RNA is an important and versatile macromolecule participating in various biological processes. In addition to experimental approaches, the computational prediction of RNA 3D structures is an alternative and important source of obtaining structural information and insights into their functions. An important part of these computational prediction approaches is structural quality assessment. For this purpose, we developed a 3D CNN-based approach named RNA3DCNN. This approach uses raw atom distributions in 3D space as the input of neural networks and the output is an RMSD-based nucleotide unfitness score for each nucleotide in an RNA molecule, thus making it possible to evaluate local structural quality. Here, we tested and made comparisons with four other traditional scoring functions on three test datasets from different sources.
https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1006514
Proposed price: 395 TECH