{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T06:11:26Z","timestamp":1772172686811,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1008184","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T00:00:00Z","timestamp":1606089600000}}],"reference-count":43,"publisher":"Public Library of Science (PLoS)","issue":"11","license":[{"start":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T00:00:00Z","timestamp":1605052800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>\n                    Complete resection of the tumor is important for survival in glioma patients. Even if the gross total resection was achieved, left-over micro-scale tissue in the excision cavity risks recurrence. High Resolution Magic Angle Spinning Nuclear Magnetic Resonance (HRMAS NMR) technique can distinguish healthy and malign tissue efficiently using peak intensities of biomarker metabolites. The method is fast, sensitive and can work with small and unprocessed samples, which makes it a good fit for real-time analysis during surgery. However, only a targeted analysis for the existence of known tumor biomarkers can be made and this requires a technician with chemistry background, and a pathologist with knowledge on tumor metabolism to be present during surgery. Here, we show that we can accurately perform this analysis in real-time and can analyze the full spectrum in an untargeted fashion using machine learning. We work on a new and large HRMAS NMR dataset of glioma and control samples (n = 565), which are also labeled with a quantitative pathology analysis. Our results show that a random forest based approach can distinguish samples with tumor cells and controls accurately and effectively with a median AUC of 85.6% and AUPR of 93.4%. We also show that we can further distinguish benign and malignant samples with a median AUC of 87.1% and AUPR of 96.1%. We analyze the feature (peak) importance for classification to interpret the results of the classifier. We validate that known malignancy biomarkers such as creatine and 2-hydroxyglutarate play an important role in distinguishing tumor and normal cells and suggest new biomarker regions. The code is released at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"http:\/\/github.com\/ciceklab\/HRMAS_NC\" xlink:type=\"simple\">http:\/\/github.com\/ciceklab\/HRMAS_NC<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1371\/journal.pcbi.1008184","type":"journal-article","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T13:44:12Z","timestamp":1605102252000},"page":"e1008184","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":20,"title":["Machine learning assisted intraoperative assessment of brain tumor margins using HRMAS NMR spectroscopy"],"prefix":"10.1371","volume":"16","author":[{"given":"Doruk","family":"Cakmakci","sequence":"first","affiliation":[]},{"given":"Emin Onur","family":"Karakaslar","sequence":"additional","affiliation":[]},{"given":"Elisa","family":"Ruhland","sequence":"additional","affiliation":[]},{"given":"Marie-Pierre","family":"Chenard","sequence":"additional","affiliation":[]},{"given":"Francois","family":"Proust","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6784-2670","authenticated-orcid":true,"given":"Martial","family":"Piotto","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1822-7759","authenticated-orcid":true,"given":"Izzie Jacques","family":"Namer","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8613-6619","authenticated-orcid":true,"given":"A. Ercument","family":"Cicek","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2020,11,11]]},"reference":[{"issue":"suppl_5","key":"pcbi.1008184.ref001","doi-asserted-by":"crossref","first-page":"v1","DOI":"10.1093\/neuonc\/nox158","article-title":"CBTRUS statistical report: primary brain and other central nervous system tumors diagnosed in the United States in 2010\u20132014","volume":"19","author":"QT Ostrom","year":"2017","journal-title":"Neuro-oncology"},{"issue":"3","key":"pcbi.1008184.ref002","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1227\/NEU.0000000000000845","article-title":"Sex, age, anatomic location, and extent of resection influence outcomes in children with high-grade glioma","volume":"77","author":"HJ McCrea","year":"2015","journal-title":"Neurosurgery"},{"issue":"6","key":"pcbi.1008184.ref003","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1007\/s00701-011-1001-x","article-title":"Cytoreductive surgery of