메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술대회자료
저자정보
Seung-Won Yoon (Chung-nam National University) In-Woo Hwang (Chung-nam National University) Jae-In Kim (Chung-nam National University) Kyu-Chul Lee (Chung-nam National University)
저널정보
한국정보통신학회 INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING 2023 INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING Vo.14 No.1
발행연도
2023.1
수록면
61 - 65 (5page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
MicroRNAs(miRNA) can regulate the protein expression level of gene in the human body. And as miRNAs have been recently revealed that those are closely relatde to the cause of disease, miRNAs are being very actively in the fields of biology and pharmacogenomics. Research to find genes related to microRNAs is of great help in understanding the mechanisms of complex microRNAs. In addition, studies that define genes related to specific microRNAs can make a significant contribution to predicting diseases related to microRNAs, and can also contribute to predicting to predicting Drugs related to microRNAs. But revealing microRNA-related genes through wet experiments(in-vivo, traditional method) requires a lot of time and cost and is not efficient. In order to overcome these problems, recent studies are being conducted to predict the relevance through deep learning models.
This study presents a method for predicting association between microRNAs and genes through a Deep learning model. First of all, it is important to set a negative data set to train association-prediction DL model. Since it is difficult to define absolute negative relationships with biological data, very few data sets of negative relationships have been opende. Togenerate Negative data set, we present our elaborate criteria by distance(between miRNAs and genes) base method. Then we reconstruct negative dataset by our elaborate method. After positive and negative data are equally constructed, we extract miRNA-gene feature by Autoencoder. Then concatenate feature vector to origin data. The concatenated data is fed to LSTM model training. Our miRNA-gene association prediction model shows the performance of 'AUC: 0.9581' and shows the best performance among studies using same microRNA-gene association data set.

목차

Abstract
Ⅰ. INTRODUCTION
Ⅱ. METHODS
Ⅲ. Experiments
Ⅳ. Conclusions
REFERENCES

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

최근 본 자료

전체보기

댓글(0)

0