Move around

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
-name = "mavemap"
-description = "Map MaveDB scoresets to reference sequences"
+name = "dcd-mapping"
+description = "Map MaveDB scoresets to VRS objects"
 authors = [
     {name = "Alex Handler Wagner", email = "[email protected]"},
     {name = "Jeremy Arbesfeld", email = "[email protected]"},
@@ -39,7 +39,7 @@ dependencies = [
 ]
 
 [project.scripts]
-dcd-map = "mavemap.cli:cli"
+dcd-map = "dcd_mapping.cli:cli"
 
 [project.optional-dependencies]
 tests = [

src/mavemap/align.py → src/dcd_mapping/align.py

@@ -1,4 +1,9 @@
-"""Align MaveDB target sequences to a human reference genome."""
+"""Align MaveDB target sequences to a human reference genome.
+
+Outstanding items/encountered errors
+------------------------------------
+
+"""
 import logging
 import subprocess
 import uuid
@@ -11,14 +16,14 @@
 from cool_seq_tool.schemas import Strand
 from gene.database.database import click
 
-from mavemap.lookup import get_chromosome_identifier, get_gene_location
-from mavemap.resources import (
+from dcd_mapping.lookup import get_chromosome_identifier, get_gene_location
+from dcd_mapping.resources import (
     LOCAL_STORE_PATH,
     get_cached_blat_output,
     get_mapping_tmp_dir,
     get_ref_genome_file,
 )
-from mavemap.schemas import (
+from dcd_mapping.schemas import (
     AlignmentResult,
     GeneLocation,
     ScoresetMetadata,
@@ -145,6 +150,8 @@ def _get_blat_output(
     # TODO
     # the notebooks handle errors here by trying different BLAT arg configurations --
     # investigate, refer to older code if it comes up
+    # ideally we should be forming correct queries up front instead of running
+    # failed alignment attempts
     output = read_blat(out_file.absolute(), "blat-psl")
 
     # clean up

src/mavemap/cli.py → src/dcd_mapping/cli.py

@@ -4,7 +4,7 @@
 
 import click
 
-from mavemap.main import map_scoreset_urn
+from dcd_mapping.main import map_scoreset_urn
 
 _logger = logging.getLogger(__name__)
 
@@ -31,7 +31,7 @@ def cli(urn: str, debug: bool) -> None:
     :param debug: if True, enable debug logging
     """  # noqa: D301
     logging.basicConfig(
-        filename="mavemap.log",
+        filename="dcd-mapping.log",
         format="%(asctime)s %(levelname)s:%(message)s",
         level=logging.INFO,
         force=True,

src/mavemap/lookup.py → src/dcd_mapping/lookup.py

@@ -17,7 +17,7 @@
 from gene.query import QueryHandler
 from gene.schemas import SourceName
 
-from mavemap.schemas import GeneLocation, ManeDescription, ScoresetMetadata
+from dcd_mapping.schemas import GeneLocation, ManeDescription, ScoresetMetadata
 
 _logger = logging.getLogger(__name__)
 

src/mavemap/main.py → src/dcd_mapping/main.py

@@ -4,15 +4,15 @@
 
 import click
 
-from mavemap.align import AlignmentError, align
-from mavemap.resources import (
+from dcd_mapping.align import AlignmentError, align
+from dcd_mapping.resources import (
     ResourceAcquisitionError,
     get_scoreset_metadata,
     get_scoreset_records,
 )
-from mavemap.schemas import ScoreRow, ScoresetMetadata
-from mavemap.transcripts import TxSelectError, select_transcript
-from mavemap.vrs_map import VrsMapError, vrs_map
+from dcd_mapping.schemas import ScoreRow, ScoresetMetadata
+from dcd_mapping.transcripts import TxSelectError, select_transcript
+from dcd_mapping.vrs_map import VrsMapError, vrs_map
 
 _logger = logging.getLogger(__name__)
 
@@ -33,11 +33,6 @@ async def map_scoreset(
         _logger.error(f"Alignment failed for scoreset {metadata.urn}")
         return None
 