glioblastoma as the key to successful adjuvant therapies: new arguments in an old discussion","volume":"153","author":"W Stummer","year":"2011","journal-title":"Acta neurochirurgica"},{"issue":"5","key":"pcbi.1008184.ref004","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1016\/S1470-2045(06)70665-9","article-title":"Fluorescence-guided surgery with 5-aminolevulinic acid for resection of malignant glioma: a randomised controlled multicentre phase III trial","volume":"7","author":"W Stummer","year":"2006","journal-title":"The lancet oncology"},{"issue":"1-2","key":"pcbi.1008184.ref005","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.wneu.2011.02.005","article-title":"Impact of the combination of 5-aminolevulinic acid\u2013induced fluorescence with intraoperative magnetic resonance imaging\u2013guided surgery for glioma","volume":"76","author":"A Tsugu","year":"2011","journal-title":"World neurosurgery"},{"issue":"11","key":"pcbi.1008184.ref006","doi-asserted-by":"crossref","first-page":"1471","DOI":"10.1016\/j.jocn.2012.03.009","article-title":"Aminolevulinic acid (ALA)\u2013protoporphyrin IX fluorescence guided tumour resection. Part 1: Clinical, radiological and pathological studies","volume":"19","author":"MJ Colditz","year":"2012","journal-title":"Journal of Clinical Neuroscience"},{"issue":"4","key":"pcbi.1008184.ref007","doi-asserted-by":"crossref","first-page":"548","DOI":"10.1364\/BOE.4.000548","article-title":"Two-peaked 5-ALA-induced PpIX fluorescence emission spectrum distinguishes glioblastomas from low grade gliomas and infiltrative component of glioblastomas","volume":"4","author":"B Montcel","year":"2013","journal-title":"Biomedical optics express"},{"issue":"1-2","key":"pcbi.1008184.ref008","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.wneu.2013.06.014","article-title":"Intraoperative fluorescence-guided resection of high-grade gliomas: a comparison of the present techniques and evolution of future strategies","volume":"82","author":"Y Li","year":"2014","journal-title":"World neurosurgery"},{"issue":"12","key":"pcbi.1008184.ref009","doi-asserted-by":"crossref","first-page":"3451","DOI":"10.1158\/0008-5472.CAN-16-0270","article-title":"Label-free neurosurgical pathology with stimulated Raman imaging","volume":"76","author":"FK Lu","year":"2016","journal-title":"Cancer research"},{"issue":"14","key":"pcbi.1008184.ref010","doi-asserted-by":"crossref","first-page":"3942","DOI":"10.1158\/0008-5472.CAN-17-0668","article-title":"Highly accurate detection of cancer in situ with intraoperative, label-free, multimodal optical spectroscopy","volume":"77","author":"M Jermyn","year":"2017","journal-title":"Cancer research"},{"issue":"12","key":"pcbi.1008184.ref011","doi-asserted-by":"crossref","first-page":"5129","DOI":"10.1364\/BOE.7.005129","article-title":"Raman spectroscopy detects distant invasive brain cancer cells centimeters beyond MRI capability in humans","volume":"7","author":"M Jermyn","year":"2016","journal-title":"Biomedical optics express"},{"issue":"5","key":"pcbi.1008184.ref012","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1016\/j.asjsur.2017.06.004","article-title":"5-Aminolevulinic acid fluorescence guided resection of malignant glioma: Hong Kong experience","volume":"41","author":"DTM Chan","year":"2018","journal-title":"Asian journal of surgery"},{"issue":"2","key":"pcbi.1008184.ref013","doi-asserted-by":"crossref","first-page":"0027","DOI":"10.1038\/s41551-016-0027","article-title":"Rapid intraoperative histology of unprocessed surgical specimens via fibre-laser-based stimulated Raman scattering microscopy","volume":"1","author":"DA Orringer","year":"2017","journal-title":"Nature biomedical engineering"},{"issue":"1","key":"pcbi.1008184.ref014","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-017-14381-1","article-title":"Optical properties, spectral, and lifetime measurements of central nervous system tumors in humans","volume":"7","author":"F Poulon","year":"2017","journal-title":"Scientific reports"},{"issue":"1","key":"pcbi.1008184.ref015","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1158\/0008-5472.CAN-17-1974","article-title":"Rapid intraoperative diagnosis of pediatric brain tumors using stimulated Raman histology","volume":"78","author":"TC Hollon","year":"2018","journal-title":"Cancer research"},{"issue":"S 04","key":"pcbi.1008184.ref016","doi-asserted-by":"crossref","first-page":"S340","DOI":"10.1055\/s-0038-1660847","article-title":"Fluorescein-Guided