cool-seq-tool 0.7.1__py3-none-any.whl → 0.9.0__py3-none-any.whl

cool_seq_tool/mappers/exon_genomic_coords.py

@@ -87,7 +87,9 @@ class GenomicTxSeg(BaseModelForbidExtra):
     """Model for representing a boundary for a transcript segment."""
 
     seg: TxSegment | None = Field(None, description="Transcript segment.")
-    gene: StrictStr | None = Field(None, description="HGNC gene symbol.")
+    gene: StrictStr | None = Field(
+        None, description="Valid, case-sensitive HGNC gene symbol."
+    )
     genomic_ac: StrictStr | None = Field(None, description="RefSeq genomic accession.")
     tx_ac: StrictStr | None = Field(None, description="RefSeq transcript accession.")
     errors: list[StrictStr] = Field([], description="Error messages.")
@@ -139,7 +141,9 @@ class GenomicTxSeg(BaseModelForbidExtra):
 class GenomicTxSegService(BaseModelForbidExtra):
     """Service model for genomic and transcript data."""
 
-    gene: StrictStr | None = Field(None, description="HGNC gene symbol.")
+    gene: StrictStr | None = Field(
+        None, description="Valid, case-sensitive HGNC gene symbol."
+    )
     genomic_ac: StrictStr | None = Field(None, description="RefSeq genomic accession.")
     tx_ac: StrictStr | None = Field(None, description="RefSeq transcript accession.")
     seg_start: TxSegment | None = Field(None, description="Start transcript segment.")
@@ -292,7 +296,7 @@ class ExonGenomicCoordsMapper:
         ('NC_000001.11', 154192135, 154170399)
 
         :param transcript: RefSeq transcript accession
-        :param gene: HGNC gene symbol
+        :param gene: Valid, case-sensitive HGNC gene symbol
         :param exon_start: Starting transcript exon number (1-based). If not provided,
             must provide ``exon_end``
         :param exon_start_offset: Starting exon offset
@@ -335,9 +339,6 @@ class ExonGenomicCoordsMapper:
         if errors:
             return _return_service_errors(errors)
 
-        if gene:
-            gene = gene.upper()
-
         # Get aligned genomic data (hgnc gene, alt_ac, alt_start_i, alt_end_i, strand)
         # for exon(s)
         (
@@ -455,7 +456,7 @@ class ExonGenomicCoordsMapper:
             following the breakpoint for the 3' end. For the negative strand, adjacent
             is defined as the exon following the breakpoint for the 5' end and the exon
             preceding the breakpoint for the 3' end.
-        :param gene: gene name. Ideally, HGNC symbol. Must be given if no ``transcript``
+        :param gene: A valid, case-sensitive HGNC symbol. Must be given if no ``transcript``
             value is provided.
         :param coordinate_type: Coordinate type for ``seg_start_genomic`` and
             ``seg_end_genomic``
@@ -473,9 +474,6 @@ class ExonGenomicCoordsMapper:
         if errors:
             return _return_service_errors(errors)
 
-        if gene is not None:
-            gene = gene.upper()
-
         params = {}
 
         if seg_start_genomic:
@@ -630,7 +628,7 @@ class ExonGenomicCoordsMapper:
             must provide ``tx_exon_end``
         :param tx_exon_end: Transcript's exon end coordinates. If not provided, must
             provide ``tx_exon_start``
-        :param gene: HGNC gene symbol
+        :param gene: A valid, case-sensitive HGNC gene symbol
         :return: Tuple containing aligned genomic data for start and end exon and
             warnings if found
         """
@@ -755,7 +753,7 @@ class ExonGenomicCoordsMapper:
         :param transcript: The transcript to use. If this is not given, we will try the
             following transcripts: MANE Select, MANE Clinical Plus, Longest Remaining
             Compatible Transcript
-        :param gene: HGNC gene symbol
+        :param gene: Valid, case-sensitive HGNC gene symbol
         :param get_nearest_transcript_junction: If ``True``, this will return the
             adjacent exon if the position specified by``seg_start_genomic`` or
             ``seg_end_genomic`` does not occur on an exon. For the positive strand, adjacent
@@ -1062,7 +1060,7 @@ class ExonGenomicCoordsMapper:
         :param genomic_ac: Genomic RefSeq accession
         :param genomic_pos: Genomic position where the transcript segment occurs
         :param is_seg_start: Whether or not ``genomic_pos`` represents the start position.
-        :param gene: HGNC gene symbol
+        :param gene: Valid, case-sensitive HGNC gene symbol
         :param tx_ac: Transcript RefSeq accession. If not provided, will use MANE
             transcript
         :return: Transcript segment data and associated genomic metadata
@@ -1171,14 +1169,32 @@ class ExonGenomicCoordsMapper:
         :param end: Genomic coordinate of breakpoint
         :return: Exon number corresponding to adjacent exon. Will be 0-based
         """
-        for i in range(len(tx_exons_genomic_coords) - 1):
+        # If a transcript has only one exon, return 0
+        if len(tx_exons_genomic_coords) == 1:
+            return 0
+
+        # Check if a breakpoint occurs before/after the transcript boundaries
+        bp = start if start else end
+        exon_list_len = len(tx_exons_genomic_coords) - 1
+
+        if strand == Strand.POSITIVE:
+            if bp < tx_exons_genomic_coords[0].alt_start_i:
+                return 0
+            if bp > tx_exons_genomic_coords[exon_list_len].alt_end_i:
+                return exon_list_len
+        if strand == Strand.NEGATIVE:
+            if bp > tx_exons_genomic_coords[0].alt_end_i:
+                return 0
+            if bp < tx_exons_genomic_coords[exon_list_len].alt_start_i:
+                return exon_list_len
+
+        for i in range(exon_list_len):
             exon = tx_exons_genomic_coords[i]
             if start == exon.alt_start_i:
                 break
             if end == exon.alt_end_i:
                 break
             next_exon = tx_exons_genomic_coords[i + 1]
-            bp = start if start else end
             if strand == Strand.POSITIVE:
                 lte_exon = exon
                 gte_exon = next_exon
@@ -1187,6 +1203,7 @@ class ExonGenomicCoordsMapper:
                 gte_exon = exon
             if bp >= lte_exon.alt_end_i and bp <= gte_exon.alt_start_i:
                 break
+
         # Return current exon if end position is provided, next exon if start position
         # is provided.
         return exon.ord if end else exon.ord + 1

