IDH wild-type glioblastoma typing method and system based on multi-modal data fusion

Abstract

The invention relates to the technical field of image analysis, in particular to a multi-modal data fusion IDH wild type glioblastoma typing method and system, and the method comprises the steps: obtaining a data set of a GBM patient; based on the data set, radiomics characteristics, pathomics characteristics, whole exon sequencing data, transcriptome sequencing data and proteomics characteristics are obtained; performing multi-modal data fusion on the image omics characteristics, the pathological omics characteristics, the whole exon sequencing data, the transcriptome sequencing data and the proteomics characteristics, and constructing a multi-modal fusion typing framework to identify the MOFS subtype; and based on image omics features, constructing a deep neural network classifier for predicting the MOFS subtype, and verifying the identified MOFS subtype. Three different subtypes in IDH wild-type adult glioma are determined and verified using an artificial intelligence method by integrating multi-mode data from MRI derived radiomics, WSI derived pathomics, WES, RNA sequencing, and MS-based proteomics.

Description

Technical Field

[0001] The present application relates to the field of image analysis technology, and in particular to a multimodal data fusion IDH wild-type glioblastoma classification method and system. Background Art

[0002] Diffuse gliomas in adults are the most common primary malignant central nervous system (CNS) tumors. Isocitrate dehydrogenase (IDH) mutations have been found to be the most influential molecular marker that can stratify patients with diffuse gliomas into two groups with different prognoses, genetic characteristics, and potential treatment options. The recently published World Health Organization classification of central nervous system tumors classifies IDH-mutant gliomas and IDH-wild-type gliomas as different tumor entities in adult patients. Notably, IDH-wild-type glioblastoma (GBM) is the most prevalent and aggressive glioma subtype in adults, with a 5-year survival rate of less than 10%. Standard treatment for GBM includes complete resection followed by radiotherapy and temozolomide (TMZ) chemotherapy. However, GBM has significant inter- and intratumor heterogeneity, with significant differences at the genomic, transcriptomic, proteomic, and epigenomic levels, posing considerable challenges for homogenous management. Therefore, further investigation of the heterogeneity and stratification of IDH-wild-type GBM is warranted.

[0003] With the advancement of technology, the integration of multimodal data has brought new insights into tumor stratification. In general, imaging, pathology, DNA, RNA, and protein can reflect the anatomical, cellular, genetic, transcriptional, and functional levels of the disease, respectively. The integration of multimodal analysis enables this application to better understand the connection between complex disease phenotypes and biological mechanisms. In fact, the microscopic phenotypes at the cellular level produced by gene mutations, abnormal signals, and abnormal expressions have a profound impact on key cellular processes such as cell proliferation, inflammatory response, and angiogenesis. These changes can be captured by histological images. Similarly, phenotypes visible to the naked eye, such as tumor shape, texture, edema, and necrosis, can be visualized using advanced imaging techniques such as multiparametric MRI. Previous studies have also shown that imaging or histopathology images can reflect the mutation status or expression level of genes. This not only provides a bridge between imaging histopathology images and molecular omics, but also provides a theoretical basis for multimodal fusion analysis.

[0004] In current studies based on fusion analysis of multi-omics datasets, first, due to the lack of multi-omics data in public cohorts, the reliance of classifier development on transcriptomics data may limit the capture of the complete molecular complexity of GBM. Future studies should focus on incorporating more comprehensive multi-omics datasets to improve the accuracy and robustness of classifiers. Second, although the imaging omics classification model shows high predictive performance, it is necessary to validate it in a larger independent cohort to confirm its generalizability. The integration of other MR sequencing, such as DTI, PWI, or functional MRI, can further improve the accuracy of the classifier and provide more insights into tumor biology. Summary of the invention

[0005] The present application provides a multimodal data fusion method and system for classifying IDH wild-type glioblastoma. By integrating multimodal data from MRI-derived imaging omics, whole slide image (WSI)-derived pathological omics, whole exome sequencing (WES), RNA sequencing (RNA-seq) and mass spectrometry (MS)-based proteomics, three different subtypes of IDH wild-type adult gliomas were identified and verified using artificial intelligence methods.

[0006] To solve the above technical problems, in the first aspect, an embodiment of the present application provides a multimodal data fusion IDH wild-type glioblastoma classification method, comprising the following steps: first, obtaining a data set of GBM patients; GBM patients include IDH wild-type glioblastoma patients; then, based on the data set, obtaining imaging genomics features, pathological genomics features, whole exome sequencing data, transcriptome sequencing data and proteomics features; next, performing multimodal data fusion on the imaging genomics features, pathological genomics features, whole exome sequencing data, transcriptome sequencing data and proteomics features, and constructing a multimodal fusion classification framework based on the transcriptome expression spectrum to identify MOFS subtypes in multimodal data; finally, based on the imaging genomics features and using a neural network algorithm based on elastic back propagation, a deep neural network classifier for predicting MOFS subtypes is constructed to verify the identified MOFS subtypes.

[0007] In some exemplary embodiments, imaging omics features are obtained based on a data set, including: first, acquiring images of the data set to obtain MRI images; the MRI images are magnetic resonance imaging images; then, the MRI images are standardized, and imaging features are extracted from the standardized MRI images to obtain imaging omics features.

[0008] In some exemplary embodiments, pathological omics features are obtained based on a data set, including: first, obtaining a WSI image by scanning a hematoxylin-eosin slide; the WSI image is a whole slide image; then, tissue segmentation is performed on the WSI image, and feature extraction is performed from the segmented tissue image to obtain the pathological omics features.

[0009] In some exemplary embodiments, whole exome sequencing data and transcriptome sequencing data are obtained based on the data set, including: performing whole exome sequencing and transcriptome sequencing on the tumor samples in the data set, respectively, to obtain whole exome sequencing data and transcriptome sequencing data, which are recorded as WES data and RNA-seq data, respectively.

[0010] In some exemplary embodiments, obtaining a proteomic feature based on a data set includes: performing mass spectrometry analysis on a tumor sample in the data set using a mass spectrometer to obtain the proteomic feature.

[0011] In some exemplary embodiments, multimodal data fusion is performed on imaging omics features, pathological omics features, whole exome sequencing data, transcriptome sequencing data and proteomics features, including: first, using multiple algorithms based on different principles to perform intermediate fusion of multimodal data of imaging omics features, pathological omics features, whole exome sequencing data, transcriptome sequencing data and proteomics features; then, post-fusion of the intermediate fusion results obtained by the multiple algorithms to obtain the final clustering results.

[0012] In some exemplary embodiments, before performing intermediate fusion of multimodal data of radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data and proteomics features, it also includes: determining the optimal number of clusters and input features; wherein, when determining the optimal number of clusters and input features, firstly calculate the median absolute deviation of the variables in each modal layer of radiomics, pathological features, transcriptomics and proteomics, select the top n variables from each layer, and combine them into 2640 variable combinations; then calculate the clustering prediction index and GAP statistic of each combination, and determine the optimal number of clusters and input features for the final clustering based on the combination with the highest sum of the clustering prediction index and the GAP statistic.

[0013] In some exemplary embodiments, the identified MOFS subtypes include: proneuronal MOFS1, proliferative MOFS2, and tumor microenvironment-enriched MOFS3; the MOFS1 subtype is a proneuronal type with increased neurodevelopmental activity, a large number of neural cell infiltrations, and a good prognosis; the MOFS2 subtype is a proliferative type with the worst prognosis, high proliferative activity, genomic instability, and sensitivity to temozolomide; the MOFS3 subtype is a tumor microenvironment-enriched type with an intermediate prognosis, rich immune and matrix components, and sensitivity to anti-PD-1 immunotherapy.

