miRBind: A Deep Learning Method for miRNA Binding
Classification

J 2022

miRBind: A Deep Learning Method for miRNA Binding Classification

KLIMENTOVÁ, Eva, Václav HEJRET, Ján KRČMÁŘ, Katarína GREŠOVÁ, Ilektra-Chara GIASSA et. al.

Basic information

Original name

miRBind: A Deep Learning Method for miRNA Binding Classification

Authors

KLIMENTOVÁ, Eva (203 Czech Republic, belonging to the institution), Václav HEJRET (203 Czech Republic, belonging to the institution), Ján KRČMÁŘ (703 Slovakia, belonging to the institution), Katarína GREŠOVÁ (703 Slovakia, belonging to the institution), Ilektra-Chara GIASSA (300 Greece, belonging to the institution) and Panagiotis ALEXIOU (300 Greece, guarantor, belonging to the institution)

Edition

GENES, MDPI, 2022, 2073-4425

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10603 Genetics and heredity

Country of publisher

Switzerland

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 3.500

RIV identification code

RIV/00216224:14740/22:00128672

Organization unit

Central European Institute of Technology

DOI

http://dx.doi.org/10.3390/genes13122323

UT WoS

000902664500001

Keywords in English

miRNA; target prediction; miRNA binding; CLASH; convolutional neural network

Abstract

V originále

The binding of microRNAs (miRNAs) to their target sites is a complex process, mediated by the Argonaute (Ago) family of proteins. The prediction of miRNA:target site binding is an important first step for any miRNA target prediction algorithm. To date, the potential for miRNA:target site binding is evaluated using either co-folding free energy measures or heuristic approaches, based on the identification of binding 'seeds', i.e., continuous stretches of binding corresponding to specific parts of the miRNA. The limitations of both these families of methods have produced generations of miRNA target prediction algorithms that are primarily focused on 'canonical' seed targets, even though unbiased experimental methods have shown that only approximately half of in vivo miRNA targets are 'canonical'. Herein, we present miRBind, a deep learning method and web server that can be used to accurately predict the potential of miRNA:target site binding. We trained our method using seed-agnostic experimental data and show that our method outperforms both seed-based approaches and co-fold free energy approaches. The full code for the development of miRBind and a freely accessible web server are freely available.

Links

GJ19-10976Y, research and development project

Name: Klasifikace miRNA vazebných míst nezávisle na „seed” oblasti

Investor: Czech Science Foundation

Citovat

KLIMENTOVÁ, Eva, Václav HEJRET, Ján KRČMÁŘ, Katarína GREŠOVÁ, Ilektra-Chara GIASSA and Panagiotis ALEXIOU. miRBind: A Deep Learning Method for miRNA Binding Classification. GENES. MDPI, 2022, vol. 13, No 12, p. 2323-2335. ISSN 2073-4425. Available from: https://dx.doi.org/10.3390/genes13122323.

@article{2257178,
   author = {Klimentová, Eva and Hejret, Václav and Krčmář, Ján and Grešová, Katarína and Giassa, IlektraandChara and Alexiou, Panagiotis},
   article_number = {12},
   doi = {http://dx.doi.org/10.3390/genes13122323},
   keywords = {miRNA; target prediction; miRNA binding; CLASH; convolutional neural network},
   language = {eng},
   issn = {2073-4425},
   journal = {GENES},
   title = {miRBind: A Deep Learning Method for miRNA Binding Classification},
   url = {https://www.mdpi.com/2073-4425/13/12/2323},
   volume = {13},
   year = {2022}
}

TY  - JOUR
ID  - 2257178
AU  - Klimentová, Eva - Hejret, Václav - Krčmář, Ján - Grešová, Katarína - Giassa, Ilektra-Chara - Alexiou, Panagiotis
PY  - 2022
TI  - miRBind: A Deep Learning Method for miRNA Binding Classification
JF  - GENES
VL  - 13
IS  - 12
SP  - 2323
EP  - 2323
PB  - MDPI
SN  - 20734425
KW  - miRNA
KW  - target prediction
KW  - miRNA binding
KW  - CLASH
KW  - convolutional neural network
UR  - https://www.mdpi.com/2073-4425/13/12/2323
N2  - The binding of microRNAs (miRNAs) to their target sites is a complex process, mediated by the Argonaute (Ago) family of proteins. The prediction of miRNA:target site binding is an important first step for any miRNA target prediction algorithm. To date, the potential for miRNA:target site binding is evaluated using either co-folding free energy measures or heuristic approaches, based on the identification of binding 'seeds', i.e., continuous stretches of binding corresponding to specific parts of the miRNA. The limitations of both these families of methods have produced generations of miRNA target prediction algorithms that are primarily focused on 'canonical' seed targets, even though unbiased experimental methods have shown that only approximately half of in vivo miRNA targets are 'canonical'. Herein, we present miRBind, a deep learning method and web server that can be used to accurately predict the potential of miRNA:target site binding. We trained our method using seed-agnostic experimental data and show that our method outperforms both seed-based approaches and co-fold free energy approaches. The full code for the development of miRBind and a freely accessible web server are freely available.
ER  -

KLIMENTOVÁ, Eva, Václav HEJRET, Ján KRČMÁŘ, Katarína GREŠOVÁ, Ilektra-Chara GIASSA and Panagiotis ALEXIOU. miRBind: A Deep Learning Method for miRNA Binding Classification. \textit{GENES}. MDPI, 2022, vol.~13, No~12, p.~2323-2335. ISSN~2073-4425. Available from: https://dx.doi.org/10.3390/genes13122323.

Detailed Information on Publication Record