biofilter 3.2.0__tar.gz

biofilter-3.2.0/PKG-INFO

@@ -0,0 +1,45 @@
+Metadata-Version: 2.1
+Name: biofilter
+Version: 3.2.0
+Summary: Biofilter3R: cloud-ready biological knowledge system
+Home-page: https://ritchielab.org
+License: MIT
+Author: Andre Rico
+Author-email: andreluis.rico@pennmedicine.upenn.edu
+Requires-Python: >=3.10,<4.0
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: aiosqlite (>=0.21.0,<0.22.0)
+Requires-Dist: alembic (>=1.16.4,<2.0.0)
+Requires-Dist: apsw (==3.46.1.0)
+Requires-Dist: click (==8.1.7)
+Requires-Dist: colorama (>=0.4.6,<0.5.0)
+Requires-Dist: duckdb (>=1.4.0,<2.0.0)
+Requires-Dist: iniconfig (==2.0.0)
+Requires-Dist: notebook (>=7.4.6,<8.0.0)
+Requires-Dist: openpyxl (>=3.1.5,<4.0.0)
+Requires-Dist: packaging (==24.1)
+Requires-Dist: pandas (>=2.2.3,<3.0.0)
+Requires-Dist: platformdirs (==4.3.6)
+Requires-Dist: pluggy (==1.5.0)
+Requires-Dist: psutil (>=6.1.1,<7.0.0)
+Requires-Dist: psycopg2-binary (>=2.9.10,<3.0.0)
+Requires-Dist: pyarrow (>=19.0.1,<20.0.0)
+Requires-Dist: requests (>=2.32.4,<3.0.0)
+Requires-Dist: sqlalchemy (>=2.0.37,<3.0.0)
+Requires-Dist: toml (>=0.10.2,<0.11.0)
+Requires-Dist: tqdm (>=4.67.1,<5.0.0)
+Requires-Dist: wget (>=3.2,<4.0)
+Description-Content-Type: text/markdown
+
+# Biofilter3R (Development Branch)
+
+**Version**: New Project (with SQLAlchemy)
+**Status**: In Development  
+**Focus**: Adding new Data Sources
+
+## Project Overview
+

biofilter-3.2.0/README.md

@@ -0,0 +1,7 @@
+# Biofilter3R (Development Branch)
+
+**Version**: New Project (with SQLAlchemy)
+**Status**: In Development  
+**Focus**: Adding new Data Sources
+
+## Project Overview

biofilter-3.2.0/biofilter/__init__.py

@@ -0,0 +1,3 @@
+from .biofilter import Biofilter
+
+__all__ = ["Biofilter"]

biofilter-3.2.0/biofilter/alembic/README

@@ -0,0 +1 @@
+Generic single-database configuration.

biofilter-3.2.0/biofilter/alembic/env.py

@@ -0,0 +1,88 @@
+import os
+from alembic import context
+from logging.config import fileConfig
+from sqlalchemy import pool
+from sqlalchemy import engine_from_config
+
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Set DB URL manually if not in alembic.ini
+# config.set_main_option("sqlalchemy.url", db_path)
+# Override sqlalchemy.url from environment variable if set
+db_path = os.getenv("BIOFILTER_DB_URI")
+if db_path:
+    config.set_main_option("sqlalchemy.url", db_path)
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# add your model's MetaData object here
+# for 'autogenerate' support
+# from myapp import mymodel
+# target_metadata = mymodel.Base.metadata
+# target_metadata = None # Default
+from biofilter.db import Base  # noqa E402
+from biofilter.db import models  # Import all models. # noqa
+
+target_metadata = Base.metadata
+
+
+# other values from the config, defined by the needs of env.py,
+# can be acquired:
+# my_important_option = config.get_main_option("my_important_option")
+# ... etc.
+
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode.
+
+    This configures the context with just a URL
+    and not an Engine, though an Engine is acceptable
+    here as well.  By skipping the Engine creation
+    we don't even need a DBAPI to be available.
+
+    Calls to context.execute() here emit the given string to the
+    script output.
+
+    """
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode.
+
+    In this scenario we need to create an Engine
+    and associate a connection with the context.
+
+    """
+    connectable = engine_from_config(
+        config.get_section(config.config_ini_section, {}),
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+
+    with connectable.connect() as connection:
+        context.configure(connection=connection, target_metadata=target_metadata)
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

biofilter-3.2.0/biofilter/alembic/script.py.mako

@@ -0,0 +1,28 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, Sequence[str], None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    ${downgrades if downgrades else "pass"}

biofilter-3.2.0/biofilter/alembic/versions/0c242ad16a44_3_0_1_base_schema.py

@@ -0,0 +1,408 @@
+"""3.0.1 - Base schema
+
+Revision ID: 0c242ad16a44
+Revises: 
+Create Date: 2025-08-21 08:49:50.931523
+
+"""
+
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = "0c242ad16a44"
+down_revision: Union[str, Sequence[str], None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f("idx_entities_group_id"), table_name="entities")
+    op.drop_index(op.f("idx_entities_has_conflict"), table_name="entities")
+    op.drop_index(op.f("idx_entities_is_deactive"), table_name="entities")
+    op.drop_index(op.f("idx_entity_names_data_source_id"), table_name="entity_names")
+    op.drop_index(
+        op.f("idx_entity_names_data_source_id_entity_id"), table_name="entity_names"
+    )
+    op.drop_index(
+        op.f("idx_entity_names_data_source_id_name"), table_name="entity_names"
+    )
+    op.drop_index(op.f("idx_entity_names_entity_id"), table_name="entity_names")
+    op.drop_index(
+        op.f("idx_entity_names_entity_id_is_primary"), table_name="entity_names"
+    )
+    op.drop_index(op.f("idx_entity_names_name"), table_name="entity_names")
+    op.drop_index(
+        op.f("idx_entity_relationship_types_code"),
+        table_name="entity_relationship_types",
+    )
+    op.drop_index(
+        op.f("idx_entity_relationships_data_source_id"),
+        table_name="entity_relationships",
+    )
+    op.drop_index(
+        op.f("idx_entity_relationships_entity_1_id"), table_name="entity_relationships"
+    )
+    op.drop_index(
+        op.f("idx_entity_relationships_entity_1_id_entity_2_id_relationship_type_id"),
+        table_name="entity_relationships",
+    )
+    op.drop_index(
+        op.f("idx_entity_relationships_entity_1_id_relationship_type_id"),
+        table_name="entity_relationships",
+    )
+    op.drop_index(
+        op.f("idx_entity_relationships_entity_2_id"), table_name="entity_relationships"
+    )
+    op.drop_index(
+        op.f("idx_entity_relationships_relationship_type_id"),
+        table_name="entity_relationships",
+    )
+    op.drop_index(
+        op.f("idx_gene_genomic_regions_chromosome"), table_name="gene_genomic_regions"
+    )
+    op.drop_index(
+        op.f("idx_gene_genomic_regions_chromosome_start_end"),
+        table_name="gene_genomic_regions",
+    )
+    op.drop_index(
+        op.f("idx_gene_genomic_regions_label"), table_name="gene_genomic_regions"
+    )
+    op.drop_index(
+        op.f("idx_gene_group_memberships_gene_id"), table_name="gene_group_memberships"
+    )
+    op.drop_index(
+        op.f("idx_gene_group_memberships_group_id"), table_name="gene_group_memberships"
+    )
+    op.drop_index(op.f("idx_gene_groups_name"), table_name="gene_groups")
+    op.drop_index(op.f("idx_gene_locations_assembly"), table_name="gene_locations")
+    op.drop_index(op.f("idx_gene_locations_chromosome"), table_name="gene_locations")
+    op.drop_index(
+        op.f("idx_gene_locations_chromosome_start_end"), table_name="gene_locations"
+    )
+    op.drop_index(
+        op.f("idx_gene_locations_data_source_id"), table_name="gene_locations"
+    )
+    op.drop_index(op.f("idx_gene_locations_gene_id"), table_name="gene_locations")
+    op.drop_index(op.f("idx_gene_locations_region_id"), table_name="gene_locations")
+    op.drop_index(op.f("idx_gene_locus_groups_name"), table_name="gene_locus_groups")
+    op.drop_index(op.f("idx_gene_locus_types_name"), table_name="gene_locus_types")
+    op.drop_index(op.f("idx_gene_masters_data_source_id"), table_name="gene_masters")
+    op.drop_index(op.f("idx_gene_masters_ensembl_id"), table_name="gene_masters")
+    op.drop_index(op.f("idx_gene_masters_entity_id"), table_name="gene_masters")
+    op.drop_index(op.f("idx_gene_masters_entrez_id"), table_name="gene_masters")
+    op.drop_index(op.f("idx_gene_masters_hgnc_id"), table_name="gene_masters")
+    op.drop_index(op.f("idx_gene_masters_locus_group_id"), table_name="gene_masters")
+    op.drop_index(op.f("idx_gene_masters_locus_type_id"), table_name="gene_masters")
+    op.drop_index(op.f("idx_gene_masters_omic_status_id"), table_name="gene_masters")
+    op.drop_index(op.f("idx_go_masters_entity_id"), table_name="go_masters")
+    op.drop_index(op.f("idx_go_masters_go_id"), table_name="go_masters")
