Validation of Whole Genome Methylation Profiling Classifier for Central Nervous System Tumors

Abstract

The 2021 WHO Classification of Tumors of the Central Nervous System includes several tumor types and subtypes for which the diagnosis is at least partially reliant on utilization of whole genome methylation profiling. The current approach to array DNA methylation profiling utilizes a reference library of tumor DNA methylation data, and a machine learning–based tumor classifier. This approach was pioneered and popularized by the German Cancer Research Network (DKFZ) and University Hospital Heidelberg. This research group has kindly made their classifier for central nervous system tumors freely available as a research tool via a web-based portal. However, their classifier is not maintained in a clinical testing environment. Therefore, the Northwestern Medicine (NM) classifier was developed and validated. The NM classifier was validated using the same training and validation data sets as the DKFZ group. Using the DKFZ validation data set, the NM classifier's performance showed high concordance (92%) and comparable accuracy (specificity 94.0% versus 84.9% for DKFZ, sensitivity 88.6% versus 94.7% for DKFZ). Receiver-operator characteristic curves showed areas under the curve of 0.964 versus 0.966 for NM and DKFZ classifiers, respectively. In addition, in-house validation was performed and performance was compared using both classifiers. The NM classifier performed comparably well and is currently offered for clinical testing. The 2021 WHO Classification of Tumors of the Central Nervous System includes several tumor types and subtypes for which the diagnosis is at least partially reliant on utilization of whole genome methylation profiling. The current approach to array DNA methylation profiling utilizes a reference library of tumor DNA methylation data, and a machine learning–based tumor classifier. This approach was pioneered and popularized by the German Cancer Research Network (DKFZ) and University Hospital Heidelberg. This research group has kindly made their classifier for central nervous system tumors freely available as a research tool via a web-based portal. However, their classifier is not maintained in a clinical testing environment. Therefore, the Northwestern Medicine (NM) classifier was developed and validated. The NM classifier was validated using the same training and validation data sets as the DKFZ group. Using the DKFZ validation data set, the NM classifier's performance showed high concordance (92%) and comparable accuracy (specificity 94.0% versus 84.9% for DKFZ, sensitivity 88.6% versus 94.7% for DKFZ). Receiver-operator characteristic curves showed areas under the curve of 0.964 versus 0.966 for NM and DKFZ classifiers, respectively. In addition, in-house validation was performed and performance was compared using both classifiers. The NM classifier performed comparably well and is currently offered for clinical testing. Historically, central nervous system (CNS) tumor classification and grading have been based on histology. Although histology provides crucial diagnostic information, there is inherent subjectivity and interobserver variability in diagnoses based solely on morphology. The importance of advanced molecular testing for diagnosis, prognosis, and targeted therapy has made ancillary molecular studies integral for classification and grading of CNS tumors today.1Horbinski C. Ligon K.L. Brastianos P. Huse J.T. Venere M. Chang S. Buckner J. Cloughesy T. Jenkins R.B. Giannini C. Stupp R. Nabors L.B. Wen P.Y. Aldape K.J. Lukas R.V. Galanis E. Eberhart C.G. Brat D.J. Sarkaria J.N. The medical necessity of advanced molecular testing in the diagnosis and treatment of brain tumor patients.Neuro Oncol. 2019; 21: 1498-1508Crossref PubMed Scopus (23) Google Scholar The 2016 and, more recently, the 2021 World Health Organization CNS tumor classification system,2Louis D.N. Perry A. Wesseling P. Brat D.J. Cree I.A. Figarella-Branger D. Hawkins C. Ng H.K. Pfister S.M. Reifenberger G. Soffietti R. von Deimling A. Ellison D.W. The 2021 WHO Classification of Tumors of the Central Nervous System: a summary.Neuro Oncol. 