Reactome v71

CHANGELOG.md

@@ -2,9 +2,85 @@
 
 ## Unreleased changes
 
+
+
+
+
+## Reactome v71
+
+#### Summary for Reactome v71 pathways that are not inferred
+##### Pathways
+
+|count| description
+|-----|------------
+|2,492| total pathways
+|  508| is in disease
+|   32| top-level pathway
+
+##### 999 (40.09%) pathways have figures
+
+|count| description
+|-----|------------
+|  999| generated figure or hand-drawn figurehttps://t.co/7xByA9uKKa?amp=1
+|  826| generated figure
+|  173| hand-drawn figure
+
+##### 2,302 pathways (92.38%) have a publication:
+
+```
+Publications summary key:
+  P -> PubMed ID
+  B -> Book
+  U -> URL
+```
+
+| count | publication keys
+|-------|-----------------
+| 2,191 | P..
+|    67 | PB.
+|    34 | .B.
+|     7 | P.U
+|     2 | ..U
+|     1 | PBU
+
+
+#### Added:
+  * One species: Clostridium perfringens (cpe, taxid=1502)
+
+#### Changed
+  * Number instances increased for relationships involving PhysicalEntity and Event except:
+    * Small decrease for:
+      * (PhysicalEntity)-[repeatedUnit]->(PhysicalEntity)
+    * No change for:
+      * (PhysicalEntity)-[entityOnOtherCell]->(PhysicalEntity)
+      * (Event)-[reverseReaction]->(Event)
+      * (Event)-[entityOnOtherCell]->(PhysicalEntity)
+  * (Person):
+    * Added about 4,000 more people (Person)
+    * Removed *BA Brown-Kipphut* and *MD Maines*
+  * (Figure):
+    * Number of figures reduced to 785 from 808
+    * Removed figure author, *Marcela Tello-Ruiz*
+    * Seven more pathways have figures
+  * (Summation):
+    * Added ~50 Pathway Summations
+  * Diseases: Added 47 and removed 4
+  * Node instances that were reduced:
+
+|Node name             |    from | to
+|----------------------|---------|------
+|GO_CellularComponent  |     338 | 304
+|Depolymerisation      |      38 | 31
+|OtherEntity           |     334 | 330
+|Polymer               |   1,518 | 1,507
+|GenomeEncodedEntity   |   6,909 | 5,915
+|ReferenceDNASequence  | 533,570 | 475,150
+|OtherEntity           |     334 | 330
+|TopLevelPathway       |     389 | 374
+
 ## Reactome v69
 
-### Release 2019-NN-NN 0.9.5
+### Release 2019-07-29 v69.00
 
 #### Added:
   * New relationships:
@@ -28,4 +104,4 @@
     * ***negativelyRegulate***
 
 
-Copyright (C) 2018-2019, DV Klopfenstein. All rights reserved.
+Copyright (C) 2018-present, DV Klopfenstein. All rights reserved.

README.md

@@ -7,7 +7,9 @@
 [![Anaconda-Server Badge](https://anaconda.org/dvklopfenstein/reactomepy/badges/platforms.svg)](https://anaconda.org/dvklopfenstein/reactomepy)
 [![Anaconda-Server Badge](https://anaconda.org/dvklopfenstein/reactomepy/badges/installer/conda.svg)](https://conda.anaconda.org/dvklopfenstein)
 
-Explore biomolecular pathways in Reactome from the command-line or a Python script.    
+Explore biomolecular pathways in the Reactome graph database from the command-line or a Python script.    
+
+## Reactome
 
