Sequence-Based CPI Predictor
Paired Compound-Protein Interaction
This file contains 831617 paired compound-protein interactions downloaded from ChEMBL.

Unpaired Compound-Protein Interaction
This file contains 831617 randomly generated unpaired compound-protein interactions.

Human Proteome Sequence
This file contains 20204 human proteome sequences downloaded from UniProt database.

Human Proteome Feature
This file contains molecular fingerprints of 20204 human proteome sequences.

RF Model File (Windows)
This file is a trained model of Random Forest (RF) and is required for sequence-based CPI prediction.

RF Model File (Linux)
This file is a trained model of Random Forest (RF) and is required for sequence-based CPI prediction.

Source Code
This file is python code for sequence-based CPI prediction.

Sequence-Based CPI Predictor