|
Manual of CircSite webserver |
CircSite is a deep learning based approach to predict RNA-binding protein (RBP) nucleotides on circular RNAs. There are 3 notices you need to pay attention to before using CircSite:
|
Content
Input
CircSite requires two types of input: Prediction model and circRNA sequences. Email address is optional. If an email is provided, a notification will be sent to the email once the job is finished.
1. Predition model
There are 37 specific models for circRNAs in CircSite. Each model is trained by the known RNA targets of one RBP. Here we only predict the binding scores between the input RNA and the specified RBP.
CircSite also provides a general model，which is trained by pooled binding circRNA targets of all kinds of RBPs, the general model can be used to predicting RBP binding nucleotides for any RBPs.
If you choose to plot motif, it will take a few hours to calculate according to the input sequence length!
2. circRNA sequence
You can type in your circRNA sequence or upload your sequence file in FASTA format.(You can also use the example sequence.) The FASTA format is shown in the following figure.
3. Email
Email address is optional. CircSite will send the results to the email address if it is provided.
Output
It will take a while for program to run. The result page URL is given but the result hasn't been finished, so you can bookmark this URL and come back later or wait for a while.
After a while (depends on the input sequence length and whether to plot motif), the result page is ready and you can click this URL to the result page.
If the RNA-binding protein has a verified motif, CircSite will provide the motif logo, which will be visualized along the input sequence.
Given multiple input sequences, CircSite would number the multiple input sequences like AGO1_0, AGO1_1, AGO1_2... on the top of the result table, _0 means the first sequence, _1 means the second sequence, and so on. In addition, you can click the following links to locate the results.
CircSite displays the score of each nucleotide with the RBP of interest in a table each sequence. What's more, CircSite provides sort function. You can click the name of each column to sort the results ascendly and descendly. (the "Nucleotide" column is not supported)
CircSite also provides visualization for the binding scores of the nucleotides along the input sequence with three figures: the raw scores, scores after filtering, and scores after binary decision. All of them display the scores in a direct way.
