Update to bio2bel v0.2.0 (#16)

* Update setup

* Fix flake8

* Update src/bio2bel_mirtarbase/manager.py

* Update constants.py

* Update constants.py

* Update iteration and tests

* Add tests for counting the human genes with Bio2BEL HGNC

* Create .readthedocs.yml

* Fix tests

* Bump version: 0.1.3-dev → 0.2.0

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.1.3-dev
+current_version = 0.2.0
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(?:-(?P<release>[0-9A-Za-z-]+(?:\.[0-9A-Za-z-]+)*))?(?:\+(?P<build>[0-9A-Za-z-]+(?:\.[0-9A-Za-z-]+)*))?

.readthedocs.yml

@@ -0,0 +1,8 @@
+# See: https://docs.readthedocs.io/en/latest/yaml-config.html
+build:
+    image: latest
+python:
+  version: 3.6
+  pip_install: true
+  extra_requirements:
+  - docs

.travis.yml

@@ -18,7 +18,6 @@ jobs:
     - env: TOXENV=flake8
     - env: TOXENV=pyroma
     - env: TOXENV=xenon
-    - env: TOXENV=vulture
     # docs stage
     - stage: docs
       env: TOXENV=doc8
@@ -31,7 +30,6 @@ jobs:
 matrix:
   allow_failures:
       - env: TOXENV=xenon
-      - env: TOXENV=vulture
 
 install:
     - sh -c 'if [ "$TOXENV" = "py" ]; then pip install tox codecov; else pip install tox; fi'

docs/source/conf.py

@@ -60,7 +60,7 @@
 # built documents.
 #
 # The full version, including alpha/beta/rc tags.
-release = '0.1.3-dev'
+release = '0.2.0'
 
 # The short X.Y version.
 parsed_version = re.match(

setup.py

@@ -18,13 +18,15 @@
     'Intended Audience :: Science/Research',
     'Operating System :: OS Independent',
     'Programming Language :: Python',
+    'Programming Language :: Python :: 3 :: Only',
     'Programming Language :: Python :: 3.6',
+    'Programming Language :: Python :: 3.7',
     'Topic :: Scientific/Engineering :: Bio-Informatics',
     'License :: OSI Approved :: MIT License',
 ]
 INSTALL_REQUIRES = [
-    'pybel>=0.12.1',
-    'bio2bel>=0.1.5',
+    'pybel>=0.12.0,<0.13.0',
+    'bio2bel>=0.2.0,<0.3.0',
     'bio2bel_hgnc>=0.1.0',
     'bio2bel_entrez>=0.1.0',
     'bio2bel_mirbase',
@@ -35,7 +37,18 @@
     'tqdm',
 ]
 EXTRAS_REQUIRE = {
-    'web': ['flask', 'flask_admin'],
+    'web': [
+        'flask',
+        'flask_admin',
+    ],
+    'docs': [
+        'flask',
+        'flask_admin',
+        'sphinx',
+        'sphinx-rtd-theme',
+        'sphinx-click',
+        'sphinx-autodoc-typehints',
+    ],
 }
 ENTRY_POINTS = {
     'bio2bel': [

src/bio2bel_mirtarbase/__init__.py

@@ -4,7 +4,7 @@
 
 from .manager import Manager  # noqa: F401
 
-__version__ = '0.1.3-dev'
+__version__ = '0.2.0'
 
 __title__ = 'bio2bel_mirtarbase'
 __description__ = "A package for converting miRTarBase to BEL"

src/bio2bel_mirtarbase/constants.py

@@ -6,7 +6,7 @@
 
 from bio2bel.utils import get_data_dir
 
-VERSION = '0.1.3-dev'
+VERSION = '0.2.0'
 
 MODULE_NAME = 'mirtarbase'
 DATA_DIR = get_data_dir(MODULE_NAME)

src/bio2bel_mirtarbase/manager.py

@@ -3,15 +3,14 @@
 """Manager for Bio2BEL miRTarBase."""
 
 import logging
+import time
 from typing import List, Mapping, Optional
 
-import bio2bel_entrez
-import bio2bel_mirbase
-import time
-from bio2bel_entrez.manager import VALID_ENTREZ_NAMESPACES
 from tqdm import tqdm
 
+import bio2bel_entrez
 import bio2bel_hgnc
+import bio2bel_mirbase
 from bio2bel import AbstractManager
 from bio2bel.manager.bel_manager import BELManagerMixin
 from bio2bel.manager.flask_manager import FlaskMixin
@@ -22,8 +21,14 @@
 from .models import Base, Evidence, Interaction, Mirna, Species, Target
 from .parser import get_data
 
+__all__ = [
+    'Manager',
+]
+
 log = logging.getLogger(__name__)
 
+VALID_ENTREZ_NAMESPACES = {'egid', 'eg', 'entrez', 'ncbigene'}
+
 
 def _build_entrez_map(hgnc_manager: bio2bel_hgnc.Manager) -> Mapping[str, HumanGene]:
     """Build a mapping from entrez gene identifiers to their database models from :py:mod:`bio2bel_hgnc.models`."""
@@ -266,14 +271,14 @@ def enrich_rnas(self, graph: BELGraph):
         log.debug('enriching inhibitors of RNA')
         count = 0
 
-        for node in graph:
+        for node in list(graph):
             if node[FUNCTION] != RNA:
                 continue
 
-            if NAMESPACE not in node:
+            namespace = node.get(NAMESPACE)
+            if namespace is None:
                 continue
 
-            namespace = node[NAMESPACE]
             identifier = node.get(IDENTIFIER)
             name = node.get(NAME)
 
@@ -292,7 +297,7 @@ def enrich_rnas(self, graph: BELGraph):
             for interaction in target.interactions:
                 for evidence in interaction.evidences:
                     count += 1
-                    evidence.add_to_graph(graph)
+                    evidence._add_to_graph(graph, evidence.interaction.mirna.as_bel(), node)
 
         log.debug('added %d MTIs', count)
 
@@ -334,6 +339,7 @@ def enrich_mirnas(self, graph: BELGraph):
         log.debug('added %d MTIs', count)
 
     def get_mirna_interaction_evidences(self):
+        """Get interaction evidences."""
         return self.session \
             .query(Mirna, Interaction, Evidence) \
             .join(Interaction) \

src/bio2bel_mirtarbase/models.py

@@ -8,6 +8,7 @@
 from sqlalchemy.ext.declarative import declarative_base
 from sqlalchemy.orm import relationship
 
+import pybel.dsl
 from pybel import BELGraph
 from pybel.dsl import mirna, rna
 from .constants import MODULE_NAME
@@ -16,11 +17,11 @@
 MIRBASE = 'mirbase'
 HGNC = 'hgnc'
 
-MIRNA_TABLE_NAME = '{}_mirna'.format(MODULE_NAME)
-TARGET_TABLE_NAME = '{}_target'.format(MODULE_NAME)
-SPECIES_TABLE_NAME = '{}_species'.format(MODULE_NAME)
-EVIDENCE_TABLE_NAME = '{}_evidence'.format(MODULE_NAME)
-INTERACTION_TABLE_NAME = '{}_interaction'.format(MODULE_NAME)
+MIRNA_TABLE_NAME = f'{MODULE_NAME}_mirna'
+TARGET_TABLE_NAME = f'{MODULE_NAME}_target'
+SPECIES_TABLE_NAME = f'{MODULE_NAME}_species'
+EVIDENCE_TABLE_NAME = f'{MODULE_NAME}_evidence'
+INTERACTION_TABLE_NAME = f'{MODULE_NAME}_interaction'
 
 # create base class
 Base = declarative_base()
@@ -42,7 +43,7 @@ def to_json(self, include_id: bool = True) -> Mapping:
         :param include_id: Include the database identifier?
         """
         rv = {
-            'name': str(self.name)
+            'name': str(self.name),
         }
 
         if include_id:
@@ -98,7 +99,7 @@ class Target(Base):
     hgnc_symbol = Column(String(32), nullable=True, unique=True, index=True, doc="HGNC gene symbol")
     hgnc_id = Column(String(32), nullable=True, unique=True, index=True, doc="HGNC gene identifier")
 
-    species_id = Column(Integer, ForeignKey('{}.id'.format(SPECIES_TABLE_NAME)), nullable=False, doc='The host species')
+    species_id = Column(Integer, ForeignKey(f'{SPECIES_TABLE_NAME}.id'), nullable=False, doc='The host species')
     species = relationship('Species')
 
     def __str__(self):  # noqa: D105
@@ -115,7 +116,7 @@ def serialize_to_entrez_node(self) -> rna:
     def serialize_to_hgnc_node(self) -> rna:
         """Serialize to PyBEL node data dictionary."""
         if self.hgnc_id is None:
-            raise ValueError('missing HGNC information for Entrez Gene {}'.format(self.entrez_id))
+            raise ValueError(f'missing HGNC information for Entrez Gene {self.entrez_id}')
 
         return rna(
             namespace=HGNC,
@@ -129,7 +130,7 @@ def to_json(self, include_id=True) -> Mapping:
             'species': self.species.to_json(),
             'identifiers': [
                 self.serialize_to_entrez_node(),
-                self.serialize_to_hgnc_node()
+                self.serialize_to_hgnc_node(),
             ]
         }
 
@@ -149,11 +150,11 @@ class Interaction(Base):
     mirtarbase_id = Column(String(64), nullable=False, unique=True, index=True,
                            doc="miRTarBase interaction identifier which is unique for a pair of miRNA and RNA targets")
 
-    mirna_id = Column(Integer, ForeignKey("{}.id".format(MIRNA_TABLE_NAME)), nullable=False, index=True,
+    mirna_id = Column(Integer, ForeignKey(f'{MIRNA_TABLE_NAME}.id'), nullable=False, index=True,
                       doc='The miRTarBase identifier of the interacting miRNA')
     mirna = relationship(Mirna, backref="interactions")
 
-    target_id = Column(Integer, ForeignKey("{}.id".format(TARGET_TABLE_NAME)), nullable=False, index=True,
+    target_id = Column(Integer, ForeignKey(f'{TARGET_TABLE_NAME}.id'), nullable=False, index=True,
                        doc='The Entrez gene identifier of the interacting RNA')
     target = relationship(Target, backref="interactions")
 
@@ -163,7 +164,7 @@ class Interaction(Base):
     )
 
     def __str__(self):  # noqa: D105
-        return '{} =| {}'.format(self.mirna.name, self.target.name)
+        return f'{self.mirna.name} =| {self.target.name}'
 
 
 class Evidence(Base):
@@ -179,7 +180,7 @@ class Evidence(Base):
                      doc="Type and strength of the miRNA - target interaction. E.g. 'Functional MTI (Weak)'")
     reference = Column(String(255), nullable=False, doc="Reference PubMed Identifier")
 
-    interaction_id = Column(Integer, ForeignKey("{}.id".format(INTERACTION_TABLE_NAME)),
+    interaction_id = Column(Integer, ForeignKey(f'{INTERACTION_TABLE_NAME}.id'),
                             doc='The interaction for which this evidence was captured')
     interaction = relationship(Interaction, backref="evidences")
 
@@ -188,14 +189,18 @@ def __str__(self):  # noqa: D105
 
     def add_to_graph(self, graph: BELGraph) -> str:
         """Add this edge to the BEL graph and return the ket for that edge."""
-        try:
-            target_node = self.interaction.target.serialize_to_hgnc_node()
-        except ValueError:
-            target_node = self.interaction.target.serialize_to_entrez_node()
+        return self._add_to_graph(
+            graph,
+            self.interaction.mirna.as_bel(),
+            self.interaction.target.serialize_to_entrez_node(),
+
+        )
 
+    def _add_to_graph(self, graph: BELGraph, source: pybel.dsl.MicroRna, target: pybel.dsl.Rna) -> str:
+        """Add this edge to the BEL graph and return the ket for that edge."""
         return graph.add_directly_decreases(
-            self.interaction.mirna.as_bel(),
-            target_node,
+            source,
+            target,
             evidence=str(self.support),
             citation=str(self.reference),
             annotations={

tests/constants.py

@@ -5,9 +5,8 @@
 import json
 import os
 
-import bio2bel_mirbase
-
 import bio2bel_hgnc
+import bio2bel_mirbase
 import bio2bel_mirtarbase
 from bio2bel.testing import AbstractTemporaryCacheClassMixin
 
@@ -25,21 +24,6 @@ class TemporaryFilledCacheMixin(AbstractTemporaryCacheClassMixin):
     hgnc_manager: bio2bel_hgnc.Manager
     mirbase_manager: bio2bel_mirbase.Manager
 
-    @classmethod
-    def setUpClass(cls):
-        """Create temporary file and populate database."""
-        super().setUpClass()
-
-        cls.hgnc_manager = bio2bel_hgnc.Manager(connection=cls.connection)
-        cls.hgnc_manager._create_tables()
-        json_data = cls.hgnc_manager.load_hgnc_json(hgnc_file_path=TEST_HGNC_JSON)
-        cls.hgnc_manager.insert_hgnc(hgnc_dict=json_data, silent=True, low_memory=False)
-
-        cls.mirbase_manager = bio2bel_mirbase.Manager(connection=cls.connection)
-        with open(TEST_MIRBASE_JSON) as file:
-            mirbase_list = json.load(file)
-            cls.mirbase_manager._populate_list(mirbase_list)
-
     @classmethod
     def populate(cls):
         """Fill the HGNC and mirTarBase databases.
@@ -58,4 +42,14 @@ def populate(cls):
         MIRT000006	hsa-miR-146a-5p	Homo sapiens	CXCR4	7852	Homo sapiens	Microarray	Functional MTI (Weak)	20375304
         MIRT000012	hsa-miR-122-5p	Homo sapiens	CYP7A1	1581	Homo sapiens	qRT-PCR//Luciferase reporter assay	Functional MTI	20351063
         """
+        cls.hgnc_manager = bio2bel_hgnc.Manager(connection=cls.connection)
+        cls.hgnc_manager._create_tables()
+        json_data = cls.hgnc_manager.load_hgnc_json(hgnc_file_path=TEST_HGNC_JSON)
+        cls.hgnc_manager.insert_hgnc(hgnc_dict=json_data, silent=True, low_memory=False)
+
+        cls.mirbase_manager = bio2bel_mirbase.Manager(connection=cls.connection)
+        with open(TEST_MIRBASE_JSON) as file:
+            mirbase_list = json.load(file)
+            cls.mirbase_manager._populate_definitions_helper(mirbase_list)
+
         cls.manager.populate(TEST_MIRTARBASE_EXCEL)