PPI-Detect

The prediction of the likelihood of protein-protein interactions (PPI) is a challenging task, especially if amino acid sequences are the only information available. We use a novel procedure for general-purpose numerical encoding of polypeptides, which transforms pairs of amino acid sequences into a machine-learning-friendly vector, whose elements represent numerical descriptors of groups of residues in the proteins. PPI-Detect is a Support-Vector-Machine model for predicting protein-protein and protein-peptide interactions.

How to cite PPI-Detect:

S. Romero‐Molina, Y. B. Ruiz‐Blanco, M. Harms, J. Münch, E. Sanchez‐Garcia. PPI‐Detect: A support vector machine model for sequence‐based prediction of protein–protein interactions J. Comput. Chem. 2019, 1‐10. DOI: 10.1002/jcc.25780

Search job

Fill the form and then the job will be listed bellow.

Select	Job No	Name	Email	Status	Submission date

stop selected

OUTPUT

#	Instance	Prediction	Score	AD 1st-99th	AD 100th

AD 1st & 99th: Applicability domain (one or more descriptors values are outside the range defined by the 1st and the 99th percentiles of the training data).
AD 100th: Extended applicability domain (one or more descriptors values are outside the range of the training data for the model).

Note: Predictions outside the AD 100th are not reliable. The authors encourage to limit the predictions to only those within the AD 1st & 99th.