• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

DSCMF：基于双稀疏协作矩阵分解的长链非编码RNA-疾病关联预测

DSCMF: prediction of LncRNA-disease associations based on dual sparse collaborative matrix factorization.

作者信息

Liu Jin-Xing, Gao Ming-Ming, Cui Zhen, Gao Ying-Lian, Li Feng

机构信息

School of Computer Science, Qufu Normal University, Rizhao, China.

Qufu Normal University Library, Qufu Normal University, Rizhao, China.

出版信息

BMC Bioinformatics. 2021 May 12;22(Suppl 3):241. doi: 10.1186/s12859-020-03868-w.

DOI:10.1186/s12859-020-03868-w
PMID:33980147
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8114493/
Abstract

BACKGROUND

In the development of science and technology, there are increasing evidences that there are some associations between lncRNAs and human diseases. Therefore, finding these associations between them will have a huge impact on our treatment and prevention of some diseases. However, the process of finding the associations between them is very difficult and requires a lot of time and effort. Therefore, it is particularly important to find some good methods for predicting lncRNA-disease associations (LDAs).

RESULTS

In this paper, we propose a method based on dual sparse collaborative matrix factorization (DSCMF) to predict LDAs. The DSCMF method is improved on the traditional collaborative matrix factorization method. To increase the sparsity, the L-norm is added in our method. At the same time, Gaussian interaction profile kernel is added to our method, which increase the network similarity between lncRNA and disease. Finally, the AUC value obtained by the experiment is used to evaluate the quality of our method, and the AUC value is obtained by the ten-fold cross-validation method.

CONCLUSIONS

The AUC value obtained by the DSCMF method is 0.8523. At the end of the paper, simulation experiment is carried out, and the experimental results of prostate cancer, breast cancer, ovarian cancer and colorectal cancer are analyzed in detail. The DSCMF method is expected to bring some help to lncRNA-disease associations research. The code can access the https://github.com/Ming-0113/DSCMF website.

摘要

背景

在科学技术的发展过程中，越来越多的证据表明长链非编码核糖核酸（lncRNAs）与人类疾病之间存在一些关联。因此，发现它们之间的这些关联将对我们治疗和预防某些疾病产生巨大影响。然而，寻找它们之间关联的过程非常困难，需要大量的时间和精力。因此，找到一些预测长链非编码核糖核酸-疾病关联（LDA）的好方法尤为重要。

结果

在本文中，我们提出了一种基于双稀疏协同矩阵分解（DSCMF）的方法来预测LDA。DSCMF方法是在传统协同矩阵分解方法的基础上改进而来。为了增加稀疏性，我们的方法中添加了L-范数。同时，我们的方法中添加了高斯交互轮廓核，这增加了长链非编码核糖核酸与疾病之间的网络相似性。最后，通过实验获得的AUC值用于评估我们方法的质量，AUC值是通过十折交叉验证法获得的。

结论

DSCMF方法获得的AUC值为0.8523。在论文结尾进行了模拟实验，并详细分析了前列腺癌、乳腺癌、卵巢癌和结直肠癌的实验结果。DSCMF方法有望为长链非编码核糖核酸-疾病关联研究带来一些帮助。代码可访问https://github.com/Ming-0113/DSCMF网站。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/d30196d96c73/12859_2020_3868_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/03a472ea0799/12859_2020_3868_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/d7e744d98d8c/12859_2020_3868_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/264b52818d87/12859_2020_3868_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/8b164c53c4a5/12859_2020_3868_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/0b252a35037b/12859_2020_3868_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/418298b0eed6/12859_2020_3868_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/ee17af5472ce/12859_2020_3868_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/7a1057f16b1c/12859_2020_3868_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/d30196d96c73/12859_2020_3868_Fig9_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/03a472ea0799/12859_2020_3868_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/d7e744d98d8c/12859_2020_3868_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/264b52818d87/12859_2020_3868_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/8b164c53c4a5/12859_2020_3868_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/0b252a35037b/12859_2020_3868_Fig5_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/418298b0eed6/12859_2020_3868_Fig6_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/ee17af5472ce/12859_2020_3868_Fig7_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/7a1057f16b1c/12859_2020_3868_Fig8_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/eaa8/8114493/d30196d96c73/12859_2020_3868_Fig9_HTML.jpg

