simplified the reporting of results for the hidden paralogy check fun…

…ction

change_log.txt

@@ -1,5 +1,9 @@
 Major changes to PhyKIT are summarized here.
 
+1.12.3
+  - hidden paralogy check now simply looks for monophyly or lack thereof for a set of taxa. Hidden paralogy
+  check still reports insufficient taxon representation.
+
 1.12.2
   - removed root.txt file from DVMC function. User's are now recommended to trim outgroup taxa beforehand
 

docs/usage/index.rst

@@ -648,24 +648,18 @@ A B C |br|
 D E F |br|
 "
 
-The output will have six columns and as many rows
-as clades were specified in the -c file. For example,
-if there were three rows of clades to examine the 
-monophyly of, there will be three rows in the output
+The output will report if the specified taxa were monophyletic
+or not. The number of rows will reflect how many groups of taxa
+were checked for monophyly. For example,
+if there were three rows of clades in the -c file, there will be
+three rows in the output
 where the first row in the output corresponds to the 
 results of the first row in the clade file. |br|
-col 1: if the clade was or wasn't monophyletic |br|
-col 2: average bipartition support value in the clade of interest |br|
-col 3: maximum bipartition support value in the clade of interest |br|
-col 4: minimum bipartition support value in the clade of interest |br|
-col 5: standard deviation of bipartition support values in the clade of interest |br|
-col 6: tip names of the clade specified in the clade file
 
 The concept behind this analysis follows
 Siu-Ting et al., Molecular Biology and Evolution (2019),
 doi: 10.1093/molbev/msz067.
 
-
 .. code-block:: shell
 
    phykit hidden_paralogy_check <tree> -c/--clade <clade_file>

phykit/phykit.py

@@ -1178,19 +1178,12 @@ def hidden_paralogy_check(argv):
                 Tip names not present in the tree will not be considered
                 when assessing hidden paralogy.
 
-                The output will have six columns and as many rows
-                as clades were specified in the -c file. For example,
-                if there were three rows of clades to examine the 
-                monophyly of, there will be three rows in the output
-                where the first row in the output corresponds to the 
+                The output will report if the specified taxa were monophyletic
+                or not. The number of rows will reflect how many groups of taxa
+                were checked for monophyly. For example, if there were three
+                rows of clades in the -c file, there will be three rows in the
+                output where the first row in the output corresponds to the 
                 results of the first row in the clade file.
-                col 1: if the clade was or wasn't monophyletic
-                col 2: average bipartition support value in the clade of interest
-                col 3: maximum bipartition support value in the clade of interest
-                col 4: minimum bipartition support value in the clade of interest
-                col 5: standard deviation of bipartition support values in the clade of interest
-                col 6: tip names of taxa monophyletic with the lineage of interest
-                       excluding those that are listed in the taxa_of_interest file
 
                 The concept behind this analysis follows
                 Siu-Ting et al., Molecular Biology and Evolution (2019).

phykit/services/tree/hidden_paralogy_check.py

@@ -1,9 +1,10 @@
 import copy
+import statistics as stat
 import sys
 
-from .base import Tree
+import numpy as np
 
-from ...helpers.stats_summary import calculate_summary_statistics_from_arr
+from .base import Tree
 
 
 class HiddenParalogyCheck(Tree):
@@ -44,10 +45,8 @@ def run(self):
                 set(clade_of_interest) ^ set(common_ancestor_tips)
             )
 
-            stats = self.get_bootstrap_statistics(tree)
-
             res_arr = self.populate_res_arr(
-                shared_tree_tips, diff_tips_between_clade_and_curr_tree, stats, res_arr
+                shared_tree_tips, diff_tips_between_clade_and_curr_tree, res_arr
             )
 
         self.print_results(res_arr)
@@ -69,47 +68,22 @@ def read_clades_file(self, clades):
 
         return clades
 
-    def get_bootstrap_statistics(self, tree):
-        # get bootstrap support values
-        bs_vals = []
-        # populate bs_vals with bootstrap values
-        for terminal in tree.get_nonterminals():
-            # only include if a bootstrap value is present
-            if terminal.confidence != None:
-                bs_vals.append(terminal.confidence)
-        stats = calculate_summary_statistics_from_arr(bs_vals)
-
-        return stats
-
     def populate_res_arr(
-        self, shared_tree_tips, diff_tips_between_clade_and_curr_tree, stats, res_arr
+        self, shared_tree_tips, diff_tips_between_clade_and_curr_tree, res_arr
     ):
         temp = []
 