 In addition to biomolecular pathways,
 Reactome contains 
@@ -75,4 +77,4 @@ _Zenodo_ | (2019) | DOI: 10.5281/zenodo.2634376
 }
 ```
 
-Copyright (C) 2018-2019, DV Klopfenstein. All rights reserved.
+Copyright (C) 2018-present, DV Klopfenstein. All rights reserved.

src/reactomepy/code/node/blackboxevent.py

@@ -53,10 +53,14 @@ class BlackBoxEvent(ReactionLikeEvent):
                                  'GenomeEncodedEntity', 'EntityWithAccessionedSequence',
                                  'Complex', 'SimpleEntity', 'OtherEntity', 'Polymer']),
             'precedingEvent': frozenset(['Polymerisation', 'Pathway', 'BlackBoxEvent', 'Reaction']),
-            # 'regulatedBy': frozenset(['Regulation']),
-            'regulatedBy': frozenset(['NegativeRegulation', 'PositiveGeneExpressionRegulation',
-                                      'Requirement',
-                                      'PositiveRegulation', 'NegativeGeneExpressionRegulation']),
+            'regulatedBy': frozenset(['Regulation']),
+            # 'regulatedBy': frozenset([
+            #     'PositiveRegulation',               # <- regulatedBy <- [4]
+            #     'NegativeRegulation',               # <- regulatedBy <- [4]
+            #     'PositiveGeneExpressionRegulation', # <- regulatedBy <- [1]
+            #     'NegativeGeneExpressionRegulation', # <- regulatedBy <- [2]
+            #     'Requirement',
+            # ]),
         }
     }
 

src/reactomepy/code/node/catalystactivity.py

@@ -26,12 +26,12 @@ class CatalystActivity(DatabaseObject):
             'GenomeEncodedEntity', 'EntityWithAccessionedSequence',
             'Complex']),
         #'literatureReference': frozenset(['URL', 'Book', 'LiteratureReference']),
-        'literatureReference': frozenset(['LiteratureReference']),
+        'literatureReference': frozenset(['LiteratureReference', 'Book']),
         # 'physicalEntity': frozenset(['PhysicalEntity']),
         'physicalEntity': frozenset([
             'CandidateSet', 'DefinedSet',
             'GenomeEncodedEntity', 'EntityWithAccessionedSequence',
-            'Complex', 'OtherEntity', 'Polymer']),
+            'Complex', 'OtherEntity', 'Polymer', 'SimpleEntity']),
     }
 
     def __init__(self):

src/reactomepy/code/node/catalystactivityreference.py

@@ -23,7 +23,7 @@ class CatalystActivityReference(ControlReference):
         **ControlReference.relationships,
         **{
             'catalystActivity': frozenset(['CatalystActivity']),
-            'literatureReference': frozenset(['LiteratureReference']),
+            'literatureReference': frozenset(['LiteratureReference', 'Book']),
         },
     }
     #    'activity': frozenset(['GO_MolecularFunction']),

src/reactomepy/code/node/failedreaction.py

@@ -40,11 +40,11 @@ class FailedReaction(ReactionLikeEvent):
             # 'entityOnOtherCell': frozenset(['PhysicalEntity']),
             'entityOnOtherCell': frozenset(['EntityWithAccessionedSequence']),
             'input': frozenset([
+                'ChemicalDrug', 'ProteinDrug',
                 'CandidateSet', 'DefinedSet',
                 'GenomeEncodedEntity', 'EntityWithAccessionedSequence',
                 'SimpleEntity', 'Complex', 'OtherEntity', 'Polymer']),
             'precedingEvent': frozenset(['Reaction']),
-            # 'regulatedBy': frozenset(['Regulation']),
             'regulatedBy': frozenset(['NegativeRegulation', 'PositiveRegulation']),
         }
     }

src/reactomepy/code/node/negativegeneexpressionregulation.py

@@ -33,7 +33,7 @@
   5,262 Regulation    197 NegativeGeneExpressionRegulation    151    197  0.7665 stIdVersion
 """
 
-__copyright__ = "Copyright (C) 2018-2019, DV Klopfenstein. All rights reserved."
+__copyright__ = "Copyright (C) 2018-present, DV Klopfenstein. All rights reserved."
 __author__ = "DV Klopfenstein"
 
 from reactomepy.code.node.negativeregulation import NegativeRegulation
@@ -52,11 +52,16 @@ class NegativeGeneExpressionRegulation(NegativeRegulation):
             'regulator': frozenset(['CandidateSet', 'DefinedSet',
                                     'EntityWithAccessionedSequence',
                                     'Complex']),
+            'activeUnit': frozenset([
+                'EntityWithAccessionedSequence', 'DefinedSet', # <- activeUnit <- Regulation
+                'Complex',      # <- activeUnit <- [4] NegReg* PosReg*
+                'CandidateSet', # <- activeUnit <- [3] NegReg* PosReg
+            ]),
         }
     }
 
     def __init__(self):
         super(NegativeGeneExpressionRegulation, self).__init__('NegativeGeneExpressionRegulation')
 
 
-# Copyright (C) 2018-2019, DV Klopfenstein. All rights reserved.
+# Copyright (C) 2018-present, DV Klopfenstein. All rights reserved.

src/reactomepy/code/node/negativeregulation.py

