push to keep safe before going back later

FlyBase · Oct 2, 2024 · 0c00313 · 0c00313
1 parent f496e26
commit 0c00313
Show file tree

Hide file tree

Showing 3 changed files with 22 additions and 11 deletions.
diff --git a/Load/drivers.py b/Load/drivers.py
@@ -65,11 +65,11 @@ def add_driver_data(cursor, org_dict, feature_id, cvterm_id, dbxref_id, pub_id,
             cursor.execute(feat_sql, (al_dbxref_id, org_id, al_name, unique_name, None, 0, cvterm_id['allele']))
             feature_id[al_name] = cursor.fetchone()[0]
             # add synonyms
-            cursor.execute(syn_sql, (feature_id[al_name], cvterm_id['symbol'], al_sym_name))
+            cursor.execute(syn_sql, (al_name, cvterm_id['symbol'], al_sym_name))
             syn_id = cursor.fetchone()[0]
             cursor.execute(fs_sql, (syn_id, feature_id[al_name], pub_id))
 
-            cursor.execute(syn_sql, (feature_id[al_name], cvterm_id['symbol'], al_sym_name[5:]))  # skip sp name
+            cursor.execute(syn_sql, (al_name, cvterm_id['symbol'], al_sym_name[5:]))  # skip sp name
             syn_id = cursor.fetchone()[0]
             cursor.execute(fs_sql, (syn_id, feature_id[al_name], pub_id))
             #  Scer\GAL4        | gene                            | FBgn0014445 | Scer         | alleleof
@@ -108,7 +108,7 @@ def add_driver_data(cursor, org_dict, feature_id, cvterm_id, dbxref_id, pub_id,
     ec_sql = """INSERT INTO expression_cvterm (expression_id, cvterm_id, cvterm_type_id) VALUES (%s, %s, %s)"""
     fr_sql = """INSERT INTO feature_relationship (subject_id, object_id, type_id) VALUES (%s, %s, %s) RETURNING feature_relationship_id"""
     frp_sql = """INSERT INTO feature_relationship_pub (feature_relationship_id, pub_id) VALUES (%s, %s)"""
-
+    fp_sql = """INSERT INTO feature_pub (feature_id, pub_id) VALUES (%s, %s)"""
     for i in range(4, 9):
         # Scer\\GAL4[DBD.hb1]INTERSECTIONHsap\\RELA[AD.pxn1]
         # Scer\GAL4<up>DBD.hb1</up>∩Hsap\RELA<up>AD.pxn1</up>
@@ -122,7 +122,8 @@ def add_driver_data(cursor, org_dict, feature_id, cvterm_id, dbxref_id, pub_id,
         cursor.execute(feat_sql, (co_dbxref_id, org_dict['Ssss'], co_name, unique_name,
                                   None, 0, cvterm_id['split system combination']))
         feature_id[co_name] = cursor.fetchone()[0]
-
+        # add feature pub
+        cursor.execute(fp_sql, (feature_id[co_name], feature_id[f'CO_paper_{i}']))
         # add synonym
         cursor.execute(syn_sql, (feature_id[co_name], cvterm_id['symbol'], co_syn))
         syn_id = cursor.fetchone()[0]
@@ -159,8 +160,11 @@ def add_driver_data(cursor, org_dict, feature_id, cvterm_id, dbxref_id, pub_id,
 
         cursor.execute(fr_sql, (feature_id[co_name], feature_id[f'Scer\\GAL4[DBD.hb{i}]'], cvterm_id['partially_produced_by']))
         fr_id = cursor.fetchone()[0]
+        cursor.execute(fp_sql, (feature_id[f'Scer\\GAL4[DBD.hb{i}]'], feature_id[f'CO_paper_{i}']))
+
         cursor.execute(frp_sql, (fr_id, feature_id[f'CO_paper_{i}']))
         cursor.execute(fr_sql, (feature_id[co_name], feature_id[f'Hsap\RELA[AD.pxn{i}]'], cvterm_id['partially_produced_by']))
         fr_id = cursor.fetchone()[0]
+        cursor.execute(fp_sql, (feature_id[f'Hsap\RELA[AD.pxn{i}]'], feature_id[f'CO_paper_{i}']))
         cursor.execute(frp_sql, (fr_id, feature_id[f'CO_paper_{i}']))
 
diff --git a/add-test_data.py b/add-test_data.py
@@ -117,6 +117,7 @@ def load_cv_cvterm(parsed_yaml):
     START = 0
     NEW_DB = 1
     FORMAT = 2
+    print_debug = {"FlyBase anatomy CV": 1}
     specific_dbs = {'SO':                       (0, 'SO', '{:07d}'),
                     'molecular_function':       (1000, 'GO', '{:07d}'),
                     'cellular_component':       (2000, 'GO', '{:07d}'),
@@ -141,9 +142,10 @@ def load_cv_cvterm(parsed_yaml):
 