[0014] In some exemplary embodiments, among the identified MOFS subtypes, STRAP emerges as a prognostic biomarker and potential therapeutic target for the MOFS2 subtype, which is associated with its proliferation phenotype; the MOFS3 subtype has abundant tumor immune infiltration and is sensitive to immunotherapy, which is an important prognostic indicator and can be used for further prognostic stratification.

[0015] In the second aspect, an embodiment of the present application also provides a multimodal data fusion IDH wild-type glioblastoma classification system, including: a dataset module, a multimodal data acquisition module, an integrated classifier development module and a model verification module connected in sequence; the dataset module is used to obtain a dataset of GBM patients; GBM patients include IDH wild-type glioblastoma patients; the multimodal data acquisition module is used to obtain imaging genomics features, pathological genomics features, whole exome sequencing data, transcriptome sequencing data and proteomics features according to the dataset; the integrated classifier development module is used to perform multimodal data fusion on imaging genomics features, pathological genomics features, whole exome sequencing data, transcriptome sequencing data and proteomics features, and construct a multimodal fusion classification framework based on the transcriptome expression spectrum to identify MOFS subtypes in multimodal data; the model verification module is used to construct a deep neural network classifier for predicting MOFS subtypes based on imaging genomics features and using a neural network algorithm based on elastic back propagation, and verify the identified MOFS subtypes.

[0016] The technical solution provided by the embodiments of the present application has at least the following advantages:

[0017] The embodiment of the present application provides a multimodal data fusion IDH wild-type glioblastoma classification method and system, the method comprising the following steps: first, obtaining a data set of GBM patients; GBM patients include IDH wild-type glioblastoma patients; then, based on the data set, obtaining radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data and proteomics features; next, performing multimodal data fusion on the radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data and proteomics features, and constructing a multimodal fusion classification framework based on the transcriptome expression spectrum to identify MOFS subtypes in multimodal data; finally, based on the radiomics features and using a neural network algorithm based on elastic back propagation, a deep neural network classifier for predicting MOFS subtypes is constructed to verify the identified MOFS subtypes.

[0018] The multimodal data fusion IDH wild-type glioblastoma classification method provided in this application integrates multimodal data from MRI-derived radiomics, WSI-derived pathological omics, WES, RNA-seq, and MS-based proteomics, and identifies and validates three different subtypes in IDH wild-type adult gliomas. The current cohort includes not only histological GBM, but also molecularly diagnosed GBM and IDH wild-type low-grade diffuse gliomas, the latter two of which are usually indistinguishable in clinical radiology and pathology. The multimodal data fusion analysis of this application provides insights into the heterogeneity of GBM tumors in terms of phenotypic manifestations, oncogenic signals, immune responses, and genomic changes. This application achieves early intervention and treatment of IDH wild-type gliomas through more accurate diagnosis and prognosis prediction, and provides patients with IDH wild-type gliomas with precise treatment plans based on tumor biological characteristics. This application provides a basis for personalized treatment by identifying prognostic biomarkers and potential therapeutic targets STRAP associated with specific subtypes. In addition, the development of a deep neural network classifier further enhances the clinical translatability of our findings and provides a non-invasive tool for predicting MOFS subtypes. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplifications do not constitute limitations on the embodiments. Unless otherwise stated, the pictures in the drawings do not constitute proportional limitations.

[0020] Figure 1 A schematic flow chart of a multimodal data fusion method for classifying IDH wild-type glioblastoma provided in one embodiment of the present application.

[0021] Figure 2A A schematic diagram of a multimodal data integration process provided in one embodiment of the present application.

[0022] Figure 2B A distribution diagram of the cluster prediction index provided in one embodiment of the present application.

[0023] Figure 2C This is a consensus matrix heat map of 122 IDH-wild-type glioma patients provided in one embodiment of the present application.

[0024] Figure 2D A principal component analysis diagram provided for an embodiment of the present application.

[0025] Figure 3 A schematic diagram of the structure of a multimodal data fusion IDH wild-type glioblastoma classification system provided in one embodiment of the present application. DETAILED DESCRIPTION

[0026] As we know from the background technology, due to the lack of multi-omics data in public cohorts, the reliance of classifier development on transcriptomics data may limit the capture of the complete molecular complexity of GBM. Although the imaging omics classification model shows high predictive performance, it is necessary to validate it in a larger independent cohort to confirm its generalizability, further improve the accuracy of the classifier, and provide more insights into tumor biology.

[0027] Over the past decade, several studies have applied large-scale, high-throughput sequencing to investigate GBM heterogeneity, identify key oncogenic events and potential therapeutic targets, and define molecular subtypes for patient stratification. The Cancer Genome Atlas (TCGA) made significant progress by delineating four transcriptional subtypes, namely proneural, neural, mesenchymal, and classical. Subsequent studies have emphasized the substantial impact of the tumor microenvironment (TME) on GBM subtyping. From this, some researchers have further refined the system by retaining proneural, mesenchymal, and classical subtypes while excluding neural subtypes that are contaminated by normal cell components. Single-cell sequencing (scRNA-seq) has revealed multiple transcriptional states in GBM, representing different biological processes such as hypoxia and cell cycle. Other studies have demonstrated that GBM transcriptional heterogeneity converges to four tumor cell subpopulations. Despite these insights, transcriptome-based subtyping has been shown to be insufficient for predicting patient survival and treatment response.

[0028] With the advancement of technology, the integration of multimodal data has brought new insights into tumor stratification. Radiomics or histopathology images can reflect the mutation status or expression level of genes, which not only provides a bridge between radiomics and molecular omics, but also provides a theoretical basis for multimodal fusion analysis. Specifically, radiomics extracts a large number of quantitative image features from MRI, reveals hidden information that cannot be detected from naked eye observation alone, and provides tumor heterogeneity information in a non-invasive way, thus providing new help for clinical diagnosis and treatment. Due to the unique biological behavior of gliomas and the challenges associated with diagnosis and treatment, people are increasingly interested in applying radiomics to gliomas. After years of development, it has been proven that non-invasive biomarkers for GBM constructed using radiomics can effectively guide prognosis for risk stratification. Pathogenomics uses artificial intelligence methods to extract morphological structures in WSI, which generates multi-scale microscopic data. The structure it displays can be represented by some features such as size, shape, texture, etc. AI-based pathogenomics can extract histopathological features independently associated with risk through cutting-edge technology to identify complex patterns and biological features, thereby predicting prognosis, etc., especially in the field of tumors. Pathogenomics has been applied to multiple oncology disciplines, including breast cancer, lung adenocarcinoma, central nervous system lesions, and hematological malignancies, among others.

[0029] In order to solve the above technical problems, an embodiment of the present application provides a multimodal data fusion IDH wild-type glioblastoma classification method and system, the method comprising the following steps: first, obtaining a data set of GBM patients; GBM patients include IDH wild-type glioblastoma patients; then, based on the data set, obtaining imaging genomics features, pathological genomics features, whole exome sequencing data, transcriptome sequencing data and proteomics features; next, performing multimodal data fusion on the imaging genomics features, pathological genomics features, whole exome sequencing data, transcriptome sequencing data and proteomics features, and constructing a multimodal fusion classification framework based on the transcriptome expression spectrum to identify MOFS subtypes in multimodal data; finally, based on the imaging genomics features and using a neural network algorithm based on elastic back propagation, a deep neural network classifier for predicting MOFS subtypes is constructed to verify the identified MOFS subtypes. This application identified and validated three distinct subtypes in IDH wild-type adult gliomas by integrating multimodal data from MRI-derived radiomics, WSI-derived pathomics, WES, RNA sequencing, and MS-based proteomics using artificial intelligence approaches.

