RibonanzaNet: Deep learning of RNA through ultra-high throughput chemical mapping data

The RibonanzaNet technology suite leverages ultra-high throughput chemical mapping data for enabling downstream tasks to predict RNA structure, experimental dropout, and degradation. Try it for yourself below!

RibonanzaNet model architecture diagram, described in the paper Ribonanza: deep learning of RNA structure through dual crowdsourcing linked on the about page RibonanzaNet model architecture diagram, described in the paper Ribonanza: deep learning of RNA structure through dual crowdsourcing linked on the about page

Submit your RibonanzaNet job

To limit how long it takes to run jobs, this webserver has a limit of 1000 nucleotides. For larger jobs, please use a local copy of RibonanzaNet. Don't know where to start? Try an example input sequence.

RNA sequence (using base letters A, G, C, and U)
Computations
Including additional computations will increase job execution time. Secondary structure will always be computed. Including mutate-and-map will reduce the maximum length to 200 nucleotides.
Provide a name for your submission to help you more easily recognize it later
Provide your email to get a notification once the job is complete

Job results are occasionally cleared to maintain system availability. We currently aim to store results for 14 days.