2021; 23: 1231-1251Crossref PubMed Scopus (877) Google Scholar list many important genetic alterations for diagnoses (eg, IDH, ATRX, TP53, TERT promoter, H3F3A, BRAF, MYB, MYBL1, MN1, etc.). Capitalizing on the genomic signature of a tumor, array DNA methylation profiling has proven valuable for the classification of tumors with diagnostically challenging or unusual morphology. It is also useful for identifying subtypes within certain tumor families.3Capper D. Jones D.T.W. Sill M. Hovestadt V. Schrimpf D. Sturm D. et al.DNA methylation-based classification of central nervous system tumours.Nature. 2018; 555: 469-474Crossref PubMed Scopus (1054) Google Scholar,4Capper D. Stichel D. Sahm F. Jones D.T.W. Schrimpf D. Sill M. Schmid S. Hovestadt V. Reuss D.E. Koelsche C. Reinhardt A. Wefers A.K. Huang K. Sievers P. Ebrahimi A. Schöler A. Teichmann D. Koch A. Hänggi D. Unterberg A. Platten M. Wick W. Witt O. Milde T. Korshunov A. Pfister S.M. von Deimling A. Practical implementation of DNA methylation and copy-number-based CNS tumor diagnostics: the Heidelberg experience.Acta Neuropathol. 2018; 136: 181-210Crossref PubMed Scopus (162) Google Scholar Furthermore, it has proven valuable in characterizing new tumor classes.5Sturm D. Orr B.A. Toprak U.H. Hovestadt V. Jones D.T.W. Capper D. et al.New brain tumor entities emerge from molecular classification of CNS-PNETs.Cell. 2016; 164: 1060-1072Abstract Full Text Full Text PDF PubMed Scopus (482) Google Scholar For instance, ependymomas are a morphologically similar family of tumors. However, DNA methylation profiling has defined biologically distinct types, which occur in distinct anatomic locations and distinct patient populations.6Witt H. Gramatzki D. Hentschel B. Pajtler K.W. Felsberg J. Schackert G. Löffler M. Capper D. Sahm F. Sill M. von Deimling A. Kool M. Herrlinger U. Westphal M. Pietsch T. Reifenberger G. Pfister S.M. Tonn J.C. Weller M. German Glioma Network DNA methylation-based classification of ependymomas in adulthood: implications for diagnosis and treatment.Neuro Oncol. 2018; 20: 1616-1624Crossref PubMed Scopus (35) Google Scholar,7Ellison D.W. Aldape K.D. Capper D. Fouladi M. Gilbert M.R. Gilbertson R.J. Hawkins C. Merchant T.E. Pajtler K. Venneti S. Louis D.N. cIMPACT-NOW update 7: advancing the molecular classification of ependymal tumors.Brain Pathol. 2020; 30: 863-866PubMed Google Scholar Some ependymoma types are characterized by distinct genetic alterations (ie, ZFTA1 and YAP1 fusions). Other types, such as posterior fossa groups A and B, lack distinct mutations and are most reliably distinguished by DNA methylation profiling.7Ellison D.W. Aldape K.D. Capper D. Fouladi M. Gilbert M.R. Gilbertson R.J. Hawkins C. Merchant T.E. Pajtler K. Venneti S. Louis D.N. cIMPACT-NOW update 7: advancing the molecular classification of ependymal tumors.Brain Pathol. 2020; 30: 863-866PubMed Google Scholar Medulloblastoma molecular subgroups were originally defined by transcriptome analysis.8Taylor M.D. Northcott P.A. Korshunov A. Remke M. Cho Y.-J. Clifford S.C. Eberhart C.G. Parsons D.W. Rutkowski S. Gajjar A. Ellison D.W. Lichter P. Gilbertson R.J. Pomeroy S.L. Kool M. Pfister S.M. Molecular subgroups of medulloblastoma: the current consensus.Acta Neuropathol. 2012; 123: 465-472Crossref PubMed Scopus (1179) Google Scholar They can also be distinguished by DNA methylation profiling.9Schwalbe E.C. Williamson D. Lindsey J.C. Hamilton D. Ryan S.L. Megahed H. Garami M. Hauser P. Dembowska-Baginska B. Perek D. Northcott P.A. Taylor M.D. Taylor R.E. Ellison D.W. Bailey S. Clifford S.C. DNA methylation profiling of medulloblastoma allows robust subclassification and improved outcome prediction using formalin-fixed biopsies.Acta Neuropathol. 2013; 125: 359-371Crossref PubMed Scopus (105) Google Scholar,10Korshunov A. Sahm F. Zheludkova O. Golanov A. Stichel D. Schrimpf D. Ryzhova M. Potapov A. Habel A. Meyer J. Lichter P. Jones D.T.W. von Deimling A. Pfister S.M. Kool M. DNA methylation profiling is a method of choice for molecular verification of pediatric WNT-activated medulloblastomas.Neuro Oncol. 