some cleaning over the project structure

.gitignore

@@ -142,8 +142,9 @@ presentations
 scratch
 test_pinf_pmir_pipo
 .vscode
-
+.idea
 # Rstudio
 .Rproj.user
 *.Rproj
-.Rhistory
+.Rhistory
+poetry.lock

pyproject.toml

@@ -1,44 +1,45 @@
-[build-system]
-requires = ["setuptools", "wheel"]
-build-backend = "setuptools.build_meta"
-
-[project]
+[tool.poetry]
 name = "krisp"
 version = "0.1.6"
+description = "A lightweight tool for finding diagnostic regions in whole genome data"
 authors = [
-  { name="Zachary S.L. Foster", email="[email protected]" },
-  { name="Andrew S. Tupper", email="[email protected]" },
-  { name="Niklaus J. Grunwald", email="[email protected]" },
+    "Zachary S.L. Foster <[email protected]>",
+    "Andrew S. Tupper <[email protected]>",
+    "Niklaus J. Grunwald <[email protected]>"
 ]
 maintainers = [
-  { name="Zachary S.L. Foster", email="[email protected]" },
-  { name="Andrew S. Tupper", email="[email protected]" },
-  { name="Niklaus J. Grunwald", email="[email protected]" },
+    "Zachary S.L. Foster <[email protected]>",
+    "Andrew S. Tupper <[email protected]>",
+    "Niklaus J. Grunwald <[email protected]>"
 ]
-description = "A lightweight tool for finding diagnostic regions in whole genome data"
 readme = "README.md"
-requires-python = ">=3.6"
+license = "MIT"
+homepage = "https://github.com/grunwaldlab/krisp"
+repository = "https://github.com/grunwaldlab/krisp"
+documentation = "https://github.com/grunwaldlab/krisp"
+keywords = ["genome", "diagnostic", "bioinformatics"]
 classifiers = [
     "Programming Language :: Python :: 3",
     "License :: OSI Approved :: MIT License",
-    "Operating System :: OS Independent",
-]
-dependencies = [
-    "pysam",
-    "Bio",
-    "nltk",
-    "prettytable",
-    "pandas",
-    "prettytable",
-    "primer3-py",
-    "colorama"
+    "Operating System :: OS Independent"
 ]
 
-[project.urls]
-"Homepage" = "https://github.com/grunwaldlab/krisp"
-"Bug Tracker" = "https://github.com/grunwaldlab/krisp/issues"
+[tool.poetry.dependencies]
+python = ">=3.10"
+pysam = "^0.22.1"
+bio = "^1.7.1"
+nltk = "^3.9.1"
+prettytable = "^3.11.0"
+pandas = "^2.2.2"
+primer3-py = "^2.0.3"
+colorama = "^0.4.6"
+
 
-[project.scripts]
+[tool.poetry.scripts]
 krisp_fasta = "krisp.krisp_fasta.krisp_fasta:main"
 kstream = "krisp.kstream.kstream:main"
 krisp_vcf = "krisp.krisp_vcf.krisp_vcf:main"
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"

tests/test_find_diag_region.py

@@ -1,27 +1,34 @@
-from krisp_vcf.find_diag_var import *
-from krisp_vcf.find_diag_var import _parse_group_data, _check_variant, GroupedVariant
-from krisp_vcf.find_diag_region import GroupedRegion, find_diag_region
+from krisp.krisp_vcf.find_diag_var import (
+    _parse_group_data,
+    GroupedVariant,
+)
+from krisp.krisp_vcf import GroupedRegion, find_diag_region
 import pysam
 from itertools import islice
 import unittest
-from Bio import SeqIO
 
 
 class TestGroupedRegion(unittest.TestCase):
     def setUp(self):
         pysam.set_verbosity(0)
-        self.vcf = pysam.VariantFile('test_data/unfilt_allscafs_n666.vcf.gz')
-        self.groups = _parse_group_data('test_data/test_metadata.tsv')
-        self.groups = {g: v for g, v in self.groups.items() if g in ["NA1", "NA2", "EU1", "EU2"]}
-        self.ref = 'test_data/PR-102_v3.1.fasta'
+        self.vcf = pysam.VariantFile("test_data/unfilt_allscafs_n666.vcf.gz")
+        self.groups = _parse_group_data("test_data/test_metadata.tsv")
+        self.groups = {
+            g: v for g, v in self.groups.items() if g in ["NA1", "NA2", "EU1", "EU2"]
+        }
+        self.ref = "test_data/PR-102_v3.1.fasta"
         self.variant1 = next(self.vcf)
         self.variant2 = next(self.vcf)
         self.variant3 = next(self.vcf)
         self.diag_var = next(islice(self.vcf, 1020, 1021))
         self.vcf_subset = islice(self.vcf, 10, 15)
 
     def test_init(self):
-        x = GroupedRegion(GroupedVariant.from_vcf(self.vcf_subset, groups=self.groups), group="NA1", reference=self.ref)
+        x = GroupedRegion(
+            GroupedVariant.from_vcf(self.vcf_subset, groups=self.groups),
+            group="NA1",
+            reference=self.ref,
+        )
         print(x.region_length())
 