[0030] The following will describe the various embodiments of the present application in detail with reference to the accompanying drawings. However, it will be appreciated by those skilled in the art that in the various embodiments of the present application, many technical details are provided in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical solution claimed in the present application can be implemented.

[0031] See also Figure 1 The present application embodiment provides a multimodal data fusion IDH wild-type glioblastoma classification method, comprising the following steps:

[0032] Step S1, obtaining a data set of GBM patients; GBM patients include IDH wild-type glioblastoma patients.

[0033] Step S2: Based on the data set, radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data and proteomic features are obtained.

[0034] Step S3: Multimodal data fusion is performed on radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data, and proteomics features, and a multimodal fusion typing framework is constructed based on transcriptome expression profiles to identify MOFS subtypes in multimodal data.

[0035] Step S4: Based on the radiomics features and using a neural network algorithm based on elastic back propagation, a deep neural network classifier for predicting MOFS subtypes is constructed to verify the identified MOFS subtypes.

[0036] The acquisition process of the data set in step S1: This application collects data on patients with IDH wild-type glioma who underwent radical resection in a certain hospital. The inclusion criteria for the patient cohort are: age ≥ 18 years; primary glioma; the combined diagnosis of IDH wild-type GBM and low-grade diffuse glioma is reclassified according to the 2021 WHO classification; no previous history of radiotherapy or chemotherapy before admission; complete clinical data and follow-up data; no serious systemic abnormalities before surgery; preoperative MRI data including T1WI, CE-T1WI, T2WI, FLAIR and ADC images obtained from DWI, with good image quality and no significant differences; HE-stained pathological sections are clear and the scanned image quality is high; and well-preserved pathological tissue. The exclusion criteria for the patient cohort are: history of brain surgery or trauma; previous radiotherapy or chemotherapy before surgery; and the presence of artifacts on MRI, which will affect the observation or depiction of lesions.

[0037] A total of 1194 IDH wild-type glioma patients with complete and qualified MRI data were included in this application. Among these cases, fresh surgical tumor specimens were collected from 202 patients. These specimens were immediately frozen in liquid nitrogen and stored at -80°C for tissue sequencing. Among them, 202 tissues were subjected to RNA sequencing (RNA-seq), 180 tissues were subjected to mass spectrometry analysis, and 122 tissues were subjected to whole exome sequencing (WES). Histological whole slide images (WSI) of 122 patients with all imaging omics and sequencing data were obtained by scanning HE-stained pathological sections. In addition, 5 adjacent brain tissues were collected from the tumor edge, and 19 peripheral blood samples were collected before surgery as normal controls for WES.

[0038] This application designated 122 samples with data from all modalities as the FAHZZU1 cohort, 80 samples with transcriptome or mass spectrometry data as the FAHZZU2 cohort, and 992 samples with only MRI data as the FAHZZU3 cohort.

[0039] In some embodiments, obtaining radiomics features based on the data set in step S2 comprises the following steps:

[0040] Step S201, collect images of a data set to obtain an MRI image; the MRI image is a magnetic resonance imaging image.

[0041] Step S202: Standardize the MRI image, and extract imaging features from the standardized MRI image to obtain radiomics features.

[0042] Specifically, during the MRI scanning and imaging feature extraction process, the patient's MRI images were scanned using a 3.0 T MRI during routine examinations. The sequences included: axial and sagittal T1-weighted imaging (T1WI), axial T2-weighted imaging (T2WI), axial T2-weighted fluid-attenuated inversion recovery (FLAIR) imaging, and axial, sagittal, and coronal post-contrast T1-weighted imaging (CE-T1WI) immediately after intravenous injection of a 0.1 mmol / kg dose of gadolinium-based contrast agent. The apparent diffusion coefficient (ADC) map was obtained by axial diffusion-weighted imaging (DWI). The acquisition parameters of each sequence were as follows:

[0043] (1) T1WI and CE-T1WI: repetition time (TR) 220~1750 ms; echo time (TE) 2.3~24 ms; echo train length (ETL) 1~12; slice thickness 5 mm; average / excitation 1; flip angle (FA) 70~111; field of view (FOV) 220×192~240×240 mm; matrix 256×162-320×256 mm.

[0044] (2) T2WI: TR 1873~5390 ms; TE 70~117 ms; ETL 16~32; slice thickness 5 mm; average / excitation 1; FA 90~142; FOV 220×192-240×240 mm; matrix 320×238-512×512 mm.

[0045] (3) FLAIR: TR 4500~8400 ms; TE 85~150 ms; inversion time (TI) 1670~2250 ms; ETL1-38; slice thickness 5 mm; average / excitation 1; FA 90~150; FOV 220×192~240×240 mm; matrix 256×179~256×256 mm.

[0046] (4) DWI: Images were processed by the corresponding post-processing workstation, and ADC images were calculated from DWI acquired at B-values ​​of 0 and 1000 s / mm. Sequence parameters included: TR 2121~6000 ms; TE 77~119 ms; ETL 1~82; slice thickness 5 mm; average / excitation 1; FA 90FOV 220×220~240×240 mm; matrix 152×114~192×192 mm. ADC maps of all imaging planes were generated on a voxel-by-voxel basis using a single exponential model.

[0047] First, bias field distortion was corrected using the N4ITK algorithm. After isotropic voxels were resampled to 1×1×1 mm by trilinear interpolation, multi-sequence MRI rigid registration was performed for each patient using the axially resampled CE-T1WI as a template and mutual information as a similarity measure. This process was completed using 3D Slicer software to generate registered images rT1WI, rCE-T1WI, rT2WI, rFLAIR, and rADC. Grayscale normalization was performed using histogram matching. An associate chief physician in neuroimaging with more than 10 years of experience in head MRI diagnosis manually outlined the tumor region of interest (ROI) on the axial plane of rFLAIR, rT2WI, and rCE-T1WI images using ITK-SNAP software to obtain the tumor volume of interest (VOI). The VOI was defined as the enhancing, non-enhancing, and necrotic areas of the tumor. The VOI outline was drawn based on the FLAIR image, and the rT2WI and rCE-T1WI were used to cross-check the tumor range and fine-tune the tumor outline. The radiologist and an associate chief physician of neurosurgery with more than 10 years of work experience used a simple random sampling method to randomly select 100 patients from the group for VOI redrawing. The interclass correlation coefficient (ICC) was used to evaluate the intra-rater reliability analysis of the test-retest dataset and the inter-rater reliability analysis of the multiple description dataset, and the characteristics of ICC ≥ 0.75 were retained. The obtained VOI images were then superimposed with the co-registered rT1WI, rCE-T1WI, rT2WI, rFLAIR, and rADC images.

[0048] Three types of features were extracted using a pyramid model, including first-order intensity statistics, shape descriptors, and high-order texture features. Five basic matrices were used to define texture features: gray-level co-occurrence matrix (GLCM), gray-level run length matrix (GLRLM), gray-level size zone matrix (GLSZM), gray-level dependency matrix (GLDM), and neighborhood gray-level difference matrix (NGTDM). This study extracted imaging features from three types of images: original images, wavelet images, and Gaussian Laplacian images. Finally, 5929 features were extracted from five MRI sequences, and 4271 features with ICC ≥ 0.75 were retained.