2019; 21: 214-221Crossref PubMed Scopus (18) Google Scholar Morphology-based grading of meningiomas is complex, and certain morphologic grading criteria are subject to interobserver variability.11Rogers C.L. Perry A. Pugh S. Vogelbaum M.A. Brachman D. McMillan W. Jenrette J. Barani I. Shrieve D. Sloan A. Bovi J. Kwok Y. Burri S.H. Chao S.T. Spalding A.C. Anscher M.S. Bloom B. Mehta M. Pathology concordance levels for meningioma classification and grading in NRG Oncology RTOG Trial 0539.Neuro Oncol. 2016; 18: 565-574Crossref PubMed Scopus (68) Google Scholar DNA methylation profiling has proven to be an objective, reliable tool in predicting risk of recurrence in meningioma.12Nassiri F. Mamatjan Y. Suppiah S. Badhiwala J.H. Mansouri S. Karimi S. Saarela O. Poisson L. Gepfner-Tuma I. Schittenhelm J. Ng H.-K. Noushmehr H. Harter P. Baumgarten P. Weller M. Preusser M. Herold-Mende C. Tatagiba M. Tabatabai G. Sahm F. von Deimling A. International Consortium on Meningiomas Zadeh G. Aldape K.D. DNA methylation profiling to predict recurrence risk in meningioma: development and validation of a nomogram to optimize clinical management.Neuro Oncol. 2019; 21: 901-910Crossref PubMed Scopus (88) Google Scholar,13Maas S.L.N. Stichel D. Hielscher T. Sievers P. Berghoff A.S. Schrimpf D. et al.Integrated molecular-morphologic meningioma classification: a multicenter retrospective analysis, retrospectively and prospectively validated.J Clin Oncol. 2021; 39: 3839-3852Crossref PubMed Scopus (21) Google Scholar Methylation profiling has also proven useful in identifying pleomorphic xanthoastrocytoma and anaplastic pleomorphic xanthoastrocytoma, which can have quite heterogeneous morphology.14Vaubel R. Zschernack V. Tran Q.T. Jenkins S. Caron A. Milosevic D. Smadbeck J. Vasmatzis G. Kandels D. Gnekow A. Kramm C. Jenkins R. Kipp B.R. Rodriguez F.J. Orr B.A. Pietsch T. Giannini C. Biology and grading of pleomorphic xanthoastrocytoma-what have we learned about it?.Brain Pathol. 2021; 31: 20-32Crossref PubMed Scopus (11) Google Scholar,15Kam K.-L. Snuderl M. Khan O. Wolinsky J.-P. Gondi V. Grimm S. Horbinski C. Using methylation profiling to diagnose systemic metastases of pleomorphic xanthoastrocytoma.Neurooncol Adv. 2020; 2: vdz057PubMed Google Scholar DNA methylation profiling revealed that the tumor class formerly known as primitive neuroectodermal tumors of the CNS, which are characterized by small round blue cell histology, is actually composed of a number of biologically distinct tumor groups with unique genetic drivers.5Sturm D. Orr B.A. Toprak U.H. Hovestadt V. Jones D.T.W. Capper D. et al.New brain tumor entities emerge from molecular classification of CNS-PNETs.Cell. 2016; 164: 1060-1072Abstract Full Text Full Text PDF PubMed Scopus (482) Google Scholar The current approach to array DNA methylation profiling utilizes a reference library of tumor DNA methylation data, and a machine learning–based tumor classifier. This approach was pioneered and popularized by the German Cancer Research Network (DKFZ) and University Hospital Heidelberg.3Capper D. Jones D.T.W. Sill M. Hovestadt V. Schrimpf D. Sturm D. et al.DNA methylation-based classification of central nervous system tumours.Nature. 2018; 555: 469-474Crossref PubMed Scopus (1054) Google Scholar,4Capper D. Stichel D. Sahm F. Jones D.T.W. Schrimpf D. Sill M. Schmid S. Hovestadt V. Reuss D.E. Koelsche C. Reinhardt A. Wefers A.K. Huang K. Sievers P. Ebrahimi A. Schöler A. Teichmann D. Koch A. Hänggi D. Unterberg A. Platten M. Wick W. Witt O. Milde T. Korshunov A. Pfister S.M. von Deimling A. Practical implementation of DNA methylation and copy-number-based CNS tumor diagnostics: the Heidelberg experience.Acta Neuropathol. 2018; 136: 181-210Crossref PubMed Scopus (162) Google Scholar This research group has kindly made their classifier for central nervous system tumors freely available as a research tool via a web-based portal. However, this classifier is not maintained in clinical testing environment. Therefore, the Northwestern Medicine (NM) classifier of CNS tumors was developed and validated. The NM classifier was trained using the same 2801 publicly available samples, as well as the same normalization strategies that were used by the DKFZ group, and validated using the same 1104 publicly available samples. Additional validation data were collected in-house and analyzed using both classifiers for comparison. A previously published data set3Capper D. Jones D.T.W. Sill M. Hovestadt V. Schrimpf D. Sturm D. et al.DNA methylation-based classification of central nervous system tumours.Nature. 2018; 555: 469-474Crossref PubMed Scopus (1054) Google Scholar comprising 3905 central nervous tumor samples was downloaded from GEO (https://www.ncbi.nlm.nih.gov/geo; accession number GSE109381). From that data set, 2801 samples were used in the original classifier training, and 1104 were used for validation, respectively labeled reference set and validation set in the GEO series metadata. In-house validation samples are available in GEO under the accession number GSE198855. Signal intensities were extracted from the methylation array raw data (IDAT files) using the minfi R package H. C. K.D. a and package for the of DNA methylation 30: PubMed Scopus Google Scholar were to previously D. Jones D.T.W. Sill M. Hovestadt V. Schrimpf D. Sturm D. et al.DNA methylation-based classification of central nervous system tumours.Nature. 2018; 555: 469-474Crossref PubMed Scopus (1054) Google Scholar intensities were used to to were and was not in the were in targeted or within of it and to more in the genome available data were analyzed using in-house samples were analyzed using Therefore, to the classifier with both were A of were used in was performed using the same as previously D. Jones D.T.W. Sill M. Hovestadt V. Schrimpf D. Sturm D. et al.DNA methylation-based classification of central nervous system tumours.Nature. 2018; 555: 469-474Crossref PubMed Scopus (1054) Google Scholar the most from 2801 training samples were was and were used for The for and for were used for and analysis, respectively. were used for studies showed classification performance of CNS tumors with a classifier by using an D. Jones D.T.W. Sill M. Hovestadt V. Schrimpf D. Sturm D. et al.DNA methylation-based classification of central nervous system tumours.Nature. 2018; 555: 469-474Crossref PubMed Scopus (1054) Google Scholar For the NM a similar was used and training was performed using the original training data set of 2801 samples. the from were This classifier the most important were by training a classifier using the The most important were and in classifier was by the in classification accuracy the was were by the of the importance The classification was trained by with the most important as previously D. Jones D.T.W. Sill M. Hovestadt V. Schrimpf D. Sturm D. et al.DNA methylation-based classification of central nervous system tumours.Nature. 2018; 555: 469-474Crossref PubMed Scopus (1054) Google Scholar classifier was trained using the R package for is to to class that can be used in a clinical Therefore, the was which as and methylation class as the and to are to in the Therefore, by a were The package for was used to this training, the classifier accuracy was using the previously D. Jones D.T.W. Sill M. Hovestadt V. Schrimpf D. Sturm D. et al.DNA methylation-based classification of central nervous system tumours.Nature. 2018; 555: 469-474Crossref PubMed Scopus (1054) Google Scholar In of the data was used as an validation set, the was used as a training the 2801 training samples have been by an trained The classifier and were also validated using an data set of 1104 CNS tumor Additional validation was performed by profiling samples collected in-house and analyzed using both the DKFZ and NM classifiers for comparison. in the were from brain which was formalin-fixed for by and at samples were extracted using DNA or DNA the samples were extracted using both as of the of The DNA from was for for as by the by a with of was by the of of the from the of a by the samples a which is the for for from to of DNA were and using the DNA Methylation Research the for DNA from samples was as previously S. M. A. A. S.M. M. of DNA methylation profiling in formalin-fixed samples using the PubMed Scopus Google Scholar the DNA was with of for at A at was performed with and by the DNA was with a DNA Research and in of DNA was for at by at for with The was with DNA Research and in of was performed to the Methylation as previously with H. C. K.D. a and package for the of DNA methylation 30: PubMed Scopus Google Scholar of DNA was used for and of was used the a CNS tumor reference DNA methylation of 2801 samples were used as previously D. Jones D.T.W. Sill M. Hovestadt V. Schrimpf D. Sturm D. et al.DNA methylation-based classification of central nervous system tumours.Nature. 