Prediction of TF-binding site by inclusion of higher order position dependencies

Jiyun Zhou, Qin Lu, Ruifeng Xu, Lin Gui, Hongpeng Wang

Research output: Contribution to journalArticle

Abstract

Most proposed methods for TF-binding site (TFBS) predictions only use low order dependencies for predictions due to the lack of efficient methods to extract higher order dependencies. In this work, We first propose a novel method to extract higher order dependencies by applying CNN on histone modification features. We then propose a novel TFBS prediction method, referred to as CNN_TF, by incorporating low order and higher order dependencies. CNN_TF is first evaluated on 13 TFs in the mES cell. Results show that using higher order dependencies outperforms low order dependencies significantly on 11 TFs. This indicates that higher order dependencies are indeed more effective for TFBS predictions than low order dependencies. Further experiments show that using both low order dependencies and higher order dependencies improves performance significantly on 12 TFs, indicating the two dependency types are complementary. To evaluate the influence of cell-types on prediction performances, CNN_TF was applied to five TFs in five cell-types of humans. Even though low order dependencies and higher order dependencies show different contributions in different cell-types, they are always complementary in predictions. When comparing to several state-of-the-art methods, CNN_TF outperforms them by at least 5.3% in AUPR.
Original languageEnglish
JournalIEEE/ACM Transactions on Computational Biology and Bioinformatics
Early online date10 Jan 2019
DOIs
Publication statusE-pub ahead of print - 10 Jan 2019

Fingerprint

Binding sites
Inclusion
Binding Sites
Higher Order
Prediction
Histone Code
Cell
Performance Prediction
Experiments

Bibliographical note

© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Cite this

Zhou, J., Lu, Q., Xu, R., Gui, L., & Wang, H. (2019). Prediction of TF-binding site by inclusion of higher order position dependencies. IEEE/ACM Transactions on Computational Biology and Bioinformatics . https://doi.org/10.1109/TCBB.2019.2892124
Zhou, Jiyun ; Lu, Qin ; Xu, Ruifeng ; Gui, Lin ; Wang, Hongpeng. / Prediction of TF-binding site by inclusion of higher order position dependencies. In: IEEE/ACM Transactions on Computational Biology and Bioinformatics . 2019.
@article{e6ebecf71c3c4a0ea330b99d88f3155e,
title = "Prediction of TF-binding site by inclusion of higher order position dependencies",
abstract = "Most proposed methods for TF-binding site (TFBS) predictions only use low order dependencies for predictions due to the lack of efficient methods to extract higher order dependencies. In this work, We first propose a novel method to extract higher order dependencies by applying CNN on histone modification features. We then propose a novel TFBS prediction method, referred to as CNN_TF, by incorporating low order and higher order dependencies. CNN_TF is first evaluated on 13 TFs in the mES cell. Results show that using higher order dependencies outperforms low order dependencies significantly on 11 TFs. This indicates that higher order dependencies are indeed more effective for TFBS predictions than low order dependencies. Further experiments show that using both low order dependencies and higher order dependencies improves performance significantly on 12 TFs, indicating the two dependency types are complementary. To evaluate the influence of cell-types on prediction performances, CNN_TF was applied to five TFs in five cell-types of humans. Even though low order dependencies and higher order dependencies show different contributions in different cell-types, they are always complementary in predictions. When comparing to several state-of-the-art methods, CNN_TF outperforms them by at least 5.3{\%} in AUPR.",
author = "Jiyun Zhou and Qin Lu and Ruifeng Xu and Lin Gui and Hongpeng Wang",
note = "{\circledC} 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2019",
month = "1",
day = "10",
doi = "10.1109/TCBB.2019.2892124",
language = "English",

}

Zhou, J, Lu, Q, Xu, R, Gui, L & Wang, H 2019, 'Prediction of TF-binding site by inclusion of higher order position dependencies', IEEE/ACM Transactions on Computational Biology and Bioinformatics . https://doi.org/10.1109/TCBB.2019.2892124

Prediction of TF-binding site by inclusion of higher order position dependencies. / Zhou, Jiyun; Lu, Qin; Xu, Ruifeng; Gui, Lin; Wang, Hongpeng.

In: IEEE/ACM Transactions on Computational Biology and Bioinformatics , 10.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Prediction of TF-binding site by inclusion of higher order position dependencies

AU - Zhou, Jiyun

AU - Lu, Qin

AU - Xu, Ruifeng

AU - Gui, Lin

AU - Wang, Hongpeng

N1 - © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2019/1/10

Y1 - 2019/1/10

N2 - Most proposed methods for TF-binding site (TFBS) predictions only use low order dependencies for predictions due to the lack of efficient methods to extract higher order dependencies. In this work, We first propose a novel method to extract higher order dependencies by applying CNN on histone modification features. We then propose a novel TFBS prediction method, referred to as CNN_TF, by incorporating low order and higher order dependencies. CNN_TF is first evaluated on 13 TFs in the mES cell. Results show that using higher order dependencies outperforms low order dependencies significantly on 11 TFs. This indicates that higher order dependencies are indeed more effective for TFBS predictions than low order dependencies. Further experiments show that using both low order dependencies and higher order dependencies improves performance significantly on 12 TFs, indicating the two dependency types are complementary. To evaluate the influence of cell-types on prediction performances, CNN_TF was applied to five TFs in five cell-types of humans. Even though low order dependencies and higher order dependencies show different contributions in different cell-types, they are always complementary in predictions. When comparing to several state-of-the-art methods, CNN_TF outperforms them by at least 5.3% in AUPR.

AB - Most proposed methods for TF-binding site (TFBS) predictions only use low order dependencies for predictions due to the lack of efficient methods to extract higher order dependencies. In this work, We first propose a novel method to extract higher order dependencies by applying CNN on histone modification features. We then propose a novel TFBS prediction method, referred to as CNN_TF, by incorporating low order and higher order dependencies. CNN_TF is first evaluated on 13 TFs in the mES cell. Results show that using higher order dependencies outperforms low order dependencies significantly on 11 TFs. This indicates that higher order dependencies are indeed more effective for TFBS predictions than low order dependencies. Further experiments show that using both low order dependencies and higher order dependencies improves performance significantly on 12 TFs, indicating the two dependency types are complementary. To evaluate the influence of cell-types on prediction performances, CNN_TF was applied to five TFs in five cell-types of humans. Even though low order dependencies and higher order dependencies show different contributions in different cell-types, they are always complementary in predictions. When comparing to several state-of-the-art methods, CNN_TF outperforms them by at least 5.3% in AUPR.

UR - https://ieeexplore.ieee.org/document/8607082/authors#authors

U2 - 10.1109/TCBB.2019.2892124

DO - 10.1109/TCBB.2019.2892124

M3 - Article

ER -

Zhou J, Lu Q, Xu R, Gui L, Wang H. Prediction of TF-binding site by inclusion of higher order position dependencies. IEEE/ACM Transactions on Computational Biology and Bioinformatics . 2019 Jan 10. https://doi.org/10.1109/TCBB.2019.2892124