Back

DesiRNA: structure-based design of RNA sequences with a Monte Carlo approach

Wirecki, T.; Lach, G.; Jaryani, F.; Badepally, N. G.; Moafinejad, N.; Klaudel, G.; Bujnicki, J. M.

2023-06-06 bioinformatics
10.1101/2023.06.04.543636 bioRxiv
Show abstract

RNA sequences underpin the formation of complex and diverse structures, subsequently governing their respective functional properties. Despite the pivotal role RNA sequences play in cellular mechanisms, creating optimized sequences that can predictably fold into desired structures remains a significant challenge. We have developed DesiRNA, a versatile Python-based software tool for RNA sequence design. This program considers a comprehensive array of constraints, ranging from secondary structures (including pseudoknots) and GC content, to the distribution of dinucleotides emulating natural RNAs. Additionally, it factors in the presence or absence of specific sequence motifs and prevents or promotes oligomerization, thereby ensuring a robust and flexible design process. DesiRNA utilizes the Monte Carlo algorithm for the selection and acceptance of mutation sites. In tests on the EteRNA benchmark, DesiRNA displayed high accuracy and computational efficiency, outperforming most existing RNA design programs.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"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.