DNA methylation-based classifier differentiates intrahepatic pancreato-biliary tumoursResearch in context
Summary: Background: Differentiating intrahepatic cholangiocarcinomas (iCCA) from hepatic metastases of pancreatic ductal adenocarcinoma (PAAD) is challenging. Both tumours have similar morphological and immunohistochemical pattern and share multiple driver mutations. We hypothesised that DNA methy...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-07-01
|
| Series: | EBioMedicine |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352396423002220 |
| _version_ | 1827919403540283392 |
|---|---|
| author | Mihnea P. Dragomir Teodor G. Calina Eilís Perez Simon Schallenberg Meng Chen Thomas Albrecht Ines Koch Peggy Wolkenstein Benjamin Goeppert Stephanie Roessler George A. Calin Christine Sers David Horst Florian Roßner David Capper |
| author_facet | Mihnea P. Dragomir Teodor G. Calina Eilís Perez Simon Schallenberg Meng Chen Thomas Albrecht Ines Koch Peggy Wolkenstein Benjamin Goeppert Stephanie Roessler George A. Calin Christine Sers David Horst Florian Roßner David Capper |
| author_sort | Mihnea P. Dragomir |
| collection | DOAJ |
| description | Summary: Background: Differentiating intrahepatic cholangiocarcinomas (iCCA) from hepatic metastases of pancreatic ductal adenocarcinoma (PAAD) is challenging. Both tumours have similar morphological and immunohistochemical pattern and share multiple driver mutations. We hypothesised that DNA methylation-based machine-learning algorithms may help perform this task. Methods: We assembled genome-wide DNA methylation data for iCCA (n = 259), PAAD (n = 431), and normal bile duct (n = 70) from publicly available sources. We split this cohort into a reference (n = 399) and a validation set (n = 361). Using the reference cohort, we trained three machine learning models to differentiate between these entities. Furthermore, we validated the classifiers on the technical validation set and used an internal cohort (n = 72) to test our classifier. Findings: On the validation cohort, the neural network, support vector machine, and the random forest classifiers reached accuracies of 97.68%, 95.62%, and 96.5%, respectively. Filtering by anomaly detection and thresholds improved the accuracy to 99.07% (37 samples excluded by filtering), 96.22% (17 samples excluded), and 100% (44 samples excluded) for the neural network, support vector machine and random forest, respectively. Because of best balance between accuracy and number of predictable cases we tested the neural network with applied filters on the in-house cohort, obtaining an accuracy of 95.45%. Interpretation: We developed a classifier that can differentiate between iCCAs, intrahepatic metastases of a PAAD, and normal bile duct tissue with high accuracy. This tool can be used for improving the diagnosis of pancreato-biliary cancers of the liver. Funding: This work was supported by Berlin Institute of Health (JCS Program), DKTK Berlin (Young Investigator Grant 2022), German Research Foundation (493697503 and 314905040 – SFB/TRR 209 Liver Cancer B01), and German Cancer Aid (70113922). |
| first_indexed | 2024-03-13T03:57:23Z |
| format | Article |
| id | doaj.art-db8391b0915642daa4b44af43c287256 |
| institution | Directory Open Access Journal |
| issn | 2352-3964 |
| language | English |
| last_indexed | 2024-03-13T03:57:23Z |
| publishDate | 2023-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EBioMedicine |
| spelling | doaj.art-db8391b0915642daa4b44af43c2872562023-06-22T05:04:19ZengElsevierEBioMedicine2352-39642023-07-0193104657DNA methylation-based classifier differentiates intrahepatic pancreato-biliary tumoursResearch in contextMihnea P. Dragomir0Teodor G. Calina1Eilís Perez2Simon Schallenberg3Meng Chen4Thomas Albrecht5Ines Koch6Peggy Wolkenstein7Benjamin Goeppert8Stephanie Roessler9George A. Calin10Christine Sers11David Horst12Florian Roßner13David Capper14Institute of Pathology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany; German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, Germany; Berlin Institute of Health, Berlin, Germany; Corresponding author. Institute of Pathology, Charité-Universitätsmedizin Berlin, Corporate member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Charitéplatz 1, 10117 Berlin, Germany.TGC Ventures UG, Berlin, GermanyDepartment of Neuropathology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany; Berlin School of Integrative Oncology (BSIO), Charite - Universitätsmedizin Berlin (CVK), Berlin, GermanyInstitute of Pathology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, GermanyDepartment of Translational Molecular Pathology, The University of Texas MD Anderson Cancer Center, Houston, TX, USAInstitute of Pathology, Heidelberg University Hospital, Heidelberg, GermanyInstitute of Pathology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, GermanyGerman Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, GermanyInstitute of Pathology, Heidelberg University Hospital, Heidelberg, Germany; Institute of Pathology and Neuropathology, Hospital RKH Kliniken Ludwigsburg, 71640 Ludwigsburg, GermanyInstitute of Pathology, Heidelberg University Hospital, Heidelberg, GermanyDepartment of Translational Molecular