| 학회 |
한국화학공학회 |
| 학술대회 |
2022년 봄 (04/20 ~ 04/23, 제주국제컨벤션센터) |
| 권호 |
28권 1호, p.1216 |
| 발표분야 |
[주제 12] 화학공학일반(부문위원회 발표) |
| 제목 |
Transcription factors prediction by DeepTFactor, a deep learning-based tool |
| 초록 |
A transcription factor (TF) is a sequence-specific DNA-binding protein that regulates transcription. It was hard to predict if TFs shows no sequence homology with previous TFs. We developed DeepTFactor, a deep learning-based tool, using a convolutional neural network that has three subnetworks in parallel. It predicted TFs successfully of both eukaryotic and prokaryotic origins. Analysis of gradients of prediction score for input suggested that DeepTFactor detects DNA-binding domains and other latent features. It predicted 332 candidate TFs in Escherichia coli K-12 MG1655, and three of them were experimentally validated by identifying genome-wide binding sites with ChIP-exo experiments. We provide DeepTFactor as a stand-alone program and made the list of 4,674,808 TFs from 73,873,012 protein sequences in 48,346 genomes. DeepTFactor can be useful tool for identifying the regulatory system. [This work was supported by the Technology Development Program to Solve Climate Changes on Systems Metabolic Engineering for Biorefineries(NRF-2012M1A2A2026556 and NRF-2012M1A2A2026557) from the Ministry of Science and ICT through the National Research Foundation(NRF) of Korea.] |
| 저자 |
박가은1, 김기배1, 이상엽1, Ye Gao2, Bernhard O. Palsson2
|
| 소속 |
1한국과학기술원, 2Univ. of California San Diego |
| 키워드 |
생물화공(Biochemical Engineering) |
| E-Mail |
|
| 원문파일 |
초록 보기 |
