Integrating Multiplex Immunohistochemistry and Machine Learning for Glioma Subtyping and Prognosis Prediction

Abstract

Glioma subtyping is crucial for treatment decisions, but traditional approaches often fail to capture tumor heterogeneity. This study proposes a novel framework integrating multiplex immunohistochemistry (mIHC) and machine learning for glioma subtyping and prognosis prediction. 185 patient samples from the Huashan hospital cohort were stained using a multi-label mIHC panel and analyzed with an AI-based auto-scanning system to calculate cell ratios and determine the proportion of positive tumor cells for various markers. Patients were divided into two cohorts (training: N = 111, testing: N = 74), and a machine learning model was then developed and validated for subtype classification and prognosis prediction. The framework identified two distinct glioma subtypes with significant differences in prognosis, clinical characteristics, and molecular profiles. The high-risk subtype, associated with older age, poorer outcomes, astrocytoma/glioblastoma, higher tumor grades, elevated mesenchymal scores, and an inhibitory immune microenvironment, exhibited IDH wild-type, 1p19q non-codeletion, and MGMT promoter unmethylation, suggesting chemotherapy resistance. Conversely, the low-risk subtype, characterized by younger age, better prognosis, astrocytoma/oligodendroglioma, lower tumor grades, and favorable molecular profiles (IDH mutation, 1p19q codeletion, MGMT promoter methylation), indicated chemotherapy sensitivity. The mIHC-based framework enables rapid glioma classification, facilitating tailored treatment strategies and accurate prognosis prediction, potentially improving patient management and outcomes.

Keywords

glioma / machine learning / mIHC / molecular subtype / prognosis

References

[1] M. Weller, P. Y. Wen, S. M. Chang, et al., “Glioma,” Nature Reviews Disease Primers 10, no. 1 (2024): 33.

[2] J. Feldheim, A. F. Kessler, J. J. Feldheim, et al., “Effects of Long-Term Temozolomide Treatment on Glioblastoma and Astrocytoma WHO Grade 4 Stem-Like Cells,” International Journal of Molecular Sciences 23, no. 9 (2022): 5238.

[3] A. Lauko, A. Lo, M. S. Ahluwalia, and J. D. Lathia, “Cancer Cell Heterogeneity & Plasticity in Glioblastoma and Brain Tumors,” Seminars in Cancer Biology 82 (2022): 162-175.

[4] H. Wu, C. Guo, C. Wang, et al., “Single-Cell RNA Sequencing Reveals Tumor Heterogeneity, Microenvironment, and Drug-Resistance Mechanisms of Recurrent Glioblastoma,” Cancer Science 114, no. 6 (2023): 2609-2621.

[5] Z. Bao, Y. Wang, Q. Wang, et al., “Intratumor Heterogeneity, Microenvironment, and Mechanisms of Drug Resistance in Glioma Recurrence and Evolution,” Frontiers in Medicine 15, no. 4 (2021): 551-561.

[6] C. Neftel, J. Laffy, M. G. Filbin, et al., “An Integrative Model of Cellular States, Plasticity, and Genetics for Glioblastoma,” Cell 178, no. 4 (2019): 835-849.E21.

[7] Y. W. Park, P. Vollmuth, M. Foltyn-Dumitru, et al., “The 2021 WHO Classification for Gliomas and Implications on Imaging Diagnosis: Part 1-Key Points of the Fifth Edition and Summary of Imaging Findings on Adult-Type Diffuse Gliomas,” Journal of Magnetic Resonance Imaging 58, no. 3 (2023): 677-689.

[8] M. Antonelli and P. L. Poliani, “Adult Type Diffuse Gliomas in the New 2021 WHO Classification,” Pathologica 114, no. 6 (2022): 397-409.

[9] D. N. Louis, A. Perry, P. Wesseling, et al., “The 2021 WHO Classification of Tumors of the Central Nervous System: A Summary,” Neuro-Oncology 23, no. 8 (2021): 1231-1251.

[10] S. Dajani, V. B. Hill, J. A. Kalapurakal, et al., “Imaging of GBM in the Age of Molecular Markers and MRI Guided Adaptive Radiation Therapy,” Journal of Clinical Medicine 11, no. 19 (2022): 5961.