相似文献

1
DSCMF: prediction of LncRNA-disease associations based on dual sparse collaborative matrix factorization.DSCMF：基于双稀疏协作矩阵分解的长链非编码RNA-疾病关联预测
BMC Bioinformatics. 2021 May 12;22(Suppl 3):241. doi: 10.1186/s12859-020-03868-w.
2
Multi-Label Fusion Collaborative Matrix Factorization for Predicting LncRNA-Disease Associations.多标签融合协同矩阵分解预测 lncRNA-疾病关联。
IEEE J Biomed Health Inform. 2021 Mar;25(3):881-890. doi: 10.1109/JBHI.2020.2988720. Epub 2021 Mar 5.
3
WGRCMF: A Weighted Graph Regularized Collaborative Matrix Factorization Method for Predicting Novel LncRNA-Disease Associations.WGRCMF：一种用于预测新型 lncRNA-疾病关联的加权图正则化协同矩阵分解方法。
IEEE J Biomed Health Inform. 2021 Jan;25(1):257-265. doi: 10.1109/JBHI.2020.2985703. Epub 2021 Jan 5.
4
Prediction of lncRNA and disease associations based on residual graph convolutional networks with attention mechanism.基于带有注意力机制的残差图卷积网络的长链非编码RNA与疾病关联预测
Sci Rep. 2024 Mar 2;14(1):5185. doi: 10.1038/s41598-024-55957-y.
5
gGATLDA: lncRNA-disease association prediction based on graph-level graph attention network.基于图级图注意力网络的 lncRNA-疾病关联预测
BMC Bioinformatics. 2022 Jan 4;23(1):11. doi: 10.1186/s12859-021-04548-z.
6
Dual-network sparse graph regularized matrix factorization for predicting miRNA-disease associations.双网络稀疏图正则化矩阵分解预测 miRNA-疾病关联
Mol Omics. 2019 Apr 1;15(2):130-137. doi: 10.1039/c8mo00244d. Epub 2019 Feb 6.
7
Prediction of lncRNA-disease associations based on inductive matrix completion.基于归纳矩阵补全的 lncRNA-疾病关联预测。
Bioinformatics. 2018 Oct 1;34(19):3357-3364. doi: 10.1093/bioinformatics/bty327.
8
DNILMF-LDA: Prediction of lncRNA-Disease Associations by Dual-Network Integrated Logistic Matrix Factorization and Bayesian Optimization.DNILMF-LDA：基于双网络集成逻辑矩阵分解和贝叶斯优化的 lncRNA-疾病关联预测。
Genes (Basel). 2019 Aug 12;10(8):608. doi: 10.3390/genes10080608.
9
Matrix factorization-based data fusion for the prediction of lncRNA-disease associations.基于矩阵分解的数据融合方法用于 lncRNA-疾病关联预测。
Bioinformatics. 2018 May 1;34(9):1529-1537. doi: 10.1093/bioinformatics/btx794.
10
DMFLDA: A Deep Learning Framework for Predicting lncRNA-Disease Associations.DMFLDA：一种用于预测 lncRNA-疾病关联的深度学习框架。
IEEE/ACM Trans Comput Biol Bioinform. 2021 Nov-Dec;18(6):2353-2363. doi: 10.1109/TCBB.2020.2983958. Epub 2021 Dec 8.

引用本文的文献

1
LDA-SCGB: inferring lncRNA-disease associations based on condensed gradient boosting.LDA-SCGB：基于凝聚梯度提升推断长链非编码RNA与疾病的关联
BMC Bioinformatics. 2025 Jul 22;26(1):190. doi: 10.1186/s12859-025-06169-2.
2
GCNFORMER: graph convolutional network and transformer for predicting lncRNA-disease associations.GCNFORMER：用于预测 lncRNA-疾病关联的图卷积网络和转换器。
BMC Bioinformatics. 2024 Jan 2;25(1):5. doi: 10.1186/s12859-023-05625-1.
3
Predicting potential lncRNA biomarkers for lung cancer and neuroblastoma based on an ensemble of a deep neural network and LightGBM.

