본문 바로가기

CNN-Peaks: ChIP-Seq peak detection pipeline using convolutional neural networks that imitate human visual inspection

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q1Scopus Q1
저널
SCIENTIFIC REPORTS10(1) · 2020
피인용
Web of Science 17Scopus 18
FWCI (Scopus)
0
JCR IF
JCR 2019 3.998
ISSN
2045-2322

저자

  1. 오동빈제1저자School of Computer Science and Engineering, Pusan National University, Busan, 46241, South Korea
  2. Strattan, J. SethDepartment of Genetics, Stanford University, Stanford, 94305, USA
  3. Hur, Junho K.School of Medicine, Kyung Hee University, Seoul, 02447, South Korea
  4. Bento, JoséDepartment of Computer Science, Boston College, Chestnut Hill, Philadelphia, MA, 02467, USA
  5. Urban, Alexander EckehartDepartment of Genetics, Stanford University, Stanford, 94305, USA
  6. 송길태교신저자School of Computer Science and Engineering, Pusan National University, Busan, 46241, South Korea
  7. Cherry, J. MichaelDepartment of Genetics, Stanford University, Stanford, 94305, USA

초록

ChIP-seq is one of the core experimental resources available to understand genome-wide epigenetic interactions and identify the functional elements associated with diseases. The analysis of ChIP-seq data is important but poses a difficult computational challenge, due to the presence of irregular noise and bias on various levels. Although many peak-calling methods have been developed, the current computational tools still require, in some cases, human manual inspection using data visualization. However, the huge volumes of ChIP-seq data make it almost impossible for human researchers to manually uncover all the peaks. Recently developed convolutional neural networks (CNN), which are capable of achieving human-like classification accuracy, can be applied to this challenging problem. In this study, we design a novel supervised learning approach for identifying ChIP-seq peaks using CNNs, and integrate it into a software pipeline called CNN-Peaks. We use data labeled by human researchers who annotate the presence or absence of peaks in some genomic segments, as training data for our model. The trained model is then applied to predict peaks in previously unseen genomic segments from multiple ChIP-seq datasets including benchmark datasets commonly used for validation of peak calling methods. We observe a performance superior to that of previous methods.

키워드

FACTOR-BINDING SITESDEFINEENCODEMETHYLATIONELEMENTSMARKSDNA

식별자

Scopus EID
2-s2.0-85084627732
WoS UID
000540463000003