Current progress and open challenges for applying deep learning across the biosciences.

Autor: Sapoval N; Department of Computer Science, Rice University, Houston, TX, USA., Aghazadeh A; Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA, USA., Nute MG; Department of Computer Science, Rice University, Houston, TX, USA., Antunes DA; Department of Biology and Biochemistry, University of Houston, Houston, TX, USA., Balaji A; Department of Computer Science, Rice University, Houston, TX, USA., Baraniuk R; Department of Electrical and Computer Engineering, Rice University, Houston, TX, USA., Barberan CJ; Department of Electrical and Computer Engineering, Rice University, Houston, TX, USA., Dannenfelser R; Department of Computer Science, Rice University, Houston, TX, USA., Dun C; Department of Computer Science, Rice University, Houston, TX, USA., Edrisi M; Department of Computer Science, Rice University, Houston, TX, USA., Elworth RAL; Department of Computer Science, Rice University, Houston, TX, USA., Kille B; Department of Computer Science, Rice University, Houston, TX, USA., Kyrillidis A; Department of Computer Science, Rice University, Houston, TX, USA., Nakhleh L; Department of Computer Science, Rice University, Houston, TX, USA., Wolfe CR; Department of Computer Science, Rice University, Houston, TX, USA., Yan Z; Department of Computer Science, Rice University, Houston, TX, USA., Yao V; Department of Computer Science, Rice University, Houston, TX, USA., Treangen TJ; Department of Computer Science, Rice University, Houston, TX, USA. treangen@rice.edu.; Department of Bioengineering, Rice University, Houston, TX, USA. treangen@rice.edu.
Jazyk: angličtina
Zdroj: Nature communications [Nat Commun] 2022 Apr 01; Vol. 13 (1), pp. 1728. Date of Electronic Publication: 2022 Apr 01.
DOI: 10.1038/s41467-022-29268-7
Abstrakt: Deep Learning (DL) has recently enabled unprecedented advances in one of the grand challenges in computational biology: the half-century-old problem of protein structure prediction. In this paper we discuss recent advances, limitations, and future perspectives of DL on five broad areas: protein structure prediction, protein function prediction, genome engineering, systems biology and data integration, and phylogenetic inference. We discuss each application area and cover the main bottlenecks of DL approaches, such as training data, problem scope, and the ability to leverage existing DL architectures in new contexts. To conclude, we provide a summary of the subject-specific and general challenges for DL across the biosciences.
(© 2022. The Author(s).)
Databáze: MEDLINE
Externí odkaz: