Merge pull request #231 from BioAnalyticResource/dev

Sync

Author: asherpasha

.github/workflows/bar-api.yml

@@ -10,7 +10,7 @@ on:
 jobs:
   test:
 
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     strategy:
       matrix:
         python-version: [3.8, 3.9, 3.10.14, 3.11, 3.12]

api/__init__.py

@@ -53,6 +53,7 @@ def create_app():
     # Now add routes
     from api.resources.gene_information import gene_information
     from api.resources.rnaseq_gene_expression import rnaseq_gene_expression
+    from api.resources.microarray_gene_expression import microarray_gene_expression
     from api.resources.proxy import bar_proxy
     from api.resources.thalemine import thalemine
     from api.resources.snps import snps
@@ -65,6 +66,7 @@ def create_app():
 
     bar_api.add_namespace(gene_information)
     bar_api.add_namespace(rnaseq_gene_expression)
+    bar_api.add_namespace(microarray_gene_expression)
     bar_api.add_namespace(bar_proxy)
     bar_api.add_namespace(thalemine)
     bar_api.add_namespace(snps)

api/models/annotations_lookup.py

@@ -10,3 +10,13 @@ class AgiAlias(db.Model):
     agi: db.Mapped[str] = db.mapped_column(db.String(30), primary_key=True, nullable=False)
     alias: db.Mapped[str] = db.mapped_column(db.String(30), primary_key=True, nullable=False)
     date: db.Mapped[datetime] = db.mapped_column(db.Date, primary_key=True, nullable=False)
+
+
+class AtAgiLookup(db.Model):
+    __bind_key__ = "annotations_lookup"
+    __tablename__ = "at_agi_lookup"
+    __table_args__ = (db.Index("probeset_date_agi", "probeset", "agi", "date"),)
+
+    probeset: db.Mapped[str] = db.mapped_column(db.String(60), primary_key=True, nullable=False)
+    agi: db.Mapped[str] = db.mapped_column(db.String(30), primary_key=True, nullable=False)
+    date: db.Mapped[datetime] = db.mapped_column(db.Date, primary_key=True, nullable=False)

api/models/arabidopsis_ecotypes.py

@@ -0,0 +1,15 @@
+from api import db
+
+
+class SampleData(db.Model):
+    __bind_key__ = "arabidopsis_ecotypes"
+    __tablename__ = "sample_data"
+
+    sample_id: db.Mapped[int] = db.mapped_column(db.Integer, nullable=False)
+    proj_id: db.Mapped[str] = db.mapped_column(db.String(15), nullable=False)
+    sample_file_name: db.Mapped[str] = db.mapped_column(db.String)
+    data_probeset_id: db.Mapped[str] = db.mapped_column(db.String(30), nullable=False, primary_key=True)
+    data_signal: db.Mapped[float] = db.mapped_column(db.Float)
+    data_call: db.Mapped[str] = db.mapped_column(db.String)
+    data_p_val: db.Mapped[float] = db.mapped_column(db.Float)
+    data_bot_id: db.Mapped[str] = db.mapped_column(db.String(16), nullable=False)

api/models/eplant2.py

@@ -37,3 +37,15 @@ class GeneRIFs(db.Model):
     gene: db.Mapped[str] = db.mapped_column(db.String(11), nullable=False, primary_key=True)
     pubmed: db.Mapped[str] = db.mapped_column(db.String(11), nullable=False, primary_key=True)
     RIF: db.Mapped[str] = db.mapped_column(TEXT(), nullable=False, primary_key=True)
+
+
+class Publications(db.Model):
+    __bind_key__ = "eplant2"
+    __tablename__ = "publications"
+
+    gene: db.Mapped[str] = db.mapped_column(db.String(12), nullable=False, primary_key=True)
+    author: db.Mapped[str] = db.mapped_column(db.String(64), nullable=False, primary_key=True)
+    year: db.Mapped[str] = db.mapped_column(db.String(6), nullable=False, primary_key=True)
+    journal: db.Mapped[str] = db.mapped_column(db.String(64), nullable=False, primary_key=True)
+    title: db.Mapped[str] = db.mapped_column(TEXT(), nullable=False, primary_key=True)
+    pubmed: db.Mapped[str] = db.mapped_column(db.String(16), nullable=False, primary_key=True)

api/resources/gene_information.py

@@ -3,6 +3,7 @@
 from markupsafe import escape
 from api.models.annotations_lookup import AgiAlias
 from api.models.eplant2 import Isoforms as EPlant2Isoforms
+from api.models.eplant2 import Publications as EPlant2Publications
 from api.models.eplant_poplar import Isoforms as EPlantPoplarIsoforms
 from api.models.eplant_tomato import Isoforms as EPlantTomatoIsoforms
 from api.models.eplant_soybean import Isoforms as EPlantSoybeanIsoforms
@@ -86,6 +87,54 @@ def post(self):
             return BARUtils.error_exit("No data for the given species/genes"), 400
 
