tests: Regression test for all_introns_counts_and_info.py

.github/workflows/tests.yaml

@@ -40,6 +40,10 @@ jobs:
           pip install --upgrade virtualenv
           pip install --upgrade pip setuptools
           virtualenv --upgrade-embed-wheels
+          pip install numpy
+          pip show numpy
+          pip install cgatcore
+          pip install cgat
           pip install -e .[tests]
       - name: Test with pytest
         run: |

pyproject.toml

@@ -37,13 +37,14 @@ keywords = [
 ]
 dependencies = [
   "apsw",
+  "cgat",
   "cgatcore",
   "gevent",
   "matplotlib",
   "numpy",
   "pandas",
   "pysam",
-  "ruffus",
+  # "ruffus",
   "sqlalchemy",
 ]
 
@@ -55,8 +56,8 @@ tests = [
   "pytest-cov",
   "pytest-github-actions-annotate-failures",
   "pytest-mpl",
-  "pytest-regtest",
   "pytest-testmon",
+  "syrupy",
 ]
 docs = [
   "Sphinx",

tests/resources/bed/test_coding_introns.bed

@@ -0,0 +1,10 @@
+9	14940	15080	ENST00000442898_intron	0	-
+9	15149	15908	ENST00000442898_intron	0	-
+9	16061	16717	ENST00000442898_intron	0	-
+9	16876	16964	ENST00000442898_intron	0	-
+9	17166	17343	ENST00000442898_intron	0	-
+9	17479	17718	ENST00000442898_intron	0	-
+9	17855	18027	ENST00000442898_intron	0	-
+9	18174	18380	ENST00000442898_intron	0	-
+9	18492	24850	ENST00000442898_intron	0	-
+9	25004	29601	ENST00000442898_intron	0	-

tests/resources/bed6/test_coding_introns.bed

@@ -0,0 +1,10 @@
+9	14940	15080	ENST00000442898_intron	0	-
+9	15149	15908	ENST00000442898_intron	0	-
+9	16061	16717	ENST00000442898_intron	0	-
+9	16876	16964	ENST00000442898_intron	0	-
+9	17166	17343	ENST00000442898_intron	0	-
+9	17479	17718	ENST00000442898_intron	0	-
+9	17855	18027	ENST00000442898_intron	0	-
+9	18174	18380	ENST00000442898_intron	0	-
+9	18492	24850	ENST00000442898_intron	0	-
+9	25004	29601	ENST00000442898_intron	0	-

tests/resources/fasta/hg38_noalt_filtered.fa.fai

@@ -0,0 +1 @@
+chr9	31000	6	60	61

tests/resources/gtf/test_wash1.gtf

@@ -0,0 +1,12 @@
+chr9	StringTie	transcript	14521	30753	1000	-	.	gene_id "MSTRG.63147"; transcript_id "ENST00000442898"; gene_name "WASH1"; ref_gene_id "ENSG00000181404"; 
+chr9	StringTie	exon	14521	14940	1000	-	.	gene_id "MSTRG.63147"; transcript_id "ENST00000442898"; exon_number "1"; gene_name "WASH1"; ref_gene_id "ENSG00000181404"; 
+chr9	StringTie	exon	15081	15149	1000	-	.	gene_id "MSTRG.63147"; transcript_id "ENST00000442898"; exon_number "2"; gene_name "WASH1"; ref_gene_id "ENSG00000181404"; 
+chr9	StringTie	exon	15909	16061	1000	-	.	gene_id "MSTRG.63147"; transcript_id "ENST00000442898"; exon_number "3"; gene_name "WASH1"; ref_gene_id "ENSG00000181404"; 
+chr9	StringTie	exon	16718	16876	1000	-	.	gene_id "MSTRG.63147"; transcript_id "ENST00000442898"; exon_number "4"; gene_name "WASH1"; ref_gene_id "ENSG00000181404"; 
+chr9	StringTie	exon	16965	17166	1000	-	.	gene_id "MSTRG.63147"; transcript_id "ENST00000442898"; exon_number "5"; gene_name "WASH1"; ref_gene_id "ENSG00000181404"; 
+chr9	StringTie	exon	17344	17479	1000	-	.	gene_id "MSTRG.63147"; transcript_id "ENST00000442898"; exon_number "6"; gene_name "WASH1"; ref_gene_id "ENSG00000181404"; 
+chr9	StringTie	exon	17719	17855	1000	-	.	gene_id "MSTRG.63147"; transcript_id "ENST00000442898"; exon_number "7"; gene_name "WASH1"; ref_gene_id "ENSG00000181404"; 
+chr9	StringTie	exon	18028	18174	1000	-	.	gene_id "MSTRG.63147"; transcript_id "ENST00000442898"; exon_number "8"; gene_name "WASH1"; ref_gene_id "ENSG00000181404"; 
+chr9	StringTie	exon	18381	18492	1000	-	.	gene_id "MSTRG.63147"; transcript_id "ENST00000442898"; exon_number "9"; gene_name "WASH1"; ref_gene_id "ENSG00000181404"; 
+chr9	StringTie	exon	24851	25004	1000	-	.	gene_id "MSTRG.63147"; transcript_id "ENST00000442898"; exon_number "10"; gene_name "WASH1"; ref_gene_id "ENSG00000181404"; 
+chr9	StringTie	exon	29602	30753	1000	-	.	gene_id "MSTRG.63147"; transcript_id "ENST00000442898"; exon_number "11"; gene_name "WASH1"; ref_gene_id "ENSG00000181404"; 

tests/test_all_introns_counts_and_info.py

@@ -0,0 +1,41 @@
+"""Tests for all_introns_counts_and_info module."""
+
+import argparse
+from pathlib import Path
+
+import pytest
+
+# import syrupy
+from isoslam import all_introns_counts_and_info
+
+BASE_DIR = Path.cwd()
+TEST_DIR = BASE_DIR / "tests"
+RESOURCES = TEST_DIR / "resources"
+GTF_DIR = RESOURCES / "gtf"
+BED_DIR = RESOURCES / "bed"
+VCF_DIR = RESOURCES / "vcf"
+BAM_DIR = RESOURCES / "bam"
+
+
+@pytest.mark.parametrize(
+    ("file_path"),
+    [
+        pytest.param(BAM_DIR / "sorted_assigned" / "d0_0hr1_filtered_remapped_sorted.sorted.assigned.bam", id="file 1"),
+        pytest.param(
+            BAM_DIR / "sorted_assigned" / "d0_no4sU_filtered_remapped_sorted.sorted.assigned.bam", id="file 2"
+        ),
+    ],
+)
+def test_main(file_path: Path, tmp_path: Path, regtest) -> None:
+    """Regression test to check that main() function returns the expected data structure."""
+    args = argparse.Namespace(
+        infile_bam=str(file_path),
+        gtf_path=list(GTF_DIR.glob("*.gtf"))[0],
+        utron_bed=list(BED_DIR.glob("*.bed"))[0],
+        vcf_path=list(VCF_DIR.glob("*.vcf.gz"))[0],
+        outfile_tsv=str(tmp_path / "test.tsv"),
+    )
+    results = all_introns_counts_and_info.main(argv=args)
+    # Ideally would like to use syrupy to test snapshots but pd.DataFrame() are not yet supported
+    # https://github.com/syrupy-project/syrupy/issues/887
+    print(results.to_string(float_format="{:.4e}".format), file=regtest)