-    print("Alignment result:")  # TODO remove these print calls
-    print(alignment_result)
-
-    breakpoint()
-
     try:
         transcript = await select_transcript(
             metadata, records, alignment_result, silent
@@ -46,9 +41,6 @@ async def map_scoreset(
         _logger.error(f"Transcript selection failed for scoreset {metadata.urn}")
         return None
 
-    print("Transcript:")
-    print(transcript)
-
     try:
         _ = vrs_map(metadata, transcript, records)
     except VrsMapError:

src/mavemap/resources.py → src/dcd_mapping/resources.py

@@ -21,13 +21,15 @@
 from pydantic import ValidationError
 from tqdm import tqdm
 
-from mavemap.schemas import ReferenceGenome, ScoreRow, ScoresetMetadata, UniProtRef
+from dcd_mapping.schemas import ReferenceGenome, ScoreRow, ScoresetMetadata, UniProtRef
 
 _logger = logging.getLogger(__name__)
 
 
 LOCAL_STORE_PATH = Path(
-    os.environ.get("MAVEDB_STORAGE_DIR", Path.home() / ".local" / "share" / "mavemap")
+    os.environ.get(
+        "MAVEDB_STORAGE_DIR", Path.home() / ".local" / "share" / "dcd-mapping"
+    )
 )
 if not LOCAL_STORE_PATH.exists():
     LOCAL_STORE_PATH.mkdir(exist_ok=True, parents=True)

src/mavemap/transcripts.py → src/dcd_mapping/transcripts.py

@@ -1,4 +1,9 @@
-"""Select best reference sequence."""
+"""Select best reference sequence.
+
+Outstanding questions/confusion
+-------------------------------
+* ``urn:mavedb:00000097-n-1``: unable to find any matching transcripts
+"""
 import logging
 import re
 from typing import List, Optional
@@ -9,7 +14,7 @@
 from cool_seq_tool.schemas import TranscriptPriority
 from gene.database.database import click
 
-from mavemap.lookup import (
+from dcd_mapping.lookup import (
     get_chromosome_identifier,
     get_gene_symbol,
     get_mane_transcripts,
@@ -19,7 +24,7 @@
     get_transcripts,
     get_uniprot_sequence,
 )
-from mavemap.schemas import (
+from dcd_mapping.schemas import (
     AlignmentResult,
     ManeDescription,
     ScoreRow,
@@ -217,7 +222,7 @@ def _offset_target_sequence(metadata: ScoresetMetadata, records: List[ScoreRow])
     amino_acids_by_position = {}
     for protein_change in protein_change_list:
         if protein_change == "_sy" or protein_change == "_wt":
-            raise ValueError
+            continue
         if ";" in protein_change:
             protein_changes = protein_change[1:-1].split(";")
         else:

src/mavemap/vrs_map.py → src/dcd_mapping/vrs_map.py

@@ -14,8 +14,8 @@
 )
 from ga4gh.vrs.normalize import normalize
 
-from mavemap.lookup import hgvs_to_vrs
-from mavemap.schemas import (
+from dcd_mapping.lookup import hgvs_to_vrs
+from dcd_mapping.schemas import (
     AlignmentResult,
     ScoreRow,
     ScoresetMetadata,

tests/conftest.py

@@ -4,7 +4,7 @@
 
 import pytest
 
-from mavemap.schemas import AlignmentResult, ScoresetMetadata, TxSelectResult
+from dcd_mapping.schemas import AlignmentResult, ScoresetMetadata, TxSelectResult
 
 
 @pytest.fixture(scope="module")

tests/unit/test_align.py

@@ -8,7 +8,7 @@
 import pytest
 from cool_seq_tool.schemas import Strand
 
-from mavemap.align import align
+from dcd_mapping.align import align
 
 
 def test_align_src_catalytic_domain(scoreset_metadata_fixture):

tests/unit/test_transcript.py

@@ -3,9 +3,9 @@
 
 import pytest
 
-from mavemap.resources import get_scoreset_records
-from mavemap.schemas import AlignmentResult, ScoresetMetadata, TxSelectResult
-from mavemap.transcripts import select_transcript
+from dcd_mapping.resources import get_scoreset_records
+from dcd_mapping.schemas import AlignmentResult, ScoresetMetadata, TxSelectResult
+from dcd_mapping.transcripts import select_transcript
 
 
 @pytest.mark.asyncio(scope="module")