[0049] In some embodiments, obtaining pathological omics features based on the data set in step S2 comprises the following steps:

[0050] Step S211, obtaining a WSI image by scanning the hematoxylin-eosin slide; the WSI image is a whole slide image.

[0051] Step S212: perform tissue segmentation on the WSI image, and extract features from the segmented tissue image to obtain pathological omics features.

[0052] Specifically, during the acquisition and feature analysis of WSI images, hematoxylin-eosin (H&E) slides were scanned using a MAGSCAN-NER scanner (KF-PRO-005, KFBIO) to obtain WSI images (WSIs). In WSIs, tissues usually occupy part of the white background on the slide, so initial tissue segmentation of the WSI images is required. The WSI with a resolution of 5x was converted from RGB to Lab color space, and the tissue segmentation threshold was calculated using the Otsu algorithm. The segmented tissue images were segmented into a large number of 1024×1024 patches at a 20x objective magnification (0.5 m / pixel), and then feature extraction was performed using CellProfiler. A total of 1035 features were extracted from 122 patients.

[0053] In some embodiments, in step S2, whole exome sequencing (WES) data and transcriptome sequencing data are obtained based on the data set, including: performing whole exome sequencing and transcriptome sequencing on the tumor samples in the data set, respectively, to obtain whole exome sequencing data and transcriptome sequencing data, which are recorded as WES data and RNA-seq data, respectively.

[0054] Specifically, during WES and analysis, DNA from tumor tissue and adjacent brain tissue was extracted from samples using the QIAamp Fast DNA Tissue Kit (Qiagen). Blood samples were collected in tubes containing EDTA and centrifuged at 1600 x g for 10 min at 4°C within 2 h of collection. Peripheral blood lymphocyte (PBL) pellets were stored at −20°C until further use, and PBL DNA was extracted using the Relaxgene Blood DNA System. DNA quantification was performed using the Qubit 3.0 Fluorometer and the Qubit dsDNA HS Assay Kit. DNA collected from tissue and PBL samples was fragmented using dsDNA Fragmentase enzyme, and then size selection of DNA fragments (150–250 bp) was performed using Ampure XP Magnetic Beads. DNA fragment libraries were constructed using the KAPA Library Preparation Kit. Clean-up steps were performed using Agencourt AMPure XP Magnetic Beads. After DNA fragmentation, end repair and 3’A tailing were performed, and then exons were captured using the Agilent SureSelect Human All Exon V6 Kit. The purity and concentration of DNA fragments were assessed using the Qubit 3.0 Fluorometer and the Qubit dsDNA HS Assay Kit. Fragment length was measured on a 4200 Bioanalyzer using the DNA1000 Kit. DNA libraries with 150 bp end sequences were sequenced using the Illumina Novaseq 6000 system. Raw data were converted to FASTQ files, and adapters and low-quality reads were trimmed using trim atorial. The median depth of coverage was 112x for tumor specimens and 128x for non-tumor specimens.

[0055] Single nucleotide variants (SNVs) and insertions or deletions (INDELs) were identified using GATK tools. Paired-end WES reads were mapped to the human reference genome (hg38) using BWA-mem. BAM files were further processed using Picard by reordering, marking duplicates, and adding read groups. Base quality score recalibration was performed using the Base Recalibrator module in GATK, and cross-sample contamination was then assessed using the Get Pileup Summaries and Calculate Contamination modules. Somatic variants were detected by Mutation 2 and annotated using ANNOVAR, with patient-matched normal DNA sequencing reads as reference. Candidate somatic variants were distinguished based on the following filtering criteria: ① variants outside exonic regions and splice sites were excluded; ② variants with variant allele fraction (VAF) ≥ 5% in tumor samples and at least 2 supporting variant reads were retained; ③ variants with mutant allele frequency (MAF) ≥ 5% in at least one database were removed, including 1000 genomes, ESP6500, gnomAD, and ExAC. Normal samples were sequenced using the same protocol, each sample was reduced to 4%, and then merged as a reference. In order to obtain high-quality and reliable somatic variants, this application used strict downstream filtering criteria: ① variants outside exonic regions and splice sites were excluded; ② variants with VAF ≥ 5%, at least 5 supporting variant reads in tumor samples, and tumor VAF variants with VAF more than five times that in normal samples were retained; ③ variants that appeared more than 100 times in COSMIC (v92) were retained; ④ variants with MAF ≥ 1% in at least one variant database (1000 genomes, ESP6500, gnomAD, and ExAC) were removed; ⑤ variants predicted to be benign in at least two of the following tools: mutation carrier, mutation container 2, polyphenol 2, and SIFT were removed. CNVkit inferred somatic CNVs using the default circular binary segmentation algorithm based on the BAM files generated during somatic mutation detection. The log2 ratios at the fragment level were calculated and converted into inputs for the GISTIC2.0 software to identify chromosomal regions that were significantly amplified or deleted in tumors. A 0.3 log2 ratio threshold was used to define CNV expansions and deletions.

[0056] Total RNA was extracted from tissue samples using the TRIzol kit during transcriptome sequencing (RNA-seq) and analysis. RNA concentration and integrity were assessed using the Qubit RNA Assay Kit, Qubit 2.0 Fluorometer, and Agilent 2100 Bioanalyzer. Samples with RNA integrity values ​​greater than 5 were included in the study. Libraries were prepared from samples with high RNA integrity, no contaminants, and sufficient RNA quantity. RNA was purified from total RNA using poly-T oligonucleotide magnetic beads. RNA was cleaved in NEBNext First Strand Synthesis Reaction Buffer (5X) at high temperature using divalent cations. cDNA synthesis, end repair, A-tailing, and NEBNext adapter ligation were performed using the NEBNext Ultra RNA Library Prep Kit. Library fragments were purified using AMPure XP, and cDNA fragments with a length of 150–200 bp were selected. Library quality was assessed using an Agilent Bioanalyzer. Libraries were sequenced on the Illumina HiSeq X Ten platform to generate 150 bp paired-end reads. Trim cardio software was used to filter the sequencing data to remove adapters and low-quality sequences, and then FastQC was used for data quality assessment. The sequences were aligned to the reference genome (hg38) using STAR. Gene expression values ​​were calculated using RSEM based on the GENCODE (v35) gene annotation file. HTSeq was used to count the number of reads aligned to each gene, and gene expression levels were quantified as FPKM (fragments per kilobase of exon model per million mapped fragments) and TPM (transcripts per kilobase of exon model per million mapped reads).

[0057] In some embodiments, obtaining the proteomic features based on the data set in step S2 includes: performing mass spectrometry analysis on the tumor samples in the data set using a mass spectrometer to obtain the proteomic features.

[0058] Specifically, a mass spectrometer was used to perform mass spectrometry analysis on tumor samples in the data set. The process included: taking out the sample from the -80°C storage box, weighing an appropriate amount of paper towels, and placing them in a liquid nitrogen pre-cooled mortar. Liquid nitrogen was added to thoroughly grind the tissue into powder. Four times the volume of powder was added to each sample. Lysis buffer (1% Triton X-100, 1% protease inhibitor, 1% phosphatase inhibitor, 3 microns TSA, 50mM NAM) was added, followed by ultrasonic lysis. The sample was centrifuged at 4°C and 12,000 g for 10 minutes to remove cell debris, and the supernatant was transferred to a new centrifuge tube. Protein concentration was determined using a BCA assay kit.

[0059] Digest equal amounts of protein from each sample with trypsin and adjust the volume with lysis buffer. Add one portion of pre-chilled acetone and vortex, then add four portions of pre-chilled acetone and precipitate at -20°C for 2 hours. Centrifuge the sample at 4,500 g for 5 minutes and discard the supernatant. Wash the pellet twice with pre-chilled acetone. Air-dry the pellet, resuspend it in a 200 mM TEAB bottle, and add trypsin at a ratio of 1:50 (protease:protein, w / w) for overnight digestion. Add dithiothreitol (DTT) to a final concentration of 5 mM and reduce the sample at 56°C for 30 minutes. Add iodoacetamide (IAA) to a final concentration of 11 mM and incubate the sample in the dark at room temperature for 15 minutes.

[0060] The samples were separated using an Agilent 300Extend C18 column (4.6×250 mm) with a detection wavelength of 214 nm and a column temperature of 35°C. 95% buffer A was used for 30 minutes to equilibrate the column. After the baseline was stable, the step gradient method was started and the peptide samples were loaded into the high performance liquid chromatography (HPLC) fractionator. Samples were collected every 1 minute, and fractions 11 to 46 were combined into 12 groups and vacuum dried. The peptides were dissolved in mobile phase A and separated using an EASY-nLC 1200 ultra-high performance liquid chromatography system. Mobile phase A consisted of 0.1% formic acid and 2% acetonitrile in water, and mobile phase B consisted of 0.1% formic acid and 90% acetonitrile in water. The gradient was set as follows: 0-96 min, 6%-25% B; 96-114 min, 25%-35% B; 114-117 min, 35%-80% B; and 117-1200 min, 80% B, and the flow rate was maintained at 500 nl / min. The separated peptides were ionized in the NSI ion source and the data were collected using an Orbitrap Exploris 480 mass spectrometer.

[0061] Liquid chromatography (LC) parameters were consistent with those used in library construction. Peptides were separated using an ultra-high performance liquid chromatography system and analyzed using an Orbitrap Exploris 480 mass spectrometer. Precursor ions and their fragment ions were detected and analyzed using a high-resolution Orbitrap. The FAIMS compensation voltage (CV) was set to -40 V, -55 V, and -70 V. The primary mass scan range was set to 350-1350 m / z with a resolution of 120,000; the secondary scan resolution was set to 30,000. The secondary data acquisition mode was set to DIA mode, followed by a primary scan using 32% collision energy to fragment the 20 m / z window peptide ions into the HCD collision cell, followed by secondary mass analysis. The automatic gain control (AGC) of the secondary spectrum was set to 600%.

[0062] It should be noted that this application aims to collect as much glioblastoma multiforme (GBM) sequencing data as possible from public databases to verify the conclusions and enrich the research content. This application obtained the transcriptome expression profiles and clinical data of samples from the Gene Expression Comprehensive Database and the Chinese Glioma Genome Atlas, including GSE72951 (GPL14951, n=112), GSE43289 (GPL570, n=26), GSE43378 (GPL570, n=32), GSE7696 (GPL570, n=84), GSE13041 (GPL570 and GPL96, n=218), GSE15824 (GPL570, n=25), GS from the series matrix files uploaded by the author. This application uses the normalizeBetweenArrays function in the limma software package to perform quantile normalization on microarray data. Subsequently, after eliminating the batch effect, the present application merged the datasets from the same sequencing platform to obtain the GBM-GPL570 (n=215), GBM-GPL6480 (n=110), GBM-GPL96 (n=326), and GBM-GPL97 (n=135) cohorts. The combat function in the sva package was used to remove the batch effect. Finally, each dataset was normalized using the scale function.

[0063] GBM immunotherapy cohort: The original transcriptome sequencing data of GBM patients with anti-PD-1 immunotherapy information were obtained from the Sequence Read Archive (SRA) database uploaded by Zhao et al. (SRA accession: PRJNA482620)

[26] . This cohort included RNA-seq data of 7 non-responders and 10 responders, which were quantified into FPKM values ​​for subsequent analysis.

[0064] Expression profiles and drug response data of GBM cell lines: Transcriptome and drug response data of 35 GBM cell lines were obtained from the Cancer Cell Line Encyclopedia and the Cancer Drug Sensitivity Genomics Database. A total of 60 drugs classified as “clinically approved” and “in clinical development” were retained to explore potential subtype-specific treatment options for the three MOFS subtypes.

[0065] This application uses multimodal fusion with unsupervised clustering. Integrating multimodal data can reveal causal features that may be masked in single-modal analysis, and provide a holistic understanding of the complexity of the disease by exploring the interactions between the modalities and how these relationships drive differences in patient outcomes (such as survival and drug response). Multimodal data fusion strategies can be divided into early fusion, mid-term fusion, and late fusion according to the time period. Early fusion connects all data forms into a single matrix, which may lead to "dimensionality disaster" and variable shift in subsequent analysis, and cannot correct the imbalance of multimodal data, which may have an adverse effect on downstream analysis. Late fusion involves analyzing each omics layer separately and then integrating the results to produce consistent results and outputs. However, this approach sacrifices the complementary interactive information of multimodal data. Intermediate fusion usually involves simultaneous integration and clustering to connect correlations between different omics layers, identify multimodal joint clusters, and infer patient stratification and molecular mechanisms. In general, intermediate fusion is more advanced, but it has higher requirements for fusion algorithms.

[0066] In some embodiments, in step S3, multimodal data fusion is performed on the radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data, and proteomics features, comprising the following steps:

[0067] Step S301: using a variety of algorithms based on different principles to perform intermediate fusion of multimodal data on radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data and proteomics features.

[0068] Step S302: perform post-fusion on the intermediate fusion results obtained by multiple algorithms to obtain the final clustering result.

[0069] This application integrates 11 algorithms based on different principles to perform intermediate fusion of multimodal data (FAHZZU1 cohort), and then performs post-fusion on the results obtained by the 11 algorithms to obtain the final clustering result. Figure 2A As shown, feature matrices from whole exome sequencing (WES), transcriptomics (RNA-seq), proteomics (LC-MS), pathomics (WSI), and radiomics data were intermediately fused using 11 different algorithms and then late-fused to generate consensus clusters.

[0070] In some embodiments, before performing intermediate fusion of multimodal data on radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data, and proteomics features in step S301, the method further includes:

[0071] Step S300: Determine the optimal number of clusters and input features.

[0072] Specifically, when determining the optimal number of clusters and input features, the process includes: (1) first calculating the median absolute deviation (MAD) of variables in each modality layer in radiomics, pathological omics, transcriptomics, and proteomics, selecting the top n variables from each layer, and combining them into 2640 variable combinations; then calculating the cluster prediction index (CPI) and GAP statistic of each combination, and determining the optimal number of clusters and input features for the final clustering based on the combination with the highest sum of CPI and GAP statistics. Figure 2B As shown, the CPI and GAP statistics are calculated to determine the optimal number of clusters, with K=3 being the optimal number of clusters.

[0073] (2) Eleven algorithms based on different principles are used for intermediate fusion of multimodal data, including CIMLR, CPCA, iClusterBayes, IntNMF, LRAcluster, MCIA, NEMO, PINSPlus, RGCCA, SGCCA and SNF.

[0074] (3) The Jaccard index was calculated using the binary results of the 11 algorithms to evaluate the similarity between samples.

