Merge pull request #133 from sudlab/ns-rse/131-expand-test-fixtures

isoslam/all_introns_counts_and_info.py

@@ -112,6 +112,9 @@ def fragment_iterator(read_iterator):
 
             # Extract features
             pair_features = isoslam.extract_features_from_pair(pair)
+            # DEBUGGING - Get information on features
+            if i_total_progress in (484):
+                print(f"{pair_features=}")
             # Temporary code sets up variables from the returned dictionary to match those currently used
             read1_start = pair_features["read1"]["start"]
             read1_end = pair_features["read1"]["end"]

tests/conftest.py

@@ -91,24 +91,60 @@ def aligned_segment_unassigned_18029(bam_unaligned_file1: AlignmentFile) -> Alig
 
 
 @pytest.fixture()
-def bam_sorted_assigned_file() -> list[AlignedSegment]:
+def bam_sorted_assigned_file_no4sU() -> list[AlignedSegment]:
     """Return a list of a ``AlignedSegment`` from a ``.bam`` file that has been sorted and assigned."""
     return list(io.load_file(BAM_SORTED_ASSIGNED_DIR / "d0_no4sU_filtered_remapped_sorted.sorted.assigned.bam"))
 
 
 @pytest.fixture()
-def aligned_segment_assigned_15967(bam_sorted_assigned_file: list[AlignedSegment]) -> AlignedSegment:
+def aligned_segment_assigned_15967(bam_sorted_assigned_file_no4sU: list[AlignedSegment]) -> AlignedSegment:
     """Return a single assigned AlignedSegment where start is 15967."""
-    return [x for x in bam_sorted_assigned_file if x.reference_start == 15967][0]
+    return [x for x in bam_sorted_assigned_file_no4sU if x.reference_start == 15967][0]
 
 
 @pytest.fixture()
-def aligned_segment_assigned_14770(bam_sorted_assigned_file: list[AlignedSegment]) -> AlignedSegment:
+def aligned_segment_assigned_14770(bam_sorted_assigned_file_no4sU: list[AlignedSegment]) -> AlignedSegment:
     """Return a single assigned AlignedSegment where start is 14770."""
-    return [x for x in bam_sorted_assigned_file if x.reference_start == 14770][0]
+    return [x for x in bam_sorted_assigned_file_no4sU if x.reference_start == 14770][0]
 
 
 @pytest.fixture()
-def aligned_segment_assigned_17814(bam_sorted_assigned_file: list[AlignedSegment]) -> AlignedSegment:
+def aligned_segment_assigned_17814(bam_sorted_assigned_file_no4sU: list[AlignedSegment]) -> AlignedSegment:
     """Return a single assigned AlignedSegment where start is 17814."""
-    return [x for x in bam_sorted_assigned_file if x.reference_start == 17814][0]
+    return [x for x in bam_sorted_assigned_file_no4sU if x.reference_start == 17814][0]
+
+
+@pytest.fixture()
+def bam_sorted_assigned_file_0hr1() -> list[AlignedSegment]:
+    """Return a list of a ``AlignedSegment`` from a ``.bam`` file that has been sorted and assigned."""
+    return list(io.load_file(BAM_SORTED_ASSIGNED_DIR / "d0_0hr1_filtered_remapped_sorted.sorted.assigned.bam"))
+
+
+@pytest.fixture()
+def aligned_segment_assigned_21051(bam_sorted_assigned_file_0hr1: list[AlignedSegment]) -> AlignedSegment:
+    """
+    Return a single assigned AlignedSegment where start is 21051.
+
+    Along with the next fixture (20906) this was the 484th pair of reads that caused some early problems with regression
+    tests which is why they have been pulled out and added to the parameterised tests.
+
+    The reason these problems occurred is because initially 9 alignments are found at this location but 6 of these
+    should be filtered out subsequently, a mistake in refactoring used the wrong length. But this will serve as a useful
+    aligned segment to be testing because of this filtering.
+    """
+    return [x for x in bam_sorted_assigned_file_0hr1 if x.reference_start == 21051][0]
+
+
+@pytest.fixture()
+def aligned_segment_assigned_20906(bam_sorted_assigned_file_0hr1: list[AlignedSegment]) -> AlignedSegment:
+    """
+    Return a single assigned AlignedSegment where start is 20906.
+
+    Along with the previous fixture (21051) this was the 484th pair of reads that cause some early problems with
+    regression tests which is why they have been pulled out and added to the parameterised tests.
+
+    The reason these problems occurred is because initially 9 alignments are found at this location but 6 of these
+    should be filtered out subsequently, a mistake in refactoring used the wrong length. But this will serve as a useful
+    aligned segment to be testing because of this filtering.
+    """
+    return [x for x in bam_sorted_assigned_file_0hr1 if x.reference_start == 20906][0]

tests/test_isoslam.py

@@ -162,6 +162,28 @@ def test_extract_segment_pairs(bam_file: str | Path, expected_length: int) -> No
             (16117,),
             id="15967 - Assigned to MSTRG.63147",
         ),
+        pytest.param(
+            "aligned_segment_assigned_21051",
+            21051,
+            21201,
+            150,
+            "Unassigned_NoFeatures",
+            None,
+            (21051,),
+            (21201,),
+            id="21051 - Unassigned",
+        ),
+        pytest.param(
+            "aligned_segment_assigned_20906",
+            20906,
+            21056,
+            150,
+            "Unassigned_NoFeatures",
+            None,
+            (20906,),
+            (21056,),
+            id="20906 - Unassigned",
+        ),
     ],
 )
 def test_extract_features_from_read(
@@ -177,7 +199,7 @@ def test_extract_features_from_read(
 ) -> None:
     """Test extract of features from an unassigned and assigned segment reads."""
     segment = isoslam.extract_features_from_read(request.getfixturevalue(aligned_segment))
-    print(f"{segment['length']}")
+    print(f"{segment=}")
     assert isinstance(segment, dict)
     assert segment["start"] == start
     assert segment["end"] == end
@@ -214,7 +236,32 @@ def test_extract_features_from_read(
                     "block_end": (14876,),
                 },
             },
-            id="28584 and 17416 - Assignment and Transcript are None",
+            id="28584 and 17416 - Assigned and transcript MSTRG.63147",
+        ),
+        pytest.param(
+            "aligned_segment_assigned_21051",
+            "aligned_segment_assigned_20906",
+            {
+                "read1": {
+                    "start": 21051,
+                    "end": 21201,
+                    "length": 150,
+                    "status": "Unassigned_NoFeatures",
+                    "transcript": None,
+                    "block_start": (21051,),
+                    "block_end": (21201,),
+                },
+                "read2": {
+                    "start": 20906,
+                    "end": 21056,
+                    "length": 150,
+                    "status": "Unassigned_NoFeatures",
+                    "transcript": None,
+                    "block_start": (20906,),
+                    "block_end": (21056,),
+                },
+            },
+            id="21051 and 21056 - Assignment and Transcript are None",
         ),
     ],
 )
@@ -262,6 +309,18 @@ def test_extract_features_from_pair(
             10,
             id="15967 - Assigned to MSTRG.63147",
         ),
+        pytest.param(
+            "aligned_segment_assigned_21051",
+            None,
+            0,
+            id="21051 - Unassigned",
+        ),
+        pytest.param(
+            "aligned_segment_assigned_20906",
+            None,
+            0,
+            id="20906 - Unassigned",
+        ),
     ],
 )
 def test_extract_utron(
@@ -309,6 +368,18 @@ def test_extract_utron(
             (16117,),
             id="15967 - Assigned to MSTRG.63147",
         ),
+        pytest.param(
+            "aligned_segment_assigned_21051",
+            (21051,),
+            (21201,),
+            id="21051 - Unassigned",
+        ),
+        pytest.param(
+            "aligned_segment_assigned_20906",
+            (20906,),
+            (21056,),
+            id="20906 - Unassigned",
+        ),
     ],
 )
 def test_zip_blocks(