ISPRED-SEQ

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

Features

ISPRED-SEQ is a method for predicting the occurrence of Interaction Sites on a protein starting from its sequence.
The input sequence is firstly embedded using ProtTrans T5 and ESM-1v in order to produce a vectorial representation of 2304 features for each residue.
This entirely substitutes the need for traditionally hand-crafted features such as physico-chemical properties of the residues or sequence profiles derived from multiple sequence alignments.


Input

The required input is a protein sequence in FASTA format, of a length in the range of 50 to 5,000 residues.
The user may insert the FASTA in two different ways:


Output

There are three sections in the result page: