1
|
Palomino-Echeverria S, Huergo E, Ortega-Legarreta A, Uson Raposo EM, Aguilar F, Peña-Ramirez CDL, López-Vicario C, Alessandria C, Laleman W, Queiroz Farias A, Moreau R, Fernandez J, Arroyo V, Caraceni P, Lagani V, Sánchez-Garrido C, Clària J, Tegner J, Trebicka J, Kiani NA, Planell N, Rautou PE, Gomez-Cabrero D. A robust clustering strategy for stratification unveils unique patient subgroups in acutely decompensated cirrhosis. J Transl Med 2024; 22:599. [PMID: 38937846 PMCID: PMC11210156 DOI: 10.1186/s12967-024-05386-2] [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: 02/01/2024] [Accepted: 06/10/2024] [Indexed: 06/29/2024] Open
Abstract
BACKGROUND Patient heterogeneity poses significant challenges for managing individuals and designing clinical trials, especially in complex diseases. Existing classifications rely on outcome-predicting scores, potentially overlooking crucial elements contributing to heterogeneity without necessarily impacting prognosis. METHODS To address patient heterogeneity, we developed ClustALL, a computational pipeline that simultaneously faces diverse clinical data challenges like mixed types, missing values, and collinearity. ClustALL enables the unsupervised identification of patient stratifications while filtering for stratifications that are robust against minor variations in the population (population-based) and against limited adjustments in the algorithm's parameters (parameter-based). RESULTS Applied to a European cohort of patients with acutely decompensated cirrhosis (n = 766), ClustALL identified five robust stratifications, using only data at hospital admission. All stratifications included markers of impaired liver function and number of organ dysfunction or failure, and most included precipitating events. When focusing on one of these stratifications, patients were categorized into three clusters characterized by typical clinical features; notably, the 3-cluster stratification showed a prognostic value. Re-assessment of patient stratification during follow-up delineated patients' outcomes, with further improvement of the prognostic value of the stratification. We validated these findings in an independent prospective multicentre cohort of patients from Latin America (n = 580). CONCLUSIONS By applying ClustALL to patients with acutely decompensated cirrhosis, we identified three patient clusters. Following these clusters over time offers insights that could guide future clinical trial design. ClustALL is a novel and robust stratification method capable of addressing the multiple challenges of patient stratification in most complex diseases.
Collapse
Affiliation(s)
| | - Estefania Huergo
- Unit of Translational Bioinformatics, Navarrabiomed - Fundación Miguel Servet, Pamplona, Spain
| | - Asier Ortega-Legarreta
- Unit of Translational Bioinformatics, Navarrabiomed - Fundación Miguel Servet, Pamplona, Spain
| | - Eva M Uson Raposo
- European Foundation for the Study of Chronic Liver Failure, Barcelona, Spain
| | - Ferran Aguilar
- European Foundation for the Study of Chronic Liver Failure, Barcelona, Spain
| | | | - Cristina López-Vicario
- European Foundation for the Study of Chronic Liver Failure, Barcelona, Spain
- Biochemistry and Molecular Genetics Service, Hospital Clínic-IDIBAPS, Barcelona, Spain
| | - Carlo Alessandria
- Division of Gastroenterology and Hepatology, A.O.U. Città della Salute e della Scienza di Torino, Torino, Italy
| | - Wim Laleman
- Department of Gastroenterology & Hepatology, Section of Liver & Biliopancreatic disorders and Liver Transplantation, University Hospitals Leuven, KU LEUVEN, Leuven, Belgium
| | - Alberto Queiroz Farias
- Department of Gastroenterology, Hospital das Clínicas, University of São Paulo School of Medicine, Paulo School, Brazil
| | - Richard Moreau
- European Foundation for the Study of Chronic Liver Failure, Barcelona, Spain
- Université Paris-Cité, Inserm, Centre de recherche sur l'inflammation, UMR 1149, Paris, France
- Assistance Publique-Hôpitaux de Paris (AP-HP), Paris, France
- Hôpital Beaujon, Service d'Hépatologie, Clichy, France
| | - Javier Fernandez
- European Foundation for the Study of Chronic Liver Failure, Barcelona, Spain
| | - Vicente Arroyo
- European Foundation for the Study of Chronic Liver Failure, Barcelona, Spain
| | - Paolo Caraceni
- Department of Medical and Surgical Science, University of Bologna, Bologna, Italy
- IRCCS Azienda Ospedaliera-Universitaria di Bologna, Bologna, Italy
| | - Vincenzo Lagani
- Biological and Environmental Science and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia
- SDAIA-KAUST Center of Excellence in Data Science and Artificial Intelligence, Thuwal, Saudi Arabia