[11] B. T. Whitfield and J. T. Huse, “Classification of Adult-Type Diffuse Gliomas: Impact of the World Health Organization 2021 Update,” Brain Pathology 32, no. 4 (2022): e13062.

[12] F. S. Varn, K. C. Johnson, J. Martinek, et al., “Glioma Progression Is Shaped by Genetic Evolution and Microenvironment Interactions,” Cell 185, no. 12 (2022): 2184-2199.E16.

[13] M. E. Hegi, A. C. Diserens, T. Gorlia, et al., “MGMT Gene Silencing and Benefit From Temozolomide in Glioblastoma,” New England Journal of Medicine 352, no. 10 (2005): 997-1003.

[14] W. Hua and X. Zhang. “Clinical Trials on Glioma,” in Progress in the Diagnosis and Treatment of Gliomas, ed. Y. Mao (Springer Nature, 2024): 107-114.

[15] W. C. C. Tan, S. N. Nerurkar, H. Y. Cai, et al., “Overview of Multiplex Immunohistochemistry/Immunofluorescence Techniques in the Era of Cancer Immunotherapy,” Cancer Communications 40, no. 4 (2020): 135-153.

[16] Z. Duan and Y. Luo, “Targeting Macrophages in Cancer Immunotherapy,” Signal Transduction and Targeted Therapy 6, no. 1 (2021): 127.

[17] F. Khan, L. Pang, M. Dunterman, M. S. Lesniak, A. B. Heimberger, and P. Chen, “Macrophages and Microglia in Glioblastoma: Heterogeneity, Plasticity, and Therapy,” Journal of Clinical Investigation 133, no. 1 (2023): e163446.

[18] N. A. Charles, E. C. Holland, R. Gilbertson, R. Glass, and H. Kettenmann, “The Brain Tumor Microenvironment,” Glia 59, no. 8 (2011): 1169-1180.

[19] M. Friedrich, R. Sankowski, L. Bunse, et al., “Tryptophan Metabolism Drives Dynamic Immunosuppressive Myeloid States in IDH-Mutant Gliomas,” Nature Cancer 2, no. 7 (2021): 723-740.

[20] C. Hu, K. Wang, C. Damon, et al., “ATRX Loss Promotes Immunosuppressive Mechanisms in IDH1 Mutant Glioma,” Neuro-Oncology 24, no. 6 (2022): 888-900.

[21] F. J. Núñez, F. M. Mendez, P. Kadiyala, et al., “IDH1-R132H Acts as a Tumor Suppressor in Glioma via Epigenetic Up-Regulation of the DNA Damage Response,” Science Translational Medicine 11, no. 479 (2019): eaaq1427.

[22] Z. An, O. Aksoy, T. Zheng, Q. W. Fan, and W. A. Weiss, “Epidermal Growth Factor Receptor and EGFRvIII in Glioblastoma: Signaling Pathways and Targeted Therapies,” Oncogene 37, no. 12 (2018): 1561-1575.

[23] H. E. Leeper, A. A. Caron, P. A. Decker, R. B. Jenkins, D. H. Lachance, and C. Giannini, “IDH Mutation, 1p19q Codeletion and ATRX Loss in WHO Grade II Gliomas,” Oncotarget 6, no. 30 (2015): 30295-30305.

[24] M. Felix, D. Friedel, A. K. Jayavelu, et al., “HIP1R and Vimentin Immunohistochemistry Predict 1p/19q Status in IDH-Mutant Glioma,” Neuro-Oncology 24, no. 12 (2022): 2121-2132.

[25] A. S. Yamashita, C. da M. Rosa, et al., “Demethylation and Epigenetic Modification With 5-Azacytidine Reduces IDH1 Mutant Glioma Growth in Combination With Temozolomide,” Neuro-Oncology 21, no. 2 (2019): 189-200.

[26] R. N. Curry, Q. Ma, M. F. McDonald, et al., “Integrated Electrophysiological and Genomic Profiles of Single Cells Reveal Spiking Tumor Cells in Human Glioma,” Cancer Cell 42, no. 10 (2024): 1713-1728.E6.

