From 2c8e894b9ea6847c7600080b3d13de6a886822e8 Mon Sep 17 00:00:00 2001
From: Larissa Glass <larissa.glass@unibas.ch>
Date: Tue, 8 Nov 2022 10:41:02 +0000
Subject: [PATCH] Resolve "Tests"
---
README.md | 11 ++-
tests/__init__.py | 1 +
tests/resources/Annotation1.gtf | 5 ++
tests/resources/Annotations2.gtf | 12 +++
tests/resources/Transcript1.csv | 7 ++
tests/resources/Transcript2.tsv | 7 ++
tests/test_main.py | 135 +++++++++++++++++++++++++++++++
7 files changed, 177 insertions(+), 1 deletion(-)
create mode 100644 tests/__init__.py
create mode 100644 tests/resources/Annotation1.gtf
create mode 100644 tests/resources/Annotations2.gtf
create mode 100644 tests/resources/Transcript1.csv
create mode 100644 tests/resources/Transcript2.tsv
create mode 100644 tests/test_main.py
diff --git a/README.md b/README.md
index 0a814af..d29a0a8 100644
--- a/README.md
+++ b/README.md
@@ -39,4 +39,13 @@ To generate the sampled transcripts, run
transcript-generator --transcripts <transcripts_file> --annotation <annotations_file> --prob_inclusion=<probability_inclusion>
```
-where the transcripts file should be csv-formatted, the annotation file gtf-formatted and the inclusion probability for introns a float in the range [0,1].
\ No newline at end of file
+where the transcripts file should be csv-formatted, the annotation file gtf-formatted and the inclusion probability for introns a float in the range [0,1].
+
+
+# Development
+
+To perform all tests, make sure your environment corresponds to the `environment.yml` file and run
+
+```
+pytest tests
+```
\ No newline at end of file
diff --git a/tests/__init__.py b/tests/__init__.py
new file mode 100644
index 0000000..8c26b48
--- /dev/null
+++ b/tests/__init__.py
@@ -0,0 +1 @@
+"""Tests for the package tsg."""
diff --git a/tests/resources/Annotation1.gtf b/tests/resources/Annotation1.gtf
new file mode 100644
index 0000000..c794aaa
--- /dev/null
+++ b/tests/resources/Annotation1.gtf
@@ -0,0 +1,5 @@
+1 havana gene 1 100 . + . gene_id "GENE1";
+1 havana transcript 1 100 . + . gene_id "GENE1"; transcript_id "TRANSCRIPT1"; transcript_support_level "1";
+1 havana exon 1 20 . + . gene_id "GENE1"; transcript_id "TRANSCRIPT1"; exon_number "1"; exon_id "ENSE00002234944"; transcript_support_level "1";
+1 havana exon 50 70 . + . gene_id "GENE1"; transcript_id "TRANSCRIPT1"; exon_number "2"; exon_id "ENSE00003582793"; transcript_support_level "1";
+1 havana exon 80 100 . + . gene_id "GENE1"; transcript_id "TRANSCRIPT1"; exon_number "3"; exon_id "ENSE00002312635"; transcript_support_level "1";
diff --git a/tests/resources/Annotations2.gtf b/tests/resources/Annotations2.gtf
new file mode 100644
index 0000000..d7f079e
--- /dev/null
+++ b/tests/resources/Annotations2.gtf
@@ -0,0 +1,12 @@
+1 havana transcript 1000 2000 . - . gene_id "GENE2"; transcript_id "TRANSCRIPT2"; transcript_support_level "1";
+1 havana exon 1980 2000 . - . gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "1"; exon_id "ENSE00001890219"; transcript_support_level "1";
+1 havana exon 1900 1950 . - . gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "2"; exon_id "ENSE00003507205"; transcript_support_level "1";
+1 havana exon 1800 1850 . - . gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "3"; exon_id "ENSE00003477500"; transcript_support_level "1";
+1 havana exon 1700 1750 . - . gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "4"; exon_id "ENSE00003565697"; transcript_support_level "1";
+1 havana exon 1600 1650 . - . gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "5"; exon_id "ENSE00003475637"; transcript_support_level "1";
+1 havana exon 1500 1550 . - . gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "6"; exon_id "ENSE00003502542"; transcript_support_level "1";
+1 havana exon 1400 1450 . - . gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "7"; exon_id "ENSE00003553898"; transcript_support_level "1";
+1 havana exon 1300 1350 . - . gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "8"; exon_id "ENSE00003621279"; transcript_support_level "1";
+1 havana exon 1200 1250 . - . gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "9"; exon_id "ENSE00002030414"; transcript_support_level "1";
+1 havana exon 1100 1150 . - . gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "10"; exon_id "ENSE00001935574"; transcript_support_level "1";
+1 havana exon 1000 1050 . - . gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "11"; exon_id "ENSE00001843071"; transcript_support_level "1";
diff --git a/tests/resources/Transcript1.csv b/tests/resources/Transcript1.csv
new file mode 100644
index 0000000..6635236
--- /dev/null
+++ b/tests/resources/Transcript1.csv
@@ -0,0 +1,7 @@
+TRANSCRIPT1,92
+TRANSCRIPT2,13
+TRANSCRIPT3,73
+TRANSCRIPT4,83
+TRANSCRIPT5,32
+TRANSCRIPT6,136
+TRANSCRIPT7,36
\ No newline at end of file
diff --git a/tests/resources/Transcript2.tsv b/tests/resources/Transcript2.tsv
new file mode 100644
index 0000000..06b14c4
--- /dev/null
+++ b/tests/resources/Transcript2.tsv
@@ -0,0 +1,7 @@
+TRANSCRIPT1 92
+TRANSCRIPT2 13
+TRANSCRIPT3 73
+TRANSCRIPT4 83
+TRANSCRIPT5 32
+TRANSCRIPT6 136
+TRANSCRIPT7 36
\ No newline at end of file
diff --git a/tests/test_main.py b/tests/test_main.py
new file mode 100644
index 0000000..48b9b55
--- /dev/null
+++ b/tests/test_main.py
@@ -0,0 +1,135 @@
+"""Tests for main module"""
+
+import numpy as np
+import pandas as pd
+import pytest
+from tsg.main import Gtf, TranscriptGenerator, dict_to_str, str_to_dict
+
+
+class TestFreeTextParsing:
+ """Test if free text dictionary is correctly parsed."""
