Merge pull request #18 from JLSteenwyk/update_python_version

removed the use of the root.txt file from the DVMC function

change_log.txt

@@ -1,5 +1,8 @@
 Major changes to PhyKIT are summarized here.
 
+1.12.2
+  - removed root.txt file from DVMC function. User's are now recommended to trim outgroup taxa beforehand
+
 1.11.3
   - Added an optional argument to the prune_tree function wherein instead of pruning tips specified
   in the input file, those tips will be kept

docs/change_log/index.rst

@@ -7,6 +7,9 @@ Change log
 ^^^^^
 
 Major changes to PhyKIT are summarized here.
+
+**1.12.2**: removed root.txt file from DVMC function. User's are now recommended to trim outgroup taxa beforehand
+
 **1.11.3**: Added an optional argument to the prune_tree function wherein instead of pruning tips
 specified in the input file, those tips will be kept.
 
@@ -75,4 +78,4 @@ alignment to compare it to
 the quality of an alignment given an input query alignment
 and a reference alignment to compare it to
 
-**0.0.9**: PhyKIT now handles error stemming from piping output
+**0.0.9**: PhyKIT now handles error stemming from piping output

docs/usage/index.rst

@@ -577,29 +577,30 @@ Degree of violation of the molecular clock
 Function names: degree_of_violation_of_a_molecular_clock, dvmc |br|
 Command line interface: pk_degree_of_violation_of_a_molecular_clock, pk_dvmc
 
-Calculate degree of violation of the molecular clock (or DVMC) in a phylogeny.
+Calculate degree of violation of a molecular clock (or DVMC) in a phylogeny.
 
 Lower DVMC values are thought to be desirable because they are indicative
 of a lower degree of violation in the molecular clock assumption.
 
 Typically, outgroup taxa are not included in molecular clock analysis. Thus,
-prior to calculating DVMC from a single gene tree, outgroup taxa are pruned
-from the phylogeny. PhyKIT will prune taxa using tip names from a single column
-file, which is specified using the -r/--root file. If the tip name does not
-exist in the input tree, rather than raising an error/warning message, the tip  
-name is skipped. If the user wants to calculate DVMC for phylogenies with incomplete
-taxa representation, this will allow the user to use one <root file> for all trees.
-Lastly, an empty root file can be used if the user does not wish to prune outgroup taxa. 
+prior to calculating DVMC from a single gene tree, users may want to prune
+outgroup taxa from the phylogeny. To prune tips from a phylogeny, see the 
+prune_tree function. 
 
-Calculate DVMC in a tree following Liu et al., PNAS (2017), doi: 10.1073/pnas.1616744114.  
+Calculate DVMC in a tree following Liu et al., PNAS (2017), doi: 10.1073/pnas.1616744114.
+
+Options
+=====================================================
+<tree>                      first argument after 
+                            function name should be
+                            a tree file
 
 .. code-block:: shell
 
-   phykit degree_of_violation_of_a_molecular_clock -t/--tree <tree>  -r/--root <root_taxa>
+   phykit degree_of_violation_of_a_molecular_clock <tree>
 
 Options: |br|
-*-t/\\-\\-tree*: input file tree name |br|
-*-r/\\-\\-root*: single column file with tip names of root taxa 
+*<tree>*: input file tree name
 
 |
 
@@ -621,7 +622,7 @@ of the Royal Society B (2014).
    phykit evolutionary_rate <tree>
 
 Options: |br|
-*-t/\\-\\-tree*: input file tree name
+*<tree>*: input file tree name
 
 |
 

phykit/phykit.py

@@ -1081,13 +1081,9 @@ def dvmc(argv):
                 of a lower degree of violation in the molecular clock assumption.
 