- Institute of Chemical Biology, Ilia State University, Tbilisi, 0162, Georgia
| | | | - Joan Clària
- European Foundation for the Study of Chronic Liver Failure, Barcelona, Spain
- Biochemistry and Molecular Genetics Service, Hospital Clínic-IDIBAPS, Barcelona, Spain
- CIBERehd, Barcelona, Spain
- Department of Biomedical Sciences, University of Barcelona, Barcelona, Spain
| | - Jesper Tegner
- Biological and Environmental Science and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia
- SDAIA-KAUST Center of Excellence in Data Science and Artificial Intelligence, Thuwal, Saudi Arabia
- Unit of Computational Medicine, Department of Medicine, Center for Molecular Medicine, Karolinska Institutet, Karolinska University Hospital, Stockholm, Sweden
- Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia
| | - Jonel Trebicka
- European Foundation for the Study of Chronic Liver Failure, Barcelona, Spain
- Department of internal medicine B, University of Münster, Münster, Germany
| | - Narsis A Kiani
- Algorithmic Dynamics Lab, Center for Molecular Medicine, Karolinska Institutet, Solna, Sweden
- Department of Oncology-Pathology, Karolinska Institutet, Solna, Sweden
| | - Nuria Planell
- Unit of Translational Bioinformatics, Navarrabiomed - Fundación Miguel Servet, Pamplona, Spain.
- Computational Biology Program, Universidad de Navarra, CIMA, Instituto de Investigación Sanitaria de Navarra (IdiSNA), Navarra, 31008, Spain.
| | - Pierre-Emmanuel Rautou
- Université Paris-Cité, Inserm, Centre de recherche sur l'inflammation, UMR 1149, Paris, France.
- AP-HP, Hôpital Beaujon, Service d'Hépatologie, DMU DIGEST, Centre de Référence des Maladies Vasculaires du Foie, FILFOIE, ERN RARE-LIVER, Clichy, France.
| | - David Gomez-Cabrero
- Unit of Translational Bioinformatics, Navarrabiomed - Fundación Miguel Servet, Pamplona, Spain.
- Biological and Environmental Science and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia.
| |
Collapse
|
2
|
Pidsley R, Lam D, Qu W, Peters TJ, Luu P, Korbie D, Stirzaker C, Daly RJ, Stricker P, Kench JG, Horvath LG, Clark SJ. Comprehensive methylome sequencing reveals prognostic epigenetic biomarkers for prostate cancer mortality. Clin Transl Med 2022; 12:e1030. [PMID: 36178085 PMCID: PMC9523674 DOI: 10.1002/ctm2.1030] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2022] [Revised: 08/02/2022] [Accepted: 08/08/2022] [Indexed: 01/28/2023] Open
Abstract
BACKGROUND Prostate cancer is a clinically heterogeneous disease with a subset of patients rapidly progressing to lethal-metastatic prostate cancer. Current clinicopathological measures are imperfect predictors of disease progression. Epigenetic changes are amongst the earliest molecular changes in tumourigenesis. To find new prognostic biomarkers to enable earlier intervention and improved outcomes, we performed methylome sequencing of DNA from patients with localised prostate cancer and long-term clinical follow-up. METHODS We used whole-genome bisulphite sequencing (WGBS) to comprehensively map and compare DNA methylation of radical prostatectomy tissue between patients with lethal disease (n = 7) and non-lethal (n = 8) disease (median follow-up 19.5 years). Validation of differentially methylated regions (DMRs) was performed in an independent cohort (n = 185, median follow-up 15 years) using targeted multiplex bisulphite sequencing of candidate regions. Survival was assessed via univariable and multivariable analyses including clinicopathological measures (log-rank and Cox regression models). RESULTS WGBS data analysis identified cancer-specific methylation patterns including CpG island hypermethylation, and hypomethylation of repetitive elements, with increasing disease risk. We identified 1420 DMRs associated with prostate cancer-specific mortality (PCSM), which showed enrichment for gene sets downregulated in prostate cancer and de novo methylated in cancer. Through comparison with public prostate cancer datasets, we refined the DMRs to develop an 18-gene prognostic panel. Applying this panel to an independent cohort, we found significant associations between PCSM and hypermethylation at EPHB3, PARP6, TBX1, MARCH6 and a regulatory element within CACNA2D4. Strikingly in a multivariable model, inclusion of CACNA2D4 methylation was a better predictor of PCSM versus grade alone (Harrell's C-index: 0.779 vs. 0.684). CONCLUSIONS Our study provides detailed methylome maps of non-lethal and lethal prostate cancer and identifies novel genic regions that distinguish these patient groups. Inclusion of our DNA methylation biomarkers with existing clinicopathological measures improves prognostic models of prostate cancer mortality, and holds promise for clinical application.