Surgery for Pediatric Brainstem Gliomas: Preliminary Study and Technical Notes","volume":"79","author":"Z Xue","year":"2018","journal-title":"Journal of Neurological Surgery Part B: Skull Base"},{"issue":"4","key":"pcbi.1008184.ref017","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/gm332","article-title":"Cancer detection and biopsy classification using concurrent histopathological and metabolomic analysis of core biopsies","volume":"4","author":"MV Brown","year":"2012","journal-title":"Genome medicine"},{"issue":"20","key":"pcbi.1008184.ref018","doi-asserted-by":"crossref","first-page":"7729","DOI":"10.1021\/ac201251s","article-title":"Real time analysis of brain tissue by direct combination of ultrasonic surgical aspiration and sonic spray mass spectrometry","volume":"83","author":"KC Sch\u00e4fer","year":"2011","journal-title":"Analytical Chemistry"},{"issue":"5","key":"pcbi.1008184.ref019","doi-asserted-by":"crossref","first-page":"1611","DOI":"10.1073\/pnas.1215687110","article-title":"Ambient mass spectrometry for the intraoperative molecular diagnosis of human brain tumors","volume":"110","author":"LS Eberlin","year":"2013","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"26","key":"pcbi.1008184.ref020","doi-asserted-by":"crossref","first-page":"6700","DOI":"10.1073\/pnas.1706459114","article-title":"Intraoperative assessment of tumor margins during glioma resection by desorption electrospray ionization-mass spectrometry","volume":"114","author":"V Pirro","year":"2017","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"30","key":"pcbi.1008184.ref021","doi-asserted-by":"crossref","first-page":"11121","DOI":"10.1073\/pnas.1404724111","article-title":"Intraoperative mass spectrometry mapping of an onco-metabolite to guide brain tumor surgery","volume":"111","author":"S Santagata","year":"2014","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"pcbi.1008184.ref022","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1016\/j.ijms.2014.06.024","article-title":"Molecular typing of meningiomas by desorption electrospray ionization mass spectrometry imaging for surgical decision-making","volume":"377","author":"D Calligaris","year":"2015","journal-title":"International journal of mass spectrometry"},{"issue":"32","key":"pcbi.1008184.ref023","doi-asserted-by":"crossref","first-page":"9978","DOI":"10.1073\/pnas.1423101112","article-title":"MALDI mass spectrometry imaging analysis of pituitary adenomas for near-real-time tumor delineation","volume":"112","author":"D Calligaris","year":"2015","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"6","key":"pcbi.1008184.ref024","doi-asserted-by":"crossref","first-page":"1486","DOI":"10.1073\/pnas.1523306113","article-title":"Lipid and metabolite profiles of human brain tumors by desorption electrospray ionization-MS","volume":"113","author":"AK Jarmusch","year":"2016","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"1","key":"pcbi.1008184.ref025","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/srep25919","article-title":"In vivo real-time mass spectrometry for guided surgery application","volume":"6","author":"B Fatou","year":"2016","journal-title":"Scientific reports"},{"issue":"2","key":"pcbi.1008184.ref026","doi-asserted-by":"crossref","first-page":"19","DOI":"10.3390\/metabo9020019","article-title":"HR-MAS NMR based quantitative metabolomics in breast cancer","volume":"9","author":"M Gogiashvili","year":"2019","journal-title":"Metabolites"},{"issue":"1","key":"pcbi.1008184.ref027","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1186\/s12916-017-0810-z","article-title":"Metabolomics approaches in pancreatic adenocarcinoma: tumor metabolism profiling predicts clinical outcome of patients","volume":"15","author":"S Battini","year":"2017","journal-title":"BMC medicine"},{"issue":"1","key":"pcbi.1008184.ref028","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1002\/mrm.27696","article-title":"A metabolic database for biomedical studies of biopsy specimens by high-resolution magic angle spinning nuclear MR: a qualitative and quantitative tool","volume":"82","author":"E Ruhland","year":"2019","journal-title":"Magnetic resonance in medicine"},{"key":"pcbi.1008184.ref029","doi-asserted-by":"crossref","unstructured":"Karakaslar EO, Coskun B, Outilaft H, Namer IJ, Cicek E. Predicting Carbon Spectrum in Heteronuclear Single Quantum Coherence Spectroscopy for Online Feedback During Surgery. IEEE\/ACM transactions on computational biology and bioinformatics. 