cool_seq_tool/sources/mane_transcript_mappings.py

@@ -61,7 +61,9 @@ class ManeTranscriptMappings:
             location information). The list is sorted so that a MANE Select entry comes
             first, followed by a MANE Plus Clinical entry, if available.
         """
-        data = self.df.filter(pl.col("symbol") == gene_symbol.upper())
+        data = self.df.filter(
+            pl.col("symbol").str.to_uppercase() == gene_symbol.upper()
+        )
 
         if len(data) == 0:
             _logger.warning(

{cool_seq_tool-0.7.1.dist-info → cool_seq_tool-0.9.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cool_seq_tool
-Version: 0.7.1
+Version: 0.9.0
 Summary: Common Operation on Lots of Sequences Tool
 Author: Kori Kuzma, James Stevenson, Katie Stahl, Alex Wagner
 License: MIT License
@@ -47,39 +47,39 @@ License-File: LICENSE
 Requires-Dist: asyncpg
 Requires-Dist: aiofiles
 Requires-Dist: boto3
-Requires-Dist: agct >=0.1.0-dev1
-Requires-Dist: polars ~=1.0
+Requires-Dist: agct>=0.1.0-dev1
+Requires-Dist: polars~=1.0
 Requires-Dist: hgvs
 Requires-Dist: biocommons.seqrepo
-Requires-Dist: pydantic ==2.*
-Requires-Dist: ga4gh.vrs ~=2.0.0a10
-Requires-Dist: wags-tails ~=0.1.3
+Requires-Dist: pydantic==2.*
+Requires-Dist: ga4gh.vrs~=2.0.0a10
+Requires-Dist: wags-tails~=0.2.2
 Requires-Dist: bioutils
 Provides-Extra: dev
-Requires-Dist: pre-commit >=3.7.1 ; extra == 'dev'
-Requires-Dist: ipython ; extra == 'dev'
-Requires-Dist: ipykernel ; extra == 'dev'
-Requires-Dist: psycopg2-binary ; extra == 'dev'
-Requires-Dist: ruff ==0.5.0 ; extra == 'dev'
+Requires-Dist: pre-commit>=3.7.1; extra == "dev"
+Requires-Dist: ipython; extra == "dev"
+Requires-Dist: ipykernel; extra == "dev"
+Requires-Dist: psycopg2-binary; extra == "dev"
+Requires-Dist: ruff==0.5.0; extra == "dev"
+Provides-Extra: tests
+Requires-Dist: pytest; extra == "tests"
+Requires-Dist: pytest-cov; extra == "tests"
+Requires-Dist: pytest-asyncio==0.18.3; extra == "tests"
+Requires-Dist: mock; extra == "tests"
 Provides-Extra: docs
-Requires-Dist: sphinx ==6.1.3 ; extra == 'docs'
-Requires-Dist: sphinx-autodoc-typehints ==1.22.0 ; extra == 'docs'
-Requires-Dist: sphinx-autobuild ==2021.3.14 ; extra == 'docs'
-Requires-Dist: sphinx-copybutton ==0.5.2 ; extra == 'docs'
-Requires-Dist: sphinxext-opengraph ==0.8.2 ; extra == 'docs'
-Requires-Dist: furo ==2023.3.27 ; extra == 'docs'
-Requires-Dist: sphinx-github-changelog ==1.2.1 ; extra == 'docs'
-Provides-Extra: test
-Requires-Dist: pytest ; extra == 'test'
-Requires-Dist: pytest-cov ; extra == 'test'
-Requires-Dist: pytest-asyncio ==0.18.3 ; extra == 'test'
-Requires-Dist: mock ; extra == 'test'
+Requires-Dist: sphinx==6.1.3; extra == "docs"
+Requires-Dist: sphinx-autodoc-typehints==1.22.0; extra == "docs"
+Requires-Dist: sphinx-autobuild==2021.3.14; extra == "docs"
+Requires-Dist: sphinx-copybutton==0.5.2; extra == "docs"
+Requires-Dist: sphinxext-opengraph==0.8.2; extra == "docs"
+Requires-Dist: furo==2023.3.27; extra == "docs"
+Requires-Dist: sphinx-github-changelog==1.2.1; extra == "docs"
 
