ISPRED-SEQ

A Deep-learning based method for the prediction of Interaction Sites starting from protein sequence

Job submission

From the Home page of the ISPRED-SEQ website, the user can submit one input protein sequence in FASTA format to the predictor by copying the text in the panel and pressing the button "Submit".

In order to submit a job, you must specify an ID line starting with a '>' character, followed by the protein sequence, that can have between 50 and 5000 residues. The server accepts single letter codes for standard residues (ARNDCQEGHILKMFPSTWYV) and non-standard selenocysteine (U). Ambiguity codes X (all residues), B (asparagine or aspartic acid) and Z (glutamine or glutamic acid) are also accepted. If any problem is found in your input, the box turns red and it indicates what has to be changed. When the box becomes green everything is correct and you can press the button "Submit".

A test sequence is available and can be uploaded by clicking the button "Load example FASTA".

Once you submit a query, you will be redirected to a new page. This means that your job has been accepted and you need to wait for the results. This page automatically refreshes every 60 seconds and it displays the status of your job (either queued or running).

In the meantime, you can bookmark the page (the results will be available at the same URL once they are ready) and/or save the Universally Unique IDentifier of your job using the "Copy" button.

You can then use the UUID from the Results page to search for your job for at least a month after the submission.

Reading the results

Once the results are ready, they are made available to the result page that consists of three sections:

  • Job information
  • On the top of the page, general data about the job are displayed, including the UUID, the date of submission and completion, the protein ID, the protein length and the total number of predicted interaction sites.

  • Feature Viewer
  • Right after, you can visualize the results with neXtProt feature viewer. The first line displays the residues of the sequence; the second and third lines show the output of ISPRED-SEQ, that is the prediction of PPI sites and the corresponding probability (real values between 0 and 1).

    If you hover the mouse over the graphs, the position of the residue will be shown. If you select a rectangular area, you can zoom on a part of the sequence. You can always click the right mouse button on the graph to reset the zoom back to normal. Alternatively, you can make use of the buttons on the top-right of the viewer to zoom-in, zoom-out, move along the sequence or take a screenshot of the selected area.

  • Table of predictions
  • At the bottom of the screen, the prediction results are reported in a table. On the left , a number of filters are available to select and combine table entries. On the top-right of the table, the button "Download TSV" allows to download data in a Tab-Separated-Value format file, that reports an additional column on the left containing the protein ID in case you want to combine multiple files together. Note that if you applied any filters, you will only download the current selection.