2019;.","DOI":"10.1109\/TCBB.2019.2920646"},{"key":"pcbi.1008184.ref030","unstructured":"Lundberg SM, Lee SI. A unified approach to interpreting model predictions. In: Advances in neural information processing systems; 2017. p. 4765\u20134774."},{"issue":"1","key":"pcbi.1008184.ref031","first-page":"92","article-title":"Multivariate analysis in metabolomics","volume":"1","author":"B Worley","year":"2013","journal-title":"Current Metabolomics"},{"issue":"3","key":"pcbi.1008184.ref032","first-page":"18","article-title":"Classification and regression by randomForest","volume":"2","author":"A Liaw","year":"2002","journal-title":"R news"},{"issue":"5","key":"pcbi.1008184.ref033","doi-asserted-by":"crossref","first-page":"683","DOI":"10.1109\/72.159058","article-title":"Multilayer perceptron, fuzzy sets, and classification","volume":"3","author":"SK Pal","year":"1992","journal-title":"IEEE Transactions on Neural Networks"},{"key":"pcbi.1008184.ref034","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R, He K, Doll\u00e1r P. Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision; 2017. p. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"issue":"19","key":"pcbi.1008184.ref035","doi-asserted-by":"crossref","first-page":"526","DOI":"10.1186\/s12859-018-2523-5","article-title":"Convolutional neural network based on SMILES representation of compounds for detecting chemical motif","volume":"19","author":"M Hirohara","year":"2018","journal-title":"BMC bioinformatics"},{"key":"pcbi.1008184.ref036","first-page":"843029","article-title":"DeepSide: A Deep Learning Framework for Drug Side Effect Prediction","author":"OC Uner","year":"2019","journal-title":"bioRxiv"},{"key":"pcbi.1008184.ref037","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. In: Advances in neural information processing systems; 2017. p. 5998\u20136008."},{"key":"pcbi.1008184.ref038","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.eswa.2019.01.080","article-title":"EEG-based user identification system using 1D-convolutional long short-term memory neural networks","volume":"125","author":"Y Sun","year":"2019","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"pcbi.1008184.ref039","doi-asserted-by":"crossref","first-page":"2522","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"SM Lundberg","year":"2020","journal-title":"Nature Machine Intelligence"},{"key":"pcbi.1008184.ref040","doi-asserted-by":"crossref","first-page":"506","DOI":"10.3389\/fonc.2019.00506","article-title":"Isocitrate dehydrogenase mutations in glioma: From basic discovery to therapeutics development","volume":"9","author":"J Huang","year":"2019","journal-title":"Frontiers in oncology"},{"issue":"1","key":"pcbi.1008184.ref041","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1093\/neuonc\/nov136","article-title":"Isocitrate dehydrogenase mutations in gliomas","volume":"18","author":"MS Waitkus","year":"2015","journal-title":"Neuro-oncology"},{"issue":"15","key":"pcbi.1008184.ref042","doi-asserted-by":"crossref","first-page":"20486","DOI":"10.18632\/oncotarget.7974","article-title":"Metabolomics profiling in plasma samples from glioma patients correlates with tumor phenotypes","volume":"7","author":"H Zhao","year":"2016","journal-title":"Oncotarget"},{"issue":"1","key":"pcbi.1008184.ref043","first-page":"3","article-title":"Evaluation of cerebral glioma grade by using normal side creatine as an internal reference in multi-voxel 1H-MR spectroscopy","volume":"13","author":"H Yerli","year":"2007","journal-title":"Diagnostic and interventional radiology"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1008184","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T00:00:00Z","timestamp":1606089600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1008184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,27]],"date-time":"2022-11-27T13:51:25Z","timestamp":1669557085000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1008184"}},"subtitle":[],"editor":[{"given":"Teresa M.","family":"Przytycka","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2020,11,11]]},"references-count":43,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2020,11,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1008184","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.02.24.20026955","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,11]]}}}