Development of a Novel Prognostic Model of Glioblastoma Based on m6A-Associated Immune Genes and Identification of a New Biomarker

Development of a web-based tool for estimating individualized survival curves in glioblastoma using clinical, mRNA, and tumor microenvironment features with fusion techniques

OBJECTIVE

Glioblastoma (GBM), one of the most common brain tumors, is known for its low survival rates and poor treatment responses. This study aims to create a robust predictive model that integrates multiple feature types, including clinical data, RNA expression, and tumor microenvironment data, using fusion techniques to enhance model performance.

METHODS

We obtained data from the SEER database to assess the impact of nine demographic and clinical features on the survival of 58,495 GBM patients and built predictive machine learning models. Additionally, mRNA expression data from 600 GBM patients from TCGA, CGGA, and GEO were analyzed. We used Cox regression and LASSO to create a gene signature, which was compared against 13 published signatures for accuracy. Twenty-one machine learning models were applied to predict survival at multiple time points. Finally, we integrated multiple feature types using fusion techniques and developed a Shiny app to provide survival predictions for GBM patients.

RESULTS

Using the SEER database, we constructed machine learning models based on nine clinical variables: age, gender, marital status, race, tumor site, laterality, surgery, chemotherapy, and radiation therapy. The best-performing model achieved AUC values of 0.775, 0.728, 0.692, and 0.683 for predicting survival at 6, 12, 18, and 24 months in the testing cohort. In the merged TCGA, CGGA, and GEO cohorts, we identified 11 genes to develop predictive models. These 11 genes outperformed 13 other published gene signatures in predicting the prognosis of GBM. When incorporating mRNA features, tumor microenvironment features, and clinical variables into the fusion models, the AUC values for predicting survival at 6, 12, 18, and 24 months were 0.641, 0.624, 0.655, and 0.637, respectively. A user-friendly tool for predicting the survival curve of individual GBM patients is available at https://zzubioinfo.shinyapps.io/mlGBM/ .

CONCLUSIONS

Our study provides a web-based tool that includes two modules: one for predicting survival curves using only clinical variables, and another that integrates multiple feature types for more comprehensive predictions.

The prognostic model of low-grade glioma based on m6A-associated immune genes and functional study of FBXO4 in the tumor microenvironment

Background

m6A plays a dual role in regulating the expression of oncogenes and tumor suppressor genes, and is crucial in tumorigenesis and progression. The immune system is closely involved in tumorigenesis and development, playing a key role in tumor therapy and resistance. However, research on m6A-related immune markers in low-grade gliomas is still limited and requires further investigation.

Methods

All data was obtained from the Chinese Glioma Genome Atlas database and The Cancer Genome Atlas. The construction of the prognostic model and the online application of the dynamic nomogram relied on univariate Cox analysis, LASSO regression, and multivariate Cox analysis. Two different clustering analyses were performed on all samples, resulting in high, medium, and low expression groups of m6A regulatory and immune genes, followed by an analysis of the correlations between these scores. Finally, the biological role of FBXO4 in glioma cells was determined through quantitative reverse transcription polymerase chain reaction, cell proliferation assays, and cell migration experiments.

Results

The prognostic model for low-grade glioma demonstrated strong performance, with an AUC over 0.9 in the training group. In the internal validation group, AUC values ranged from 0.831 to 0.894, while in the external validation group, the AUC ranged from 0.623 to 0.813. Additionally, the online application of the dynamic nomogram allowed for relatively accurate predictions of LGG patients' survival time. Further analysis revealed that the high-expression groups of m6A regulatory genes and m6A-related immune genes exhibited higher levels of immune cells and stromal cells, lower tumor purity, and poorer survival rates. GSEA enrichment analysis suggested that these findings might be related to the activation of multiple signaling pathways. This may explain the lower survival rates observed in this group. Furthermore, the m6A score was significantly associated with moderate to high expression of immune genes and high expression of m6A regulatory genes, and it showed a positive correlation with most immune cell types. Finally, in vitro experiments confirmed that silencing FBXO4 significantly inhibited proliferation and migration in glioma cell lines, further supporting the biological relevance of our model.

Conclusion

Based on multi-dimensional clustering analysis and experimental validation, the prognostic model developed in this study can effectively assess the prognosis of LGG patients and their relationship with the immune microenvironment. Furthermore, the correlation analysis between m6A scores and the tumor microenvironment provides a foundation for further exploration of the disease's pathophysiology. Additionally, we suggest that FBXO4 may serve as an important biomarker for the diagnosis and prognosis of LGG.

