Construction of a Risk Model to Predict the Prognosis and Immunotherapy of Low-Grade Glioma Ground on 7 Ferroptosis-Related Genes

Prognosis Individualized: Survival predictions for WHO grade II and III gliomas with a machine learning-based web application

WHO grade II and III gliomas demonstrate diverse biological behaviors resulting in variable survival outcomes. In the context of glioma prognosis, machine learning (ML) approaches could facilitate the navigation through the maze of factors influencing survival, aiding clinicians in generating more precise and personalized survival predictions. Here we report the utilization of ML models in predicting survival at 12, 24, 36, and 60 months following grade II and III glioma diagnosis. From the National Cancer Database, we analyze 10,001 WHO grade II and 11,456 grade III cranial gliomas. Using the area under the receiver operating characteristic (AUROC) values, we deploy the top-performing models in a web application for individualized predictions. SHapley Additive exPlanations (SHAP) enhance the interpretability of the models. Top-performing predictive models are the ones built with LightGBM and Random Forest algorithms. For grade II gliomas, the models yield AUROC values ranging from 0.813 to 0.896 for predicting mortality across different timeframes, and for grade III gliomas, the models yield AUROCs ranging from 0.855 to 0.878. ML models provide individualized survival forecasts for grade II and III glioma patients across multiple clinically relevant time points. The user-friendly web application represents a pioneering digital tool to potentially integrate predictive analytics into neuro-oncology clinical practice, to empower prognostication and personalize clinical decision-making.

Systematic discrimination of the repetitive genome in proximity of ferroptosis genes and a novel prognostic signature correlating with the oncogenic lncRNA CRNDE in multiple myeloma

Emerging insights into iron-dependent form of regulated cell death ferroptosis in cancer have opened a perspective for its use in cancer therapy. Of interest, a systematic profiling of ferroptosis gene signatures as prognostic factors has gained special attention in several cancers. Herein, we sought to investigate the presence of repetitive genomes in the vicinity of ferroptosis genes that may influence their expression and to establish a prognostic gene signature associated with multiple myeloma (MM). Our analysis showed that genes associated with ferroptosis were enriched with the repetitive genome in their vicinity, with a strong predominance of the SINE family, followed by LINE, of which the most significant discriminant values were SINE/Alu and LINE/L1, respectively. In addition, we examined in detail the performance of these genes as a cancer risk prediction model and specified fourteen ferroptosis-related gene signatures, which identified MM high-risk patients with lower immune/stromal scores with higher tumor purity in their immune microenvironment. Of interest, we also found that lncRNA CRNDE correlated with a risk score and was highly associated with the majority of genes comprising the signature. Taken together, we propose to investigate the molecular impact of the repetitive genome we have highlighted on the local transcriptome of ferroptosis genes in cancer. Furthermore, we revealed a genomic signature/biomarker related to ferroptosis that can be used to predict the risk of survival in MM patients.

Construction of a prognostic risk model based on apoptosis-related genes to assess tumor immune microenvironment and predict prognosis in hepatocellular carcinoma

BACKGROUND

Hepatocellular carcinoma (HCC) is a serious malignant disease with high incidence, high mortality and poor prognosis. This study aimed to establish a novel signature based on apoptosis-related genes (ARGs) to predict the prognosis of HCC.

METHODS

Expression data of HCC from TCGA database and the list of 160 ARGs from MSigDB were downloaded. The genes included in apoptosis-related signature were selected by univariate Cox regression analysis and lasso Cox regression analysis. Subsequently, a prognostic risk model for scoring patients was developed, and then separates patients into two groups. Kaplan-Meier and receiver operating characteristic analysis were performed to evaluate the prognostic value of the model in TCGA, GEO and ICGC databases. The characteristics of immune cell infiltration between two groups of HCC were investigated. Finally, a nomogram was plotted to visualize the prognosis prediction.

RESULTS

Nine genes (CDC25B, DAP3, ETF1, GSR, LGALS3, MGMT, PPP2R5B, SQSTM1 and VDAC2) were included in the prognostic risk model. Survival was lower in the high-risk group. Surprisingly, the high-risk group was significantly more in immune cell infiltration and with higher immunoscore and stromalscore than in the low-risk group. In addition, the risk score was an independent prognostic factor for HCC.

CONCLUSIONS

Prognostic signature comprising nine ARGs could be used as a potential prognostic factor for HCC. It also provides an important idea for further understanding the immunotherapy of HCC.