+    op.drop_index(op.f("idx_go_masters_namespace"), table_name="go_masters")
+    op.drop_index(op.f("idx_go_relations_child_id"), table_name="go_relations")
+    op.drop_index(
+        op.f("idx_go_relations_child_id_relation_type"), table_name="go_relations"
+    )
+    op.drop_index(op.f("idx_go_relations_parent_id"), table_name="go_relations")
+    op.drop_index(
+        op.f("idx_go_relations_parent_id_relation_type"), table_name="go_relations"
+    )
+    op.drop_index(op.f("idx_go_relations_relation_type"), table_name="go_relations")
+    op.drop_index(op.f("idx_omic_status_name"), table_name="omic_status")
+    op.drop_index(
+        op.f("idx_pathway_masters_data_source_id"), table_name="pathway_masters"
+    )
+    op.drop_index(op.f("idx_pathway_masters_entity_id"), table_name="pathway_masters")
+    op.drop_index(op.f("idx_pathway_masters_pathway_id"), table_name="pathway_masters")
+    op.drop_index(op.f("idx_protein_entities_entity_id"), table_name="protein_entities")
+    op.drop_index(
+        op.f("idx_protein_entities_protein_master_id_is_isoform"),
+        table_name="protein_entities",
+    )
+    op.drop_index(op.f("idx_protein_masters_protein_id"), table_name="protein_masters")
+    op.drop_index(
+        op.f("idx_protein_pfam_links_pfam_pk_id"), table_name="protein_pfam_links"
+    )
+    op.drop_index(op.f("idx_protein_pfams_clan_acc"), table_name="protein_pfams")
+    op.drop_index(op.f("idx_protein_pfams_pfam_id"), table_name="protein_pfams")
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_index(
+        op.f("idx_protein_pfams_pfam_id"), "protein_pfams", ["pfam_id"], unique=False
+    )
+    op.create_index(
+        op.f("idx_protein_pfams_clan_acc"), "protein_pfams", ["clan_acc"], unique=False
+    )
+    op.create_index(
+        op.f("idx_protein_pfam_links_pfam_pk_id"),
+        "protein_pfam_links",
+        ["pfam_pk_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_protein_masters_protein_id"),
+        "protein_masters",
+        ["protein_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_protein_entities_protein_master_id_is_isoform"),
+        "protein_entities",
+        ["protein_master_id", "is_isoform"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_protein_entities_entity_id"),
+        "protein_entities",
+        ["entity_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_pathway_masters_pathway_id"),
+        "pathway_masters",
+        ["pathway_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_pathway_masters_entity_id"),
+        "pathway_masters",
+        ["entity_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_pathway_masters_data_source_id"),
+        "pathway_masters",
+        ["data_source_id"],
+        unique=False,
+    )
+    op.create_index(op.f("idx_omic_status_name"), "omic_status", ["name"], unique=False)
+    op.create_index(
+        op.f("idx_go_relations_relation_type"),
+        "go_relations",
+        ["relation_type"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_go_relations_parent_id_relation_type"),
+        "go_relations",
+        ["parent_id", "relation_type"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_go_relations_parent_id"), "go_relations", ["parent_id"], unique=False
+    )
+    op.create_index(
+        op.f("idx_go_relations_child_id_relation_type"),
+        "go_relations",
+        ["child_id", "relation_type"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_go_relations_child_id"), "go_relations", ["child_id"], unique=False
+    )
+    op.create_index(
+        op.f("idx_go_masters_namespace"), "go_masters", ["namespace"], unique=False
+    )
+    op.create_index(op.f("idx_go_masters_go_id"), "go_masters", ["go_id"], unique=False)
+    op.create_index(
+        op.f("idx_go_masters_entity_id"), "go_masters", ["entity_id"], unique=False
+    )
+    op.create_index(
+        op.f("idx_gene_masters_omic_status_id"),
+        "gene_masters",
+        ["omic_status_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_gene_masters_locus_type_id"),
+        "gene_masters",
+        ["locus_type_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_gene_masters_locus_group_id"),
+        "gene_masters",
+        ["locus_group_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_gene_masters_hgnc_id"), "gene_masters", ["hgnc_id"], unique=False
+    )
+    op.create_index(
+        op.f("idx_gene_masters_entrez_id"), "gene_masters", ["entrez_id"], unique=False
+    )
+    op.create_index(
