Connecting GraphQL to MariaDB

README.md

@@ -137,8 +137,9 @@ then run
 1. ``CREATE USER 'username'@'localhost' IDENTIFIED BY 'password';``
 2. ``GRANT ALL PRIVILEGES ON *.* TO 'username'@'localhost' WITH GRANT OPTION;``
 3. ``flush privileges;``
-
 More information https://dev.mysql.com/doc/refman/5.5/en/adding-users.html
+4. Set environment variable BIOM_MASS that holds user's password
+   ``export BIOM_MASS="password"``
 
 load_local_database.py script needs mysql.connect module.
 

dbqueries.py

@@ -0,0 +1,83 @@
+#  This file holds all queries run in database.py
+
+
+
+all_counts_query='''select count(id) as total from project
+                    union all select count(id) as total from participant
+                    union all select count(id) as total from sample
+                    union all select count(distinct data_format) as total from file_sample
+                    union all select count(id) as total from file_sample where  type="rawFiles"
+                    union all select count(id) as total from file_sample where type="processedFiles"'''
+projects_query="select id from project"
+version_query="select * from version order by updated desc limit 1"
+files_query="select id from file_sample"
+cases_query="select id from participant"
+files_size_query="select sum(file_size) as sum_size from  file_sample"
+files_total_query="select count(id) as total from file_sample"
+cases_total_query="select count(distinct id) as total from participant"
+
+def project_query(p_id):
+    return "select * from project where  id =" + str(p_id)
+
+def project_counts_query(p_id):
+    query="select count(id) as total from  file_sample where project='"+p_id+"'"
+    query=query+" union all "
+    query=query+"select count(distinct participant) as total from file_sample where project='"+p_id+"'"
+    query=query+" union all "
+    query=query+"select sum(file_size) as total from file_sample where project='"+p_id+"'"
+    return query
+
+def data_cat_query(table, p_id):
+    return "select distinct data_category from file_sample where "+ table+"='" + str(p_id)+"'"
+
+def data_cat_counts_query(table,p_id,data_cat):
+    query="select count(id) as total from file_sample where data_category='"+data_cat+"' and "+table+"='"+str(p_id)+"'"
+    query=query+" union all "
+    query=query+"select count(distinct participant) as total from file_sample where data_category='"+data_cat+"' and "+table+"='"+str(p_id)+"'"
+    return query
+
+def exp_str_query(table,p_id):
+    return "select distinct experimental_strategy from file_sample where "+ table+"='" + str(p_id) +"'"
+
+def exp_str_counts_query(table,p_id,exp_str):
+    query="select count(id) as total from file_sample where experimental_strategy='"+exp_str+"' and "+table+"='"+str(p_id)+"'"
+    query=query+" union all "
+    query=query+ "select count(distinct participant) as total from file_sample where experimental_strategy='"+exp_str+"' and "+table+"='"+str(p_id)+"'"
+    return query
+
+def file_query(f_id):
+    query='''select file_sample.*,
+                      project.id as p_id, project.project_id as proj_id,project.primary_site,
+                      participant.id as part_id, participant.age_2012, participant.totMETs1, participant.weight_lbs
+                      from file_sample,project,participant where file_sample.id='''+str(f_id)
+    query=query+''' and file_sample.project=project.project_id and
+                                  file_sample.participant=participant.entity_participant_id'''
+    return query
+
+def case_query(p_id):
+     return '''select participant.entity_participant_id, file_sample.id, file_sample.experimental_strategy,
+               file_sample.data_category, file_sample.platform, file_sample.access,file_sample.data_format
+               from participant, file_sample
+               where participant.id='''+str(p_id)+" and file_sample.participant=participant.entity_participant_id"
+
+def case_counts_query(p_id):
+    query="select count(id) as total from participant where entity_participant_id="+str(p_id)
+    query=query+" union all "
+    query=query+ "select count(id) as total from file_sample where participant="+str(p_id)
+    query=query+" union all "
+    query=query+"select sum(file_size) as total from file_sample where participant="+str(p_id)
+    return query
+
+def case_project_query(p_id):
+    query="select distinct file_sample.project, project.id as p_id, project.primary_site "
+    query=query+"from file_sample, project where file_sample.participant='"
+    query=query+str(p_id)+"' and project.project_id=file_sample.project limit 1"
+    return query
+
+
+def metadata_part_query(p_id):
+    return "select * from participant where entity_participant_id="+str(p_id)
+
+def metadata_sample_query(p_id):
+    return "select * from sample where participant="+str(p_id)
+

