Gast ::
| Hauptseite > Publikationsdatenbank > Leveraging data-efficient RNA contact prediction toward reliable RNA structure prediction |
| Hauptseite > Publikationsdatenbank > Leveraging data-efficient RNA contact prediction toward reliable RNA structure prediction |
| Abstract | FZJ-2025-01063 |
; ; ;
2024
This record in other databases:
Please use a persistent id in citations: doi:10.1016/j.bpj.2023.11.2761
Abstract: On the molecular level, life is orchestrated through an interplay of many biomolecules. To gain any detailed understanding of biomolecular function, one needs to know their structure. For proteins, the richness of labeled training data enables highly successfully deep-learning approaches for structure prediction. Deep learning on RNA, however, is hampered by the simple lack of such data. The limited available data, however, can still be used to predict spatial adjacencies (“contact maps”) as a proxy for 3D structure and as part of structure prediction workflows. In short, 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. We observe a considerable improvement over both the established classical baseline and a neural network. Our positive predictive values of predicted contacts of up to 90% pave the way towards reliable RNA structure prediction.
; BIOSIS Previews ; Biological Abstracts ; Clarivate Analytics Master Journal List ; Current Contents - Life Sciences ; Essential Science Indicators ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection
|
The record appears in these collections: |
PDF