[27] H. Harada, K. Nakagawa, S. Iwata, et al., “Restoration of Wild-Type p16 Down-Regulates Vascular Endothelial Growth Factor Expression and Inhibits Angiogenesis in Human Gliomas,” Cancer Research 59, no. 15 (1999): 3783-3789.

[28] H. Ahmeti, D. Kiese, S. Freitag-Wolf, et al., “IDH1 Mutation Is Associated With Improved Resection Rates, Progression-Free Survival and Overall Survival in Patients With Anaplastic Astrocytomas,” Journal of Neuro-Oncology 169, no. 2 (2024): 423-435.

[29] C. Koschmann, A. A. Calinescu, F. J. Nunez, et al., “ATRX Loss Promotes Tumor Growth and Impairs Nonhomologous End Joining DNA Repair in Glioma,” Science Translational Medicine 8, no. 328 (2016): 328ra28.

[30] P. Jonsson, A. L. Lin, R. J. Young, et al., “Genomic Correlates of Disease Progression and Treatment Response in Prospectively Characterized Gliomas,” Clinical Cancer Research 25, no. 18 (2019): 5537-5547.

[31] A. Zerrouqi, B. Pyrzynska, M. Febbraio, D. J. Brat, and E. G. Van Meir, “P14ARF Inhibits Human Glioblastoma-Induced Angiogenesis by Upregulating the Expression of TIMP3,” Journal of Clinical Investigation 122, no. 4 (2012): 1283-1295.

[32] S. Khagi and C. R. Miller, “Putting “Multiforme” Back Into Glioblastoma: Intratumoral Transcriptome Heterogeneity Is a Consequence of Its Complex Morphology,” Neuro-Oncology 19, no. 12 (2017): 1570-1571.

[33] Y. Hoogstrate, K. Draaisma, S. A. Ghisai, et al., “Transcriptome Analysis Reveals Tumor Microenvironment Changes in Glioblastoma,” Cancer Cell 41, no. 4 (2023): 678-692.E7.

[34] Y. Xiao, Z. Wang, M. Zhao, et al., “Single-Cell Transcriptomics Revealed Subtype-Specific Tumor Immune Microenvironments in Human Glioblastomas,” Frontiers in Immunology 13 (2022): 914236.

[35] Q. Wang, B. Hu, X. Hu, et al., “Tumor Evolution of Glioma-Intrinsic Gene Expression Subtypes Associates With Immunological Changes in the Microenvironment,” Cancer Cell 32, no. 1 (2017): 42-56.E6.

[36] M. D. Wood, G. F. Reis, D. E. Reuss, and J. J. Phillips, “Protein Analysis of Glioblastoma Primary and Posttreatment Pairs Suggests a Mesenchymal Shift at Recurrence,” Journal of Neuropathology and Experimental Neurology 75, no. 10 (2016): 925-935.

[37] Y. Chen, R. Huo, W. Kang, et al., “Tumor-Associated Monocytes Promote Mesenchymal Transformation Through EGFR Signaling in Glioma,” Cell Reports Medicine 4, no. 9 (2023): 101177.

[38] K. Yoshihara, M. Shahmoradgoli, E. Martínez, et al., “Inferring Tumour Purity and Stromal and Immune Cell Admixture From Expression Data,” Nature Communications 4 (2013): 2612.

[39] R. Chen, V. M. Ravindra, A. L. Cohen, et al., “Molecular Features Assisting in Diagnosis, Surgery, and Treatment Decision Making in Low-Grade Gliomas,” Neurosurgical Focus 38, no. 3 (2015): E2.

[40] H. Xu, A. Zhang, X. Han, et al., “ITGB2 as a Prognostic Indicator and a Predictive Marker for Immunotherapy in Gliomas,” Cancer Immunology, Immunotherapy 71, no. 3 (2022): 645-660.

[41] E. H. Bell, P. Zhang, B. J. Fisher, et al., “Association of MGMT Promoter Methylation Status with Survival Outcomes in Patients With High-Risk Glioma Treated with Radiotherapy and Temozolomide an Analysis From the NRG Oncology/RTOG 0424 Trial,” Jama Oncology 4, no. 10 (2018): 1405-1409.

[42] J. Cheng, J. He, S. Wang, et al., “Biased Influences of Low Tumor Purity on Mutation Detection in Cancer,” Frontiers in Molecular Biosciences 7 (2020): 533196.

