Machine-learning-based classification of diffuse large B-cell lymphoma patients by a 7-mRNA signature enriched with immune infiltration and cell cycle

BACKGROUND

Diffuse large B-cell lymphoma (DLBCL) exhibits remarkable heterogeneity but still remains undiagnosed in identifying the subpopulation of DLBCL to predict the prognosis and guide clinical treatment.

METHODS

Molecular subgroups were identified in gene expression data from GSE10846 by a consensus clustering algorithm. And gene set enrichment analysis, immune infiltration, and the proposed cell cycle algorithm were applied to explore the biological functions of different subtypes. Meanwhile, univariate and multivariate Cox regression analyses were used to evaluate independent prognostic factors of DLBCL. Finally, the prognostic model, including some key genes screened by Lasso regression, Random Forest algorithm, and point-biserial correlation, was constructed by an optimal classifier from seven machine learning algorithms and validated by another three external datasets (GSE34171, GSE87371, GSE31312).

RESULTS

Comprehensive genomic analysis of 1,143 DLBCL samples identify 2 molecularly, prognostically relevant subtypes: immune-enriched (IME) and cell-cycle-enriched (CCE). Then a new predictive model including seven key genes (SERPING1, TIMP2, NME1, DCTPP1, RFC4, POLE2, and SNRPD1) was developed with high prediction accuracy (88.6%) and strong predictive power (AUC = 0.973) based on the Support Vector Machine (SVM) algorithm in 414 patients from GSE10846. The predictive power was similar in another three testing sets (HR > 1.400, p < 0.05).

CONCLUSION

This model could evaluate survival independently with strong predictive power compared with other clinical risk factors. Our study constructed a reliable model to predict two new subtypes of DLBCL patients, which could guide the implementation of individualized treatment.

Development and validation of a 23-gene expression signature for molecular subtyping of medulloblastoma in a long-term Chinese cohort

PURPOSE

Medulloblastoma is the most common childhood malignant brain tumor and is a leading cause of cancer-related death in children. Recent transcriptional studies have shown that medulloblastomas comprise at least four molecular subgroups, each with distinct demographics, genetics, and clinical outcomes. Medulloblastoma subtyping has become critical for subgroup-specific therapies. The use of gene expression assays to determine the molecular subgroup of clinical specimens is a long-awaited application of molecular biology for this pediatric cancer.

METHODS

In the current study, we established a medulloblastoma transcriptome database of 460 samples retrieved from three published datasets (GSE21140, GSE37382, and GSE37418). With this database, we identified a 23-gene signature that is significantly associated with the medulloblastoma subgroups and achieved a classification accuracy of 95.2%.

RESULTS

The 23-gene signature was further validated in a long-term cohort of 142 Chinese medulloblastoma patients. The 23-gene signature classified 21 patients as WNT (15%), 41 as SHH (29%), 16 as Group 3 (11%), and 64 as Group 4 (45%). For patients of WNT, SHH, Group 3, and Group 4, 5-year overall-survival rate reached 80%, 62%, 27%, and 47%, respectively (p < 0.0001), meanwhile 5-year progression-free survival reached 80%, 52%, 27%, and 45%, respectively (p < 0.0001). Besides, SHH/TP53-mutant tumors were associated with worse prognosis compared with SHH/TP53 wild-type tumors and other subgroups. We demonstrated that subgroup assignments by the 23-gene signature and Northcott's NanoString assay were highly comparable with a concordance rate of 96.4%.

CONCLUSIONS

In conclusion, we present a novel gene signature that is capable of accurately and reliably assigning FFPE medulloblastoma samples to their molecular subgroup, which may serve as an auxiliary tool for medulloblastoma subtyping in the clinic. Future incorporation of this gene signature into prospective clinical trials is warranted to further evaluate its clinical.

Incidence and Risk Factors for Necessitating Cerebrospinal Fluid Diversion Following Medulloblastoma Surgery in Children

BACKGROUND

There are insufficient data on pediatric patients with medulloblastoma who require cerebrospinal fluid (CSF) diversion following resection. Therefore, this study aimed to determine the incidence and the characteristics associated with it in this subset of patients.

