3차원 유전자 발현 데이터에서의 시간 관계 규칙을 이용한 유전자 상호작용 조절 네트워크 구축

( Meijing Li ),박진형 ( Jin Hyoung Park ),이헌규 ( Heon Gyu Lee ),류근호 ( Keun Ho Ryu ) 한국정보처리학회 2008 한국정보처리학회 학술대회논문집 Vol.15 No.2

유전자들은 복잡한 상호작용을 통해 세포의 기능이 조절된다. 상호작용하는 유전자 그룹들을 유전자 조절 네트워크라고 한다. 기존의 유전자 조절 네트워크는 2D microarray 데이터를 이용하여 시간의 흐름에 따른 유전자간의 상호작용을 알 수가 없었다. 이 논문에서는 시간의 변화에 따른 유전자들 간의 조절관계를 살펴 볼 수 있는 조절네트워크 모델링의 방법을 제시한다. 유전자의 발현양을 표시하기 위해 이진 이산화 방법을 사용하였고 3D microarray 데이터에서 유전자 발현 패턴을 찾기 위해 Cube mining 알고리즘을 적용하였고, 유전자간의 관계를 밝히기 위해 시간 관계 규칙탐사 기법을 사용하여 유전자들 간의 시간 관계를 포함한 유전자 조절네트워크를 구축하였다. 이 연구는 시간의 흐름에 따른 유전자간의 상호작용을 알 수 있으며, 모델링된 조절 네트워크를 이용하여 기능이 아직 발견되지 않은 유전자들의 기능을 예측 할 수 있다.

A Novel Approach for Predicting Disordered Regions in A Protein Sequence

Meijing Li,조성범,류근호 질병관리본부 2014 Osong Public Health and Research Persptectives Vol.5 No.4

Objectives: A number of published predictors are based on various algorithms and disordered protein sequence properties. Although many predictors have been published, the study ofprotein disordered region prediction is ongoing because different prediction methods can find different disordered regions in a protein sequence. Methods: Therefore we have used a new approach to find the more varying disordered regions formore efficient and accurate prediction of protein structures. In this study, we propose a novel approach called “emerging subsequence (ES) mining” without using the characteristics of the disordered protein. We first adapted the approach to generate emerging protein subsequences on public protein sequence data. Second, the disordered and ordered regions in a protein sequence were predicted by searching the generated emerging protein subsequence with a sliding window, which tends to overlap. Third, the scores of the overlapping regions were calculated based on support and growthrate values in both classes. Finally, the score of predicted regions in the target class were compared with the score of the source class, and the class having a higher score was selected. Results: In this experiment, disordered sequence data and ordered sequence data was extracted from DisProt 6.02 and PDB respectively and used as training data. The test data come from CASP 9 and CASP 10 where disordered and ordered regions are known. Conclusion: Comparing with several published predictors, the results of the experiment show higher accuracy rates than with other existing methods.

Classification in Different Genera by Cytochrome Oxidase Subunit I Gene Using CNN-LSTM Hybrid Model

Meijing Li,Dongkeun Kim The Korea Institute of Information and Commucation 2023 Journal of information and communication convergen Vol.21 No.2

The COI gene is a sequence of approximately 650 bp at the 5' terminal of the mitochondrial Cytochrome c Oxidase subunit I (COI) gene. As an effective DeoxyriboNucleic Acid (DNA) barcode, it is widely used for the taxonomic identification and evolutionary analysis of species. We created a CNN-LSTM hybrid model by combining the gene features partially extracted by the Long Short-Term Memory ( LSTM ) network with the feature maps obtained by the CNN. Compared to K-Means Clustering, Support Vector Machines (SVM), and a single CNN classification model, after training 278 samples in a training set that included 15 genera from two orders, the CNN-LSTM hybrid model achieved 94% accuracy in the test set, which contained 118 samples. We augmented the training set samples and four genera into four orders, and the classification accuracy of the test set reached 100%. This study also proposes calculating the cosine similarity between the training and test sets to initially assess the reliability of the predicted results and discover new species.