Collapse
Affiliation(s)
- Ruth Pidsley
- Garvan Institute of Medical ResearchSydneyNew South WalesAustralia,School of Clinical MedicineSt Vincent's Healthcare Clinical Campus, Faculty of Medicine and Health, UNSW SydneySydneyNew South WalesAustralia
| | - Dilys Lam
- Garvan Institute of Medical ResearchSydneyNew South WalesAustralia,Present address:
School of Molecular Sciences, The University of Western Australia, Crawley, Western Australia 6009, Australia,Present address:
Harry Perkins Institute of Medical Research, Nedlands, Western Australia 6009, Australia
| | - Wenjia Qu
- Garvan Institute of Medical ResearchSydneyNew South WalesAustralia
| | - Timothy J. Peters
- Garvan Institute of Medical ResearchSydneyNew South WalesAustralia,School of Clinical MedicineSt Vincent's Healthcare Clinical Campus, Faculty of Medicine and Health, UNSW SydneySydneyNew South WalesAustralia
| | - Phuc‐Loi Luu
- Garvan Institute of Medical ResearchSydneyNew South WalesAustralia,School of Clinical MedicineSt Vincent's Healthcare Clinical Campus, Faculty of Medicine and Health, UNSW SydneySydneyNew South WalesAustralia
| | - Darren Korbie
- Centre for Personalised NanomedicineAustralian Institute for Bioengineering and NanotechnologyThe University of QueenslandSt. LuciaQueenslandAustralia
| | - Clare Stirzaker
- Garvan Institute of Medical ResearchSydneyNew South WalesAustralia,School of Clinical MedicineSt Vincent's Healthcare Clinical Campus, Faculty of Medicine and Health, UNSW SydneySydneyNew South WalesAustralia
| | - Roger J. Daly
- Cancer Research Program and Department of Biochemistry and Molecular BiologyBiomedicine Discovery InstituteMonash UniversityClaytonVictoriaAustralia
| | - Phillip Stricker
- Garvan Institute of Medical ResearchSydneyNew South WalesAustralia,School of Clinical MedicineSt Vincent's Healthcare Clinical Campus, Faculty of Medicine and Health, UNSW SydneySydneyNew South WalesAustralia,Department of UrologySt. Vincent's Prostate Cancer CentreSydneyNew South WalesAustralia
| | - James G. Kench
- Garvan Institute of Medical ResearchSydneyNew South WalesAustralia,Department of Tissue PathologyNSW Health PathologyRoyal Prince Alfred HospitalCamperdownSydneyNew South WalesAustralia
| | - Lisa G. Horvath
- Garvan Institute of Medical ResearchSydneyNew South WalesAustralia,School of Clinical MedicineSt Vincent's Healthcare Clinical Campus, Faculty of Medicine and Health, UNSW SydneySydneyNew South WalesAustralia,Chris O'Brien Lifehouse, CamperdownSydneyNew South WalesAustralia,University of SydneySydneyNew South WalesAustralia
| | - Susan J. Clark
- Garvan Institute of Medical ResearchSydneyNew South WalesAustralia,School of Clinical MedicineSt Vincent's Healthcare Clinical Campus, Faculty of Medicine and Health, UNSW SydneySydneyNew South WalesAustralia
| |
Collapse
|
4
|
Supplitt S, Karpinski P, Sasiadek M, Laczmanska I. Current Achievements and Applications of Transcriptomics in Personalized Cancer Medicine. Int J Mol Sci 2021; 22:1422. [PMID: 33572595 PMCID: PMC7866970 DOI: 10.3390/ijms22031422] [Citation(s) in RCA: 48] [Impact Index Per Article: 16.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2020] [Revised: 01/19/2021] [Accepted: 01/21/2021] [Indexed: 12/12/2022] Open
Abstract
Over the last decades, transcriptome profiling emerged as one of the most powerful approaches in oncology, providing prognostic and predictive utility for cancer management. The development of novel technologies, such as revolutionary next-generation sequencing, enables the identification of cancer biomarkers, gene signatures, and their aberrant expression affecting oncogenesis, as well as the discovery of molecular targets for anticancer therapies. Transcriptomics contribute to a change in the holistic understanding of cancer, from histopathological and organic to molecular classifications, opening a more personalized perspective for tumor diagnostics and therapy. The further advancement on transcriptome profiling may allow standardization and cost reduction of its analysis, which will be the next step for transcriptomics to become a canon of contemporary cancer medicine.