load_local_database.py

@@ -23,7 +23,7 @@ def parse_arguments(args):
         required=False)
     parser.add_argument(
         "--key-file",
-        default="biom-mass-fdcadb440fdf.json",
+        default="/home/hutlab_public/compute_engine_service_account_key/biom-mass-8dc9ab934396.json",
         help="google project service account private key file path\n]",
         required=False)
     parser.add_argument(
@@ -256,7 +256,7 @@ def main():
            new_version = str(0.1)
 
     now = datetime.datetime.now()
-    release_date ="Date Release "+new_version+" "+ now.strftime("%b %d, %Y")
+    release_date ="Data Release "+new_version+" - "+ now.strftime("%b %d, %Y")
     commit ="commit_"+now.strftime("%m%d%Y")
     query_insert_version ='''INSERT INTO `version` (
            commit,

query_bigquery.py

@@ -22,7 +22,7 @@ def parse_arguments(args):
         required=False)
     parser.add_argument(
         "--key-file",
-        default="biom-mass-fdcadb440fdf.json", 
+        default="/home/hutlab_public/compute_engine_service_account_key/biom-mass-8dc9ab934396.json", 
         help="google project service account private key file path\n]", 
         required=False)
     parser.add_argument(

schema.graphql

@@ -23,16 +23,59 @@ type Case implements Node {
   primary_site: String
   submitter_id: String
   demographic: Demographic
+  metadata_participant: MetadataParticipant
+  metadata_sample: [MetadataSample]
   project: Project
   summary: Summary
   annotations: CaseAnnotations
   files: CaseFiles
 }
 
+type MetadataParticipant {
+  id: Int
+  participant: Int
+  age_2012: Int
+  totMETs1: Float
+  weight_lbs: Float
+}
+
+type MetadataSample 
+  id: Int
+  project: String
+  sample: String
+  participant: Int
+  DaysSince1Jan12: Int
+  drAlcohol: Float
+  drB12: Float
+  drCalories: Float
+  drCarbs: Float
+  drCholine: Float
+  drFat: Float
+  drFiber: Float
+  drFolate: Float
+  drIron: Float
+  drProtein: Float
+  participant: Int
+  q2Alcohol: String
+  q2B12: String
+  q2Calories: String
+  q2Carbs: String
+  q2Choline: String
+  q2Fat: String
+  q2Fiber: String
+  q2Folate: String
+  q2Iron: String
+  q2Protein: String
+  Time: String
+  week: Int
+
 type CaseAggregations {
   demographic__ethnicity: Aggregations
   demographic__gender: Aggregations
   demographic__race: Aggregations
+  metadata_participant__age_2012: Aggregations
+  metadata_participant__totMETs1: Aggregations
+  metadata_participant__weight_lbs: Aggregations
   primary_site: Aggregations
   project__project_id: Aggregations
   project__program__name: Aggregations
@@ -180,6 +223,7 @@ type FileCase implements Node {
   case_id: String
   project: Project
   demographic: Demographic
+  metadata_participant: MetadataParticipant
   primary_site: String
 }
 

schema.py

@@ -91,13 +91,51 @@ class Demographic(graphene.ObjectType):
     gender = graphene.String()
     race = graphene.String()
 
