KIT | KIT-Bibliothek | Impressum | Datenschutz

RNA contact prediction by data efficient deep learning

Taubert, Oskar ORCID iD icon 1; von der Lehr, Fabrice; Bazarova, Alina; Faber, Christian; Knechtges, Philipp; Weiel, Marie ORCID iD icon 1; Debus, Charlotte 1; Coquelin, Daniel ORCID iD icon 1; Basermann, Achim; Streit, Achim ORCID iD icon 1; Kesselheim, Stefan; Götz, Markus ORCID iD icon 1; Schug, Alexander 1
1 Scientific Computing Center (SCC), Karlsruher Institut für Technologie (KIT)

Abstract:

On the path to full understanding of the structure-function relationship or even design of RNA, structure prediction would offer an intriguing complement to experimental efforts. Any deep learning on RNA structure, however, is hampered by the sparsity of labeled training data. Utilizing the limited data available, we here focus on predicting spatial adjacencies ("contact maps”) as a proxy for 3D structure. Our model, BARNACLE, combines the utilization of unlabeled data through self-supervised pre-training and efficient use of the sparse labeled data through an XGBoost classifier. BARNACLE shows a considerable improvement over both the established classical baseline and a deep neural network. In order to demonstrate that our approach can be applied to tasks with similar data constraints, we show that our findings generalize to the related setting of accessible surface area prediction.


Verlagsausgabe §
DOI: 10.5445/IR/1000162205
Veröffentlicht am 22.09.2023
Originalveröffentlichung
DOI: 10.1038/s42003-023-05244-9
Scopus
Zitationen: 2
Web of Science
Zitationen: 1
Dimensions
Zitationen: 2
Cover der Publikation
Zugehörige Institution(en) am KIT Scientific Computing Center (SCC)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2023
Sprache Englisch
Identifikator ISSN: 2399-3642
KITopen-ID: 1000162205
HGF-Programm 46.21.04 (POF IV, LK 01) HAICU
Weitere HGF-Programme 46.21.02 (POF IV, LK 01) Cross-Domain ATMLs and Research Groups
Erschienen in Communications Biology
Verlag Nature Research
Band 6
Heft 1
Seiten 913
Vorab online veröffentlicht am 06.09.2023
Nachgewiesen in Dimensions
Scopus
Web of Science
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page