Datasets

File name Description Download
Training_data.tar.gz This file contains all training data of Arabidopsis-Pseudomonas syringae (Ara-Psy), Arabidopsis-Hpaloperonospora arabidopsis (Ara-Hpa), Arabidopsis-Golovinomyces orontii (Ara-Gor), and Arabidopsis-All pathogens (Ara-All_pathogens).
Independent_test_data.tar.gz This file contains all independent test data of Ara-Psy, Ara-Hpa, Ara-Gor, and Ara-All_pathogens.
Proteome_scanning_result.tar.gz This file contains all predicted PPIs of Ara-Psy, Ara-Hpa, Ara-Gor, and Ara-All_pathogens.
Arabidopsis_PPIs.txt This file contains all Arabidopsis PPIs.
Pathogen_sequences.tar.gz This file contains all pathogen protein sequences.
Arabidopsis_sequences.fasta This file contains all Arabidopsis protein sequences.

Software

InterSPPI_v1.3 (2017-12-01) Download for linux

Command Line Interface Overview

$ python intersppi.py -h
            USAGE
                python intersppi.py  [-i  [-d ] [-o ] [-h] [-v]
                Example: python intersppi.py -i example.fasta -t TAIR.id -d /home/pub/2014nr/nr -o test_result

            OPTIONAL ARGUMENTS
                -i    : the file name contains pathogen protein sequences in FASTA file format.
                -t    : the file name contains TAIR(https://www.arabidopsis.org/) ids of arabidopsis thaliana.
                -d    : the nr database.
                -o    : the file name of final prediction result.
                -h    : print USAGE, DESCRIPTION and ARGUMENTS messages.

            DESCRIPTION
               Name               : InterSPPI (Inter-species Protein-Protein Interaction)
               Version            : 1.0
               Update Time        : 2017-06-01

Dependencies

  • Python 2.7, 3.4 or newer
  • Scikit-learn 1.70
  • PSIBLAST 2.6 or newer
  • NR database

To install dependancies on Linux operating systems:

  1. Install python and pip:

    see https://www.python.org/

  2. Install Scikit-learn via pip:

    $ pip install -U scikit-learn

  3. Download the NR database

    NR database can be obtained from ftp://ftp.ncbi.nlm.nih.gov/blast/db/FASTA