TY  - JOUR
AU  - Taubert, Oskar
AU  - von der Lehr, Fabrice
AU  - Bazarova, Alina
AU  - Faber, Christian
AU  - Knechtges, Philipp
AU  - Weiel, Marie
AU  - Debus, Charlotte
AU  - Coquelin, Daniel
AU  - Basermann, Achim
AU  - Streit, Achim
AU  - Kesselheim, Stefan
AU  - Götz, Markus
AU  - Schug, Alexander
TI  - RNA contact prediction by data efficient deep learning
JO  - Communications biology
VL  - 6
IS  - 1
SN  - 2399-3642
CY  - London
PB  - Springer Nature
M1  - FZJ-2023-04901
SP  - 913
PY  - 2023
AB  - 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.
LB  - PUB:(DE-HGF)16
C6  - 37674020
UR  - <Go to ISI:>//WOS:001060848200001
DO  - DOI:10.1038/s42003-023-05244-9
UR  - https://juser.fz-juelich.de/record/1018573
ER  -