@@ -52,7 +52,15 @@ class NegativeRegulation(Regulation):
             'regulator': frozenset(['CandidateSet', 'DefinedSet',
                                     'ChemicalDrug',
                                     'GenomeEncodedEntity', 'EntityWithAccessionedSequence',
-                                    'Complex', 'Polymer', 'SimpleEntity']),
+                                    'Complex', 'SimpleEntity']),
+            'activeUnit': frozenset([
+                'EntityWithAccessionedSequence', 'DefinedSet', # <- [5] activeUnit <- Regulation
+                'Complex',      # <- activeUnit <- [4] NegReg* PosReg*
+                'CandidateSet', # <- activeUnit <- [3] NegReg* PosReg
+                'SimpleEntity', # <- activeUnit <- [2] NegReg  PosReg
+                'ProteinDrug',  # <- activeUnit <- [1] self
+                'ChemicalDrug', # <- activeUnit <- [1] self
+            ]),
         }
     }
 

src/reactomepy/code/node/pathway.py

@@ -32,7 +32,7 @@
 from reactomepy.code.node.event import Event
 
 
-# pylint: disable=too-few-public-methods
+# pylint: disable=too-few-public-methods,line-too-long
 class Pathway(Event):
     """Params seen on all Physical Entities."""
 
@@ -51,7 +51,7 @@ class Pathway(Event):
             'figure': frozenset(['Figure']),
             'relatedSpecies': frozenset(['Species']),
             'crossReference': frozenset(['DatabaseIdentifier']),
-            'hasEvent': frozenset(['Pathway', 'TopLevelPathway',
+            'hasEvent': frozenset(['Pathway',
                                    'Reaction', 'FailedReaction', 'BlackBoxEvent',
                                    'Depolymerisation', 'Polymerisation']),
             'precedingEvent': frozenset(['Pathway', 'Reaction', 'BlackBoxEvent']),

src/reactomepy/code/node/polymerisation.py

@@ -42,7 +42,7 @@ class Polymerisation(ReactionLikeEvent):
             'output': frozenset(['CandidateSet', 'DefinedSet',
                                  'Complex', 'SimpleEntity', 'Polymer']),
             'precedingEvent': frozenset(['Polymerisation', 'BlackBoxEvent', 'Reaction']),
-            'regulatedBy' : frozenset(['PositiveRegulation']),
+            'regulatedBy' : frozenset(['PositiveRegulation', 'NegativeRegulation']),
         }
     }
 

src/reactomepy/code/node/positivegeneexpressionregulation.py

@@ -56,6 +56,11 @@ class PositiveGeneExpressionRegulation(PositiveRegulation):
                 'Complex',
                 'SimpleEntity',
             ]),
+            'activeUnit': frozenset([
+                'EntityWithAccessionedSequence', 'DefinedSet', # <- activeUnit <- Regulation
+                'Complex',      # <- activeUnit <- [4] NegReg* PosReg*
+                'CandidateSet', # <- activeUnit <- [3] NegReg* self
+            ]),
         }
     }
 

src/reactomepy/code/node/positiveregulation.py

@@ -60,6 +60,11 @@ class PositiveRegulation(Regulation):
                 'OtherEntity',
                 'SimpleEntity',
             ]),
+            'activeUnit': frozenset([
+                'EntityWithAccessionedSequence', 'DefinedSet', # <- activeUnit <- Regulation
+                'Complex',      # <- activeUnit <- [4] NegReg* PosReg*
+                'SimpleEntity', # <- activeUnit <- [2] NegReg  PosReg
+            ]),
         }
     }
 

src/reactomepy/code/node/reaction.py

@@ -65,11 +65,11 @@ class Reaction(ReactionLikeEvent):
                 'Pathway']),
             # 'regulatedBy': frozenset(['Regulation']),
             'regulatedBy': frozenset([
-                'PositiveRegulation',
+                'Requirement',                        # [2] <- regulatedBy
+                'NegativeRegulation',                 # [4] <- regulatedBy
+                'PositiveRegulation',                 # [4] <- regulatedBy
+                'NegativeGeneExpressionRegulation',   # [2] <- regulatedBy
                 #'PositiveGeneExpressionRegulation',
-                'Requirement',
-                'NegativeRegulation',
-                #'NegativeGeneExpressionRegulation']),
                 ]),
             # 'requiredInputComponent': frozenset(['PhysicalEntity']),
             'requiredInputComponent': frozenset([

src/reactomepy/code/node/regulation.py

@@ -48,11 +48,7 @@ class Regulation(DatabaseObject):
 
     relationships = {
         'literatureReference': frozenset(['LiteratureReference']),
-        #'regulator': frozenset(['PhysicalEntity']),
         'summation': frozenset(['Summation']),
-        'activeUnit': frozenset(['EntityWithAccessionedSequence', 'GenomeEncodedEntity',
-                                 'CandidateSet', 'DefinedSet',
-                                 'Complex', 'SimpleEntity']),
         'activity': frozenset(['GO_MolecularFunction']),
     }
 

src/reactomepy/code/node/regulationreference.py