                 Typically, outgroup taxa are not included in molecular clock analysis. Thus,
-                prior to calculating DVMC from a single gene tree, outgroup taxa are pruned
-                from the phylogeny. PhyKIT will prune taxa using tip names from a single column
-                file, which is specified using the -r/--root file. If the tip name does not
-                exist in the input tree, rather than raising an error/warning message, the tip  
-                name is skipped. If the user wants to calculate DVMC for phylogenies with incomplete
-                taxa representation, this will allow the user to use one <root file> for all trees.
-                Lastly, an empty root file can be used if the user does not wish to prune outgroup taxa. 
+                prior to calculating DVMC from a single gene tree, users may want to prune
+                outgroup taxa from the phylogeny. To prune tips from a phylogeny, see the 
+                prune_tree function. 
 
                 Calculate DVMC in a tree following Liu et al., PNAS (2017), doi: 10.1073/pnas.1616744114.
 
@@ -1097,24 +1093,17 @@ def dvmc(argv):
                   pk_degree_of_violation_of_a_molecular_clock, pk_dvmc
 
                 Usage:
-                phykit degree_of_violation_of_a_molecular_clock -t/--tree <tree>
-                    -r/--root <root_taxa>
+                phykit degree_of_violation_of_a_molecular_clock <tree>
 
                 Options
                 =====================================================
-                -t/--tree                   input file tree name
-            
-                -r/--root                   single column file with
-                                            tip names of root taxa
+                <tree>                      first argument after 
+                                            function name should be
+                                            a tree file 
                 """
             ),
         )
-        parser.add_argument(
-            "-r", "--root", type=str, required=True, help=SUPPRESS, metavar=""
-        )
-        parser.add_argument(
-            "-t", "--tree", type=str, required=True, help=SUPPRESS, metavar=""
-        )
+        parser.add_argument("tree", type=str, help=SUPPRESS)
         args = parser.parse_args(argv)
         DVMC(args).run()
 

phykit/services/tree/dvmc.py

@@ -12,26 +12,12 @@ def __init__(self, args) -> None:
 
     def run(self):
         tree = self.read_tree_file()
-        outgroup = read_single_column_file_to_list(self.outgroup_taxa_file_path)
-        dvmc = self.determine_dvmc(tree, outgroup)
+        dvmc = self.determine_dvmc(tree)
 
         print(round(dvmc, 4))
 
     def process_args(self, args):
-        return dict(tree_file_path=args.tree, outgroup_taxa_file_path=args.root)
-
-    def get_names_of_outgroup_taxa_that_are_present(
-        self, outgroup: list, tree: Tree
-    ) -> list:
-        # initialize list for outgroup taxa that are present in tree
-        out_pres = []
-        # loop through terminal branch
-        for term in tree.get_terminals():
-            # if outgroup taxa is present, append it to out_pres
-            if term.name in outgroup:
-                out_pres.append(term.name)
-
-        return out_pres
+        return dict(tree_file_path=args.tree)
 
     def get_term_to_root_dist_and_sum_of_distances(self, tree) -> Tuple[float, float]:
         """
@@ -68,16 +54,7 @@ def calculate_dvmc(self, dist: float, sum_dist: float, num_spp: int) -> float:
 
         return dvmc
 
-    def determine_dvmc(self, tree: Tree, outgroup: list):
-        # get names of outgroup taxa in tree
-        out_pres = self.get_names_of_outgroup_taxa_that_are_present(outgroup, tree)
-
-        # root tree on outgroup
-        tree.root_with_outgroup(out_pres)
-
-        # prune outgroup taxa from tree
-        tree = self.prune_tree_using_taxa_list(tree, out_pres)
-
+    def determine_dvmc(self, tree: Tree):
         # loop through terminal branches and store
         # distances from the root to the tip in a list.
         # Also, calc the sum of all tip to root distances

phykit/version.py

@@ -1 +1 @@
-__version__ = "1.12.1"
+__version__ = "1.12.2"

tests/integration/tree/test_dvmc_integration.py

@@ -14,79 +14,38 @@
 class TestDVMC(object):
     @patch("builtins.print")
     def test_dvmc(self, mocked_print):
-        expected_result = 42.8016
+        expected_result = 40.0185
         testargs = [
             "phykit",
             "dvmc",
-            "-t",
             f"{here.parent.parent.parent}/sample_files/tree_simple.tre",
-            "-r",
-            f"{here.parent.parent.parent}/sample_files/tree_simple.outgroup.txt",
         ]
         with patch.object(sys, "argv", testargs):
             Phykit()
         assert mocked_print.mock_calls == [call(expected_result)]
 