     # def test_sliding_window(self):
@@ -34,7 +41,4 @@ def test_init(self):
     #         print(len(x.variants))
 
     def test_find_diag_region(self):
-        find_diag_region(self.vcf,
-                         groups=self.groups,
-                         reference=self.ref)
-
+        find_diag_region(self.vcf, groups=self.groups, reference=self.ref)

tests/test_find_diag_var.py

@@ -1,38 +1,49 @@
-from diagvar.find_diag_var import *
-from diagvar.find_diag_var import _parse_group_data, _check_variant, GroupedVariant
+from krisp.krisp_vcf.find_diag_var import (
+    _parse_group_data,
+    GroupedVariant,
+)
 import pysam
 from itertools import islice
 import unittest
 
 
 class TestGroupedVariant(unittest.TestCase):
-
     def setUp(self):
         pysam.set_verbosity(0)
-        self.vcf = pysam.VariantFile('test_data/unfilt_allscafs_n666.vcf.gz')
-        self.groups = _parse_group_data('test_data/test_metadata.tsv')
-        self.groups = {k: v for k, v in self.groups.items() if k in ['NA1','NA2', 'EU1', 'EU2']}
+        self.vcf = pysam.VariantFile("test_data/unfilt_allscafs_n666.vcf.gz")
+        self.groups = _parse_group_data("test_data/test_metadata.tsv")
+        self.groups = {
+            k: v for k, v in self.groups.items() if k in ["NA1", "NA2", "EU1", "EU2"]
+        }
         self.variant1 = GroupedVariant(next(self.vcf), self.groups)
         self.variant2 = GroupedVariant(next(self.vcf), self.groups)
         self.variant3 = GroupedVariant(next(self.vcf), self.groups)
         self.diag_var = GroupedVariant(next(islice(self.vcf, 1020, 1021)), self.groups)
         self.vcf_subset = islice(self.vcf, 10, 15)
 
     def test_init(self):
-        self.assertEqual(self.diag_var.sample_counts,
-                         {'NA1': 222, 'EU1': 202, 'EU2': 0, 'NA2': 18})
-        self.assertEqual(self.diag_var.allele_counts,
-                         {'NA1': {'T': 222}, 'EU1': {'C': 202}, 'EU2': {}, 'NA2': {'C': 18}})
-        self.assertEqual(self.diag_var.conserved,
-                         {'NA1': 'T', 'EU1': 'C', 'EU2': None, 'NA2': 'C'})
-        self.assertEqual(self.diag_var.diagnostic,
-                         {'NA1': None, 'EU1': None, 'EU2': None, 'NA2': None})
+        self.assertEqual(
+            self.diag_var.sample_counts, {"NA1": 222, "EU1": 202, "EU2": 0, "NA2": 18}
+        )
+        self.assertEqual(
+            self.diag_var.allele_counts,
+            {"NA1": {"T": 222}, "EU1": {"C": 202}, "EU2": {}, "NA2": {"C": 18}},
+        )
+        self.assertEqual(
+            self.diag_var.conserved, {"NA1": "T", "EU1": "C", "EU2": None, "NA2": "C"}
+        )
+        self.assertEqual(
+            self.diag_var.diagnostic,
+            {"NA1": None, "EU1": None, "EU2": None, "NA2": None},
+        )
 
     def test_from_vcf(self):
         gen = GroupedVariant.from_vcf(self.vcf_subset, groups=self.groups)
-        self.assertEqual(next(gen).allele_counts,
-                         {'NA1': {'T': 236}, 'EU1': {'C': 207}, 'EU2': {}, 'NA2': {'C': 22}})
+        self.assertEqual(
+            next(gen).allele_counts,
+            {"NA1": {"T": 236}, "EU1": {"C": 207}, "EU2": {}, "NA2": {"C": 22}},
+        )
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     unittest.main()