@@ -7,7 +7,7 @@
   --- RegulationReference
 """
 
-__copyright__ = "Copyright (C) 2018-2019, DV Klopfenstein. All rights reserved."
+__copyright__ = "Copyright (C) 2018-present, DV Klopfenstein. All rights reserved."
 __author__ = "DV Klopfenstein"
 
 from reactomepy.code.node.controlreference import ControlReference
@@ -22,36 +22,20 @@ class RegulationReference(ControlReference):
     relationships = {
         **ControlReference.relationships,
         **{
-            #'regulation': 'Regulation',
             'regulation': frozenset([
                 'NegativeRegulation',
                 'NegativeGeneExpressionRegulation',
                 'PositiveRegulation',
                 'PositiveGeneExpressionRegulation',
                 'Requirement',
             ]),
-        #     'catalystActivity': frozenset(['CatalystActivity']),
-        #     'literatureReference': frozenset(['LiteratureReference']),
+            # 'catalystActivity': frozenset(['CatalystActivity']),
+            'literatureReference': frozenset(['LiteratureReference', 'Book']),
         },
     }
-    #relationships = {
-    #    'activity': frozenset(['GO_MolecularFunction']),
-
-    #    'activeUnit': frozenset([
-    #        'CandidateSet', 'DefinedSet',
-    #        'GenomeEncodedEntity', 'EntityWithAccessionedSequence',
-    #        'Complex']),
-    #    #'literatureReference': frozenset(['URL', 'Book', 'LiteratureReference']),
-    #    'literatureReference': frozenset(['LiteratureReference']),
-    #    # 'physicalEntity': frozenset(['PhysicalEntity']),
-    #    'physicalEntity': frozenset([
-    #        'CandidateSet', 'DefinedSet',
-    #        'GenomeEncodedEntity', 'EntityWithAccessionedSequence',
-    #        'Complex', 'OtherEntity', 'Polymer']),
-    #}
 
     def __init__(self):
         super(RegulationReference, self).__init__('RegulationReference')
 
 
-# Copyright (C) 2018-2019, DV Klopfenstein. All rights reserved.
+# Copyright (C) 2018-present, DV Klopfenstein. All rights reserved.

src/reactomepy/code/node/requirement.py

@@ -56,6 +56,7 @@ class Requirement(PositiveRegulation):
                                     'Complex',
                                     'SimpleEntity',
                                     ]),
+            'activeUnit': frozenset(['DefinedSet', 'EntityWithAccessionedSequence']),
         }
     }
 

src/reactomepy/code/wrpy/inferredfrom.py

@@ -3,7 +3,7 @@
 
 from __future__ import print_function
 
-__copyright__ = "Copyright (C) 2018-2019, DV Klopfenstein. All rights reserved."
+__copyright__ = "Copyright (C) 2018-present, DV Klopfenstein. All rights reserved."
 __author__ = "DV Klopfenstein"
 
 import os
@@ -22,6 +22,8 @@ class InferredFrom(object):
     """Print to Python all inferred Pathways and the Pathway that they are inferred from."""
 
     QUERY = 'MATCH (hi:Pathway)<-[inferredTo]-(lo:Pathway{speciesName:"Mus musculus"}) RETURN hi, lo'
+    # https://github.com/reactome/graph-core/issues/3
+    # QUERY = 'MATCH (hi:Pathway)<-[inferredTo]-(lo:Pathway) RETURN hi, lo'
 
     def __init__(self, gdbdr):
         self.gdbdr = gdbdr  # GraphDatabase.driver
@@ -64,15 +66,26 @@ def _init_dcts(self, fields_keep):
         """Determine pathways that are determined from another species."""
         org2plo2phi = cx.defaultdict(lambda: cx.defaultdict(set))
         tic = timeit.default_timer()
+        ctr_hi = cx.Counter()
+        ctr_lo = cx.Counter()
         with self.gdbdr.session() as session:
             res = session.run(self.QUERY)
             for rec in res.records():
-                assert rec['lo']['isInferred']
+                ctr_hi[rec['hi']['speciesName']] += 1
+                ctr_lo[rec['lo']['speciesName']] += 1
+                #       MATCH (hi:Pathway)<-[inferredTo]-(lo:Pathway) RETURN hi, lo
+                # isInferred:     True                       False
+                assert rec['hi']['isInferred'], rec
+                # https://github.com/reactome/graph-core/issues/3
+                # if not rec['hi']['isInferred']:
+                #     print(rec)
                 # if not rec['hi']['isInferred']:
                 # print(rec['hi'])
                 pidlo = rec['lo']['stId']
                 abc = pidlo.split('-')[1].lower()
                 org2plo2phi[abc][pidlo].add(rec['hi']['stId'])
+        print('HI', ctr_hi.most_common())
+        print('LO', ctr_lo.most_common())
         print('{N} species pathways are inferred from other species'.format(N=len(org2plo2phi)))
         print(sorted(org2plo2phi.keys()))
         self.chk_cnts(org2plo2phi)
@@ -93,4 +106,4 @@ def chk_cnts(self, org2plo2phi):
         print(ctr.most_common())
 
 
-# Copyright (C) 2018-2019, DV Klopfenstein. All rights reserved.
+# Copyright (C) 2018-present, DV Klopfenstein. All rights reserved.