本文引用的文献

1
LncRNA-Disease Associations Prediction Using Bipartite Local Model With Nearest Profile-Based Association Inferring.基于二分局部模型和基于最近邻谱的关联推断的 LncRNA-疾病关联预测
IEEE J Biomed Health Inform. 2020 May;24(5):1519-1527. doi: 10.1109/JBHI.2019.2937827. Epub 2019 Aug 28.
2
LncRNA-Disease Association Prediction Using Two-Side Sparse Self-Representation.基于双边稀疏自表示的长链非编码RNA-疾病关联预测
Front Genet. 2019 May 28;10:476. doi: 10.3389/fgene.2019.00476. eCollection 2019.
3
L-GRMF: an improved graph regularized matrix factorization method to predict drug-target interactions.
基于深度神经网络和LightGBM集成模型预测肺癌和神经母细胞瘤的潜在长链非编码RNA生物标志物
Front Genet. 2023 Aug 16;14:1238095. doi: 10.3389/fgene.2023.1238095. eCollection 2023.
4
iLncDA-RSN: identification of lncRNA-disease associations based on reliable similarity networks.iLncDA-RSN：基于可靠相似性网络的长链非编码RNA-疾病关联识别
Front Genet. 2023 Aug 8;14:1249171. doi: 10.3389/fgene.2023.1249171. eCollection 2023.
5
SCCPMD: Probability matrix decomposition method subject to corrected similarity constraints for inferring long non-coding RNA-disease associations.SCCPMD：基于校正相似性约束的概率矩阵分解方法用于推断长链非编码RNA与疾病的关联
Front Microbiol. 2023 Jan 11;13:1093615. doi: 10.3389/fmicb.2022.1093615. eCollection 2022.
6
Prediction of lncRNA-disease association based on a Laplace normalized random walk with restart algorithm on heterogeneous networks.基于拉普拉斯归一化随机游走重启动算法的异质网络中 lncRNA 疾病关联预测。
BMC Bioinformatics. 2022 Jan 4;23(1):5. doi: 10.1186/s12859-021-04538-1.
L-GRMF：一种改进的图正则化矩阵分解方法，用于预测药物-靶标相互作用。
BMC Bioinformatics. 2019 Jun 10;20(Suppl 8):287. doi: 10.1186/s12859-019-2768-7.
4
Dual-network sparse graph regularized matrix factorization for predicting miRNA-disease associations.双网络稀疏图正则化矩阵分解预测 miRNA-疾病关联
Mol Omics. 2019 Apr 1;15(2):130-137. doi: 10.1039/c8mo00244d. Epub 2019 Feb 6.
5
The computational prediction of drug-disease interactions using the dual-network L-CMF method.基于双网络 L-CMF 方法的药物-疾病相互作用的计算预测。
BMC Bioinformatics. 2019 Jan 5;20(1):5. doi: 10.1186/s12859-018-2575-6.
6
NTSHMDA: Prediction of Human Microbe-Disease Association Based on Random Walk by Integrating Network Topological Similarity.NTSHMDA：基于随机游走并整合网络拓扑相似性的人类微生物-疾病关联预测
IEEE/ACM Trans Comput Biol Bioinform. 2020 Jul-Aug;17(4):1341-1351. doi: 10.1109/TCBB.2018.2883041. Epub 2018 Nov 23.
7
A Novel Approach for Predicting Disease-lncRNA Associations Based on the Distance Correlation Set and Information of the miRNAs.一种基于距离相关集和微小RNA信息预测疾病与长链非编码RNA关联的新方法。
Comput Math Methods Med. 2018 Jun 26;2018:6747453. doi: 10.1155/2018/6747453. eCollection 2018.
8
A Novel Method for LncRNA-Disease Association Prediction Based on an lncRNA-Disease Association Network.基于 lncRNA 疾病关联网络的 lncRNA 疾病关联预测新方法。
IEEE/ACM Trans Comput Biol Bioinform. 2019 Mar-Apr;16(2):688-693. doi: 10.1109/TCBB.2018.2827373. Epub 2018 Apr 16.
9
Long non-coding RNA SNHG16 promotes cell growth and metastasis in ovarian cancer.长链非编码 RNA SNHG16 促进卵巢癌中的细胞生长和转移。
Eur Rev Med Pharmacol Sci. 2018 Feb;22(3):616-622. doi: 10.26355/eurrev_201802_14284.
10
TPGLDA: Novel prediction of associations between lncRNAs and diseases via lncRNA-disease-gene tripartite graph.TPGLDA：基于 lncRNA-疾病-基因三节点图预测 lncRNA 与疾病的关联
Sci Rep. 2018 Jan 18;8(1):1065. doi: 10.1038/s41598-018-19357-3.