[0075] (4) Clustering of cluster analysis is used to obtain consistent results from 11 algorithms based on the Jaccard distance matrix.

[0076] (5), the proportion of fuzzy clustering (PAC) and the Calinski and Harabasz index (CHI) were used to evaluate the fitness of the number of clusters.

[0077] (6) The silhouette coefficient is calculated for each cluster, and samples with a silhouette coefficient lower than 0.4 are removed to obtain the core sample set.

[0078] In some embodiments, the identified MOFS subtypes include: proneuronal MOFS1, proliferative MOFS2, and tumor microenvironment-enriched MOFS3; MOFS1 subtype is a proneuronal type with increased neurodevelopmental activity and a large number of neural cell infiltrations and a good prognosis; MOFS2 subtype is a proliferative type with the worst prognosis, high proliferative activity, genomic instability, and sensitivity to temozolomide; MOFS3 subtype is a tumor microenvironment-enriched type with a moderate prognosis, rich immune and matrix components, and sensitivity to anti-PD-1 immunotherapy. Figure 2C Shown is a heat map of the consensus matrix of 122 patients with IDH-wild-type gliomas, showing three distinct multimodal fusion subtypes (MOFS1, MOFS2, and MOFS3).

[0079] In some embodiments, among the identified MOFS subtypes, STRAP appears as a prognostic biomarker and potential therapeutic target for the MOFS2 subtype, which is associated with its proliferation phenotype; the MOFS3 subtype has abundant tumor immune infiltration and is sensitive to immunotherapy, which is an important prognostic indicator and can be used for further prognostic stratification. Figure 2D The principal component analysis (PCA) showed that the three MOFS isoforms were clearly separated in two-dimensional space.

[0080] It should be noted that this application uses multimodal analysis to provide insights into GBM tumor heterogeneity in terms of phenotypic manifestations, oncogenic signals, immune responses, and genomic alterations. Multimodal analysis includes: functional enrichment analysis, genomic alteration analysis, transcriptome and proteome expression profiling. Multimodal analysis mainly emphasizes potential effective prediction and treatment strategies for IDH wild-type GBM patients.

[0081] Functional enrichment analysis, which integrates C2-CP, C5-GO, and Hallmark gene sets from the MSigDB database. Functional enrichment analysis of transcriptome or proteome data of different subtypes was performed using three methods, including single sample gene set detection (ssGST), overrepresentation analysis (ORA), and gene set enrichment analysis (GSEA). ssGST analysis was performed using the yaGST software package to obtain the normalized enrichment score (NES) of each pathway in each sample. Then, each pathway of different subtypes was differentially analyzed, and pathways with FDR<0.001 and NES difference>1 were considered significantly enriched. ORA analysis was performed using the default parameters in the Metascape tool, and pathways with FDR<0.001 were considered significantly enriched. GSEA analysis was performed using the clusterProfiler software package, and pathways with FDR<0.001 were considered significantly enriched.

[0082] Analysis of genomic alterations: In this part, mutation data were processed using the maftools package, and single nucleotide variations (SNVs), insertions / deletions (INDELs), and tumor mutation burden (TMB) were calculated for each sample. Genes with mutation frequencies greater than 5% in all samples were retained. Broad and focal CNV burdens were defined as the sum of CNVs occurring in chromosome arms and focal segments, respectively. Due to the limited number of proteins detected by MS in this study, mRNA expression profiles were associated with CNVs to identify functional CNV genes. The Pearson correlation between mRNA expression and CNV variation scores of each gene was calculated, and genes with FDR < 0.05 and Pearson coefficient > 0.3 were retained (n=3888). Subsequently, a critical value of 0.3 was used to define CNV amplifications and deletions, and genes with an alteration rate > 5% were retained. If a certain CNV variation frequency of a gene was high, it was considered to be a dominant variation of the gene. Genes with dominant variations more than twice that of non-dominant variations were retained (n=2168). Fisher's exact test was used to detect CNV differences among the three isoforms for each gene, and genes with FDR < 0.05 were retained (n = 1023).

[0083] Transcriptome and proteome expression profile analysis: Kruskal-Wallis test was used to compare the differential gene expression between the three subtypes, and genes with FDR < 0.05 were retained. Subsequently, Wilcoxon rank sum test was used to further compare the expression differences between the two groups, and genes with FDR < 0.05 were considered subtype-specific genes.

[0084] Given the abundance of high-quality GBM transcriptome data in public databases, this application developed an integrated classification framework (MOFS ensemble classifier) ​​based on transcriptome expression profiles to identify MOFS subtypes in new cohorts. The development process was based on the FAHZZU1 cohort as a training set:

[0085] (1) Logistic regression and receiver operating characteristic (ROC) analysis were performed on all genes of each subtype. For each subtype, genes with FDR < 0.05 and area under the ROC curve (AUC) > 0.7 were retained.

[0086] (2) The Lasso algorithm was used for feature selection and dimensionality reduction, and genes with non-zero Lasso coefficients were used as input variables during modeling. For the gene set test (GST) classifier, only genes with coefficients greater than 0 were used for single-sample enrichment analysis.

[0087] (3) The classifier consists of 17 algorithms, including GST, adaptive boosting (AdaBoost), decision tree (DT), elastic net (Enet), gradient boosted decision tree (GBDT), k-nearest neighbor (KNN), Lasso, linear discriminant analysis (LDA), naive Bayes (NBayes), neural network (NNet), principal component analysis (PCA), random forest (RF), ridge regression, stepwise logistic regression (StepLR), singular value decomposition (SVD), support vector machine (SVM) and XGBoost. The output of each algorithm is the probability of three subtypes, and the sum of the probabilities of the three subtypes is equal to 1. Algorithms that show a trend in median survival that is inconsistent with the training set are considered unqualified.

[0088] (4) For each subtype, the average discrimination probability of all qualified algorithms is taken as the final subtype probability, and the subtype with the highest probability is taken as the final classification result.

[0089] (5) This classifier was used to identify MOFS subtypes in the GSE72951, GBM-GPL570, GBM-GPL6480, GBM-GPL96, GBM-GPL97, CGGA-Array, CGGA-RNAseq, and PRJNA482620 datasets.

[0090] (6) The classifier was tested on the CGGA-RNAseq dataset using different RNA-seq quantification metrics (FPKM and TPM), and 93% (312 / 334) of the results were consistent. For the GBM-GPL570 dataset, the classifier was tested before and after batch removal, and 89% (191 / 215) of the results were consistent. These results demonstrate the stability of the integrated MOFS classifier of this application.

[0091] The tumor microenvironment (TME) has a substantial impact on GBM classification. In the TME analysis process, the ESTIMATE package was used to evaluate the abundance of immune components, stromal components, and tumor purity in GBM expression data. The GSVA software package was used to calculate the infiltration abundance of microglia, monocytes, CD8+ T cells, oligodendrocytes, astrocytes, neurons, and matrix scores, which were determined based on cell markers in previous GBM single-cell studies. The CIBERSORT tool was used to evaluate the infiltration abundance of CD4+ T cells, mast cells, natural killer cells, dendritic cells, and neutrophils. The immune regulatory gene set was downloaded from the TISIDB database and included five categories: antigen presentation, immune co-stimulation, immune checkpoints, chemokines, and receptors. The differences in TME components, cell abundance, and immune regulatory factors between different subtypes were compared.

