PSOPIA - Prediction Server of Protein-Protein Interactions

Home Page | Overview | Help page | Example results

- HELP -


Step 1: Enter a protein sequence pair(s) in the text box or upload a file containing the pair(s). The sequence(s) must be in FASTA format. When doing predictions for more than one sequence pair(maximum = 10 currently), each pair must be partitioned into each pair by a symbol of #.

Step 2: (Option) Please enter your email address, where your prediction results will be sent.

Step 3: Click 'submit' to submit your protein sequence(s) for prediction.



After your submission, a page reporting job ID(s) and the status of your job(s) will appear. This page will automatically refresh every 15 seconds and update the job status. As soon as the results become available, the job status will change to be available and will also be reported by a colourful folder icon . To access the results page, please click the folder icon. If you do not provide your email address to get the results by email, we encourage you to bookmark the web link of the results page so you are able to access it again at a later time.



On the results page, AODE scores (probabilties; 0~1.0) for a query protein pair are shown.

(1) Sseq is a score predicted using only information of sequence similarities to a known interacting protein pair.

(2) Sdom is a score predicted using only information of statistical propensities of domain-domain interactions.

(3) Snet is a score predicted using only information of a sum of edge weights along the shortest path between homologous proteins in a protein-protein interaction network.

(4) ALL is a score predicted using all the three features (1)~(3).

results page


The optimal threshold value of 0.995, which gave the highest F-measure (0.156) in the 10-fold CV (recall = 13.4%, precision = 18.8%, specificity = 99.7%, MCC =0.157), can be used for predicting whether submitted sequence pairs interact or not.



- References -

Yoichi Murakmai and Kenji Mizuguchi


© PSOPIA Copyright Bioinformatics Project, NIBIO