Protein Contact Map Prediction


RaptorX-Contact is a web server that predicts contact map of a protein sequence without using any template information. It applies an ultra-deep learning model to predict contacts and works particularly well on proteins without many sequence homologs. Our deep learning method has a very high accuracy by integrating a variety of information including sequence conservation, residue co-evolution and contact occurrence patterns. This server also predicts the tertiary structure of the input sequence by feeding the predicted contacts into CNS as distance restraints, but without using any templates. RaptorX-Contact was ranked 1st in contact prediction in terms of the total F1 score in the worldwide protein structure prediction (CASP) competition round XII. See here for a ranking list of all the CASP12 contact predictors on 38 CASP12 free-modeling targets. Ranking may be slightly changed depending on performance metrics.


Job Identification
: :

Sequence for Prediction      (example)
:

: Do not build 3D models using predicted contacts

Current server load
751 jobs pending
105 jobs done in the last 24 hours
6694 jobs done in the last 30 days

#server users: 35344
#processed jobs: 214842

Job policy
To maximize the utility of the server to the community at large the following limits on job submission for each user are enforced.
  • Please submit up to 50 protein sequences (in the FASTA format) in a batch for prediction. If your email box cannot receive a large attachment file, please submit a SMALL number of sequences in a batch. Otherwise the result package may be too big to be received.
  • Please SAVE the assigned JobID for retrieval of job results, especially when an email address is not provided in submission.
  • Each user can have no more than 500 sequences pending prediction at any time.
  • Should you have a special project that requires more resources, please contact us to inquire further.