A novel methylation signature predicts radiotherapy sensitivity in glioma

Feng, Yuemei; Li, Guanzhang; Shi, Zhongcheng; Yan, Xu; Wang, Zhiliang; Jiang, Haiyan; Chen, Ye; Li, Renpeng; Zhai, You; Chang, Yuanhao; Zhang, Wei; Yuan, Fang

doi:10.1038/s41598-020-77259-9

Cited by 6 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a consequence, the impact of radiotherapy on gene signatures has been extensively studied. Transcriptomic, methylation, mutational and mesenchymal signatures following radiotherapy all have been reported to correlate with patient's prognosis in glioblastoma (GBM) (168)(169)(170)(171)(172). For example, gene signatures focusing on mesenchymal traits, which can be induced by radiation, distinctively correlate with worse prognosis (173).…”

Section: Discussionmentioning

confidence: 99%

Radioresistance of Human Cancers: Clinical Implications of Genetic Expression Signatures

2021

View full text Add to dashboard Cite

Although radiotherapy is given to more than 50% of cancer patients, little progress has been made in identifying optimal radiotherapy - drug combinations to improve treatment efficacy. Using molecular data from The Cancer Genome Atlas (TCGA), we extracted a total of 1016 cancer patients that received radiotherapy. The patients were diagnosed with head-and-neck (HNSC - 294 patients), cervical (CESC - 166 patients) and breast (BRCA - 549 patients) cancer. We analyzed mRNA expression patterns of 50 hallmark gene sets of the MSigDB collection, which we divided in eight categories based on a shared biological or functional process. Tumor samples were split into upregulated, neutral or downregulated mRNA expression for all gene sets using a gene set analysis (GSEA) pre-ranked analysis and assessed for their clinical relevance. We found a prognostic association between three of the eight gene set categories (Radiobiological, Metabolism and Proliferation) and overall survival in all three cancer types. Furthermore, multiple single associations were revealed in the other categories considered. To the best of our knowledge, our study is the first report suggesting clinical relevance of molecular characterization based on hallmark gene sets to refine radiation strategies.

show abstract

Section: Discussionmentioning

confidence: 99%

Radioresistance of Human Cancers: Clinical Implications of Genetic Expression Signatures

2021

View full text Add to dashboard Cite

show abstract

“…The methylome of tumors has been integrated in most heterogeneity papers using high-throughput methods, especially for temporal heterogeneity studies. DNA methylation has also advanced the knowledge in intra-tumor spatial heterogeneity, especially in the characterization of CSCs and inflammatory cells [78][79][80][81]. Notably, differences in DNA methylation between tumor areas as close as 5 mm apart were observed, both in IDH mutant and IDH wild-type gliomas [64].…”

Section: Dna Methylation Analysesmentioning

confidence: 99%

“…Recently, Feng et al proposed a signature based on the methylome profile composed by five candidate probes closely associated with the DNA damage repair function as an independent predictive marker for radiation therapy in gliomas [79]. Similarly, Wang et al proposed a methylation-based classification of GBMs to predict response to immunotherapy [81].…”

Section: Dna Methylation Analysesmentioning

confidence: 99%

Tumor Heterogeneity in Glioblastomas: From Light Microscopy to Molecular Pathology

Becker

Sells

Haque

et al. 2021

Cancers

102

View full text Add to dashboard Cite

One of the main reasons for the aggressive behavior of glioblastoma (GBM) is its intrinsic intra-tumor heterogeneity, characterized by the presence of clonal and subclonal differentiated tumor cell populations, glioma stem cells, and components of the tumor microenvironment, which affect multiple hallmark cellular functions in cancer. “Tumor Heterogeneity” usually encompasses both inter-tumor heterogeneity (population-level differences); and intra-tumor heterogeneity (differences within individual tumors). Tumor heterogeneity may be assessed in a single time point (spatial heterogeneity) or along the clinical evolution of GBM (longitudinal heterogeneity). Molecular methods may detect clonal and subclonal alterations to describe tumor evolution, even when samples from multiple areas are collected in the same time point (spatial-temporal heterogeneity). In GBM, although the inter-tumor mutational landscape is relatively homogeneous, intra-tumor heterogeneity is a striking feature of this tumor. In this review, we will address briefly the inter-tumor heterogeneity of the CNS tumors that yielded the current glioma classification. Next, we will take a deeper dive in the intra-tumor heterogeneity of GBMs, which directly affects prognosis and response to treatment. Our approach aims to follow technological developments, allowing for characterization of intra-tumor heterogeneity, beginning with differences on histomorphology of GBM and ending with molecular alterations observed at single-cell level.

show abstract

“…A large number of regularization regression models (e.g. LASSO regression) have been demonstrated to be effective [ 9 – 14 ]. Other gene-based machine-learning algorithms such as random forest, partial least squares, and SVM could also successfully predict radiosensitivity and radiocurability [ 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

Prediction of radiosensitivity and radiocurability using a novel supervised artificial neural network

Zeng

Luo

et al. 2022

BMC Cancer

View full text Add to dashboard Cite

Background Radiotherapy has been widely used to treat various cancers, but its efficacy depends on the individual involved. Traditional gene-based machine-learning models have been widely used to predict radiosensitivity. However, there is still a lack of emerging powerful models, artificial neural networks (ANN), in the practice of gene-based radiosensitivity prediction. In addition, ANN may overfit and learn biologically irrelevant features. Methods We developed a novel ANN with Selective Connection based on Gene Patterns (namely ANN-SCGP) to predict radiosensitivity and radiocurability. We creatively used gene patterns (gene similarity or gene interaction information) to control the "on–off" of the first layer of weights, enabling the low-dimensional features to learn the gene pattern information. ANN-SCGP was trained and tested in 82 cell lines and 1,101 patients from the 11 pan-cancer cohorts. Results For survival fraction at 2 Gy, the root mean squared errors (RMSE) of prediction in ANN-SCGP was the smallest among all algorithms (mean RMSE: 0.1587–0.1654). For radiocurability, ANN-SCGP achieved the first and second largest C-index in the 12/20 and 4/20 tests, respectively. The low dimensional output of ANN-SCGP reproduced the patterns of gene similarity. Moreover, the pan-cancer analysis indicated that immune signals and DNA damage responses were associated with radiocurability. Conclusions As a model including gene pattern information, ANN-SCGP had superior prediction abilities than traditional models. Our work provided novel insights into radiosensitivity and radiocurability.

show abstract

A novel methylation signature predicts radiotherapy sensitivity in glioma

Cited by 6 publications

References 30 publications

Radioresistance of Human Cancers: Clinical Implications of Genetic Expression Signatures

Radioresistance of Human Cancers: Clinical Implications of Genetic Expression Signatures

Tumor Heterogeneity in Glioblastomas: From Light Microscopy to Molecular Pathology

Prediction of radiosensitivity and radiocurability using a novel supervised artificial neural network

Contact Info

Product

Resources

About