adding additional documentation to the code

conekt/models/blast_db.py

@@ -11,7 +11,9 @@
 class BlastDB:
     @staticmethod
     def create_db():
-        # Raise an error if BLAST is not enabled
+        """
+        Creates a blast database using the settings specified in the app's configuration
+        """
         assert current_app.config['BLAST_ENABLED']
 
         TEMP_DIR = tempfile.mkdtemp()

conekt/models/clades.py

@@ -50,13 +50,18 @@ def add_clade(name, species, tree):
 
     @staticmethod
     def add_clades_from_json(data):
+        """
+        Adds a clade from a dict with clade details
+
+        :param data: dict with clade details
+        """
         for c, data in data.items():
             Clade.add_clade(c, data['species'], data['tree'])
 
     @staticmethod
     def update_clades():
         """
-        Loop over all families and determine what clade they belong too
+        Loop over all families and determine what clade they belong too. Results are stored in the database
         """
         clades = Clade.query.all()
         families = GeneFamily.query.all()
@@ -119,6 +124,11 @@ def update_clades_interpro():
 
     @property
     def newick_tree_species(self):
+        """
+        Returns a Newick tree with the species present in the current clade.
+
+        :return: Newick tree (string) with species for the current clade
+        """
         species = {s.code: s.name for s in Species.query.all()}
 
         tree = newick.loads(self.newick_tree)[0]

conekt/models/gene_families.py

@@ -245,6 +245,13 @@ def sequence_stats(sequence_ids):
 
     @staticmethod
     def sequence_stats_subquery(sequences):
+        """
+        Same as sequence_stats but takes a BaseQuery returning sequences as input (to avoid multiple times querying
+        sequences by ID)
+
+        :param sequences: BaseQuery returning sequences
+        :return: dict with for each InterPro domain linked with any of the input sequences stats
+        """
         subquery = sequences.subquery()
 
         data = SequenceFamilyAssociation.query.join(subquery, SequenceFamilyAssociation.sequence_id == subquery.c.id).all()
@@ -286,6 +293,13 @@ def family_stats(self):
 
     @staticmethod
     def __add_families(families, family_members):
+        """
+        Adds gene families to the database and assigs genes to their designated family
+
+        :param families:
+        :param family_members:
+        :return:
+        """
         for i, f in enumerate(families):
             db.session.add(f)