         cursor.execute(cv_sql, (cv_name,))
         cv_id[cv_name] = cursor.fetchone()[0]
-
-        print("adding cv {} [{}] and db [{}]".format(cv_name, cv_id[cv_name], db_id[cv_name]))
+        if cv_name in print_debug:
+            print("adding cv {} [{}] and db [{}]".format(cv_name, cv_id[cv_name], db_id[cv_name]))
         # for specific cvterm we want to unique numbers as dbxrefs.
+        count = 0
         if cv_name in specific_dbs:
             count = specific_dbs[cv_name][START]
         for cvterm_name in cv_cvterm[cv_name]:
@@ -167,7 +169,9 @@ def load_cv_cvterm(parsed_yaml):
             cursor.execute(cvterm_sql, (dbxref_id[cvterm_name], cv_id[cv_name], cvterm_name))
             cvterm_id[cvterm_name] = cursor.fetchone()[0]
             cv_cvterm_id[cv_name][cvterm_name] = cvterm_id[cvterm_name]
-            print("\t{} cvterm [{}] and dbxref [{}]".format(cvterm_name, cvterm_id[cvterm_name], dbxref_id[cvterm_name]))
+            if cv_name in print_debug:
+                print(f"\t{cvterm_name} cvterm [{cvterm_id[cvterm_name]}], {cv_name} cv [{cv_id[cv_name]}] and dbxref [{dbxref_id[cvterm_name]}]")
+    # exit(-1)
     add_cvterm_namespace(cv_cvterm_id)
 
 
@@ -301,7 +305,7 @@ def load_pub_author_pubprop(parsed_yaml):
 cvprop_sql = """ INSERT INTO cvtermprop (cvterm_id, type_id, value) VALUES (%s, %s, %s) """
 
 conn.commit()
-count = cursor.rowcount
+# count = cursor.rowcount
 
 ###################
 # create chromosome

diff --git a/data/cv_cvterm.yaml b/data/cv_cvterm.yaml
@@ -21,6 +21,8 @@ FlyBase anatomy CV: ['embryo','dopaminergic PAM neuron 1', 'dopaminergic PAM neu
                      'increased number']
 ####### End of order matters cv/cvterms
 
+anonymous: ['affectedby']
+
 cell_line_cvtermprop type: ['basis']
 cell_lineprop type: ['internalnotes', 'lab_of_origin', 'comment', 'source_genotype',
                      'source_strain', 'source_cross', 'karyotype']
@@ -40,7 +42,8 @@ feature_cvtermprop type: [
 feature_expression property type: ['curated_as', 'comment']
 feature_pubprop type: ['abstract_languages']
 feature_relationshipprop type: ['fly_disease-implication_change', 'comment', 'relative_position', 'score',
-                                'start_location', 'end_location', 'is_subset_expression', 'is_relative_wildtype']
+                                'start_location', 'end_location', 'is_subset_expression', 'is_relative_wildtype',
+                                'control_comment']
 
 FlyBase: ['FlyBase analysis']
 FlyBase_internal: ['pubprop type:curated_by']
@@ -114,7 +117,7 @@ property type: [
     'propagate_transgenic_uses', 'protein_coding_gene', 'protocol', 'reported_antibod_gen',
     'significant_subject_in_review', 'source_prep', 'stage', 'strain', 'strain_type', 'sub_datatype', 'taxgroup', 'wild_type_role',
     'curated_chromosomal_location', 'curated_cytological_location', 'flanking_type', 'first_base_of_target',
-    'problem', 'first_base_of_unique_in_natTE']
+    'problem', 'first_base_of_unique_in_natTE', 'is_multiple_insertion_line', 'chromosomal_orientation']
 
 pub type: [
     'computer file', 'unattributed', 'unspecified', 'personal communication to FlyBase',
@@ -143,7 +146,7 @@ relationship type: [
     'overlap_inferred', 'partially_produced_by', 'parent_grp', 'part_deletes', 'part_duplicates', 'partof',
     'primer_progenitor_of', 'producedby', 'progenitor', 'replacement_descendant_of', 'representative_isoform',
     'recom_right_end', 'recom_left_end', 'related_tool', 'segregant_of', 'tagged_with', 'undefined_grp',
-    'transposed_descendant_of', 'recombinant_descendant_of', 'modified_descendant_of']
+    'transposed_descendant_of', 'recombinant_descendant_of', 'modified_descendant_of', 'affectedby']
 
 selected_anatomy: [
     'unassigned_class', 'selected_anatomy', 'unassigned_anatomy', 'selected_class',