EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Identifying cancer prognosis genes through causal learning

Siwei Wu iD, Chaoyi Yin, Yuezhu Wang iD, Huiyan Sun

Briefings in Bioinformatics · 2024

DOI: 10.1093/bib/bbae721 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2024. Verfasst von Siwei Wu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence, Jilin University, 3003 Qianjin Street, 130012 Changchun, China. Hauptthemen laut MEDLINE: Neoplasms, Biomarkers, Tumor. Die Arbeit nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jilin Province, Jilin University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate identification of causal genes for cancer prognosis is critical for estimating disease progression and guiding treatment interventions. In this study, we propose CPCG (Cancer Prognosis’s Causal Gene), a two-stage framework identifying gene sets causally associated with patient prognosis across diverse cancer types using transcriptomic data. Initially, an ensemble approach models gene expression’s impact on survival with parametric and semiparametric hazard models. Subsequently, an iterative conditional independence test combined with graph pruning is utilized to infer the causal skeleton, thereby pinpointing prognosis-related genes. Experiments on transcriptomic data from 18 cancer types sourced from The Cancer Genome Atlas Project demonstrate CPCG’s effectiveness in predicting prognosis under four evaluation metrics. Validations on 24 additional datasets covering 12 cancer types from the Gene Expression Omnibus and the Chinese Glioma Genome Atlas Project further demonstrate CPCG’s robustness and generalizability. CPCG identifies a concise but reliable set of genes, obviating the need for gene combination enumeration for survival time estimation. These genes are also proved closely linked to crucial biological processes in cancer. Moreover, CPCG constructs a stable causal skeleton and exhibits insensitivity to the order of data shuffling. Overall, CPCG is a powerful tool for extracting cancer prognostic biomarkers, offering interpretability, generalizability, and robustness. CPCG holds promise for facilitating targeted interventions in clinical treatment strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NeoplasmsBiomarkers, TumorHumansPrognosisGene Expression Regulation, NeoplasticGene Expression ProfilingTranscriptomeComputational BiologyDatabases, Genetic

Stichwörter der Autor:innen

cancer prognosiscausal structure learningcompact gene setgeneralizable and robust predictionstranscriptomic data

Substanzen

Biomarkers, Tumor

Autor:innen und Institutionen

  • School of Artificial Intelligence, Jilin University, 3003 Qianjin Street, 130012 Changchun, China.
  • International Center of Future Science, Jilin University, 3003 Qianjin Street, 130012 Changchun, China.
  • Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, Jilin University, 3003 Qianjin Street, 130012 Changchun, China.

ORCID-Profile: Siwei Wu, Yuezhu Wang

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jilin Province
  • Jilin University
  • Graduate Innovation Fund of Jilin University
  • 'Medical + X' Cross Innovation Team 'Unveiling the List and Taking Command' Construction Project of Bethune Medical College of Jilin University
  • ‘Medical + X’ Cross Innovation Team ‘Unveiling the List and Taking Command’ Construction Project of Bethune Medical College of Jilin University

Zitieren

APA

Wu, S., Yin, C., Wang, Y., & Sun, H. (2024). Identifying cancer prognosis genes through causal learning. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae721

Vancouver

Wu S, Yin C, Wang Y, Sun H. Identifying cancer prognosis genes through causal learning. Briefings in Bioinformatics. 2024. doi:10.1093/bib/bbae721

BibTeX
@article{Wu2024,
  author = {Wu, Siwei and Yin, Chaoyi and Wang, Yuezhu and Sun, Huiyan},
  title = {Identifying cancer prognosis genes through causal learning},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  doi = {10.1093/bib/bbae721}
}
Kostenlos starten →