RT info:eu-repo/semantics/article
T1 Deep learning and support vector machines for transcription start site identification
A1 Barbero Aparicio, José Antonio
A1 Olivares Gil, Alicia
A1 Diez Pastor, José Francisco
A1 García Osorio, César
K1 Transcription start site
K1 Bioinformatics
K1 Machine learning
K1 Deep learning
K1 Support vector machine
K1 Long short-term memory
K1 Convolutional neural network
K1 Bioinformática
K1 Bioinformatics
K1 Aprendizaje automático
K1 Machine learning
AB Recognizing transcription start sites is key to gene identification. Several approaches have been employed in related problems such as detecting translation initiation sites or promoters, many of the most recent ones based on machine learning. Deep learning methods have been proven to be exceptionally effective for this task, but their use in transcription start site identification has not yet been explored in depth. Also, the very few existing works do not compare their methods to support vector machines (SVMs), the most established technique in this area of study, nor provide the curated dataset used in the study. The reduced amount of published papers in this specific problem could be explained by this lack of datasets. Given that both support vector machines and deep neural networks have been applied in related problems with remarkable results, we compared their performance in transcription start site predictions, concluding that SVMs are computationally much slower, and deep learning methods, specially long short-term memory neural networks (LSTMs), are best suited to work with sequences than SVMs. For such a purpose, we used the reference human genome GRCh38. Additionally, we studied two different aspects related to data processing: the proper way to generate training examples and the imbalanced nature of the data. Furthermore, the generalization performance of the models studied was also tested using the mouse genome, where the LSTM neural network stood out from the rest of the algorithms. To sum up, this article provides an analysis of the best architecture choices in transcription start site identification, as well as a method to generate transcription start site datasets including negative instances on any species available in Ensembl. We found that deep learning methods are better suited than SVMs to solve this problem, being more efficient and better adapted to long sequences and large amounts of data. We also create a transcription start site (TSS) dataset large enough to be used in deep learning experiments.
PB PeerJ
SN 2376-5992
YR 2023
FD 2023-04
LK https://hdl.handle.net/10259/11429
UL https://hdl.handle.net/10259/11429
LA eng
NO This work has been supported by the Junta de Castilla y León under project BU055P20 (JCyL/FEDER, UE), by the Ministry of Science and Innovation under project PID2020- 119894GB-I00, co-financed through European Union FEDER funds and by Fundación Bancaria Caixa under project 2020/00062/001. José A. Barbero-Aparicio is founded through a pre-doctoral grant by the University of Burgos and Alicia Olivares-Gil is founded by the predoctoral grant from the Department of Education of Junta de Castilla y León (VA) (ORDEN EDU/875/2021) (Spain). NVIDIA Corporation donated the TITAN Xp GPUs used in this research. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
DS Repositorio Institucional de la Universidad de Burgos
RD 07-may-2026