2018; 555: 469-474Crossref PubMed Scopus (1054) Google Scholar was performed using which the of distinct methylation in with D. Jones D.T.W. Sill M. Hovestadt V. Schrimpf D. Sturm D. et al.DNA methylation-based classification of central nervous system tumours.Nature. 2018; 555: 469-474Crossref PubMed Scopus (1054) Google Scholar A classifier was developed using the as previously D. Jones D.T.W. Sill M. Hovestadt V. Schrimpf D. Sturm D. et al.DNA methylation-based classification of central nervous system tumours.Nature. 2018; 555: 469-474Crossref PubMed Scopus (1054) Google Scholar is using a that the raw a or the of this an group of 1104 samples was D. Jones D.T.W. Sill M. Hovestadt V. Schrimpf D. Sturm D. et al.DNA methylation-based classification of central nervous system tumours.Nature. 2018; 555: 469-474Crossref PubMed Scopus (1054) Google Scholar The under the curve was for both the DKFZ and NM classifiers classifiers showed comparable areas under the 0.966 and 0.964 for DKFZ and NM classifiers, respectively A of a of and sensitivity of the to a of with a of and sensitivity of A of a and sensitivity and the and be used for In the DKFZ classifier a of and a sensitivity of the of was of the 1104 samples as compared to the DKFZ classifier can be in samples are and can be to have high using classifier or the not the to the utilization of more classifier. DKFZ and NM concordance was a of was for both classifiers of the the same in the of the classifiers. also showed similar as NM was with a of and DKFZ was with a of the accuracy of the methylation DNA methylation were performed on unique samples a of tumor types The diagnoses were using the of histology, and with ancillary studies available (eg, and methylation compared with diagnosis, was a of was and was the classification was a In DKFZ accuracy was for in-house samples a of was and was the classification was a It is important to that samples on the DKFZ and of samples not using the NM to the accuracy on the The NM and DKFZ was with the with as in that were more are in The were to that was and samples were or more Classification the sets of samples was for of the was in performance for of the that were showed in the by samples extracted with the and showed in the by samples by versus tumor tumor group and with are a IDH, in a new with are a IDH, The DNA is to However, the to as as on the accuracy of the classifier class class class class class and class are not by DNA of in a new Classification and class are not by DNA of such as and tumor the classification of tumors. Therefore, were for in-house accuracy samples. were and classification for and classification and classification and tumor and classification were and respectively. The to a of a that the for of a with diagnostic and clinical Therefore, methylation and are the and are a for are a for is reference for this brain tumor classifier. Although samples were in the development and validation of the classifier (eg, diagnostic are not to be the or reference The of whole genome methylation profiling of brain tumors for clinical testing was the development and validation of the NM classifier. the of was made publicly D. Jones D.T.W. Sill M. Hovestadt V. Schrimpf D. Sturm D. et al.DNA methylation-based classification of central nervous system tumours.Nature. 2018; 555: 469-474Crossref PubMed Scopus (1054) Google Scholar Using the same data sets and normalization the NM classifier be developed and validated with an set of data and showed the NM classifier to be comparably samples can be with high by not with This is to in the development of the and the of more classifier to a to in-house validation samples and compared with the diagnosis, the NM classifier accuracy was a of was and was the classification was a versus and for It be that the for the DKFZ was samples on the DKFZ and of samples not using the NM to the accuracy on the The accuracy a the accuracy of both classifiers (92%) using the 1104 data set that the accuracy for the in-house samples be to The are samples used in the validation, which were DNA samples. Therefore, are the of the be tumor A number can be useful to the and of the DNA for a DNA have more or in the