[0092] In order to better describe the cancer immune cycle (CIC), this application constructs an immune map consisting of eight aspects: tumor antigenicity, T cell chemotaxis and infiltration, T cell immunity, tumor cell recognition, T cell priming and activation, immunostimulatory factors, immunosuppressive molecules, and cytotoxicity. Tumor antigenicity is expressed as log2(TMB). Cytotoxicity is calculated according to the formula proposed by Rooney et al. Other pathways are calculated using the published immune cycle gene set and GSVA package. When drawing the immune map, the score of each of the eight immune pathways for each patient is converted to a Z score. If M represents the mean of the score and SD represents the standard deviation of the score, the final score for each patient is calculated as 3+1.5×(Score-M) / SD. Two glioma tissue microarrays (NGL1001, n=100) were purchased from SUPERBIOTEK. The clinical data of 100 tumor patients were all from the company's official website.

[0093] Immunohistochemical staining. Immunohistochemistry (IHC) experiments used anti-strip (Cat No. 18277-1-AP, Proteintech 1:200) and anti-S100A4 (Cat No. 16105-1-AP, Proteintech 1:200). The staining percentage was scored as 1 (1-25%), 2 (26-50%), 3 (51-75%), or 4 (76-100%), while the staining intensity was scored from 0 (no signal color) to 3 (light yellow, brown, and dark brown). Three people who were not familiar with the clinical parameters scored the tissue staining. The final IHC score was calculated by multiplying the percentage of positively stained cells by the nuclear staining intensity score.

[0094] For specific drug identification, this application retrieved drug response data and gene expression profiles of 35 GBM cell lines from the CCLE and GDSC databases. The drug response data was quantified using IC50 (half-maximal inhibitory concentration), where a lower IC50 value indicates a higher drug sensitivity. This application retains a set of genes specifically expressed in GBM cells in the gene expression profile data. Then, this application used the ridge regression model in the promprovetic software package to evaluate drug response in clinical samples, which has been used in many studies. The model is trained based on the expression profile and drug response data of GBM cell lines, and is used to predict drug response using mRNA and protein expression profiles specific to GBM cells in clinical samples. For each subtype, if the IC50 value of a drug is significantly lower than that of the other two subtypes (FDR<0.05), the drug is considered a subtype-specific drug.

[0095] Deep neural network model for predicting MOFS subtypes based on MRI features. In clinical practice, imaging images have advantages over molecular omics data, such as convenience, low cost, and non-invasive collection. In order to promote the clinical translation of this application work, this study adopted a neural network algorithm based on elastic back propagation, which further improved the clinical practicality of the study. The process is as follows:

[0096] (1) Feature selection: For each MOFS subtype, MRI imaging features with a univariate logistic regression P value less than 0.01 were retained. Then, 70% of the samples were randomly selected from all samples for logistic regression using the bootstrap method and repeated 1000 times. Genes that maintained a significance level of more than 95% after the resampling process were retained (P < 0.05). Next, the Lasso algorithm was used for further dimensionality reduction and model simplification, and input variables with non-zero Lasso coefficients were retained as input variables for modeling.

[0097] (2) Hyperparameter optimization: This application divides the FAHZZU1 cohort into a training set and a test set in a ratio of 7:3. The neural network model is constructed using the neural network package, and the parameters include learning rate, loss function, activation function, number of hidden layers, and number of nodes per layer. This application performs hyperparameter optimization through grid search and selects the parameter combination with the highest accuracy on the test set as the final model.

[0098] (3) Model validation: Confusion matrix and ROC analysis were used to validate the training set, test set, FAHZZU2 validation set, and FAHZZU3 validation set.

[0099] (4) Development of a web-based tool: To further facilitate researchers and clinical practitioners, this application developed a web application based on Shiny and HTML5, CSS, and JavaScript libraries.

[0100] Based on this, this application proposes a multimodal fusion classification (MOFS) framework, which integrates the imaging, pathology, whole exome sequencing, RNA sequencing and mass spectrometry data of 122 IDH wild-type adult glioma patients (including 106 histological glioblastomas, 9 molecular glioblastomas and 7 diffuse astrocytomas), and identifies three subtypes: MOFS1 (pro-neuronal type) with increased neurodevelopmental activity and a large number of neuronal cell infiltration and a good prognosis; MOFS2 (proliferative type) with the worst prognosis, high proliferation activity, genomic instability and sensitivity to temozolomide; MOFS3 (tumor microenvironment-enriched type) with a moderate prognosis, rich immune and matrix components and sensitivity to anti-PD-1 immunotherapy. This application identifies biomarkers and finds that STRAP appears as a prognostic biomarker and potential therapeutic target for MOFS2, which is associated with its proliferation phenotype. Stromal infiltration in MOFS3 is an important prognostic indicator and can be used for further prognostic stratification. In addition, a deep neural network (DNN) classifier based on imaging features was developed to further enhance clinical translatability, providing a non-invasive tool for predicting MOFS subtypes. In summary, the potential of multimodal fusion in improving the classification, prognostic accuracy, and precision treatment of IDH wild-type gliomas is emphasized, providing a new avenue for personalized treatment.

[0101] See also Figure 3 The embodiment of the present application also provides a multimodal data fusion IDH wild-type glioblastoma classification system, including: a data set module 101, a multimodal data acquisition module 102, an integrated classifier development module 103 and a model verification module 104 connected in sequence; the data set module 101 is used to obtain a data set of GBM patients; GBM patients include IDH wild-type glioblastoma patients; the multimodal data acquisition module 102 is used to obtain radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data and proteomics features according to the data set; the integrated classifier development module 103 is used to perform multimodal data fusion on radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data and proteomics features, and construct a multimodal fusion classification framework based on transcriptome expression profiles to identify MOFS subtypes in multimodal data; the model verification module 104 is used to construct a deep neural network classifier for predicting MOFS subtypes based on radiomics features and using a neural network algorithm based on elastic back propagation, and verify the identified MOFS subtypes.

[0102] Previous studies have shown that the integration of multimodal data brings new insights into tumor stratification. In general, radiology, pathology, DNA, RNA, and protein can reflect the anatomical, cellular, genetic, transcriptional, and functional levels of the disease, respectively. The integration of multimodal analysis enables this application to better understand the connection between complex disease phenotypes and biological mechanisms. In fact, the cellular-level microscopic phenotypes produced by gene mutations, abnormal signals, and abnormal expressions have a profound impact on key cellular processes such as cell proliferation, inflammatory response, and angiogenesis. These changes can be captured by histological images. Similarly, phenotypes visible to the naked eye, such as tumor shape, texture, edema, and necrosis, can be visualized using advanced imaging techniques such as multiparametric MRI. Previous studies have also shown that radiological or histopathological images can reflect the mutation status or expression level of genes. This not only provides a bridge between radiological histopathology images and molecular omics, but also provides a theoretical basis for multimodal fusion analysis.

[0103] Compared with the prior art, the modality data fusion IDH wild-type glioblastoma classification method and system provided in this application has the following advantages: This application integrates multimodal data from MRI-derived radiomics, WSI-derived pathological omics, WES, RNA-seq, and MS-based proteomics, and identifies and verifies three different subtypes in IDH wild-type adult gliomas. The current cohort includes not only histological GBM, but also molecularly diagnosed GBM and IDH wild-type low-grade diffuse gliomas, the latter two of which are usually indistinguishable clinically radiologically and pathologically. The multimodal analysis of this application provides insights into the heterogeneity of GBM tumors in terms of phenotypic manifestations, oncogenic signals, immune responses, and genomic alterations. In addition, this work highlights the potential effective prediction and treatment strategies for IDH wild-type GBM patients.