METHODS

We conducted a single-center, retrospective, observational cohort study of patients aged 18 years or less who underwent medulloblastoma resection at our department between 2010 and 2021. The primary outcome was the incidence of CSF diversion surgery required after resection. Participant demographics, tumor biology, and interventions were analyzed using univariate- and multivariate-adjusted models.

RESULTS

Of the 183 patients admitted to our department, 131 (71.6%) participated in this study. The incidence of permanent CSF diversion was 26.0% (95% confidence interval [CI]: 18.7 to 34.3). Factors independently associated with requirement of permanent CSF diversion were medulloblastoma volume >46.4 cm³ (odds ratio [OR]: 2.919, 95% CI: 1.191 to 7.156) and CSF channel invasion (OR: 2.849, 95% CI: 1.142 to 7.102). The duration of manifestation may be a covariate of tumor volume with increased risk of requirement for permanent CSF diversion (OR: 1.006, 95% CI: 1.000 to 1.013), and tumor volume may be a predictor in patients who underwent subtotal resection (OR: 4.900, 95% CI: 0.992 to 24.208, P = 0.05). Finally, patients who required permanent CSF diversion were divided according to medulloblastoma molecular subgroups, and no significant differences were found.

CONCLUSION

We report major predictive factors for permanent CSF diversion surgery in patients with medulloblastoma. Our study suggests that the presence of postresection hydrocephalus is not high enough to warrant permanent, prophylactic CSF diversion in all patients.

Medulloblastoma: Current Perspectives and Recent Advances

Medulloblastoma is the most common embryonal tumor of the central nervous system in childhood. Combined multimodality approaches, including surgery, radiation, and chemotherapy, have improved the outcome of medulloblastoma. Advances in genomic research have shown that medulloblastoma is not a biologically or clinically discrete entity. Previously, the risk was divided according to histology, presence of metastasis, degree of resection, and age at diagnosis. Through the development of integrated genomics, new biology-based risk stratification methods have recently been proposed. It is also important to understand the genetic predisposition of patients with medulloblastoma. Therefore, treatment goal aimed to improve the survival rate with minimal additional adverse effects and reduced long-term sequelae. It is necessary to incorporate genetic findings into the standard of care, and clinical trials that reflect this need to be conducted.

Radiomics signature for the prediction of progression-free survival and radiotherapeutic benefits in pediatric medulloblastoma

PURPOSE

To develop and validate a radiomics signature for progression-free survival (PFS) and radiotherapeutic benefits in pediatric medulloblastoma.

MATERIALS AND METHODS

We retrospectively enrolled 253 consecutive children with medulloblastoma from two hospitals. A total of 1294 radiomic features were extracted from the region of tumor on the T1-weighted and contrast-enhanced T1-weighted (CE-T1w) MRI. Radiomic feature selection and machine learning modelling were performed to build radiomics signature for the prediction of PFS on the training set. Moreover, the prognostic performance of the clinical parameters was investigated for PFS. The Concordance index (a value of 0.5 indicates no predictive discrimination, and a value of 1 indicates perfect predictive discrimination) was used to measure and compare the prognostic performance of these models.

RESULTS

The radiomics signature for the prediction of the PFS yielded Concordance indices of 0.711, 0.707, and 0.717 on the training and held-out test sets 1 and 2, respectively. The radiomics nomogram integrating the radiomics signature, age, and metastasis performed better than the nomogram incorporating only clinicopathological factors (C-index, 0.723 vs. 0.665 and 0.722 vs. 0.677 on the held-out test sets 1 and 2, respectively), which was also validated by the good calibration and decision curve analysis. Further analysis demonstrated that patients with lower value of radiomics signature were associated with better clinical outcomes after postoperative radiotherapy (p < 0.001).

CONCLUSION

The radiomics signature and nomogram performed well for the prediction of PFS and could stratify patients underwent postoperative radiotherapy into the high- and low-risk groups with significantly different clinical outcomes.

Predisposition of Wingless Subgroup Medulloblastoma for Primary Tumor Hemorrhage

BACKGROUND

Primary intratumoral hemorrhage as a presenting sign is rare in children with medulloblastomas but may result in severe complications. Given the distinct properties of molecular medulloblastoma subgroups, the impact on neurosurgical practice has still to be defined.