+class MetadataParticipant(graphene.ObjectType):
+    id = graphene.Int()
+    participant = graphene.Int()
+    age_2012 = graphene.Int()
+    totMETs1 = graphene.Float()
+    weight_lbs = graphene.Float()
+
+class MetadataSample(graphene.ObjectType):
+    id = graphene.Int()
+    project = graphene.String()
+    sample = graphene.String()
+    participant = graphene.Int()
+    DaysSince1Jan12 = graphene.Int()
+    drAlcohol = graphene.Float()
+    drB12 = graphene.Float()
+    drCalories = graphene.Float()
+    drCarbs = graphene.Float()
+    drCholine = graphene.Float()
+    drFat = graphene.Float()
+    drFiber = graphene.Float()
+    drFolate = graphene.Float()
+    drIron = graphene.Float()
+    drProtein = graphene.Float()
+    participant = graphene.Int()
+    q2Alcohol = graphene.String()
+    q2B12 = graphene.String()
+    q2Calories = graphene.String()
+    q2Carbs = graphene.String()
+    q2Choline = graphene.String()
+    q2Fat = graphene.String()
+    q2Fiber = graphene.String()
+    q2Folate = graphene.String()
+    q2Iron = graphene.String()
+    q2Protein = graphene.String()
+    Time = graphene.String()
+    week = graphene.Int()
+
 class FileCase(graphene.ObjectType):
     class Meta:
         interfaces = (graphene.relay.Node,)
 
     case_id = graphene.String()
     project = graphene.Field(Project)
     demographic = graphene.Field(Demographic)
+    metadata_participant = graphene.Field(MetadataParticipant)
     primary_site = graphene.String()
 
 class FileCaseConnection(graphene.relay.Connection):
@@ -137,7 +175,7 @@ class Meta:
     type = graphene.String()
 
     def resolve_file_id(self, info):
-        return self.name
+        return self.file_id
 
     def resolve_type(self, info):
         return self.data_format
@@ -160,6 +198,7 @@ class Meta:
     total = graphene.Int()
 
     def resolve_total(self, info):
+       # return data.get_files_total()
         return len(self.edges)
 
 class Bucket(graphene.ObjectType):
@@ -214,6 +253,9 @@ class CaseAggregations(graphene.ObjectType):
     demographic__ethnicity = graphene.Field(Aggregations)
     demographic__gender = graphene.Field(Aggregations)
     demographic__race = graphene.Field(Aggregations)
+    metadata_participant__age_2012 = graphene.Field(Aggregations)
+    metadata_participant__totMETs1 = graphene.Field(Aggregations)
+    metadata_participant__weight_lbs = graphene.Field(Aggregations)
     primary_site = graphene.Field(Aggregations)
     project__project_id = graphene.Field(Aggregations)
     project__program__name = graphene.Field(Aggregations)
@@ -280,8 +322,9 @@ class Meta:
     case_id = graphene.String()
     primary_site = graphene.String()
     submitter_id = graphene.String()
-
     demographic = graphene.Field(Demographic)
+    metadata_participant = graphene.Field(MetadataParticipant)
+    metadata_sample = graphene.List(MetadataSample)
     project = graphene.Field(Project)
     summary = graphene.Field(Summary)
     annotations = graphene.Field(CaseAnnotations)
@@ -298,6 +341,7 @@ class Meta:
     total = graphene.Int()
 
     def resolve_total(self, info):
+        #return data.get_cases_total()
         return len(self.edges)
 
 class RepositoryCases(graphene.ObjectType):

server.py

@@ -10,11 +10,13 @@
 import os
 
 import flask
+import flask_cors
 import flask_graphql
 import graphene
 
 import schema
-import const
+#import const
+from  database import data
 
 NAME = "firecloud_graphql"
 HOST = "0.0.0.0"
@@ -41,7 +43,8 @@ def process_query(request, schema):
 def main():
     # create the graphql flask app
     app = flask.Flask(NAME)
-
+    # allow initial OPTIONS requests
+    flask_cors.CORS(app)
     # add the root graphql queries
     @app.route('/graphql', methods=["POST"])
     def get_root_schema():
@@ -55,8 +58,8 @@ def get_schema(name):
     # add static endpoint for version/status
     @app.route('/status', methods=["GET"])
     def get_version():
-        return flask.jsonify(const.VERSION)
-
+        return flask.jsonify(data.get_current_version())
+    # app.debug = True
     # add end point for graphql gui
     app.add_url_rule('/test', view_func=flask_graphql.GraphQLView.as_view(
         'test', schema=graphene.Schema(query=schema.Query, auto_camelcase=False), graphiql=True))