**Sequence-based Protein-Peptide binding residue Prediction using genetic programming and ensemble learning. **\
Please cite the relevant publication if You will use this work.
**Citation: ** S. Shafiee, A. Fathi and G. Taherzadeh, SPPPred: Sequence-based Protein-Peptide binding residue Prediction using genetic programming and ensemble learning, IEEE transaction computational biology and bioinformatics.
-Protein-peptide dataset are stored in Dataset.zip.Dataset file contains:
-Data.Set.py
-
Test.Set.txt
-
Train.Set.txt
-
Test.Labels.txt
-
Train.Labels.txt
-There are three lines for each sample that include seq label, the chain sequence, and the enriched binding annotation: 0=non-binding,1=binding, respectively.
-There are two files that contain labels for Test.Set and Train. Set.
• SPPPred_model.py • Convert_new_data_to_csv.py • Classification2_independent_data2.py • Classification2_ data2.py • arch2_data2.py
Run in Linux: python SPPPred_model.py for peptide binding residues prediction.
SPPPred_model.py is the main file.
Provide all above files in one folder and run the SPPPred_mode.py file.
For further details or questions, it is possible to communicate through email (shafiee.shima@razi.ac.ir)