 <h1 align="center">
-CoolSeqTool
+Cool-Seq-Tool
 </h1>
 
-[![image](https://img.shields.io/pypi/v/cool-seq-tool.svg)](https://pypi.python.org/pypi/cool-seq-tool) [![image](https://img.shields.io/pypi/l/cool-seq-tool.svg)](https://pypi.python.org/pypi/cool-seq-tool) [![image](https://img.shields.io/pypi/pyversions/cool-seq-tool.svg)](https://pypi.python.org/pypi/cool-seq-tool) [![Actions status](https://github.com/genomicmedlab/cool-seq-tool/actions/workflows/checks.yaml/badge.svg)](https://github.com/genomicmedlab/cool-seq-tool/actions/checks.yaml)
+[![image](https://img.shields.io/pypi/v/cool-seq-tool.svg)](https://pypi.python.org/pypi/cool-seq-tool) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.14007783.svg)](https://doi.org/10.5281/zenodo.14007783) [![image](https://img.shields.io/pypi/l/cool-seq-tool.svg)](https://pypi.python.org/pypi/cool-seq-tool) [![image](https://img.shields.io/pypi/pyversions/cool-seq-tool.svg)](https://pypi.python.org/pypi/cool-seq-tool) [![Actions status](https://github.com/genomicmedlab/cool-seq-tool/actions/workflows/checks.yaml/badge.svg)](https://github.com/genomicmedlab/cool-seq-tool/actions/checks.yaml)
 
 ---
 
@@ -90,18 +90,18 @@ CoolSeqTool
 ## Overview
 
 <!-- description -->
-The **CoolSeqTool** provides:
+The Common Operations On Lots-Of Sequences Tool, **Cool-Seq-Tool**, provides:
 
- - A Pythonic API on top of sequence data of interest to tertiary analysis tools, including mappings between gene names and transcripts, [MANE transcript](https://www.ncbi.nlm.nih.gov/refseq/MANE/) descriptions, and the [Universal Transcript Archive](https://github.com/biocommons/uta)
- - Augmented access to the [SeqRepo](https://github.com/biocommons/biocommons.seqrepo) database, including multiple additional methods and tools
- - Mapping tools that combine the above to support translation between references sequences, annotation layers, and MANE transcripts
+- A Pythonic API on top of sequence data of interest to tertiary analysis tools, including mappings between gene names and transcripts, [MANE transcript](https://www.ncbi.nlm.nih.gov/refseq/MANE/) descriptions, and transcript alignment data from the [Universal Transcript Archive](https://github.com/biocommons/uta)
+- Augmented access to the [SeqRepo](https://github.com/biocommons/biocommons.seqrepo) database, including multiple additional methods and tools
+- Mapping tools, including a transcript selection algorithm for selecting a representative transcript defined [here](https://coolseqtool.readthedocs.io/stable/transcript_selection.html), that combine the above to support translation between references sequences, annotation layers, and transcripts
 <!-- /description -->
 
 ---
 
 ## Install
 
-CoolSeqTool is available on [PyPI](https://pypi.org/project/cool-seq-tool)
+Cool-Seq-Tool is available on [PyPI](https://pypi.org/project/cool-seq-tool)
 
 ```shell
 python3 -m pip install cool-seq-tool
@@ -113,7 +113,7 @@ See the [installation instructions](https://coolseqtool.readthedocs.io/stable/in
 
 ## Usage
 
-All CoolSeqTool resources can be initialized by way of a top-level class instance:
+All Cool-Seq-Tool resources can be initialized by way of a top-level class instance:
 
