://github.com/ShiMGLab/RRLSL). A short abstract We proposed the Rescaled linear square Regression based Least Squares Learning (RRLSL), a jointly developed semi-supervised feature selection and classifier, for predicting prognostic outcome of cancer patients. RRLSL used the least square regression to identify the scale factors to rank the features in available multiple types of molecular data. RRLSL produced the constraint with kernel functions to bridge the gap between label information and geometry information from messenger RNA and microRNA expression profiling. Importantly, this semi-supervised model proposed the least squares learning with L2 regularization to develop the semi-supervised classifier. RRLSL suggested the performance improvement in the prognostic outcome prediction and successfully discriminated between the recurrent patients and non-recurrent ones.
Collapse
Affiliation(s)
- Mingguang Shi
- School of Electric Engineering and Automation, Hefei University of Technology, Hefei, Anhui, 230009 China
| | - Zhou Sheng
- School of Electric Engineering and Automation, Hefei University of Technology, Hefei, Anhui, 230009 China
| | - Hao Tang
- School of Electric Engineering and Automation, Hefei University of Technology, Hefei, Anhui, 230009 China
| |
Collapse
|
|
50
|
Wu Y, Wan X, Jia G, Xu Z, Tao Y, Song Z, Du T. Aberrantly Methylated and Expressed Genes as Prognostic Epigenetic Biomarkers for Colon Cancer. DNA Cell Biol 2020; 39:1961-1969. [PMID: 33085517 DOI: 10.1089/dna.2020.5591] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022] Open
Abstract
This study aimed to identify prognostic epigenetic biomarkers for colon cancer (CC). Methylation and mRNA expression in CC samples with clinical characteristics that corresponded to those in The Cancer Genome Atlas were analyzed. Differentially methylated genes (DMGs) and differentially expressed genes (DEGs) were screened between matched tumor and nontumor tissues. Among the 415 DEGs and DMGs that significantly correlated between cytosine-phosphate-guanine (CpG) methylation and gene expression, unc-5 netrin receptor C (UNC5C), solute carrier family 35 member F (SLC35F)1, Ly6/Neurotoxin (LYNX)1, stathmin (STMN)2, slit guidance ligand (SLIT)3, cell adhesion molecule L1 like (CHL1), CAP-Gly domain containing linker protein family member 4 (CLIP4), transmembrane protein (TMEM) 255A, granzyme B (GZMB), and brain expressed X-Linked (BEX)1 were promising epigenetic biomarkers. Prediction was more accurate when models were based on the expression and/or methylation of GZMB rather than clinical stage. Comparisons of tissues with high or low GZMB expression significantly associated the DEGs with natural killer-mediated cytotoxicity, cytokine-cytokine receptor interactions, and chemokine signaling pathways. From among the 10 epigenetic biomarkers, GZMB might serve as a tumor suppressor and function in several immune-related pathways in CC. Prognostic models based on GZMB expression and/or methylation would be significant for patients with CC.
Collapse
Affiliation(s)
- Yuanyu Wu
- Department of Gastrointestinal and Colorectal Surgery, China-Japan Union Hospital of Jilin University, Changchun, China
| | - Xiaoyu Wan
- Department of Breast Surgery and The Second Clinical Hospital of Jilin University, Changchun, China
| | - Guoliang Jia
- Department of Orthopedics, The Second Clinical Hospital of Jilin University, Changchun, China
| | - Zhonghang Xu
- Department of Gastrointestinal and Colorectal Surgery, China-Japan Union Hospital of Jilin University, Changchun, China
| | - Youmao Tao
- Department of Gastrointestinal and Colorectal Surgery, China-Japan Union Hospital of Jilin University, Changchun, China
| | - Zheyu Song
- Department of Gastrointestinal and Colorectal Surgery, China-Japan Union Hospital of Jilin University, Changchun, China
| | - Tonghua Du
- Department of Breast Surgery and The Second Clinical Hospital of Jilin University, Changchun, China
| |
Collapse
|