TY - JOUR
T1 - SSCI
T2 - Self-Supervised Deep Learning Improves Network Structure for Cancer Driver Gene Identification
AU - Xu, Jialuo
AU - Hao, Jun
AU - Liao, Xingyu
AU - Shang, Xuequn
AU - Li, Xingyi
N1 - Publisher Copyright:
© 2024 by the authors.
PY - 2024/10
Y1 - 2024/10
N2 - The pathogenesis of cancer is complex, involving abnormalities in some genes in organisms. Accurately identifying cancer genes is crucial for the early detection of cancer and personalized treatment, among other applications. Recent studies have used graph deep learning methods to identify cancer driver genes based on biological networks. However, incompleteness and the noise of the networks will weaken the performance of models. To address this, we propose a cancer driver gene identification method based on self-supervision for graph convolutional networks, which can efficiently enhance the structure of the network and further improve predictive accuracy. The reliability of SSCI is verified by the area under the receiver operating characteristic curves (AUROC), the area under the precision-recall curves (AUPRC), and the F1 score, with respective values of 0.966, 0.964, and 0.913. The results show that our method can identify cancer driver genes with strong discriminative power and biological interpretability.
AB - The pathogenesis of cancer is complex, involving abnormalities in some genes in organisms. Accurately identifying cancer genes is crucial for the early detection of cancer and personalized treatment, among other applications. Recent studies have used graph deep learning methods to identify cancer driver genes based on biological networks. However, incompleteness and the noise of the networks will weaken the performance of models. To address this, we propose a cancer driver gene identification method based on self-supervision for graph convolutional networks, which can efficiently enhance the structure of the network and further improve predictive accuracy. The reliability of SSCI is verified by the area under the receiver operating characteristic curves (AUROC), the area under the precision-recall curves (AUPRC), and the F1 score, with respective values of 0.966, 0.964, and 0.913. The results show that our method can identify cancer driver genes with strong discriminative power and biological interpretability.
KW - cancer driver genes
KW - graph learning
KW - network structure enhancement
KW - self-supervised deep learning
UR - http://www.scopus.com/inward/record.url?scp=85206436482&partnerID=8YFLogxK
U2 - 10.3390/ijms251910351
DO - 10.3390/ijms251910351
M3 - 文章
C2 - 39408682
AN - SCOPUS:85206436482
SN - 1661-6596
VL - 25
JO - International Journal of Molecular Sciences
JF - International Journal of Molecular Sciences
IS - 19
M1 - 10351
ER -