Thrombosis risk prediction in lymphoma patients: A multi-institutional, retrospective model development and validation study

Venous thromboembolism (VTE) poses a significant risk to cancer patients receiving systemic therapy. The generalizability of pan-cancer models to lymphomas is limited. Currently, there are no reliable risk prediction models for thrombosis in patients with lymphoma. Our objective was to create a risk assessment model (RAM) specifically for lymphomas. We performed a retrospective cohort study to develop Fine and Gray sub-distribution hazard model for VTE and pulmonary embolism (PE)/ lower extremity deep vein thrombosis (LE-DVT) respectively in adult lymphoma patients from the Veterans Affairs national healthcare system (VA). External validations were performed at the Harris Health System (HHS) and the MD Anderson Cancer Center (MDACC). Time-dependent c-statistic and calibration curves were used to assess discrimination and fit. There were 10,313 (VA), 854 (HHS), and 1858 (MDACC) patients in the derivation and validation cohorts with diverse baseline. At 6 months, the VTE incidence was 5.8% (VA), 8.2% (HHS), and 8.8% (MDACC), respectively. The corresponding estimates for PE/LE-DVT were 3.9% (VA), 4.5% (HHS), and 3.7% (MDACC), respectively. The variables in the final RAM included lymphoma histology, body mass index, therapy type, recent hospitalization, history of VTE, history of paralysis/immobilization, and time to treatment initiation. The RAM had c-statistics of 0.68 in the derivation and 0.69 and 0.72 in the two external validation cohorts. The two models achieved a clear differentiation in risk stratification in each cohort. Our findings suggest that easy-to-implement, clinical-based model could be used to predict personalized VTE risk for lymphoma patients.

Systematic integration of m6A regulators and autophagy-related genes in combination with long non-coding RNAs predicts survival in glioblastoma multiforme

Glioblastoma multiforme (GBM) is probably the only tumor in which a unique epigenetic alteration, namely methylation of the MGMT gene, possesses direct clinical relevance. Now with the emergence of aberrant N6 methyladenosine (m6A) modifications (the most common epigenetic modification of mRNA, closely linked to the autophagy process) in cancer, the epi-transcriptomic landscape of GBM pathobiology has been expanded. Considering this, herein, we systematically analyzed m6A regulators, assessed their correlation with autophagy-related genes (ATG), and established a long non-coding RNAs (lncRNA)-dependent prognostic signature (m6A-autophagy-lncRNAs) for GBM. Our analysis identified a novel signature of five long non-coding RNAs (lncRNAs: ITGA6-AS1, AC124248.1, NFYC-AS1, AC025171.1, and AC005229.3) associated with survival of GBM patients, and four among them clearly showed cancer-associated potential. We further validated and confirmed the altered expression of two lncRNAs (AC124248.1, AC005229.3) in GBM associated clinical samples using RT-PCR. Concerning the prognostic ability, the obtained signature determined high-/low-risk groups in GBM patients and showed sensitivity to anticancer drugs. Collectively, the m6A-autophagy-lncRNAs signature presented in the study is clinically relevant and is the first attempt to systematically predict the potential interaction between the three key determinants (m6A, autophagy, lncRNA) in cancer, particularly in GBM.

Deep learning classification of uveal melanoma based on histopathological images and identification of a novel indicator for prognosis of patients

BACKGROUND

Deep learning has been extensively used in digital histopathology. The purpose of this study was to test deep learning (DL) algorithms for predicting the vital status of whole-slide image (WSI) of uveal melanoma (UM).

METHODS

We developed a deep learning model (Google-net) to predict the vital status of UM patients from histopathological images in TCGA-UVM cohort and validated it in an internal cohort. The histopathological DL features extracted from the model and then were applied to classify UM patients into two subtypes. The differences between two subtypes in clinical outcomes, tumor mutation, and microenvironment, and probability of drug therapeutic response were investigated further.

RESULTS

We observed that the developed DL model can achieve a high accuracy of >  = 90% for patches and WSIs prediction. Using 14 histopathological DL features, we successfully classified UM patients into Cluster1 and Cluster2 subtypes. Compared to Cluster2, patients in the Cluster1 subtype have a poor survival outcome, increased expression levels of immune-checkpoint genes, higher immune-infiltration of CD8 + T cell and CD4 + T cells, and more sensitivity to anti-PD-1 therapy. Besides, we established and verified prognostic histopathological DL-signature and gene-signature which outperformed the traditional clinical features. Finally, a well-performed nomogram combining the DL-signature and gene-signature was constructed to predict the mortality of UM patients.

CONCLUSIONS

Our findings suggest that DL model can accurately predict vital status in UM patents just using histopathological images. We found out two subgroups based on histopathological DL features, which may in favor of immunotherapy and chemotherapy. Finally, a well-performing nomogram that combines DL-signature and gene-signature was constructed to give a more straightforward and reliable prognosis for UM patients in treatment and management.