NARRMDA：一种新的预测miRNA-疾病关联的算法

163 浏览量更新于2024-08-27 收藏 1.89MB PDF 举报

"NARRMDA 是一种针对 miRNA（微小核糖核酸）与疾病关联预测的新型计算模型，旨在解决可靠预测潜在疾病相关 miRNA 的方法短缺问题。该模型基于已知的 miRNA-疾病关联数据、miRNA 功能相似性、疾病语义相似性和高斯交互轮廓内核相似性，结合了负样本意识和评分基础推荐算法。NARRMDA 在 Mol.BioSyst. 期刊2017年的文章中被详细介绍，由 Lihong Peng、Yeqing Chen、Ning Ma 和 Xing Chen 等人提出，该研究对生物医学领域具有重要意义，因为它有助于发现与疾病相关的 miRNA，进而推动疾病的预防和治疗。" 在当前的生物医学研究中，miRNA 已被证实与众多重要的生物过程密切相关，并在多种人类疾病中扮演关键角色。因此，预测 miRNA 与疾病之间的关联对于理解和治疗疾病至关重要。NARRMDA 模型的创新之处在于它采用了一种综合的方法，不仅考虑了已知的 miRNA-疾病关联数据，还利用了 miRNA 的功能相似性来推测未被发现的关联。 miRNA 功能相似性的计算通常是基于它们在基因表达调控中的作用和相互作用，这有助于识别可能具有类似病理效应的 miRNA。另一方面，疾病语义相似性则是通过分析疾病在疾病 Ontology 中的层次结构来确定，这种相似性可以帮助识别与特定疾病可能相关的 miRNA。高斯交互轮廓内核相似性是 NARRMDA 中的一个关键概念，它允许模型处理缺失数据和噪声，并能捕捉到 miRNA 与疾病之间复杂的关系模式。此外，模型结合了负样本意识，意味着它不仅关注正向关联，也考虑了非关联信息，这有助于提高预测的准确性，避免假阳性预测。 NARRMDA 的应用前景广阔，它能辅助研究人员快速筛查大量的 miRNA 数据，预测可能与特定疾病相关的 miRNA，从而减少实验验证的成本和时间。这在个性化医疗和药物研发领域具有巨大的潜力，为未来的疾病诊断和治疗提供了新的策略和方向。

2650 | Mol. BioSyst., 2017, 13, 2650--2659 This journal is

The Royal Society of Chemistry 2017

Cite this: Mol. BioSyst., 2017,

13,2650

NARRMDA: negative-aware and rating-based

recommendation algorithm for miRNA–disease

association prediction†

Lihong Peng,‡

Yeqing Chen,‡

Ning Ma

and Xing Chen *

An increasing amount of evidence indicates that microRNAs (miRNAs) are closely related to many

important biological processes and play a significant role in various human diseases. More and more

researchers have begun to seek eﬀective methods to predict potential miRNA–disease associations.

However, reliable computational methods to predict potential disease-related miRNAs are lacking. In this

study, we developed a new miRNA–disease association prediction model called Negative-Aware and

rating-based Recommendation algorithm for miRNA–Disease Association prediction (NARRMDA) based

on the known miRNA–disease associations in the HMDD database, miRNA functional similarity, disease

semantic similarity and Gaussian interaction profile kernel similarity. NARRMDA combined a rating-based

recommendation algorithm and a negative-aware algorithm to score and rank miRNAs without known

associations with investigated diseases. Furthermore, we used leave-one-out cross validation to evaluate

the accuracy of NARRMDA and compared NARRMDA with four previous classical prediction models

(RLSMDA, HDMP, RWRMDA and MCMDA). As it turned out, NARRMDA and the other four prediction

models achieved AUCs of 0.8053, 0.6953, 0.7702, 0.7891 and 0.7718, respectively, which proved that

NARRMDA has superior performance of prediction accuracy. Furthermore, we verified the prediction

results associated with colon neoplasms, esophageal neoplasms, lymphoma and breast neoplasms by

two different validation schemas. In these case studies, 92%, 84%, 92%, and 100% of the top 50 potential

miRNAs for these four diseases were confirmed by experimental discoveries, respectively. These results

further show that NARRMDA has reliable performance of prediction ability.

Introduction

MicroRNAs (miRNAs) are a class of short (B22 nt) endogenous

noncoding RNAs which have many important regulatory roles

in gene expression. It is generally recognized that miRNA

functions by binding to the 3’UTRs of the target mRNA through

sequence-specific base pairing at a post-transcriptional level.

1–4

A large number of research studies indicate that miRNAs are closely

related to many biological processes, such as cell proliferation,

cell

differentiation,

apoptosis,

signal transduction,

viral infection,

and the occurrence

9–14

and development

of many diseases,

especially cancer. Besides that, experiments indicate that each

miRNA could have more than one target gene, and multiple

miRNAs can regulate the same gene.

The networks based on

these complex relationships provide an approach to research

the associations between miRNAs and diseases based on genes

using computational and mathematical methods. Furthermore,

if we can discover the associations between miRNAs and

diseases, it would be possible to diagnose diseases at an early

stage, and even to control the occurrence and development of

diseases by regulating miRNAs through certain medical means.

Therefore, the large-scale study of the relationship between

miRNA and disease has become an important goal of biomedical

research.

To date, thousands of miRNAs have been discovered in

eukaryotic organisms by applying various experimental methods

and computational models. In addition, an increasing number

of experimentally verified human miRNA–disease associations

have been identified. An open human miRNA–disease associa-

tion database HMDD (http://www.cuilab.cn/hmdd), aiming to

collect experimental evidence of human miRNA–disease associa-

tions, has collected 10 368 miRNA–disease associations referring

College of Information Engineering, Changsha Medical University, Changsha,

410219, China

College of Informatics, Huazhong Agricultural University, Wuhan, 430070, China

College of Pharmacy, Changsha Medical University, Changsha, 410219, China

School of Information and Control Engineering, China University of Mining and

Technology, Xuz hou, 221116, China. E-mail: xingchen@amss.ac.cn

† Electronic supplementary information (ESI) available. See DOI: 10.1039/

c7mb00499k

‡ The authors wish it to be known that, in their opinion, the first two authors

should be regarded as joint First Authors.

Received 10th August 2017,

Accepted 11th October 2017

DOI: 10.1039/c7mb00499k

rsc.li/molecular-biosystems

Molecular

BioSystems

PAPER

下载后可阅读完整内容，剩余9页未读，立即下载

weixin_38695727

粉丝: 8
资源: 951

NARRMDA：一种新的预测miRNA-疾病关联的算法

解决推荐系统过平滑问题： Interest-aware Message-Passing GCN模型

对抗恶意软件：Spybot与Ad-aware的防御策略

mono-no-aware: 单人冒险游戏探索与皇后救援

SALSA - Scalable and Low Synchronization NUMA-aware Algorithm for Producer-Consumer Pools (spaa049-gidron)-计算机科学

Taxonomy-aware collaborative denoising autoencoder for personalized recommendation

Content-Aware Prediction AlgorithmWith Inter-View Mode Decision for MVC

Expenditure Aware Rating Prediction for Recommendation

A. Security-aware mapping for CAN-based real-time distributed au

Deviation-based neighborhood model for context-aware QoS prediction of cloud and IoT services

Security-aware attribute-based access control for fog-based eldercare system

最新资源