EUVIMEDEUVIMED entdecken
Crossref

EECFS: Efficient Ensemble Causal Feature Selection for High-Dimensional Molecular Data

Chen Ye iD, Ziheng Hong, Na Cheng, Junfeng Xia iD, Di Zhang

Journal of Chemical Information and Modeling · 10.08.2026 · 66 (15) · 9607-9620

DOI: 10.1021/acs.jcim.6c00965 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 16.06.2026. Verfasst von Chen Ye und 4 weiteren Autor:innen. Beteiligte Einrichtung: Information Materials and Intelligent Sensing Laboratory of Anhui Province and School of Life Sciences and Medical Engineering, Anhui University, Hef…. Hauptthemen laut MEDLINE: Algorithms, Computational Biology. Die Arbeit nennt 74 Literaturangaben. Gefördert von: National Natural Science Foundation of China (NSFC).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

High-dimensional feature spaces combined with limited sample sizes present substantial challenges for biological prediction tasks. Traditional feature selection methods rely on statistical associations between features and labels, whereas causal feature selection identifies features causally related to the target, improving the interpretability and robustness. Among them, constraint-based methods identify the Markov blanket of the target variable through the conditional independence tests. However, existing constraint-based ensemble strategies are computationally demanding, particularly during the spouse-discovery stage. To address this limitation, we propose EECFS, a novel ensemble causal feature selection algorithm that reduces the computational cost through an efficient spouse discovery strategy. Extensive evaluations on 16 Bayesian network datasets and 17 real-world datasets demonstrate that EECFS achieves improved efficiency while maintaining competitive or superior predictive performance compared with 11 representative methods. Furthermore, we extend causal feature selection to the task of synonymous variant effect prediction and developed CFDPSM. From an initial pool of 23 866 features spanning DNA, RNA, and protein molecular levels, CFDPSM identifies a compact set of 30 Markov blanket features. The experimental results show that it outperforms 13 existing variant effect prediction methods while providing enhanced interpretability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsComputational BiologyBayes TheoremMarkov ChainsProteins

Substanzen

Proteins

Autor:innen und Institutionen

  • Information Materials and Intelligent Sensing Laboratory of Anhui Province and School of Life Sciences and Medical Engineering, Anhui University, Hefei, Anhui230601, China.
  • School of Biomedical Engineering, Anhui Medical University, Hefei, Anhui230032, China.
  • College of Information Engineering, Shaoguan University, Shaoguan, Guangdong512005, China.

ORCID-Profile: Chen Ye, Junfeng Xia

Förderung

  • National Natural Science Foundation of China (NSFC)

Zitieren

APA

Ye, C., Hong, Z., Cheng, N., Xia, J., & Zhang, D. (2026). EECFS: Efficient Ensemble Causal Feature Selection for High-Dimensional Molecular Data. Journal of Chemical Information and Modeling, 66(15), 9607-9620. https://doi.org/10.1021/acs.jcim.6c00965

Vancouver

Ye C, Hong Z, Cheng N, Xia J, Zhang D. EECFS: Efficient Ensemble Causal Feature Selection for High-Dimensional Molecular Data. Journal of Chemical Information and Modeling. 2026;66(15):9607-9620. doi:10.1021/acs.jcim.6c00965

BibTeX
@article{Ye2026,
  author = {Ye, Chen and Hong, Ziheng and Cheng, Na and Xia, Junfeng and Zhang, Di},
  title = {EECFS: Efficient Ensemble Causal Feature Selection for High-Dimensional Molecular Data},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  volume = {66},
  number = {15},
  pages = {9607--9620},
  doi = {10.1021/acs.jcim.6c00965}
}
Kostenlos starten →