Dataset Information

PMAMCA: prediction of microRNA-disease association utilizing a matrix completion approach.

ABSTRACT: BACKGROUND:Numerous experimental results have indicated that microRNAs (miRNAs) play a vital role in biological processes, as well as outbreaks of diseases at the molecular level. Despite their important role in biological processes, knowledge regarding specific functions of miRNAs in the development of human diseases is very limited. While attempting to solve this problem, many computational approaches have been proposed and attracted significant attention. However, most previous approaches suffer from the common problem of being inapplicable to new diseases without any known miRNA-disease associations. RESULTS:This paper proposes a novel method for inferring disease-miRNA associations utilizing a machine learning technique called matrix factorization, which is widely used in recommendation systems. In recommendation systems, the goal is to predict rating scores that a user might assign to specific items. By replacing users with miRNAs and items with diseases, we can efficiently predict miRNA-disease associations without seed miRNAs. As a result, our proposed model, called prediction of microRNA-disease association utilizing a matrix completion approach, achieves excellent performance compared to previous approaches with a reliable AUC value of 0.882 by implementing five-fold cross validation. CONCLUSIONS:To the best of our knowledge, the proposed method applies the matrix completion technique to infer miRNA-disease associations and overcome the seed-miRNA problem negatively affects existing computational models.

SUBMITTER: Ha J

PROVIDER: S-EPMC6425656 | biostudies-literature | 2019 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

PMAMCA: prediction of microRNA-disease association utilizing a matrix completion approach.

Ha Jihwan J Park Chihyun C Park Sanghyun S

BMC systems biology 20190320 1

<h4>Background</h4>Numerous experimental results have indicated that microRNAs (miRNAs) play a vital role in biological processes, as well as outbreaks of diseases at the molecular level. Despite their important role in biological processes, knowledge regarding specific functions of miRNAs in the development of human diseases is very limited. While attempting to solve this problem, many computational approaches have been proposed and attracted significant attention. However, most previous approa ...[more]

PMID: 30894171

Similar Datasets

Project description:Protein kinases become an important source of potential drug targets. Developing new, efficient, and safe small-molecule kinase inhibitors has become an important topic in the field of drug research and development. In contrast with traditional wet experiments which are time-consuming and expensive, machine learning-based approaches for predicting small molecule inhibitors for protein kinases are time-saving and cost-effective, which are highly desired for us. However, the issue of sample scarcity (known active and inactive compounds are usually limited for most kinases) poses a challenge to the research and development of machine learning-based kinase inhibitors' active prediction methods. To alleviate the data scarcity problem in the prediction of kinase inhibitors, in this study, we present a novel Meta-learning-based inductive logistic matrix completion method for the Prediction of Kinase Inhibitors (MetaILMC). MetaILMC adopts a meta-learning framework to learn a well-generalized model from tasks with sufficient samples, which can fast adapt to new tasks with limited samples. As MetaILMC allows the effective transfer of the prior knowledge learned from kinases with sufficient samples to kinases with a small number of samples, the proposed model can produce accurate predictions for kinases with limited data. Experimental results show that MetaILMC has excellent performance for prediction tasks of kinases with few-shot samples and is significantly superior to the state-of-the-art multi-task learning in terms of AUC, AUPR, etc., various performance metrics. Case studies also provided for two drugs to predict Kinase Inhibitory scores, further validating the proposed method's effectiveness and feasibility. SCIENTIFIC CONTRIBUTION: Considering the potential correlation between activity prediction tasks for different kinases, we propose a novel meta learning algorithm MetaILMC, which learns a prior of strong generalization capacity during meta-training from the tasks with sufficient training samples, such that it can be easily and quickly adapted to the new tasks of the kinase with scarce data during meta-testing. Thus, MetaILMC can effectively alleviate the data scarcity problem in the prediction of kinase inhibitors.

Dataset Information

PMAMCA: prediction of microRNA-disease association utilizing a matrix completion approach.

Publications

PMAMCA: prediction of microRNA-disease association utilizing a matrix completion approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets