Tutorial of mRNAviewer webserver
To enhance the mRNA translation efficiency and support the potential of mRNA therapies, we have developed a deep learning model for mRNA sequence optimization. Different with other existing tools only optimizing codon of open reading frame (ORF), our model can further generate optimal 5′ untranslated region (UTR) and 3′ UTR, besides codon. User just need to input the amino acid sequence of the target protein and our model will output the complete optimized sequence including 5′ UTR, ORF, and 3′ UTR. What's more, our model has been validated with biological experiments that our model-optimized mRNA sequence has higher translation efficiency than that from conventional optimization approach. Consistently, with further analysis, our model-optimized mRNA sequence has more stable secondary structure and less miRNA binding sites. More details can be found in our work published in the "Briefings in Bioinformatics" journal.
Visit the web server by clicking the link at https://relab.xidian.edu.cn/mRNAviewer/ and you will see the page as shown in Fig. 1. The Microsoft Edge and Google Chrome browsers are recommended.
Click the Server button, and you can enter the query interface, as shown in Fig. 2.
Step 1: Input and Submit the amino acid sequence
You can directly enter or paste the amino acid sequence into the input box. all sequences should be in English letters. You can also use the clear button on the upper right to clear existing amino acid sequences. Then, you need to choose the location where the mRNA is expected to be translated. Finally, click the Submit button to get the website working. You can also see the detailed in Fig. 3.
Step 2: View results
When the button is gray, the site is being analyzed. When the button turns yellow, it indicates that the website has been analyzed. You can click the button to query the analysis results. Fig. 4 shows the different analysis states.
Soon, the complete output sequence and its statistics are displayed, as shown in Fig. 5. After a short wait, the secondary structure information of the sequence and the rest of the matching information are displayed, as shown in Fig. 6 and Fig. 7.