The job results are generally summarized in a webpage, the link of which is sent to the users after the job is completed (see an example of the MapPred output
). This page includes a detailed explanation on the data listed on the MapPred output page.
The input to MapPred can be either the sequence or MSA of the query protein. As shown in Figure 1, the MapPred works as follows.
(1) When the query sequence is given, the MSA of it will be generated by MSA generator. PSSM will be computed and two contact maps will be predicted using CCMpred and in-house DeepMSA based on the input or generated MSA.
(2) The secondary structure and relative solvent accessibility of the sequence will be predicted using PSIPRED and SOLVPRED, and are tranformed into 2D features by pairing.
(3) All above data are concatenated into 2D features and as input to in-house DeepMeta, the final contact map will be predicted using DeepMeta.
Figure 1. The flowchart of the MapPred algorithm.
Submit a job to MapPred
Figure 2. The submission page of MapPred.
Download the complete set of results
Figure 3. The tarball of the MapPred results.
View the predicted contact map
Figure 4. The predicted contact map.
View the generated MSA
Figure 5. The generated MSA.
How to cite MapPred?
Please cite the following article when you use the MapPred server:
Qi Wu, Zhenling Peng, Ivan, Qian, Jianyi Yang,Protein contact prediction using metagenome sequence data and residual neural networks, Bioinformatics, 36: 41-48 (2020).
Need more help?
If you have more questions or comments about the server, please email yangjy