Restore gff3 chromosome name aliasing (2.1.2)

.github/workflows/build-check.yml

@@ -0,0 +1,39 @@
+name: Build check
+
+on:
+  pull_request:
+    branches:
+      - master
+    paths:
+      - 'src/**'
+      - 'pyproject.toml'
+      - 'setup.cfg'
+      - 'VERSION.txt'
+      - 'MANIFEST.in'
+      - '.github/workflows/build-check.yml'
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v7
+
+      - name: Set up Python
+        uses: actions/setup-python@v7
+        with:
+          python-version: '3.12'
+
+      - name: Install build tools
+        run: |
+          python -m pip install --upgrade pip
+          pip install build twine
+
+      - name: Build sdist and wheel
+        run: python -m build
+
+      - name: Check package metadata
+        run: python -m twine check dist/*

.github/workflows/codeql.yml

@@ -23,12 +23,12 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v7
 
       - name: Initialize CodeQL
-        uses: github/codeql-action/init@v3
+        uses: github/codeql-action/init@v4
         with:
           languages: ${{ matrix.language }}
 
       - name: Perform CodeQL Analysis
-        uses: github/codeql-action/analyze@v3
+        uses: github/codeql-action/analyze@v4

.github/workflows/dependency-review.yml

@@ -23,9 +23,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: 'Checkout repository'
-        uses: actions/checkout@v4
+        uses: actions/checkout@v7
       - name: 'Dependency Review'
-        uses: actions/dependency-review-action@v4
+        uses: actions/dependency-review-action@v5.0.0
         # Commonly enabled options, see https://github.com/actions/dependency-review-action#configuration-options for all available options.
         with:
           comment-summary-in-pr: always

.github/workflows/docs-build.yml

@@ -18,10 +18,10 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v7
 
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@v7
         with:
           python-version: '3.12'
 

.github/workflows/lint.yml

@@ -18,7 +18,7 @@ jobs:
     steps:
       # Step 1: Checkout the repository
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v7
         with:
           fetch-depth: 0  # Fetch the full history to allow branch checkout
 

.github/workflows/tests.yml

@@ -13,9 +13,9 @@ jobs:
         python-version: ['3.10', '3.11', '3.12']
 
     steps:
-    - uses: actions/checkout@v4
+    - uses: actions/checkout@v7
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v5
+      uses: actions/setup-python@v7
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies

CHANGELOG.md

@@ -6,6 +6,10 @@
 * planned new feature: during import of long reads, (optionally) correct for short exon alignment issues.
 * separate new read import and classification of isoforms.
 
+## [2.1.2]
+
+* fixed: gff3 import silently dropped genes when the file's chromosome/seqid naming didn't match the genome (e.g. RefSeq-style accessions like `NC_000001.11` vs a plain `1`/`chr1` genome FASTA); chromosome name aliasing via `region` feature lines is now resolved again, restoring behavior lost when the tabix-based reader was replaced to fix #28 (#36)
+
 ## [2.1.1]
 
 * fixed: `Transcriptome[...]` gene lookup by name silently returned an arbitrary gene when the name was shared by multiple genes (common for duplicated gene symbols); now warns clearly, separately from the existing gene id ambiguity check (which itself had a bug: it checked against the combined id+name index instead of ids alone) (#27)

VERSION.txt

@@ -1 +1 @@
-2.1.1
+2.1.2

src/isotools/_transcriptome_io.py

@@ -1782,6 +1782,12 @@ def _read_gff_file(file_name, chromosomes, infer_genes=False, progress_bar=True)
 
     is_gz = file_name.endswith(".gz")
     openfun = gziplib.open if is_gz else open
+    # seqid -> chromosome name, learned from "region" feature lines that
+    # carry a "chromosome" attribute (common in RefSeq-style GFF3, where
+    # seqid is an accession like NC_000001.11 and "chromosome" gives the
+    # plain name, e.g. "1") -- restores the chromosome aliasing that the
+    # old TabixFile-based reader did via get_gff_chrom_dict
+    chrom_alias = {}
 
     with (
         openfun(file_name, "rt") as gff,
@@ -1808,20 +1814,35 @@ def _read_gff_file(file_name, chromosomes, infer_genes=False, progress_bar=True)
                 logger.warning("GFF line has fewer than 9 fields, skipping:\n%s", line)
                 continue
 
-            chrom = ls[0]
+            raw_chrom = ls[0]
+            chrom = chrom_alias.get(raw_chrom, raw_chrom)
+            region_info = None
+            if ls[2] == "region":
+                try:
+                    region_info = dict(
+                        [pair.split("=", 1) for pair in ls[8].rstrip(";").split(";")]
+                    )
+                except ValueError:
+                    region_info = {}
+                if "chromosome" in region_info:
+                    chrom = chrom_alias[raw_chrom] = region_info["chromosome"]
+
             if chromosomes is not None and chrom not in chromosomes:
                 logger.debug("skipping line from chr " + chrom)
                 continue
-            try:
-                info = dict(
-                    [pair.split("=", 1) for pair in ls[8].rstrip(";").split(";")]
-                )  # some gff lines end with ';' in gencode 36
-            except ValueError:
-                logger.warning(
-                    "GFF format error in infos (should be ; separated key=value pairs). Skipping line:\n%s",
-                    line,
-                )
-                continue
+            if region_info is not None:
+                info = region_info
+            else:
+                try:
+                    info = dict(
+                        [pair.split("=", 1) for pair in ls[8].rstrip(";").split(";")]
+                    )  # some gff lines end with ';' in gencode 36
+                except ValueError:
+                    logger.warning(
+                        "GFF format error in infos (should be ; separated key=value pairs). Skipping line:\n%s",
+                        line,
+                    )
+                    continue
 
             start, end = [int(i) for i in ls[3:5]]
             start -= 1  # to make 0 based

tests/data/refseq_style_chrom_alias.gff3

@@ -0,0 +1,5 @@
+##gff-version 3
+NC_000001.11	RefSeq	region	1	248956422	.	+	.	ID=NC_000001.11:1..248956422;chromosome=1;gbkey=Src
+NC_000001.11	BestRefSeq	gene	100	500	.	+	.	ID=GENE1
+NC_000001.11	BestRefSeq	transcript	100	500	.	+	.	ID=GENE1.1;Parent=GENE1
+NC_000001.11	BestRefSeq	exon	100	500	.	+	.	Parent=GENE1.1

tests/data_import_test.py

@@ -16,6 +16,22 @@ def test_import_gff():
     assert True
 
 
+def test_import_gff_chromosome_alias():
+    # regression test for #36: RefSeq-style GFF3 files use an accession as
+    # seqid (e.g. NC_000001.11) with the plain chromosome name (e.g. "1")
+    # given via a "chromosome" attribute on a "region" feature line. Genes
+    # were previously silently dropped when filtering against the plain
+    # name, since the tabix-based alias resolution was lost when the
+    # reader was rewritten to fix #28.
+    transcriptome = Transcriptome.from_reference(
+        "tests/data/refseq_style_chrom_alias.gff3", chromosomes={"1"}
+    )
+    assert len(transcriptome) == 1, "gene should be found via chromosome alias"
+    gene = next(iter(transcriptome))
+    assert gene.id == "GENE1"
+    assert gene.chrom == "1", "gene should be indexed under the aliased chromosome name"
+
+
 def test_add_sample_from_csv_missing_gene_info():
     # regression test for #25: a coverage csv row referencing a transcript_id
     # not found in the transcripts file previously broke gene_id/chr column