number and tumor have the is for a a new or tumor that was not in the classifier or a of the classifier with clinical histology, and ancillary studies is for with The can also be useful for samples with The is a approach for of The data are of 2801 training samples, and it is a that used to the tumor which is by For high samples with the classifier the is the to a group and provides with number histology, and clinical to the most (eg, tumor or a validation studies methylation array on samples to be robust and such as and tumor on testing of samples showed or and as as showed D. Stichel D. Sahm F. Jones D.T.W. Schrimpf D. Sill M. Schmid S. Hovestadt V. Reuss D.E. Koelsche C. Reinhardt A. Wefers A.K. Huang K. Sievers P. Ebrahimi A. Schöler A. Teichmann D. Koch A. Hänggi D. Unterberg A. Platten M. Wick W. Witt O. Milde T. Korshunov A. Pfister S.M. von Deimling A. Practical implementation of DNA methylation and copy-number-based CNS tumor diagnostics: the Heidelberg experience.Acta Neuropathol. 2018; 136: 181-210Crossref PubMed Scopus (162) Google D. Orr B.A. Toprak U.H. Hovestadt V. Jones D.T.W. Capper D. et al.New brain tumor entities emerge from molecular classification of CNS-PNETs.Cell. 2016; 164: 1060-1072Abstract Full Text Full Text PDF PubMed Scopus (482) Google H. Gramatzki D. Hentschel B. Pajtler K.W. Felsberg J. Schackert G. Löffler M. Capper D. Sahm F. Sill M. von Deimling A. Kool M. Herrlinger U. Westphal M. Pietsch T. Reifenberger G. Pfister S.M. Tonn J.C. Weller M. German Glioma Network DNA methylation-based classification of ependymomas in adulthood: implications for diagnosis and treatment.Neuro Oncol. 2018; 20: 1616-1624Crossref PubMed Scopus (35) Google D.W. Aldape K.D. Capper D. Fouladi M. Gilbert M.R. Gilbertson R.J. Hawkins C. Merchant T.E. Pajtler K. Venneti S. Louis D.N. cIMPACT-NOW update 7: advancing the molecular classification of ependymal tumors.Brain Pathol. 2020; 30: 863-866PubMed Google M.D. Northcott P.A. Korshunov A. Remke M. Cho Y.-J. Clifford S.C. Eberhart C.G. Parsons D.W. Rutkowski S. Gajjar A. Ellison D.W. Lichter P. Gilbertson R.J. Pomeroy S.L. Kool M. Pfister S.M. Molecular subgroups of medulloblastoma: the current consensus.Acta Neuropathol. 2012; 123: 465-472Crossref PubMed Scopus (1179) Google E.C. Williamson D. Lindsey J.C. Hamilton D. Ryan S.L. Megahed H. Garami M. Hauser P. Dembowska-Baginska B. Perek D. Northcott P.A. Taylor M.D. Taylor R.E. Ellison D.W. Bailey S. Clifford S.C. DNA methylation profiling of medulloblastoma allows robust subclassification and improved outcome prediction using formalin-fixed biopsies.Acta Neuropathol. 2013; 125: 359-371Crossref PubMed Scopus (105) Google A. Sahm F. Zheludkova O. Golanov A. Stichel D. Schrimpf D. Ryzhova M. Potapov A. Habel A. Meyer J. Lichter P. Jones D.T.W. von Deimling A. Pfister S.M. Kool M. DNA methylation profiling is a method of choice for molecular verification of pediatric WNT-activated medulloblastomas.Neuro Oncol. 2019; 21: 214-221Crossref PubMed Scopus (18) Google Scholar whole genome methylation profiling of brain tumors can be useful for pediatric brain tumors with and of group and and of In addition, it be used for diagnostically challenging and of new entities that have and useful can be a methylation methylation and number P. M. of the and of genetic and to predict the methylation in and 2016; 18: Full Text Full Text PDF PubMed Scopus Google Scholar have classification of methylation using on the methylation This approach was compared with methylation by as a validation and performed well not For number as compared with there are inherent an to of or However, number can be and validation of this approach to number in brain tumors is in In methylation profiling of brain tumors for clinical testing has been developed and validated. A crucial of this validation was the development and validation of a classifier that can be and within a clinical the classifier to data and clinical of data sets be important for the of this of clinical such are currently and and the validation and performed and and performed testing and analyzed developed classifier and performed and the and and the is the of this and, as to of the data in the and for the of the data and the accuracy of the data with with

Topics & Concepts