Sungkyu Kim

miTarget: microRNA target gene prediction using a support vector machine

BackgroundMicroRNAs (miRNAs) are small noncoding RNAs, which play significant roles as posttranscriptional regulators. The functions of animal miRNAs are generally based on complementarity for their 5 components. Although several computational miRNA target-gene prediction methods have been proposed, they still have limitations in revealing actual target genes.ResultsWe implemented miTarget, a support vector machine (SVM) classifier for miRNA target gene prediction. It uses a radial basis function kernel as a similarity measure for SVM features, categorized by structural, thermodynamic, and position-based features. The latter features are introduced in this study for the first time and reflect the mechanism of miRNA binding. The SVM classifier produces high performance with a biologically relevant data set obtained from the literature, compared with previous tools. We predicted significant functions for human miR-1, miR-124a, and miR-373 using Gene Ontology (GO) analysis and revealed the importance of pairing at positions 4, 5, and 6 in the 5 region of a miRNA from a feature selection experiment. We also provide a web interface for the program.ConclusionmiTarget is a reliable miRNA target gene prediction tool and is a successful application of an SVM classifier. Compared with previous tools, its predictions are meaningful by GO analysis and its performance can be improved given more training examples.

ProMiR II: a web server for the probabilistic prediction of clustered, nonclustered, conserved and nonconserved microRNAs

ProMiR is a web-based service for the prediction of potential microRNAs (miRNAs) in a query sequence of 60–150 nt, using a probabilistic colearning model. Identification of miRNAs requires a computational method to predict clustered and nonclustered, conserved and nonconserved miRNAs in various species. Here we present an improved version of ProMiR for identifying new clusters near known or unknown miRNAs. This new version, ProMiR II, integrates additional evidence, such as free energy data, G/C ratio, conservation score and entropy of candidate sequences, for more controllable prediction of miRNAs in mouse and human genomes. It also provides a wider range of services, e.g. the prediction of miRNA genes in long nonrelated sequences such as viral genomes. Importantly, we have validated this method using several case studies. All data used in ProMiR II are structured in the MySQL database for efficient analysis. The ProMiR II web server is available at .

A Kernel Method for MicroRNA Target Prediction Using Sensible Data and Position-Based Features

MicroRNAs (miRNAs) are small endogenous RNAs of ~ 22nt that act as direct post-transcriptional regulators in animals and plants. MicroRNAs generally perform a function by binding to the complementary site on the 3’ untranslated region of its target gene and especially the 8mers on the 5’ part of miRNA seems important as a seed. Computational methods for miRNA target prediction have been focusing on this seed region, but recent researches revealed that the specificity of the seed region may be sharply decreased even by a point mutation. In this paper, we present a kernel method for miRNA target prediction in animals, which improves the prediction performance with biologically sensible data and position-based features reflecting the way of miRNA: mRNA pairing mechanism. In building a training dataset, we choose experimentally verified data only to improve the quality of dataset by excluding randomly synthesized one and consequently to make the result of learning valid. We use sensitivity, specificity, and area under ROC curve as performance measures of our algorithm and compare the results of various dataset configurations. The overall results were 92.1% in sensitivity, 83.3% in specificity, and 0.931 in area under ROC curve. With position-based features, an increase of 3.3% in sensitivity and 1.6% in specificity were observed.

A Study on the Effects of Factors of Traffic Accidents Caused by Frozen Urban Road Surfaces in the Winter

PURPOSES: According to accident statistics for road built in 2004, the ratio of accidents on frozen roads to normal roads is 0.9%, whereas the fatality ratio is 2.7%. The risk of accidents on frozen roads is very high. Measures taken every year to prevent traffic accidents of frozen roads in the winter season are still insufficient. Additionally, measures have been established mainly on rural roads. Therefore, for urban roads, analyses and measures to prevent accidents are lacking. In this study, data on accidents on frozen roads was used to search for the causes behind these accidents and measures to reduce accidents have been recommended. METHODS: In this study, collected data from the TAMS (Traffic Accident Management System), which were collected by the Seoul National Police Agency was used. The data were divided into vehicle, people, and condition of road. The analytical model used here was the Logistic Regression Model, which is frequently used for traffic safety and accident analysis. This study uses the odds ratio analysis to search for variables related to frozen road traffic accidents in each category. A total of 18 out of 47 variables were found to be the causes of accidents. RESULTS: From the results of the comparative analysis of 18 variables, the category of the condition of the road was found to be the most critical. Contrary to expectations, more accidents occurred in clear weather than in other conditions. Accidents on bridges occurred frequently, and its odds ratio was the highest compared with other road types. When BPT is operated, the probability of accidents on frozen roads is lower than in general conditions, and accidents occurred frequently on roads with less than four lanes. CONCLUSIONS : Based on the results of this study, suggestions for reducing the risk of future domestic road accidents in freezing conditions are indicated as follows. First, it is necessary to perform a technical review of the urban road traffic accidents caused by frozen roads. Second, it is necessary to establish criteria for the study of the road environment based on the major causes of road accidents on frozen roads. Third, improvements in urban road environmental factors should be made.

Study on Design Principle of Reverse Curve in Superhighway

PURPOSES : This study is to conduct the research on the design principle for the driver`s safety and comfort in installing consecutive curves of superhighway. METHODS : Superhighway does not currently exist in domestic area. Thus, this study is conducted by collecting driving behavior usage of 30 people who are involved in the members of the virtual driving simulation. By identifying the distribution characteristics of each scenario in ANOVA & Tukey Test, the distribution are categorized into three groups. RESULTS : In the case of Group A in Section 3 (R2 entry part), lane departure exceeds the safety standard, which means to be risky condition. And then in the case of Group B and C, the lane departure values applying theoretical formula was evenly distributed compared to the proven values. CONCLUSIONS : Based on the result, the continuous curve design principles at superhighway should follow three standards as follow. First, an additional linear part needs to be inserted between two curves. Second, what if inserting the linear part is difficult, it would be better to insert a curve more than 2,000m. Third, R1/R2 ratio should not be over two. This design primarily aims to the safety of the operator. Such road alignment also meets the expectations of drivers, thus, it may help drivers to be compatible and amenable while driving continuous curve in superhighway.