+        op.f("idx_gene_masters_entity_id"), "gene_masters", ["entity_id"], unique=False
+    )
+    op.create_index(
+        op.f("idx_gene_masters_ensembl_id"),
+        "gene_masters",
+        ["ensembl_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_gene_masters_data_source_id"),
+        "gene_masters",
+        ["data_source_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_gene_locus_types_name"), "gene_locus_types", ["name"], unique=False
+    )
+    op.create_index(
+        op.f("idx_gene_locus_groups_name"), "gene_locus_groups", ["name"], unique=False
+    )
+    op.create_index(
+        op.f("idx_gene_locations_region_id"),
+        "gene_locations",
+        ["region_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_gene_locations_gene_id"), "gene_locations", ["gene_id"], unique=False
+    )
+    op.create_index(
+        op.f("idx_gene_locations_data_source_id"),
+        "gene_locations",
+        ["data_source_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_gene_locations_chromosome_start_end"),
+        "gene_locations",
+        ["chromosome", "start", "end"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_gene_locations_chromosome"),
+        "gene_locations",
+        ["chromosome"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_gene_locations_assembly"),
+        "gene_locations",
+        ["assembly"],
+        unique=False,
+    )
+    op.create_index(op.f("idx_gene_groups_name"), "gene_groups", ["name"], unique=False)
+    op.create_index(
+        op.f("idx_gene_group_memberships_group_id"),
+        "gene_group_memberships",
+        ["group_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_gene_group_memberships_gene_id"),
+        "gene_group_memberships",
+        ["gene_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_gene_genomic_regions_label"),
+        "gene_genomic_regions",
+        ["label"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_gene_genomic_regions_chromosome_start_end"),
+        "gene_genomic_regions",
+        ["chromosome", "start", "end"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_gene_genomic_regions_chromosome"),
+        "gene_genomic_regions",
+        ["chromosome"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_entity_relationships_relationship_type_id"),
+        "entity_relationships",
+        ["relationship_type_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_entity_relationships_entity_2_id"),
+        "entity_relationships",
+        ["entity_2_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_entity_relationships_entity_1_id_relationship_type_id"),
+        "entity_relationships",
+        ["entity_1_id", "relationship_type_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_entity_relationships_entity_1_id_entity_2_id_relationship_type_id"),
+        "entity_relationships",
+        ["entity_1_id", "entity_2_id", "relationship_type_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_entity_relationships_entity_1_id"),
+        "entity_relationships",
+        ["entity_1_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_entity_relationships_data_source_id"),
+        "entity_relationships",
+        ["data_source_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_entity_relationship_types_code"),
+        "entity_relationship_types",
+        ["code"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_entity_names_name"), "entity_names", ["name"], unique=False
+    )
+    op.create_index(
+        op.f("idx_entity_names_entity_id_is_primary"),
+        "entity_names",
+        ["entity_id", "is_primary"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_entity_names_entity_id"), "entity_names", ["entity_id"], unique=False
+    )
+    op.create_index(
+        op.f("idx_entity_names_data_source_id_name"),
+        "entity_names",
+        ["data_source_id", "name"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_entity_names_data_source_id_entity_id"),
+        "entity_names",
+        ["data_source_id", "entity_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_entity_names_data_source_id"),
+        "entity_names",
+        ["data_source_id"],
+        unique=False,
+    )
+    op.create_index(
+        op.f("idx_entities_is_deactive"), "entities", ["is_deactive"], unique=False
+    )
+    op.create_index(
+        op.f("idx_entities_has_conflict"), "entities", ["has_conflict"], unique=False
+    )
+    op.create_index(
+        op.f("idx_entities_group_id"), "entities", ["group_id"], unique=False
+    )
+    # ### end Alembic commands ###