A three-stage eccDNA based molecular profiling significantly improves the identification, prognosis assessment and recurrence prediction accuracy in patients with glioma

Li, Zesheng; Wang, Bo; Liang, Hao; Li, Ying; Zhang, Zhenyu; Han, Lei

doi:10.1016/j.canlet.2023.216369

Cited by 5 publications

(3 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accurately identifying molecular subtypes is pivotal to better understanding the biological characteristics of IDH wild-type GBM, thereby developing more personalized treatment administration. Our previous study demonstrated that eccDNA plays an important role in predicting the grade and prognosis of glioma patients and the recurrence of GBM ( Li et al, 2023 ). Here, we would like to further explore the potential of eccDNA in the identification of IDH wild-type GBM molecular subtypes.…”

Section: Discussionmentioning

confidence: 99%

ecGBMsub: an integrative stacking ensemble model framework based on eccDNA molecular profiling for improving IDH wild-type glioblastoma molecular subtype classification

Li,

Wei,

Zhang

et al. 2024

Front. Pharmacol.

Self Cite

View full text Add to dashboard Cite

IDH wild-type glioblastoma (GBM) intrinsic subtypes have been linked to different molecular landscapes and outcomes. Accurate prediction of molecular subtypes of GBM is very important to guide clinical diagnosis and treatment. Leveraging machine learning technology to improve the subtype classification was considered a robust strategy. Several single machine learning models have been developed to predict survival or stratify patients. An ensemble learning strategy combines several basic learners to boost model performance. However, it still lacked a robust stacking ensemble learning model with high accuracy in clinical practice. Here, we developed a novel integrative stacking ensemble model framework (ecGBMsub) for improving IDH wild-type GBM molecular subtype classification. In the framework, nine single models with the best hyperparameters were fitted based on extrachromosomal circular DNA (eccDNA) molecular profiling. Then, the top five optimal single models were selected as base models. By randomly combining the five optimal base models, 26 different combinations were finally generated. Nine different meta-models with the best hyperparameters were fitted based on the prediction results of 26 different combinations, resulting in 234 different stacked ensemble models. All models in ecGBMsub were comprehensively evaluated and compared. Finally, the stacking ensemble model named “XGBoost.Enet-stacking-Enet” was chosen as the optimal model in the ecGBMsub framework. A user-friendly web tool was developed to facilitate accessibility to the XGBoost.Enet-stacking-Enet models (https://lizesheng20190820.shinyapps.io/ecGBMsub/).

show abstract

Section: Discussionmentioning

confidence: 99%

ecGBMsub: an integrative stacking ensemble model framework based on eccDNA molecular profiling for improving IDH wild-type glioblastoma molecular subtype classification

Li,

Wei,

Zhang

et al. 2024

Front. Pharmacol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Furthermore, novel disease models have emerged that combine eccDNA signatures with clinical data to assess the correlation of eccDNA expression with disease and predict clinical outcomes. For instance, Li et al ( Li et al, 2023 ) established a three-stage model for gliomas based on eccDNA-carrying genes, employing hundreds of machine learning algorithms and stacked ensemble modeling for clinical diagnosis, prognostic prediction, and recurrence risk prediction. Despite the advancements in machine learning-based tools, there remains a necessity for comprehensive training datasets to refine the model and enhance its adaptability and robustness in diverse scenarios.…”

Section: Computational Identification and Prediction For Eccdnamentioning

confidence: 99%

“…Furthermore, results such as eccDNA containing oncogenes ( Kalavska et al, 2018 ; Gu et al, 2020 ; Li et al, 2022 ; Li et al, 2022 ) and being associated with drug resistance ( Alt et al, 1978 ; Kaufman et al, 1979 ; Haber and Schimke, 1981 ; Kaufman et al, 1981 ; Shoshani et al, 2021 ) have highlighted the possible use of eccDNA in tumor therapy and monitoring. Freshly, several studies have suggested the use of eccDNA for the diagnosis, treatment, and monitoring of gliomas ( Li et al, 2023 ), gynecologic tumors ( Wu et al, 2024 ), and genitourinary disorders ( Lv et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

Characterization, biogenesis model, and current bioinformatics of human extrachromosomal circular DNA

Zhou,

Tang,

et al. 2024

Front. Genet.

View full text Add to dashboard Cite

Human extrachromosomal circular DNA, or eccDNA, has been the topic of extensive investigation in the last decade due to its prominent regulatory role in the development of disorders including cancer. With the rapid advancement of experimental, sequencing and computational technology, millions of eccDNA records are now accessible. Unfortunately, the literature and databases only provide snippets of this information, preventing us from fully understanding eccDNAs. Researchers frequently struggle with the process of selecting algorithms and tools to examine eccDNAs of interest. To explain the underlying formation mechanisms of the five basic classes of eccDNAs, we categorized their characteristics and functions and summarized eight biogenesis theories. Most significantly, we created a clear procedure to help in the selection of suitable techniques and tools and thoroughly examined the most recent experimental and bioinformatics methodologies and data resources for identifying, measuring and analyzing eccDNA sequences. In conclusion, we highlighted the current obstacles and prospective paths for eccDNA research, specifically discussing their probable uses in molecular diagnostics and clinical prediction, with an emphasis on the potential contribution of novel computational strategies.

show abstract

Personalized prediction of postoperative complication and survival among Colorectal Liver Metastases Patients Receiving Simultaneous Resection using machine learning approaches: A multi-center study

Chen,

Deng

et al. 2024

Cancer Letters

View full text Add to dashboard Cite

A three-stage eccDNA based molecular profiling significantly improves the identification, prognosis assessment and recurrence prediction accuracy in patients with glioma

Cited by 5 publications

References 77 publications

ecGBMsub: an integrative stacking ensemble model framework based on eccDNA molecular profiling for improving IDH wild-type glioblastoma molecular subtype classification

ecGBMsub: an integrative stacking ensemble model framework based on eccDNA molecular profiling for improving IDH wild-type glioblastoma molecular subtype classification

Characterization, biogenesis model, and current bioinformatics of human extrachromosomal circular DNA

Personalized prediction of postoperative complication and survival among Colorectal Liver Metastases Patients Receiving Simultaneous Resection using machine learning approaches: A multi-center study

Contact Info

Product

Resources

About