OBJECTIVE

To investigate both clinical and radiological presentation of intratumoral hemorrhage in medulloblastoma patients in the context of molecular subgroups.

METHODS

Data of all consecutive medulloblastoma patients treated at our institution between 1993 and 2018 (n = 104) were retrospectively reviewed in respect of clinical and radiological presentation as well as molecular subgroups. For cases with available tumor tissue (n = 86), subgroups were assigned by either 450 K methylation array or immunohistochemistry and CTNNB1 sequencing. Available imaging at diagnosis (n = 62) was reviewed by an experienced neuroradiologist.

RESULTS

Within the entire cohort, 4 patients (4%) presented with massive spontaneous hemorrhage. Although no patient died as a direct consequence of hemorrhage, all suffered from serious sequelae. Moreover, 3 additional patients displayed radiological evidence of significant hemorrhage. Interestingly, all 7 cases belonged to the wingless (WNT) subgroup (n = 13), resulting in intratumoral hemorrhage in 54% (7/13) of pediatric WNT medulloblastomas. In contrast, significant hemorrhage was absent in all other molecular subgroups.

CONCLUSION

Our results suggest that a substantial proportion of pediatric WNT medulloblastomas display significant intratumoral hemorrhage at the time of diagnosis. Consequently, the presence of significant hemorrhage in fourth ventricle childhood tumors is suggestive of WNT medulloblastoma and should lead to a less aggressive attempt for total resection in this prognostically favorable tumor type.

Characterization of global 5-hydroxymethylcytosine in pediatric posterior fossa ependymoma

Background

5-Hydroxymethylcytosine (5hmC) is a novel epigenetic mark and may be involved in the mechanisms of tumorigenesis and malignant transformation. However, the role of 5hmC in ependymoma, the third most common brain tumor in children, remains unclear. The aim of this study sought to identify the characterization of 5hmC levels in pediatric posterior fossa ependymoma and to evaluate whether 5hmC levels could be a potential factor to predict clinical outcomes.

Results

Our results showed that 5hmC levels were globally decreased in posterior fossa ependymoma compared with normal cerebellum tissues (P < 0.001). Group A posterior fossa ependymomas had higher 5hmC levels than group B tumors (P = 0.007). Moreover, 5hmC levels positively correlated with Ki-67 index in posterior fossa ependymoma (r = 0.428, P = 0.003). Multivariate Cox hazards model revealed that patients with high 5hmC levels (> 0.102%) had worse PFS and OS than patients with lower 5hmC levels (< 0.102%) (PFS: HR = 3.014; 95% CI, 1.040–8.738; P = 0.042; OS: HR = 2.788; 95% CI, 0.974–7.982; P = 0.047).

Conclusions

Our findings suggest that loss of 5hmC is an epigenetic hallmark for pediatric posterior fossa ependymoma. 5hmC levels may represent a potential biomarker to predict prognosis in children with posterior fossa ependymoma.

Prognostic value of Ki-67 index in adult medulloblastoma after accounting for molecular subgroup: a retrospective clinical and molecular analysis

INTRODUCTION

Medulloblastoma (MB) is a rare primary brain tumor in adults. We previously evaluated that combining both clinical and molecular classification could improve current risk stratification for adult MB. In this study, we aimed to identify the prognostic value of Ki-67 index in adult MB.

METHOD

Ki-67 index of 51 primary adult MBs was reassessed using a computer-based image analysis (Image-Pro Plus). All patients were followed up ranging from 12 months up to 15 years. Gene expression profiling and immunochemistry were used to establish the molecular subgroups in adult MB. Combined risk stratification models were designed based on clinical characteristics, molecular classification and Ki-67 index, and identified by multivariable Cox proportional hazards analysis.