     @patch("builtins.print")
     def test_dvmc_alias(self, mocked_print):
-        expected_result = 42.8016
+        expected_result = 40.0185
         testargs = [
             "phykit",
             "degree_of_violation_of_a_molecular_clock",
-            "-t",
             f"{here.parent.parent.parent}/sample_files/tree_simple.tre",
-            "-r",
-            f"{here.parent.parent.parent}/sample_files/tree_simple.outgroup.txt",
         ]
         with patch.object(sys, "argv", testargs):
             Phykit()
         assert mocked_print.mock_calls == [call(expected_result)]
 
-    @patch("builtins.print")
-    def test_dvmc_incorrect_outgroup_file(self, mocked_print):
-        testargs = [
-            "phykit",
-            "dvmc",
-            "-t",
-            f"{here.parent.parent.parent}/sample_files/tree_simple.tre",
-            "-r",
-            f"{here.parent.parent.parent}/sample_files/tree_simple.outgroup.tx",
-        ]
-        with pytest.raises(SystemExit) as pytest_wrapped_e:
-            Phykit()
-
-        assert pytest_wrapped_e.type == SystemExit
-        assert pytest_wrapped_e.value.code == 2
-
     @patch("builtins.print")
     def test_dvmc_incorrect_tree_file(self, mocked_print):
         testargs = [
             "phykit",
             "dvmc",
-            "-t",
-            f"{here.parent.parent.parent}/sample_files/tree_simple.tr",
-            "-r",
-            f"{here.parent.parent.parent}/sample_files/tree_simple.outgroup.txt",
+            "no_file",
         ]
         with pytest.raises(SystemExit) as pytest_wrapped_e:
             Phykit()
 
         assert pytest_wrapped_e.type == SystemExit
         assert pytest_wrapped_e.value.code == 2
 
-    @patch("builtins.print")
-    def test_dvmc_wrong_file_path(self, mocked_print):
-        testargs = [
-            "phykit",
-            "dvmc",
-            "-t",
-            f"{here.parent.parent.parent}/sample_files/tree_simple.tre",
-            "-r",
-            f"no_file"
-        ]
-
-        with pytest.raises(SystemExit) as pytest_wrapped_e:
-            Phykit()
-
-        assert pytest_wrapped_e.type == SystemExit
-        assert pytest_wrapped_e.value.code == 2

tests/unit/services/tree/test_dvmc.py

@@ -8,14 +8,13 @@
 
 @pytest.fixture
 def args():
-    kwargs = dict(tree="/some/path/to/file.tre", root="/home/path/to/file.txt",)
+    kwargs = dict(tree="/some/path/to/file.tre")
     return Namespace(**kwargs)
 
 
 class TestDVMC(object):
     def test_init_sets_tree_file_path(self, args):
         d = DVMC(args)
-        assert d.outgroup_taxa_file_path == args.root
         assert d.output_file_path is None
 
     def test_read_file_reads_tree_file_path(self, mocker, args):
@@ -24,13 +23,3 @@ def test_read_file_reads_tree_file_path(self, mocker, args):
         d.read_tree_file()
         mock_read.assert_called_with(args.tree, "newick")
 
-    # def test_calculate_dvmc_zero_branch_len(self, tree_zero_branch_length, args):
-    #     d = DVMC(args)
-    #     res = d.calculate_dvmc(tree_zero_branch_length, args.root)
-    #     assert res == 0.0
-
-    # def test_calculate_dvmc(self, tree_simple, tree_simple_outgroup, args):
-    #     d = DVMC(args)
-    #     res = d.calculate_dvmc(tree_simple, tree_simple_outgroup)
-    #     assert isinstance(res, float)
-    #     assert isclose(res, 42.80162365633575, rel_tol=0.001)