MapReduce-based web mining for prediction of web-user navigation

Li, Meijing,Yu, Xiuming,Ryu, Keun Ho SAGE Publications 2014 JOURNAL OF INFORMATION SCIENCE Vol.40 No.5

<P>Predicting web user behaviour is typically an application for finding frequent sequence patterns. With the rapid growth of the Internet, a large amount of information is stored in web logs. Traditional frequent-sequence-pattern-mining algorithms are hard pressed to analyse information from within big datasets. In this paper, we propose an efficient way to predict navigation patterns of web users by improving frequent-sequence-pattern-mining algorithms based on the programming model of MapReduce, which can handle huge datasets efficiently. During the experiments, we show that our proposed MapReduce-based algorithm is more efficient than traditional frequent-sequence-pattern-mining algorithms, and by comparing our proposed algorithms with current existed algorithms in web-usage mining, we also prove that using the MapReduce programming model saves time.</P>

A Novel Approach for Protein-Named Entity Recognition and Protein-Protein Interaction Extraction

Li, Meijing,Munkhdalai, Tsendsuren,Yu, Xiuming,Ryu, Keun Ho Hindawi Limited 2015 Mathematical problems in engineering Vol.2015 No.-

<P>Many researchers focus on developing protein-named entity recognition (Protein-NER) or PPI extraction systems. However, the studies about these two topics cannot be merged well; then existing PPI extraction systems’ Protein-NER still needs to improve. In this paper, we developed the protein-protein interaction extraction system named PPIMiner based on Support Vector Machine (SVM) and parsing tree. PPIMiner consists of three main models: natural language processing (NLP) model, Protein-NER model, and PPI discovery model. The Protein-NER model, which is named ProNER, identifies the protein names based on two methods: dictionary-based method and machine learning-based method. ProNER is capable of identifying more proteins than dictionary-based Protein-NER model in other existing systems. The final discovered PPIs extracted via PPI discovery model are represented in detail because we showed the protein interaction types and the occurrence frequency through two different methods. In the experiments, the result shows that the performances achieved by our ProNER and PPI discovery model are better than other existing tools. PPIMiner applied this protein-named entity recognition approach and parsing tree based PPI extraction method to improve the performance of PPI extraction. We also provide an easy-to-use interface to access PPIs database and an online system for PPIs extraction and Protein-NER.</P>

출현 시퀀스 마이닝 기반의 단백질 2 차 구조 예측

( Meijing Li ),이헌규 ( Heon Gyu Lee ),( Khalid E. K. Saeed ),손호선 ( Ho Sun Shon ),류근호 ( Keun Ho Ryu ) 한국정보처리학회 2009 한국정보처리학회 학술대회논문집 Vol.16 No.1

최근 단백질 기능 예측을 위한 서열비교와 구조비교 기법들은 정확한 분류가 가능한 반면, 새로운 단백질 기능 분류를 함에 있어서 많은 복잡도가 따른다. 따라서 이 논문에서는 보다 빠른 단백질의 구조 분류 및 예측을 위하여 출현 시퀀스(emerging sequence)를 기반으로 하는 분류기법을 제안하였다. 이 기법에서는 먼저, 출현 시퀀스 마이닝 알고리즘을 이용하여 단백질 서열 데이터로부터 4 가지의 단백질 2 차 구조 출현 시퀀스를 발견하고, SVM 을 이용하여 단백질의 출현 시퀀스 속성으로부터 단백질의 2 차 구조를 예측하였다.

Application of a Mobile Chronic Disease Health-Care System for Hypertension Based on Big Data Platforms

Li, Dingkun,Park, Hyun Woo,Batbaatar, Erdenebileg,Munkhdalai, Lkhagvadorj,Musa, Ibrahim,Li, Meijing,Ryu, Keun Ho Hindawi Limited 2018 Journal of sensors Vol.2018 No.-

<P>Hadoop is a globally famous framework for big data processing. Data mining (DM) is the key technique for the discovery of the useful information from massive datasets. In our work, we take advantage of both platforms to design a real-time and intelligent mobile health-care system for chronic disease detection based on IoT device data, government-provided public data and user input data. The purpose of our work is the provision of a practical assistant system for self-based patient health care, as well as the design of a complementary system for patient disease diagnosis. This system was only applied to hypertensive disease during the first research stage. Nevertheless, a detailed design, an implementation, a clear overview of the whole system, and a significant guide for further work are provided; the entire step-by-step procedure is depicted. The experiment results show a relatively high accuracy.</P>

A New Direction of Cancer Classification: Positive Effect of Low-Ranking MicroRNAs