RESULTS

In our cohort, the mean Ki-67 value was 30.0 ± 11.3% (range 6.56-63.55%). The average Ki-67 value was significantly higher in LC/AMB than in CMB and DNMB (P = .001). Among three molecular subgroups, Group 4-tumors had the highest average Ki-67 value compared with WNT- and SHH-tumors (P = .004). Patients with Ki-67 index large than 30% displayed poorer overall survival (OS) and progression free survival (PFS) than those with Ki-67 less than 30% (OS: P = .001; PFS: P = .006). Ki-67 index (i.e. > 30%, < 30%) was identified as an independent significant prognostic factor (OS: P = .017; PFS: P = .024) by using multivariate Cox proportional hazards model.

CONCLUSIONS

In conclusion, Ki-67 index can be considered as a valuable independent prognostic biomarker for adult patients with MB.

Comparative analysis of histologically classified oligodendrogliomas reveals characteristic molecular differences between subgroups

Background

Molecular data of histologically classified oligodendrogliomas are available offering the possibility to stratify these human brain tumors into clinically relevant molecular subtypes.

Methods

Gene copy number, mutation, and expression data of 193 histologically classified oligodendrogliomas from The Cancer Genome Atlas (TCGA) were analyzed by well-established computational approaches (unsupervised clustering, statistical testing, network inference).

Results

We applied hierarchical clustering to tumor gene copy number profiles and revealed three molecular subgroups within histologically classified oligodendrogliomas. We further screened these subgroups for molecular glioma markers (1p/19q co-deletion, IDH mutation, gain of chromosome 7 and loss of chromosome 10) and found that our subgroups largely resemble known molecular glioma subtypes. We excluded glioblastoma-like tumors (7a10d subgroup) and derived a gene expression signature distinguishing histologically classified oligodendrogliomas with concurrent 1p/19q co-deletion and IDH mutation (1p/19q subgroup) from those with predominant IDH mutation alone (IDHme subgroup). Interestingly, many signature genes were part of signaling pathways involved in the regulation of cell proliferation, differentiation, migration, and cell-cell contacts. We further learned a gene regulatory network associated with the gene expression signature revealing novel putative major regulators with functions in cytoskeleton remodeling (e.g. APBB1IP, VAV1, ARPC1B), apoptosis (CCNL2, CREB3L1), and neural development (e.g. MYTIL, SCRT1, MEF2C) potentially contributing to the manifestation of differences between both subgroups. Moreover, we revealed characteristic expression differences of several HOX and SOX transcription factors suggesting the activity of different glioma stemness programs in both subgroups.

Conclusions

We show that gene copy number profiles alone are sufficient to derive molecular subgroups of histologically classified oligodendrogliomas that are well-embedded into general glioma classification schemes. Moreover, our revealed novel putative major regulators and characteristic stemness signatures indicate that different developmental programs might be active in these subgroups, providing a basis for future studies.

Electronic supplementary material

The online version of this article (10.1186/s12885-018-4251-7) contains supplementary material, which is available to authorized users.

Distinctive localization and MRI features correlate of molecular subgroups in adult medulloblastoma

Medulloblastoma (MB) is recognized as comprising four molecular subgroups with distinct transcriptional profiles, clinical features, and outcomes. Previous studies demonstrate that pediatric MBs present with subgroup-specific MRI manifestations. We hypothesized that combination of anatomical localization and conventional features based on MR imaging can predict these subgroups in adult MBs. MR Imaging manifestations of 125 adult patients with MB were analyzed retrospectively based on pre-operative MRI scans. MB molecular subgroups were evaluated by the expression profiling array and immunohistochemistry. A pediatric MB cohort of 60 patients were analyzed for comparison with data of adult patients. Multiple logistic regression analysis revealed that tumor location (P < 0.0001) and pattern of enhancement (P = 0.0048) were significantly correlated with molecular subgroups in adult MBs. Ninety-two percent of adult MBs were correctly predicted by using logistic regression model based on the anatomical localization patterns and pattern of enhancement. Exclusively intra-cerebellar growth, localization in the rostral cerebellum, and no brainstem contact were specific to adult SHH-MBs. Group 4-MBs in adult were characterized by minimal/no enhancement compared with other two subgroups. Infant SHH-MBs represented significant different localization patterns compared with SHH tumors in children and adults. We identified that molecular subgroups of adult MBs could be well predicted by tumor localization patterns and enhancement pattern. Our study also provided important evidence that MB subgroups in adult possibly derived from different cellular origins.