 ```pycon
 >>> from cool_seq_tool import CoolSeqTool

{cool_seq_tool-0.7.1.dist-info → cool_seq_tool-0.9.0.dist-info}/RECORD

@@ -6,7 +6,7 @@ cool_seq_tool/handlers/__init__.py,sha256=KalQ46vX1MO4SJz2SlspKoIRy1n3c3Vp1t4Y2p
 cool_seq_tool/handlers/seqrepo_access.py,sha256=Jd19jbdUvPRPn_XWozL67ph-nSIxpb4_UUimapDrsm4,9162
 cool_seq_tool/mappers/__init__.py,sha256=O0JRxNFk8nWxD4v5ij47xelhvfVLdEXS43l2tzRuiUE,305
 cool_seq_tool/mappers/alignment.py,sha256=nV6PS3mhkQ2MD1GcpNBujBOqd3AKxYSYA9BCusFOa1o,9636
-cool_seq_tool/mappers/exon_genomic_coords.py,sha256=lfmzuVXaYT7w2FBDS3xhJNgETusllomFy5Utzhfhlpc,48782
+cool_seq_tool/mappers/exon_genomic_coords.py,sha256=XYHWYHL9PcBIKHB_EsN1YKwmhP-KLrGyZv8yH_7huuo,49533
 cool_seq_tool/mappers/liftover.py,sha256=lltx9zxfkrb5PHtJlKp3a39JCwPP4e0Zft-mQc1jXL8,3367
 cool_seq_tool/mappers/mane_transcript.py,sha256=nirxlf3EGVInFYG4fsAqiEmDdTc_h1XuPyX2ul-a7Rk,54368
 cool_seq_tool/resources/__init__.py,sha256=VwUC8YaucTS6SmRirToulZTF6CuvuLQRSxFfSfAovCc,77
@@ -14,11 +14,11 @@ cool_seq_tool/resources/data_files.py,sha256=3lhu28tzlSoTs4vHZNu-hhoAWRrPGuZj_oI
 cool_seq_tool/resources/status.py,sha256=L0KM-VG3N4Yuaqh3AKZd_2KPDLR0Y7rvW_OD6x8mF7A,5717
 cool_seq_tool/resources/transcript_mapping.tsv,sha256=AO3luYQAbFiCoRgiiPXotakb5pAwx1jDCeXpvGdIuac,24138769
 cool_seq_tool/sources/__init__.py,sha256=51QiymeptF7AeVGgV-tW_9f4pIUr0xtYbyzpvHOCneM,304
-cool_seq_tool/sources/mane_transcript_mappings.py,sha256=E_pj7FEBcB6HUR8yhSVibB0beMMlKJ62pK0qvl4y5nw,5358
+cool_seq_tool/sources/mane_transcript_mappings.py,sha256=Q6J57O2lLWXlgKT0zq3BIwkwFawySnORHOX-UxzfyDE,5399
 cool_seq_tool/sources/transcript_mappings.py,sha256=903RKTMBO2rbKh6iTQ1BEWnY4C7saBFMPw2_4ATuudg,10054
 cool_seq_tool/sources/uta_database.py,sha256=gc5wsKOIhvzhwFmPmqOY0hhaVfRkRSzYNa9tpBt81_U,35017
-cool_seq_tool-0.7.1.dist-info/LICENSE,sha256=IpqC9A-tZW7XXXvCS8c4AVINqkmpxiVA-34Qe3CZSjo,1072
-cool_seq_tool-0.7.1.dist-info/METADATA,sha256=Y9_RZI2iHpmNOFwXoFCCKyHs6aXmNrzKQfyHkmqUVmQ,6226
-cool_seq_tool-0.7.1.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-cool_seq_tool-0.7.1.dist-info/top_level.txt,sha256=cGuxdN6p3y16jQf6hCwWhE4OptwUeZPm_PNJlPb3b0k,14
-cool_seq_tool-0.7.1.dist-info/RECORD,,
+cool_seq_tool-0.9.0.dist-info/LICENSE,sha256=IpqC9A-tZW7XXXvCS8c4AVINqkmpxiVA-34Qe3CZSjo,1072
+cool_seq_tool-0.9.0.dist-info/METADATA,sha256=GgGZqNTW98YoV49Reizkz2UnPq1MqJOR4jjDHlcWTDQ,6556
+cool_seq_tool-0.9.0.dist-info/WHEEL,sha256=A3WOREP4zgxI0fKrHUG8DC8013e3dK3n7a6HDbcEIwE,91
+cool_seq_tool-0.9.0.dist-info/top_level.txt,sha256=cGuxdN6p3y16jQf6hCwWhE4OptwUeZPm_PNJlPb3b0k,14
+cool_seq_tool-0.9.0.dist-info/RECORD,,

{cool_seq_tool-0.7.1.dist-info → cool_seq_tool-0.9.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.1.0)
+Generator: setuptools (75.7.0)
 Root-Is-Purelib: true
 Tag: py3-none-any