Feifei Li,Minghao Piao,Yongjun Piao,Meijing Li,류근호 질병관리본부 2014 Osong Public Health and Research Persptectives Vol.5 No.5

Objectives: Many studies based on microRNA (miRNA) expression profiles showed a new aspect of cancer classification. Because one characteristic of miRNA expression data is the high dimensionality, feature selection methods have been used to facilitate dimensionality reduction. The feature selection methods have one shortcoming thus far: they just consider the problem of where feature to class is 1:1 or n:1. However, because one miRNA may influence more than one type of cancer, human miRNA is considered to be ranked low in traditional feature selection methods and are removed most of the time. In view of the limitation of the miRNA number, low-ranking miRNAs are also important to cancer classification. Methods: We considered both high- and low-ranking features to cover all problems (1:1, n:1, 1:n, and m:n) in cancer classification. First, we used the correlation-based feature selection method to select the high-ranking miRNAs, and chose the support vector machine, Bayes network, decision tree, k-nearestneighbor, and logistic classifier to construct cancer classification. Then, we chose Chi-square test, information gain, gain ratio, and Pearson’s correlation feature selection methods to build the m:n feature subset, and used the selected miRNAs to determine cancer classification. Results: The low-ranking miRNA expression profiles achieved higher classification accuracy compared with just using high-ranking miRNAs in traditional feature selection methods. Conclusion: Our results demonstrate that the m:n feature subset made a positive impression of low-ranking miRNAs in cancer classification.

A Main Framework for Token-based Source Code Clone Detection and Extraction by Using Data Mining Methods

Dingkun Li(이정곤),Minghao Piao(박명호),Meijing Li(이미정),Keun Ho Ryu(류근호) 한국정보과학회 2014 한국정보과학회 학술발표논문집 Vol.2014 No.6

Psoralen synergies with zinc implants to promote bone repair by regulating ZIP4 in rats with bone defect

Meijing Liu,Junlong Tan,Shuang Li,Chaoyang Sun,Xiangning Liu,Hongtao Yang,Xiaogang Wang 한국생체재료학회 2023 생체재료학회지 Vol.27 No.00

Background The regulation of dose-dependent biological effects induced by biodegradation is a challenge for the production of biodegradable bone-substitute materials, especially biodegradable zinc (Zn) -based materials. Cytotoxicity caused by excess local Zn ions (Zn2+) from degradation is one of the factors limiting the wide application of Zn implants. Given that previous studies have revealed that delayed degradation of Zn materials by surface modification does not reduce cytotoxicity; in the present study, we explore whether preventing the entry of excess Zn2+ into cells may can reduce local Zn toxicity by applying Psoralen (PRL) to Zn implants and assessing its ability to regulate intracellular Zn2+ concentrations. Methods The effects of different concentrations of Zn2+ on cellular activity and cytotoxicity were investigated; briefly, we identified natural compounds that regulate Zn transporters, thereby regulating the concentrations of intracellular Zn2+, and applied them to Zn materials. Of these materials, PRL, a natural, tricyclic, coumarin-like aromatic compound that promotes the proliferation and differentiation of osteoblasts and enhances osteogenic activity, was loaded onto the surface of a Zn material using peptides and chitosan (CS), and the surface characteristics, electrochemical properties, and activity of the modified Zn material were evaluated. In addition, the ability of Zn + CS/pPRL implants to promote bone formation and accelerate large-scale bone defect repairs was assessed both in vitro and in vivo. Results We determined that 180 μM Zn2+ significantly induced pre-osteoblast cytotoxicity, and a 23-fold increase in Zrt- and Irt-like protein 4 (ZIP4) expression. We also found that PRL dynamically regulates the expression of ZIP4 in response to Zn2+ concentration. To address the problem of cytotoxicity caused by excessive Zn2+ in local Zn implants, PRL was loaded onto the surface of Zn implants in vivo using peptides and CS, which dynamically regulated ZIP4 levels, maintained the balance of intracellular Zn2+ concentrations, and enhanced the osteogenic activity of Zn implants. Conclusions This study reveals the importance of Zn2+ concentration when using Zn materials to promote bone formation and introduces a natural active ingredient, PRL, that can regulate intracellular Zn2+ levels, and thus may be clinically applicable to Zn implants for the treatment of critical bone defects.