Collapse
Affiliation(s)
- Stanislaw Supplitt
- Department of Genetics, Wroclaw Medical University, Marcinkowskiego 1, 50-368 Wroclaw, Poland; (P.K.); (M.S.); (I.L.)
| | - Pawel Karpinski
- Department of Genetics, Wroclaw Medical University, Marcinkowskiego 1, 50-368 Wroclaw, Poland; (P.K.); (M.S.); (I.L.)
- Laboratory of Genomics and Bioinformatics, Hirszfeld Institute of Immunology and Experimental Therapy, Polish Academy of Sciences, Weigla 12, 53-114 Wroclaw, Poland
| | - Maria Sasiadek
- Department of Genetics, Wroclaw Medical University, Marcinkowskiego 1, 50-368 Wroclaw, Poland; (P.K.); (M.S.); (I.L.)
| | - Izabela Laczmanska
- Department of Genetics, Wroclaw Medical University, Marcinkowskiego 1, 50-368 Wroclaw, Poland; (P.K.); (M.S.); (I.L.)
| |
Collapse
|
5
|
Karstoft KI, Tsamardinos I, Eskelund K, Andersen SB, Nissen LR. Applicability of an Automated Model and Parameter Selection in the Prediction of Screening-Level PTSD in Danish Soldiers Following Deployment: Development Study of Transferable Predictive Models Using Automated Machine Learning. JMIR Med Inform 2020; 8:e17119. [PMID: 32706722 PMCID: PMC7407253 DOI: 10.2196/17119] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2019] [Revised: 03/30/2020] [Accepted: 04/16/2020] [Indexed: 12/14/2022] Open
Abstract
BACKGROUND Posttraumatic stress disorder (PTSD) is a relatively common consequence of deployment to war zones. Early postdeployment screening with the aim of identifying those at risk for PTSD in the years following deployment will help deliver interventions to those in need but have so far proved unsuccessful. OBJECTIVE This study aimed to test the applicability of automated model selection and the ability of automated machine learning prediction models to transfer across cohorts and predict screening-level PTSD 2.5 years and 6.5 years after deployment. METHODS Automated machine learning was applied to data routinely collected 6-8 months after return from deployment from 3 different cohorts of Danish soldiers deployed to Afghanistan in 2009 (cohort 1, N=287 or N=261 depending on the timing of the outcome assessment), 2010 (cohort 2, N=352), and 2013 (cohort 3, N=232). RESULTS Models transferred well between cohorts. For screening-level PTSD 2.5 and 6.5 years after deployment, random forest models provided the highest accuracy as measured by area under the receiver operating characteristic curve (AUC): 2.5 years, AUC=0.77, 95% CI 0.71-0.83; 6.5 years, AUC=0.78, 95% CI 0.73-0.83. Linear models performed equally well. Military rank, hyperarousal symptoms, and total level of PTSD symptoms were highly predictive. CONCLUSIONS Automated machine learning provided validated models that can be readily implemented in future deployment cohorts in the Danish Defense with the aim of targeting postdeployment support interventions to those at highest risk for developing PTSD, provided the cohorts are deployed on similar missions.
Collapse
Affiliation(s)
- Karen-Inge Karstoft
- Research and Knowledge Centre, The Danish Veterans Centre, Ringsted, Denmark.,Department of Psychology, University of Copenhagen, Copenhagen, Denmark
| | - Ioannis Tsamardinos
- Department of Computer Science, University of Crete, Heraklion, Crete, Greece.,Gnosis Data Analysis PC, Heraklion, Greece
| | - Kasper Eskelund
- Research and Knowledge Centre, The Danish Veterans Centre, Ringsted, Denmark.,Department of Military Psychology, The Danish Veterans Centre, Copenhagen, Denmark
| | - Søren Bo Andersen
- Research and Knowledge Centre, The Danish Veterans Centre, Ringsted, Denmark
| | | |
Collapse
|