         if len(diff_tips_between_clade_and_curr_tree) == 0:
             temp.append("monophyletic")
         else:
             temp.append("not_monophyletic")
-        temp.append(stats["mean"])
-        temp.append(stats["maximum"])
-        temp.append(stats["minimum"])
-        temp.append(stats["standard_deviation"])
         temp.append(diff_tips_between_clade_and_curr_tree)
         res_arr.append(temp)
 
         return res_arr
 
     def print_results(self, res_arr):
         for res in res_arr:
-            try:
-                if len(res[5]) != 0:
-                    res[5].sort()
-                    print(
-                        f"{res[0]}\t{round(res[1], 4)}\t{round(res[2], 4)}\t{round(res[3], 4)}\t{round(res[4], 4)}\t{';'.join(res[5])}"
-                    )
-                else:
-                    print(
-                        f"{res[0]}\t{round(res[1], 4)}\t{round(res[2], 4)}\t{round(res[3], 4)}\t{round(res[4], 4)}"
-                    )
-            except IndexError:
-                print(f"{res[0]}")
+            print(
+                f"{res[0]}"
+            )

phykit/version.py

@@ -1 +1 @@
-__version__ = "1.12.2"
+__version__ = "1.12.3"

tests/integration/tree/test_hidden_paralogy_check_integration.py

@@ -25,8 +25,8 @@ def test_hidden_paralogy_check(self, mocked_print):
             Phykit()
 
         assert mocked_print.mock_calls == [
-            call("monophyletic\t100\t100\t100\t0.0"),
-            call("not_monophyletic\t95.7143\t100\t85\t7.3193\tAspergillus_fischeri_NRRL181.GCF_000149645.1_ASM14964v1;Aspergillus_fischeri_NRRL4585;Aspergillus_fumigatus_CEA10;Aspergillus_fumigatus_HMR_AF_270;Aspergillus_fumigatus_Z5;Aspergillus_oerlinghausenensis_CBS139183"),
+            call("monophyletic"),
+            call("not_monophyletic"),
             call("insufficient_taxon_representation"),
         ]
 
@@ -43,8 +43,8 @@ def test_hidden_paralogy_check_long(self, mocked_print):
             Phykit()
 
         assert mocked_print.mock_calls == [
-            call("monophyletic\t100\t100\t100\t0.0"),
-            call("not_monophyletic\t95.7143\t100\t85\t7.3193\tAspergillus_fischeri_NRRL181.GCF_000149645.1_ASM14964v1;Aspergillus_fischeri_NRRL4585;Aspergillus_fumigatus_CEA10;Aspergillus_fumigatus_HMR_AF_270;Aspergillus_fumigatus_Z5;Aspergillus_oerlinghausenensis_CBS139183"),
+            call("monophyletic"),
+            call("not_monophyletic"),
             call("insufficient_taxon_representation"),
         ]
 
@@ -61,8 +61,8 @@ def test_hidden_paralogy_check_alias(self, mocked_print):
             Phykit()
 
         assert mocked_print.mock_calls == [
-            call("monophyletic\t100\t100\t100\t0.0"),
-            call("not_monophyletic\t95.7143\t100\t85\t7.3193\tAspergillus_fischeri_NRRL181.GCF_000149645.1_ASM14964v1;Aspergillus_fischeri_NRRL4585;Aspergillus_fumigatus_CEA10;Aspergillus_fumigatus_HMR_AF_270;Aspergillus_fumigatus_Z5;Aspergillus_oerlinghausenensis_CBS139183"),
+            call("monophyletic"),
+            call("not_monophyletic"),
             call("insufficient_taxon_representation"),
         ]
 
@@ -71,7 +71,7 @@ def test_hidden_paralogy_check_file_error0(self, mocked_print):
         testargs = [
             "phykit",
             "clan_check",
-            f"{here.parent.parent.parent}/sample_files/small_Aspergillus_tree.t",
+            "file doesn't exist",
             "-c",
             f"{here.parent.parent.parent}/sample_files/small_Aspergillus_tree.hidden_paralogy_check.txt",
         ]
@@ -88,10 +88,10 @@ def test_hidden_paralogy_check_file_error1(self, mocked_print):
             "clan_check",
             f"{here.parent.parent.parent}/sample_files/small_Aspergillus_tree.tre",
             "-c",
-            f"{here.parent.parent.parent}/sample_files/small_Aspergillus_tree.hidden_paralogy_check.t",
+            "file doesn't exist",
         ]
         with pytest.raises(SystemExit) as pytest_wrapped_e:
             Phykit()
 
         assert pytest_wrapped_e.type == SystemExit
-        assert pytest_wrapped_e.value.code == 2
+        assert pytest_wrapped_e.value.code == 2