Pathology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA; Center for RNA Interference and Non-coding RNAs, The University of Texas MD Anderson Cancer Center, Houston, TX, USAInstitute of Pathology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, GermanyInstitute of Pathology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany; German Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, GermanyInstitute of Pathology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, GermanyGerman Cancer Consortium (DKTK), Partner Site Berlin, and German Cancer Research Center (DKFZ), Heidelberg, Germany; Department of Neuropathology, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, GermanySummary: Background: Differentiating intrahepatic cholangiocarcinomas (iCCA) from hepatic metastases of pancreatic ductal adenocarcinoma (PAAD) is challenging. Both tumours have similar morphological and immunohistochemical pattern and share multiple driver mutations. We hypothesised that DNA methylation-based machine-learning algorithms may help perform this task. Methods: We assembled genome-wide DNA methylation data for iCCA (n = 259), PAAD (n = 431), and normal bile duct (n = 70) from publicly available sources. We split this cohort into a reference (n = 399) and a validation set (n = 361). Using the reference cohort, we trained three machine learning models to differentiate between these entities. Furthermore, we validated the classifiers on the technical validation set and used an internal cohort (n = 72) to test our classifier. Findings: On the validation cohort, the neural network, support vector machine, and the random forest classifiers reached accuracies of 97.68%, 95.62%, and 96.5%, respectively. Filtering by anomaly detection and thresholds improved the accuracy to 99.07% (37 samples excluded by filtering), 96.22% (17 samples excluded), and 100% (44 samples excluded) for the neural network, support vector machine and random forest, respectively. Because of best balance between accuracy and number of predictable cases we tested the neural network with applied filters on the in-house cohort, obtaining an accuracy of 95.45%. Interpretation: We developed a classifier that can differentiate between iCCAs, intrahepatic metastases of a PAAD, and normal bile duct tissue with high accuracy. This tool can be used for improving the diagnosis of pancreato-biliary cancers of the liver. Funding: This work was supported by Berlin Institute of Health (JCS Program), DKTK Berlin (Young Investigator Grant 2022), German Research Foundation (493697503 and 314905040 – SFB/TRR 209 Liver Cancer B01), and German Cancer Aid (70113922).http://www.sciencedirect.com/science/article/pii/S2352396423002220PathologyMachine learningOncologyMolecular diagnosisEpigenetic |
| spellingShingle | Mihnea P. Dragomir Teodor G. Calina Eilís Perez Simon Schallenberg Meng Chen Thomas Albrecht Ines Koch Peggy Wolkenstein Benjamin Goeppert Stephanie Roessler George A. Calin Christine Sers David Horst Florian Roßner David Capper DNA methylation-based classifier differentiates intrahepatic pancreato-biliary tumoursResearch in context EBioMedicine Pathology Machine learning Oncology Molecular diagnosis Epigenetic |
| title | DNA methylation-based classifier differentiates intrahepatic pancreato-biliary tumoursResearch in context |
| title_full | DNA methylation-based classifier differentiates intrahepatic pancreato-biliary tumoursResearch in context |
| title_fullStr | DNA methylation-based classifier differentiates intrahepatic pancreato-biliary tumoursResearch in context |
| title_full_unstemmed | DNA methylation-based classifier differentiates intrahepatic pancreato-biliary tumoursResearch in context |
| title_short | DNA methylation-based classifier differentiates intrahepatic pancreato-biliary tumoursResearch in context |
| title_sort | dna methylation based classifier differentiates intrahepatic pancreato biliary tumoursresearch in context |
| topic | Pathology Machine learning Oncology Molecular diagnosis Epigenetic |
| url | http://www.sciencedirect.com/science/article/pii/S2352396423002220 |
| work_keys_str_mv | AT mihneapdragomir dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext AT teodorgcalina dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext AT eilisperez dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext AT simonschallenberg dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext AT mengchen dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext AT thomasalbrecht dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext AT ineskoch dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext AT peggywolkenstein dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext AT benjamingoeppert dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext AT stephanieroessler dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext AT georgeacalin dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext AT christinesers dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext AT davidhorst dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext AT florianroßner dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext AT davidcapper dnamethylationbasedclassifierdifferentiatesintrahepaticpancreatobiliarytumoursresearchincontext |