+
+ def test_str2dict(self):
+ res = str_to_dict(
+ 'gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "1"; exon_id "EXON1";'
+ )
+
+ assert res == {
+ "gene_id": "GENE2",
+ "transcript_id": "TRANSCRIPT2",
+ "exon_number": "1",
+ "exon_id": "EXON1",
+ }
+
+ def test_dict2str(self):
+ res = dict_to_str(
+ {
+ "gene_id": "GENE2",
+ "transcript_id": "TRANSCRIPT2",
+ "exon_number": "1",
+ "exon_id": "EXON1",
+ }
+ )
+ print(res)
+ assert (
+ res
+ == 'gene_id "GENE2"; transcript_id "TRANSCRIPT2"; exon_number "1"; exon_id "EXON1";'
+ )
+
+
+class TestGtf:
+ "Test if Gtf class works correctly."
+ cols = [
+ "seqname",
+ "source",
+ "feature",
+ "start",
+ "end",
+ "score",
+ "strand",
+ "frame",
+ "free_text",
+ ]
+
+ def test_init(self):
+ annotations = Gtf()
+ annotations.read_file("tests/resources/Annotation1.gtf")
+
+ assert annotations.parsed == False
+ assert annotations.original_columns == self.cols
+ assert annotations.free_text_columns == []
+
+ def test_parsed(self):
+ annotations = Gtf()
+ annotations.read_file("tests/resources/Annotation1.gtf")
+ annotations.parse_free_text()
+
+ assert annotations.parsed == True
+ assert set(annotations.free_text_columns) == set(
+ [
+ "gene_id",
+ "transcript_id",
+ "exon_number",
+ "exon_id",
+ "transcript_support_level",
+ ]
+ )
+ assert set(annotations.original_columns) == set(
+ ["seqname", "source", "feature", "start", "end", "score", "strand", "frame"]
+ )
+
+
+class TestTranscriptGenerator:
+ cols = [
+ "start",
+ "end",
+ "strand",
+ "transcript_id",
+ ]
+
+ df1 = pd.DataFrame(
+ {
+ "start": [1, 50, 80],
+ "end": [20, 70, 100],
+ "strand": ["+", "+", "+"],
+ "exon_id": ["EXON1", "EXON2", "EXON3"],
+ }
+ )
+ df2 = pd.DataFrame(columns=["start", "end", "strand"])
+
+ def test_init(self):
+ transcripts = TranscriptGenerator("TRANSCRIPT1", 3, self.df1, 0.05)
+
+ assert transcripts.strand == "+"
+
+ def test_init_2(self):
+ with pytest.raises(AssertionError):
+ transcripts = TranscriptGenerator("TRANSCRIPT2", 3, self.df2, 0.05)
+
+ def test_init_3(self):
+ with pytest.raises(AssertionError):
+ transcripts = TranscriptGenerator("TRANSCRIPT1", 0, self.df1, 0.05)
+
+ def test_inclusions(self):
+ transcripts = TranscriptGenerator("TRANSCRIPT1", 3, self.df1, 0.5)
+ res = transcripts._get_inclusions()
+
+ assert res.shape == (3, 3)
+
+ def test_unique_inclusions(self):
+ transcripts = TranscriptGenerator("TRANSCRIPT1", 3, self.df1, 0.5)
+ res1, res2, res3 = transcripts._get_unique_inclusions()
+
+ def test_get_df(self):
+ inclusions = [False, True, False]
+ expected_end = pd.Series([20, 79, 100], name="end")
+ transcript_id = "TRANSCRIPT1_1"
+
+ transcripts = TranscriptGenerator("TRANSCRIPT1", 3, self.df1, 0.5)
+ res = transcripts._get_df(inclusions, transcript_id)
+
+ assert res["transcript_id"].unique().item() == "TRANSCRIPT1_1"
+ assert res["strand"].unique().item() == "+"
+ assert res["exon_id"].tolist() == ["EXON1", "EXON2_1", "EXON3"]
+ pd.testing.assert_series_equal(res["start"], self.df1["start"])
+ pd.testing.assert_series_equal(res["end"], expected_end)
--
GitLab