 
+@gene_information.route("/gene_publications/<string:species>/<string:gene_id>")
+class GenePublications(Resource):
+    @gene_information.param("species", _in="path", default="arabidopsis")
+    @gene_information.param("gene_id", _in="path", default="AT1G01010")
+    def get(self, species="", gene_id=""):
+        """This end point provides publications given a gene ID."""
+        publications = []
+
+        # Escape input
+        species = escape(species)
+        gene_id = escape(gene_id)
+
+        # truncate gene ID
+        for i in range(len(gene_id)):
+            if gene_id[i] == ".":
+                gene_id = gene_id[0:i]
+                break
+
+        # Set the database and check if genes are valid
+        if species == "arabidopsis":
+            database = EPlant2Publications
+
+            if not BARUtils.is_arabidopsis_gene_valid(gene_id):
+                return BARUtils.error_exit("Invalid gene id"), 400
+        else:
+            return BARUtils.error_exit("No data for the given species")
+
+        # Get data
+        rows = db.session.execute(db.select(database).where(database.gene == gene_id)).scalars().all()
+        for row in rows:
+            publications.append(
+                {
+                    "gene_id": row.gene,
+                    "author": row.author,
+                    "year": row.year,
+                    "journal": row.journal,
+                    "title": row.title,
+                    "pubmed": row.pubmed,
+                }
+            )
+
+        # Return results if there are data
+        if len(publications) > 0:
+            return BARUtils.success_exit(publications)
+        else:
+            return BARUtils.error_exit("There are no data found for the given gene")
+
+
 @gene_information.route("/gene_isoforms/<string:species>/<string:gene_id>")
 class GeneIsoforms(Resource):
     @gene_information.param("species", _in="path", default="arabidopsis")

api/resources/microarray_gene_expression.py

@@ -0,0 +1,60 @@
+from flask_restx import Namespace, Resource
+from markupsafe import escape
+from api import db
+from api.models.annotations_lookup import AtAgiLookup
+from api.models.arabidopsis_ecotypes import SampleData as EcotypesSampleData
+from api.utils.bar_utils import BARUtils
+from api.utils.world_efp_utils import WorldeFPUtils
+
+
+microarray_gene_expression = Namespace(
+    "Microarray Gene Expression",
+    description="Microarray (probe-based) Gene Expression data from the BAR Databases",
+    path="/microarray_gene_expression",
+)
+
+
+@microarray_gene_expression.route("/world_efp/<string:species>/<string:gene_id>")
+class GetWorldeFPExpression(Resource):
+    @microarray_gene_expression.param("species", _in="path", default="arabidopsis")
+    @microarray_gene_expression.param("gene_id", _in="path", default="At1g01010")
+    def get(self, species="", gene_id=""):
+        """This end point returns World Efp gene expression data"""
+        species = escape(species)
+        gene_id = escape(gene_id)
+
+        if species == "arabidopsis":
+            if not BARUtils.is_arabidopsis_gene_valid(gene_id):
+                return BARUtils.error_exit("Invalid gene id")
+        else:
+            return BARUtils.error_exit("Invalid species")
+        subquery = (
+            db.select(AtAgiLookup.probeset)
+            .where(AtAgiLookup.agi == gene_id)
+            .order_by(AtAgiLookup.date.desc())
+            .limit(1)
+            .subquery()
+        )
+
+        sq_query = db.session.query(subquery)
+        if sq_query.count() > 0:
+            sq_result = sq_query[0][0]
+        else:
+            return BARUtils.error_exit("There are no data found for the given gene")
+
+        rows = db.session.execute(
+            db.select(
+                EcotypesSampleData.data_probeset_id, EcotypesSampleData.data_signal, EcotypesSampleData.data_bot_id
+            ).where(EcotypesSampleData.data_probeset_id == sq_result)
+        ).all()
+        final_json = {}
+
+        if len(rows) > 0:
+            for row in rows:
+                if row[2][5:8] not in final_json:
+                    final_json[row[2][5:8]] = WorldeFPUtils.wrap_json(row[2][5:8], row[2], row[1], row[0])
+                elif row[2][5:8] in final_json:
+                    final_json[row[2][5:8]]["values"].update({row[2]: row[1]})
+            return BARUtils.success_exit(final_json)
+        else:
+            return BARUtils.error_exit("There are no data found for the given gene")