Cancer molecular subtyping using limited multi-omics data with missingness

Diagnosing cancer subtypes is a prerequisite for precise treatment. Existing multi-omics data fusion-based diagnostic solutions build on the requisite of sufficient samples with complete multi-omics data, which is challenging to obtain in clinical applications. To address the bottleneck of collectin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:PLoS computational biology Jg. 20; H. 12; S. e1012710
Hauptverfasser: Bu, Yongqi, Liang, Jiaxuan, Li, Zhen, Wang, Jianbo, Wang, Jun, Yu, Guoxian
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States Public Library of Science 26.12.2024
Public Library of Science (PLoS)
Schlagworte:
Algorithms
Biology and Life Sciences
Biomarkers, Tumor - genetics
Biomarkers, Tumor - metabolism
Cancer
Computational biology
Computational Biology - methods
Diagnosis
Genomics - methods
Humans
Medicine and Health Sciences
Multiomics
Neoplasms - classification
Neoplasms - genetics
Prognosis
China
ISSN:1553-7358, 1553-734X, 1553-7358
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Diagnosing cancer subtypes is a prerequisite for precise treatment. Existing multi-omics data fusion-based diagnostic solutions build on the requisite of sufficient samples with complete multi-omics data, which is challenging to obtain in clinical applications. To address the bottleneck of collecting sufficient samples with complete data in clinical applications, we proposed a flexible integrative model (CancerSD) to diagnose cancer subtype using limited samples with incomplete multi-omics data. CancerSD designs contrastive learning tasks and masking-and-reconstruction tasks to reliably impute missing omics, and fuses available omics data with the imputed ones to accurately diagnose cancer subtypes. To address the issue of limited clinical samples, it introduces a category-level contrastive loss to extend the meta-learning framework, effectively transferring knowledge from external datasets to pretrain the diagnostic model. Experiments on benchmark datasets show that CancerSD not only gives accurate diagnosis, but also maintains a high authenticity and good interpretability. In addition, CancerSD identifies important molecular characteristics associated with cancer subtypes, and it defines the Integrated CancerSD Score that can serve as an independent predictive factor for patient prognosis.
Bibliographie:new_version
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
The authors have declared that no competing interests exist.
ISSN:1553-7358
1553-734X
1553-7358
DOI:10.1371/journal.pcbi.1012710