Author Archives: Admin

ACL 2018 in Melbourne, Australia

graduation_all

graduation_alumn

Graduation on Aug 2017

graduation_all

graduation_alumn

Sehwan Moon

Sehwan Moon

Sehwan

Education

  • 2018.03 – Current : Gwangju Institute of Science and Technology, Gwangju, Korea
  • 2014.03 – 2018.02 Catholic University (B.S.-Biotechnology / B.S.-Computer Engineering)

Research Topic

  • Bioinformatics

Activities

Publications

Contact

Phone: +82-62-715-3160
E-mail : sehwanmoon@gist.ac.kr

Hajeong Son

Hajeong Son

Euiyoung

Education

  • 2017.09 – Current : Gwangju Institute of Science and Technology, Gwangju, Korea

Research Topic

  • Text Mining, Deep Learning

Activities

Publications

Contact

Phone: +82-62-715-3160
E-mail : hajungsohn@gist.ac.kr

우수 논문상

장호, 김정균 학생이 우수 논문상을 수상했습니다.

 

장호

  • 한국생물정보시스템생물학회(Korean Society of Bioinformatics, KSBi ) – 우수 논문상 (2016.08.19)
  • 2016 Qualcomm-GIST Innovation Award – IT Research Paper Award (2016.12.16)

김정균

  • 한국생명정보학회(Korean Society of Bioinformatics, KSBi ) – 우수 논문상 (2017.11.02)

Graduation on Feb 2017

graduation_all

graduation_alumn

2014.10 Social Event

2014 년 10월 소셜이벤트 주제는 풍암지구 채식뷔페에서의 채식음식 맛보기 체험이었습니다.

콩고기, 밀까스 등 기존에는 맛볼수 없었던 다양한 채식음식을 음미하면서 즐거운 소셜이벤트 시간을 보냈습니다.

아래는 단체사진!

KakaoTalk_20141008_210750973

Social Event on May 7, 2013

Dear , Lab members,

The social event of April will be held on May 7.
Actually, it should’ve been held oneday of last month, but it has been delayed due to midterm exam schedules and member’s busy working.
Finally, now i am pleased to announce that i will hold the social event on May 7.

The detailed plan is listed below :
2013-5-7 (Tues)

16:00 – 17:50
(reserved)
 The soccer game to enhance member’s health and sociality.
( Location : big football ground next to the main gate of school )
( we will play basketball if the number of participants is not enough. )
18:00 – 20:00  we will eat Sam-gyup-sal (Pork belly) for dinner, which is called ‘삼겹살’ in korean.
( for those who cannot eat pork, you can choose any other food. )

Participating is not your obligation. So, feel free not to join but, i hope all of you will join because it’s going to be fun.
If you want to participate, please prepare your clothes and 10,000 won.
One more thing, If you cannot join, please let me know by e-mailing me in advance.

Thank you very much for reading.
I am looking forward to seeing you on the ground soon.

 

CAM00078   CAM00077

 

Song, B. and Lee, H. (2012) Prioritizing Disease Genes by Integrating Domain Interactions and Disease Mutations in a Protein-Protein Interaction Network,IJICIC, 8(2), 1327-1338

Prioritizing Disease Genes by Integrating Domain Interactions and Disease Mutations in a Protein-Protein Interaction Network

Abstract

Complex diseases such as cancer are involved in inter-relationship amongseveral genes, with protein-protein interaction networks being extensively studied in at-tempts to reveal the relationship between genes and diseases. Although these studies haveshown promising results for identifying disease genes, it is not systemically studied that aprotein functions differently depending on its interaction partners in the network since aprotein can have multiple functions. In this study, domains are considered as functionalunits of proteins and we investigate how disease-related mutations in domains can be usedto identify other disease genes in a domain-domain interaction network. We subsequentlypropose a computational method to predict disease genes based on the following two as-sumptions. The first assumption is that proteins closely interacting with known diseaseproteins in a protein interaction network are likely to be involved in the same disease.Second, although two proteins are in the same distance from known disease genes in aprotein interaction network, the protein interacting with known disease genes through adomain with mutation is more likely to be related to the disease than other proteins thatinteract through domains with no mutation. As a result, when the proposed approach isapplied to five diseases, it highly ranks disease-related genes compared to a model usingonly a protein interaction data set.

Azad, A., Shahid, S., Noman N., and Lee, H. (2011) Prediction of Plant Promoters Based on hexamers and Random Triplet Pair Analysis. Algorithms for Molecular Biology, 6:19 (IF: 2.80)

Prediction of Plant Promoters Based on hexamers and Random Triplet Pair Analysis

  • Author : A K M Azad, Saima Shahid, Nasimul Noman, Hyunju Lee
  • Published Date : 2011
  • Category : 
  • Place of publication : Algorithms for Molecular Biology

Abstract

BACKGROUND:

With an increasing number of plant genome sequences, it has become important to develop a robust computational method for detecting plant promoters. Although a wide variety of programs are currently available, prediction accuracy of these still requires further improvement. The limitations of these methods can be addressed by selecting appropriate features for distinguishing promoters and non-promoters.

METHODS:

In this study, we proposed two feature selection approaches based on hexamer sequences: the Frequency Distribution Analyzed Feature Selection Algorithm (FDAFSA) and the Random Triplet Pair Feature Selecting Genetic Algorithm (RTPFSGA). In FDAFSA, adjacent triplet-pairs (hexamer sequences) were selected based on the difference in the frequency of hexamers between promoters and non-promoters. In RTPFSGA, random triplet-pairs (RTPs) were selected by exploiting a genetic algorithm that distinguishes frequencies of non-adjacent triplet pairs between promoters and non-promoters. Then, a support vector machine (SVM), a nonlinear machine-learning algorithm, was used to classify promoters and non-promoters by combining these two feature selection approaches. We referred to this novel algorithm as PromoBot.

RESULTS:

Promoter sequences were collected from the PlantProm database. Non-promoter sequences were collected from plant mRNA, rRNA, and tRNA of PlantGDB and plant miRNA of miRBase. Then, in order to validate the proposed algorithm, we applied a 5-fold cross validation test. Training data sets were used to select features based on FDAFSA and RTPFSGA, and these features were used to train the SVM. We achieved 89% sensitivity and 86% specificity.

CONCLUSIONS:

We compared our PromoBot algorithm to five other algorithms. It was found that the sensitivity and specificity of PromoBot performed well (or even better) with the algorithms tested. These results show that the two proposed feature selection methods based on hexamer frequencies and random triplet-pair could be successfully incorporated into a supervised machine learning method in promoter classification problem. As such, we expect that PromoBot can be used to help identify new plant promoters. Source codes and analysis results of this work could be provided upon request.