Merge branch 'pr264'

pypath/inputs/lncdisease.py

@@ -21,6 +21,7 @@
 
 import pypath.resources.urls as urls
 import pypath.share.curl as curl
+import pypath.utils.taxonomy as taxonomy
 
 
 def lncdisease_interactions():
@@ -53,7 +54,7 @@ def lncdisease_interactions():
                 source_type = l[3].split('-')[0],
                 target_type = l[3].split('-')[1] if '-' in l[3] else '',
                 mechanism = l[4].lower(),
-                organism = l[6].lower(),
+                organism = taxonomy.ensure_ncbi_tax_id(l[6]),
                 pmid = l[9],
             )
         )

pypath/inputs/lncrnadb.py

@@ -24,6 +24,7 @@
 
 import pypath.resources.urls as urls
 import pypath.share.curl as curl
+import pypath.utils.taxonomy as taxonomy
 
 
 def lncrnadb_interactions():
@@ -73,7 +74,7 @@ def lncrnadb_interactions():
                         lncrna = lncrna,
                         partner = partner,
                         type = typ,
-                        organism = organism,
+                        organism = taxonomy.ensure_ncbi_tax_id(organism),
                         pmid = pmid,
                     )
                 )

pypath/inputs/mirecords.py

@@ -22,6 +22,7 @@
 import pypath.resources.urls as urls
 import pypath.share.curl as curl
 import pypath.inputs.common as inputs_common
+import pypath.utils.taxonomy as taxonomy
 
 
 def mirecords_interactions():
@@ -54,8 +55,8 @@ def mirecords_interactions():
             mirna_name = l[6],
             target_refseq = l[3],
             target_genesymbol = l[2],
-            mirna_organism = l[1],
-            target_organism = l[5],
+            mirna_organism = taxonomy.ensure_ncbi_tax_id(l[1]),
+            target_organism = taxonomy.ensure_ncbi_tax_id(l[5]),
             pmid = l[0].split('.')[0],
         )
         for l in

pypath/inputs/mirtarbase.py

@@ -24,6 +24,7 @@
 import pypath.resources.urls as urls
 import pypath.share.curl as curl
 import pypath.inputs.common as inputs_common
+import pypath.utils.taxonomy as taxonomy
 
 
 def mirtarbase_interactions(curated = True, strong = True, all = False):
@@ -82,10 +83,13 @@ def _mirtarbase_interactions(dataset):
 
     return [
         MirtarbaseInteraction(
-            *l[:6],
+            *l[:2],
+            taxonomy.ensure_ncbi_tax_id(l[2]),
+            *l[3:5],
+            taxonomy.ensure_ncbi_tax_id(l[5]),
             l[6] if dataset == 'curated' else None,
             *l[-3:],
-            dataset
+            dataset,
         )
         for l in tbl[1:]
     ]

pypath/inputs/trrust.py

@@ -23,8 +23,8 @@
 
 from pypath.share import curl
 from pypath.resources.urls import urls
-from pypath.utils import taxonomy
 from pypath.share import session
+from pypath.utils import taxonomy
 
 _log = session.Logger(name = 'trrust_input')._log
 
@@ -39,14 +39,14 @@ def trrust_interactions(
 
     Args:
         organism:
-            Either "human" or "mouse".
+            Name or NCBI Taxonomy ID of the organism. Human and mouse
+            are available in TRRUST.
     """
 
     organisms = {'human', 'mouse'}
+    _organism = taxonomy.ensure_common_name(organism, lower = True)
 
-    organism_ = taxonomy.ensure_common_name(organism, lower = True)
-
-    if organism not in organisms:
+    if _organism not in organisms:
 
         err = f'Only human and mouse are availble in TRRUST, not `{organism}`.'
         _log(err)
@@ -67,7 +67,7 @@ def __new__(cls, line):
             return super().__new__(cls, *line[:-1], refs)
 
 
-    url = urls['trrust']['tsv_url'] % organism_
+    url = urls['trrust']['tsv_url'] % _organism
 
     c = curl.Curl(
         url,
@@ -86,6 +86,7 @@ def trrust_human():
 
     return trrust_interactions('human')
 
+
 def trrust_mouse():
 
     return trrust_interactions('mouse')

pypath/resources/data_formats.py

@@ -27,7 +27,6 @@
 import pypath.resources.urls as urls
 import pypath.share.common as common
 import pypath.share.constants as constants
-import pypath.utils.taxonomy as taxonomy
 
 
 __all__ = [
@@ -2658,16 +2657,9 @@ def _pathwaycommons_single_resource(resource, transcription = False):
         is_directed = True,
         sign = False,
         ncbi_tax_id = {
-            'A': {
-                'col': 3,
-                'dict': taxonomy.latin_name_to_ncbi_tax_id,
-                'include': {9606},
-            },
-            'B': {
-                'col': 4,
-                'dict': taxonomy.latin_name_to_ncbi_tax_id,
-                'include': {9606},
-            }},
+            'A': {'col': 3, 'include': {9606}},
+            'B': {'col': 4, 'include': {9606}},
+        },
         input = 'mirecords.mirecords_interactions',
         interaction_type = 'post_transcriptional',
         references = 5,
@@ -2689,16 +2681,8 @@ def _pathwaycommons_single_resource(resource, transcription = False):
         is_directed = True,
         sign = False,
         ncbi_tax_id = {
-            'A': {
-                'col': 2,
-                'dict': taxonomy.latin_name_to_ncbi_tax_id,
-                'include': {9606},
-            },
-            'B': {
-                'col': 5,
-                'dict': taxonomy.latin_name_to_ncbi_tax_id,
-                'include': {9606},
-            },
+            'A': {'col': 2, 'include': {9606}},
+            'B': {'col': 5, 'include': {9606}},
         },
         positive_filters = [(8, 'Functional MTI')],
         input = 'mirtarbase.mirtarbase_interactions',
@@ -2854,11 +2838,7 @@ def _pathwaycommons_single_resource(resource, transcription = False):
         entity_type_b = 'protein',
         is_directed = True,
         sign = False,
-        ncbi_tax_id= {
-                'col': 5,
-                'dict': common.swap_dict(taxonomy.taxids),
-                'include': set([9606])
-            },
+        ncbi_tax_id = {'col': 5, 'include': {9606}},
         positive_filters = [(2, 'RNA'), (3, 'Protein')],
         input = 'lncdisease.lncdisease_interactions',
         interaction_type = 'lncrna_post_transcriptional',
@@ -2882,11 +2862,7 @@ def _pathwaycommons_single_resource(resource, transcription = False):
         entity_type_b = 'protein',
         is_directed = True,
         sign = False,
-        ncbi_tax_id= {
-                'col': 3,
-                'dict': common.swap_dict(taxonomy.phosphoelm_taxids),
-                'include': set([9606])
-            },
+        ncbi_tax_id = {'col': 3, 'include': {9606}},
         positive_filters = [(2, 'protein')],
         input = 'lncrnadb.lncrnadb_interactions',
         interaction_type = 'lncrna_post_transcriptional',

pypath/utils/taxonomy.py

@@ -524,7 +524,8 @@ def init_db(key):
 
     if swap:
 
-        this_db = common.swap_dict_simple(this_db)
+        this_db = common.swap_dict(this_db)
+        this_db = {k: min(v, key = len) for k, v in this_db.items()}
 
     else: