RT info:eu-repo/semantics/article
T1 Nonlinear physics opens a new paradigm for accurate transcription start site prediction
A1 Barbero Aparicio, José Antonio
A1 Cuesta López, Santiago
A1 García Osorio, César
A1 Pérez-Rodríguez, Javier
A1 García-Pedrajas, Nicolás
K1 DNA modelling
K1 DNA breathing
K1 Machine learning
K1 TSS prediction
K1 SVM
K1 String kernels
K1 Informática
K1 Computer science
AB There is evidence that DNA breathing (spontaneous opening of the DNA strands)plays a relevant role in the interactions of DNA with other molecules, and in particularin the transcription process. Therefore, having physical models that can predict theseopenings is of interest. However, this source of information has not been used beforeeither in transcription start sites (TSSs) or promoter prediction. In this article, one suchmodel is used as an additional information source that, when used by a machine learn‑ing (ML) model, improves the results of current methods for the prediction of TSSs. Inaddition, we provide evidence on the validity of the physical model, as it is able by itselfto predict TSSs with high accuracy. This opens an exciting avenue of research at theintersection of statistical mechanics and ML, where ML models in bioinformatics can beimproved using physical models of DNA as feature extractors.
PB Springer Nature
YR 2022
FD 2022-12
LK http://hdl.handle.net/10259/7337
UL http://hdl.handle.net/10259/7337
LA eng
NO This work has been supported by the Junta de Andalucia under project UCO1264182 and by the Ministry of Science, Innovation and Universities under project PID2019-109481GB-I00/AEI/q10.13039/501100011033, in both cases co-financed through European Union FEDER funds. José A. Barbero-Aparicio is founded through a predoctoral grant from the University of Burgos.
DS Repositorio Institucional de la Universidad de Burgos
RD 23-dic-2024