GenerRNA: A generative pre-trained language model for de novo RNA design
Zhao, Y.; Oono, K.; Takizawa, H.; Kotera, M.
Show abstract
AO_SCPLOWBSTRACTC_SCPLOWThe design of RNA plays a crucial role in developing RNA vaccines, nucleic acid therapeutics, and innovative biotechnological tools. Nevertheless, existing techniques lack versatility across various tasks and frequently suffer from a deficiency of automated generation. Inspired by the remarkable success of Large Language Models (LLMs) in the realm of protein and molecule design, we present GenerRNA, the first large-scale pre-trained model for RNA generation, aiming to further automate RNA design. Our approach eliminates the need for secondary structure or other prior knowledge and is capable of de novo generation of RNA with stable secondary structures while ensuring its distinctiveness from existing sequences. This widens our exploration of RNA space, thereby enriching our understanding of RNA structures and functions. Moreover, GenerRNA is fine-tunable on smaller, more specialized datasets for particular subtasks. This flexibility and versatility enables the generation of RNAs with desired specific functionalities or properties. Upon fine-tuning GenerRNA, we successfully generated novel RNA sequences exhibiting high affinity for target proteins. GenerRNA is freely available at the following repository: https://github.com/pfnet-research/GenerRNA
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- bpRNA-align: Improved RNA Secondary Structure Global Alignment for Comparing and Clustering RNA Structures 97%
- On the emergence of structural complexity in RNA replicators. 94%
- Unraveling Unbreakable Hairpins: Characterizing RNA secondary structures that are persistent after dinucleotide shuffling 94%
Similar papers in this journal
- Gra-CRC-miRTar: The pre-trained nucleotide-to-graph neural networks to identify potential miRNA targets in colorectal cancer 94%
- Structural characterization of NORAD reveals a stabilizing role of spacers and two new repeat units. 94%
- PRIMITI: a computational approach for accurate prediction of miRNA-target mRNA interaction 93%
Similar papers in this journal
- Deep learning models for RNA secondary structure prediction (probably) do not generalise across families 96%
- OligoFormer: an accurate and robust prediction method for siRNA design 96%
- DUETT quantitatively identifies known and novel events in nascent RNA structural dynamics from chemical probing data 95%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.