[0104] In addition, the present application also found that STRAP is specifically overexpressed and amplified in MOFS2, and STRAP serves as a prognostic biomarker and potential therapeutic target for the MOFS2 subtype. The MOFS3 subtype has abundant tumor immune infiltration and is sensitive to immunotherapy.

[0105] Based on the above technical scheme, the embodiment of the present application provides a multimodal data fusion IDH wild-type glioblastoma classification method and system, the method comprising the following steps: first, obtaining a data set of GBM patients; GBM patients include IDH wild-type glioblastoma patients; then, based on the data set, obtaining imaging genomics features, pathological genomics features, whole exome sequencing data, transcriptome sequencing data and proteomics features; next, performing multimodal data fusion on the imaging genomics features, pathological genomics features, whole exome sequencing data, transcriptome sequencing data and proteomics features, and constructing a multimodal fusion classification framework based on the transcriptome expression spectrum to identify MOFS subtypes in multimodal data; finally, based on the imaging genomics features and using a neural network algorithm based on elastic back propagation, a deep neural network classifier for predicting MOFS subtypes is constructed to verify the identified MOFS subtypes.

[0106] The multimodal data fusion IDH wild-type glioblastoma classification method provided in this application integrates multimodal data from MRI-derived radiomics, WSI-derived pathological omics, WES, RNA-seq, and MS-based proteomics, and identifies and validates three different subtypes in IDH wild-type adult gliomas. The current cohort includes not only histological GBM, but also molecularly diagnosed GBM and IDH wild-type low-grade diffuse gliomas, the latter two of which are usually indistinguishable in clinical radiology and pathology. The multimodal data fusion analysis of this application provides insights into the heterogeneity of GBM tumors in terms of phenotypic manifestations, oncogenic signals, immune responses, and genomic changes. This application achieves early intervention and treatment of IDH wild-type gliomas through more accurate diagnosis and prognosis prediction, and provides patients with IDH wild-type gliomas with precise treatment plans based on tumor biological characteristics. This application provides a basis for personalized treatment by identifying prognostic biomarkers and potential therapeutic targets STRAP associated with specific subtypes. In addition, the development of a deep neural network classifier further enhances the clinical translatability of our findings and provides a non-invasive tool for predicting MOFS subtypes.

[0107] Those skilled in the art can understand that the above-mentioned embodiments are specific examples for implementing the present application, and in practical applications, various changes can be made to them in form and detail without departing from the spirit and scope of the present application. Any person skilled in the art can make their own changes and modifications without departing from the spirit and scope of the present application, so the scope of protection of the present application shall be based on the scope defined in the claims.

Claims

1. A multimodal data fusion IDH wild-type glioblastoma classification method, characterized in that: The following steps are involved: Obtaining a data set of GBM patients; the GBM patients include IDH wild-type glioblastoma patients; Based on the data set, radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data and proteomics features are obtained; Multimodal data fusion was performed on radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data, and proteomics features, and a multimodal fusion typing framework was constructed based on transcriptome expression profiles to identify MOFS subtypes in multimodal data; Based on the described radiomics features and using a neural network algorithm based on elastic back-propagation, a deep neural network classifier for predicting MOFS subtypes was constructed, and the identified MOFS subtypes were verified.

2. The multimodal data fusion IDH wild-type glioblastoma classification method according to claim 1, characterized in that: Based on the dataset, radiomics features were obtained, including: Performing image acquisition on the data set to obtain an MRI image; the MRI image is a magnetic resonance imaging image; The MRI image is standardized, and imaging features are extracted from the standardized MRI image to obtain radiomics features.

3. The multimodal data fusion IDH wild-type glioblastoma classification method according to claim 1, characterized in that: Based on the data set, pathological omics features are obtained, including: A WSI image is obtained by scanning a hematoxylin-eosin slide; the WSI image is a whole slide image; The WSI image is subjected to tissue segmentation, and features are extracted from the segmented tissue image to obtain pathological omics features.

4. The multimodal data fusion IDH wild-type glioblastoma classification method according to claim 1, characterized in that: Based on the data set, whole exome sequencing data and transcriptome sequencing data are obtained, including: Whole exome sequencing and transcriptome sequencing were performed on the tumor samples in the data set to obtain whole exome sequencing data and transcriptome sequencing data, which were recorded as WES data and RNA-seq data, respectively.

5. The multimodal data fusion IDH wild-type glioblastoma classification method according to claim 1, characterized in that: Based on the data set, proteomic features were obtained, including: A mass spectrometer is used to perform mass spectrometry analysis on the tumor samples in the dataset to obtain proteomic features.

6. The multimodal data fusion IDH wild-type glioblastoma classification method according to claim 1, characterized in that: Multimodal data fusion of radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data and proteomics features, including: Using a variety of algorithms based on different principles, we can perform intermediate fusion of multimodal data including radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data, and proteomics features. The intermediate fusion results obtained by multiple algorithms are later fused to obtain the final clustering result.

7. The multimodal data fusion IDH wild-type glioblastoma classification method according to claim 6, characterized in that: Before the intermediate fusion of multimodal data of radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data and proteomics features, it also includes: Determine the optimal number of clusters and input features; When determining the optimal number of clusters and input features, we first calculated the median absolute deviation of the variables in each modal layer in radiomics, pathological omics, transcriptomics, and proteomics, and selected the top n variables from each layer to form 2640 variable combinations. Then, we calculated the clustering prediction index and GAP statistic for each combination, and determined the optimal number of clusters and input features for the final clustering based on the combination with the highest sum of the clustering prediction index and GAP statistic.

8. The multimodal data fusion IDH wild-type glioblastoma classification method according to claim 1, characterized in that: The identified MOFS subtypes include: proneuronal MOFS1, proliferative MOFS2, and tumor microenvironment-enriched MOFS3; The MOFS1 subtype is a proneuronal type with increased neurodevelopmental activity and a large number of neuronal infiltrations, and a good prognosis; The MOFS2 subtype is a proliferative type with the worst prognosis, high proliferation activity, genomic instability, and sensitivity to temozolomide; The MOFS3 subtype is a tumor microenvironment-enriched type with intermediate prognosis, rich immune and stromal components, and sensitive to anti-PD-1 immunotherapy.

9. The multimodal data fusion IDH wild-type glioblastoma classification method according to claim 8, characterized in that: Among the identified MOFS subtypes, STRAP emerged as a prognostic biomarker and potential therapeutic target for the MOFS2 subtype, which is associated with its proliferation phenotype; the MOFS3 subtype has rich tumor immune infiltration and is sensitive to immunotherapy, which is an important prognostic indicator and can be used for further prognostic stratification.

10. A multimodal data fusion IDH wild-type glioblastoma classification system, characterized in that: include: A dataset module, a multimodal data acquisition module, an integrated classifier development module, and a model validation module connected in sequence; The data set module is used to obtain a data set of GBM patients; the GBM patients include IDH wild-type glioblastoma patients; The multimodal data acquisition module is used to obtain radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data and proteomics features according to the data set; The integrated classifier development module is used to perform multimodal data fusion on radiomics features, pathological features, whole exome sequencing data, transcriptome sequencing data and proteomics features, and to construct a multimodal fusion typing framework based on transcriptome expression profiles to identify MOFS subtypes in multimodal data; The model verification module is used to construct a deep neural network classifier for predicting MOFS subtypes based on the radiomics features and adopt a neural network algorithm based on elastic back propagation to verify the identified MOFS subtypes.

Images