Literature DB >> 35633468

EPI-Mind: Identifying Enhancer-Promoter Interactions Based on Transformer Mechanism.

Yu Ni1,2,3, Linqi Fan4, Miao Wang2, Ning Zhang1, Yongchun Zuo5, Mingzhi Liao6.   

Abstract

MOTIVATION: Enhancer-Promoter Interactions (EPIs) is an essential step in the gene regulation process. However, the detection of EPIs by traditional wet experimental techniques is time-consuming and expensive. Thus, computational methods would be very useful for understanding the mechanism of EPIs. A number of approaches have been proposed to address this problem. Nevertheless, there is room for exploration and improvement for the existing research methods.
METHODS: In this study, a novel deep-learning model named EPI-Mind was proposed to predict EPIs with sequences features. First, we encoded enhancers and promoters sequences with pre-trained DNA vectors. Then, the Convolutional Neural Network (CNN) was utilized to rough extract the global and local features. Finally, the transformer mechanism was introduced to further extract the feature. We first trained a model named EPI-Mind_spe which can predict EPIs in one cell line. To achieve general prediction across different cell lines and further improve the performance of the model, a second-time training was carried on. The redivided dataset were used to train a new model called EPI-Mind_gen which can predict EPIs across different cell lines. To further improve the accuracy, a new model named EPI-Mind_best was trained which used the EPI-Mind_gen as a pre-trained model.
RESULTS: EPI-Mind_spe has the ability of predict EPIs with average AUROC above 90% and average AUPR above 70% but with cell lines specificity. EPI-Mind_gen can predict EPIs across different cell lines and its average AUROC is higher than the EPI-Mind_spe about 4.8%. EPI-Mind_best is superior to the state-of-the-art predictors on benchmarking datasets. EPI-Mind_best achieved best in 5 indicators within 12 indicators consists of AUPR and AUROC which is better than pioneers.
CONCLUSION: This research proposed a method, which was called EPI-Mind, to predict EPIs only with enhancer and promoters sequences, the framework of which was based on deep learning. This manuscript may provide a new route to solve the problem.
© 2022. International Association of Scientists in the Interdisciplinary Areas.

Entities:  

Keywords:  Convolutional Neural Network; Deep learning; Enhancer–promoter interactions; Prediction; Sequences; Transformer mechanism

Mesh:

Year:  2022        PMID: 35633468     DOI: 10.1007/s12539-022-00525-z

Source DB:  PubMed          Journal:  Interdiscip Sci        ISSN: 1867-1462            Impact factor:   3.492


  25 in total

1.  Characterization of genome-wide enhancer-promoter interactions reveals co-expression of interacting genes and modes of higher order chromatin organization.

Authors:  Iouri Chepelev; Gang Wei; Dara Wangsa; Qingsong Tang; Keji Zhao
Journal:  Cell Res       Date:  2012-01-24       Impact factor: 25.617

2.  Words of wisdom. Re: genome-wide association study of prostate cancer identifies a second risk locus at 8q24.

Authors:  Lambertus A Kiemeney
Journal:  Eur Urol       Date:  2007-09       Impact factor: 20.096

3.  Enhancers: from developmental genetics to the genetics of common human disease.

Authors:  Iain Williamson; Robert E Hill; Wendy A Bickmore
Journal:  Dev Cell       Date:  2011-07-19       Impact factor: 12.270

4.  Extensive promoter-centered chromatin interactions provide a topological basis for transcription regulation.

Authors:  Guoliang Li; Xiaoan Ruan; Raymond K Auerbach; Kuljeet Singh Sandhu; Meizhen Zheng; Ping Wang; Huay Mei Poh; Yufen Goh; Joanne Lim; Jingyao Zhang; Hui Shan Sim; Su Qin Peh; Fabianus Hendriyan Mulawadi; Chin Thing Ong; Yuriy L Orlov; Shuzhen Hong; Zhizhuo Zhang; Steve Landt; Debasish Raha; Ghia Euskirchen; Chia-Lin Wei; Weihong Ge; Huaien Wang; Carrie Davis; Katherine I Fisher-Aylor; Ali Mortazavi; Mark Gerstein; Thomas Gingeras; Barbara Wold; Yi Sun; Melissa J Fullwood; Edwin Cheung; Edison Liu; Wing-Kin Sung; Michael Snyder; Yijun Ruan
Journal:  Cell       Date:  2012-01-20       Impact factor: 41.582

Review 5.  Transcriptional enhancers: from properties to genome-wide predictions.

Authors:  Daria Shlyueva; Gerald Stampfel; Alexander Stark
Journal:  Nat Rev Genet       Date:  2014-03-11       Impact factor: 53.242

Review 6.  Regulation of translation initiation in eukaryotes: mechanisms and biological targets.

Authors:  Nahum Sonenberg; Alan G Hinnebusch
Journal:  Cell       Date:  2009-02-20       Impact factor: 41.582

7.  Preferential associations between co-regulated genes reveal a transcriptional interactome in erythroid cells.

Authors:  Stefan Schoenfelder; Tom Sexton; Lyubomira Chakalova; Nathan F Cope; Alice Horton; Simon Andrews; Sreenivasulu Kurukuti; Jennifer A Mitchell; David Umlauf; Daniela S Dimitrova; Christopher H Eskiw; Yanquan Luo; Chia-Lin Wei; Yijun Ruan; James J Bieker; Peter Fraser
Journal:  Nat Genet       Date:  2009-12-13       Impact factor: 38.330

Review 8.  The role of enhancers in cancer.

Authors:  Inderpreet Sur; Jussi Taipale
Journal:  Nat Rev Cancer       Date:  2016-07-01       Impact factor: 60.716

Review 9.  Enhancers: five essential questions.

Authors:  Len A Pennacchio; Wendy Bickmore; Ann Dean; Marcelo A Nobrega; Gill Bejerano
Journal:  Nat Rev Genet       Date:  2013-04       Impact factor: 53.242

10.  Identification of a new prostate cancer susceptibility locus on chromosome 8q24.

Authors:  Meredith Yeager; Nilanjan Chatterjee; Julia Ciampa; Kevin B Jacobs; Jesus Gonzalez-Bosquet; Richard B Hayes; Peter Kraft; Sholom Wacholder; Nick Orr; Sonja Berndt; Kai Yu; Amy Hutchinson; Zhaoming Wang; Laufey Amundadottir; Heather Spencer Feigelson; Michael J Thun; W Ryan Diver; Demetrius Albanes; Jarmo Virtamo; Stephanie Weinstein; Fredrick R Schumacher; Geraldine Cancel-Tassin; Olivier Cussenot; Antoine Valeri; Gerald L Andriole; E David Crawford; Christopher A Haiman; Brian Henderson; Laurence Kolonel; Loic Le Marchand; Afshan Siddiq; Elio Riboli; Timothy J Key; Rudolf Kaaks; William Isaacs; Sarah Isaacs; Kathleen E Wiley; Henrik Gronberg; Fredrik Wiklund; Pär Stattin; Jianfeng Xu; S Lilly Zheng; Jielin Sun; Lars J Vatten; Kristian Hveem; Merethe Kumle; Margaret Tucker; Daniela S Gerhard; Robert N Hoover; Joseph F Fraumeni; David J Hunter; Gilles Thomas; Stephen J Chanock
Journal:  Nat Genet       Date:  2009-09-20       Impact factor: 38.330

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.