HIGHLIGHTS
SUMMARY
Since probing of RNA structure experimentally is laborious, computationally predicting secondary_structure from sequence often serves as starting point to investigate ncRNA secondary_structure. To no surprise, deep neural_networks have been employed successfully to predict RNA secondary_structure. An obvious problem is the limited amount of training data for specific families or motifs of secondary_structure. The idea is to obtain a deep learning model that has explicitly learned secondary_structure through inverse folding, whilst maintaining the unconstrained flexibility to learn unknown and implicit variances beyond secondary_structure subsequent to pre-training. To address this, the authors perform systematic in . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.