[43] D. Aran, M. Sirota, and A. J. Butte, “Systematic Pan-Cancer Analysis of Tumour Purity,” Nature Communications 6 (2015): 8971.

[44] T. Yu, Q. Huang, X. Zhao, et al., “Tumour Purity as an Underlying Key Factor in Tumour Mutation Detection in Colorectal Cancer,” Clinical and Translational Medicine 13, no. 5 (2023): e1252.

[45] L. Wu, W. Wu, J. Zhang, et al., “Natural Coevolution of Tumor and Immunoenvironment in Glioblastoma,” Cancer Discovery 12, no. 12 (2022): 2820-2837.

[46] H. Xu, A. Zhang, C. Fang, et al., “SLC11A1 as a Stratification Indicator for Immunotherapy or Chemotherapy in Patients With Glioma,” Frontiers in Immunology 13 (2022): 980378.

[47] E. M. Liu, Z. F. Shi, K. K. Li, et al., “Molecular Landscape of IDH-Wild Type, pTERT-Wild Type Adult Glioblastomas,” Brain Pathology 32, no. 6 (2022): e13107.

[48] L. G. Richardson, L. T. Nieman, A. O. Stemmer-Rachamimov, et al., “IDH-Mutant Gliomas Harbor Fewer Regulatory T Cells in Humans and Mice,” Oncoimmunology 9, no. 1 (2020): 1806662.

[49] A. Makarevic, C. Rapp, S. Dettling, et al., “Increased Radiation-Associated T-Cell Infiltration in Recurrent IDH-Mutant Glioma,” International Journal of Molecular Sciences 21, no. 20 (2020): 7801.

[50] A. T. Yeo, S. Rawal, B. Delcuze, et al., “Single-Cell RNA Sequencing Reveals Evolution of Immune Landscape During Glioblastoma Progression,” Nature Immunology 23, no. 6 (2022): 971-984.

[51] Y. Yu, H. Chen, W. Ouyang, et al., “Unraveling the Role of M1 Macrophage and CXCL9 in Predicting Immune Checkpoint Inhibitor Efficacy Through Multicohort Analysis and Single-Cell RNA Sequencing,” MedComm 5, no. 3 (2024): e471.

[52] V. M. Ravi, P. Will, J. Kueckelhaus, et al., “Spatially Resolved Multi-Omics Deciphers Bidirectional Tumor-host Interdependence in Glioblastoma,” Cancer Cell 40, no. 6 (2022): 639-655.E13.

[53] J. C. L. Ong, B. J. J. Seng, J. Z. F. Law, et al., “Artificial Intelligence, ChatGPT, and Other Large Language Models for Social Determinants of Health: Current State and Future Directions,” Cell Reports Medicine 5, no. 1 (2024): 101356.

[54] D. Q. Wang, L. Y. Feng, J. G. Ye, J. G. Zou, and Y. Zheng, “Accelerating the Integration of ChatGPT and Other Large-Scale AI Models Into Biomedical Research and Healthcare,” MedComm—Future Medicine 2, no. 2 (2023): e43.

[55] T. Wu, E. Hu, S. Xu, et al., “ClusterProfiler 4.0: A Universal Enrichment Tool for Interpreting Omics Data,” Innovation 2, no. 3 (2021): 100141.

[56] S. Hänzelmann, R. Castelo, and J. Guinney, “GSVA: Gene Set Variation Analysis for Microarray and RNA-Seq Data,” BMC Bioinformatics [Electronic Resource] 14 (2013): 7.

[57] D. Kim, J. M. Paggi, C. Park, C. Bennett, and S. L. Salzberg, “Graph-Based Genome Alignment and Genotyping With HISAT2 and HISAT-Genotype,” Nature Biotechnology 37, no. 8 (2019): 907-915.

[58] Y. Liao, G. K. Smyth, and W. Shi, “featureCounts: An Efficient General Purpose Program for Assigning Sequence Reads to Genomic Features,” Bioinformatics 30, no. 7 (2014): 923-930.

RIGHTS & PERMISSIONS

2025 The Author(s). MedComm published by Sichuan International Medical Exchange & Promotion Association (SCIMEA) and John Wiley & Sons Australia, Ltd.