#!/usr/bin/env python

# Dénes Türei Uniklinik RWTH Aachen & EMBL Heidelberg 2018
# turei.denes@gmail.com

# how to load non-human interaction data directly in pypath
# note: for mammalians the recommended method is to
# translate from human network by orthology
# as most of the data is available for human

import pypath

# first we need to set the `ncbi_tax_id` parameter
# of the PyPath instance to 10090
pa = pypath.PyPath(ncbi_tax_id = 10090)

# all network inputs in pypath are defined by
# `ReadSettings` objects
# many predefined input settings reside in various
# dicts in `data_formats`
# to load mouse data from Signor we need to set the
# parameter below; this will result the reader to
# check column #13 in original Signor data and load
# only those with values `10090` or `10090;10090` in
# this column, and also to consider these having a
# taxon ID `10090` (values in the dict; this determines
# ID translation later)
# these settings are specific for individual resources
# one need to check the output of the corresponding
# `pypath.dataio` method to find out the values;
# find the methods under the `inFile` attribute of the
# `ReadSettings` object, e.g.
# `pypath.data_formats.pathway['signor'].inFile`
# ok, this is misleading because it's not a file but
# a function, but in theory it could be also a file name
# or URL
pypath.data_formats.pathway['signor'].ncbiTaxId = {
    'col': 12,
    'dict': {
        '10090': 10090,
        '10090;10090': 10090
    }
}

# these `reference lists` are used to make sure all entities
# have their type and taxon correctly identified
# for example this is simply a list of all mouse UniProts
# if you want only SwissProts add `swissprot = True`
pa.reflists[('uniprot', 'protein', 10090)] = (
    pypath.reflists.ReferenceList('uniprot', 'protein', 10090, 'all_uniprots')
)
pa.reflists[('uniprot', 'protein', 10090)].load()

# in order to get any mouse interaction from Signor
# we need to pass `organism = 10090` to
# `dataio.signor_interactions()`
# this is redundant and undocumented, sorry about that
# will improve later
pypath.data_formats.pathway['signor'].inputArgs['organism'] = 10090

# after setting all these it is possible to load mouse interactions
# as they are defined in Signor
pa.init_network({'singor': pypath.data_formats.pathway['signor']})
# output:
# > 355 interactions between 373 nodes
# from 1 resources have been loaded
#
# this network is much smaller than human
# in my opinion is better to have more complete data
# translated from human