msreport 0.0.24__tar.gz → 0.0.26__tar.gz

{msreport-0.0.24 → msreport-0.0.26}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: msreport
-Version: 0.0.24
+Version: 0.0.26
 Summary: Post processing and analysis of quantitative proteomics data
 Author-email: "David M. Hollenstein" <hollenstein.david@gmail.com>
 License: Apache-2.0

{msreport-0.0.24 → msreport-0.0.26}/msreport/__init__.py

@@ -10,4 +10,4 @@ import msreport.normalize
 import msreport.plot
 import msreport.reader
 
-__version__ = "0.0.24"
+__version__ = "0.0.26"

{msreport-0.0.24 → msreport-0.0.26}/msreport/helper/table.py

@@ -176,12 +176,22 @@ def find_sample_columns(
             columns.
 
     Returns:
-        A list of sample column names.
+        A list of column names containing the substring and any entry of 'samples'.
+        Columns are returned in the order of entries in 'samples'.
     """
+    WHITESPACE_CHARS = " ."
+
     matched_columns = []
-    for column in find_columns(table, substring):
-        if any([sample in column for sample in samples]):
-            matched_columns.append(column)
+    substring_columns = find_columns(table, substring)
+    for sample in samples:
+        sample_columns = [c for c in substring_columns if sample in c]
+        for col in sample_columns:
+            column_remainder = (
+                col.replace(substring, "").replace(sample, "").strip(WHITESPACE_CHARS)
+            )
+            if column_remainder == "":
+                matched_columns.append(col)
+                break
     return matched_columns
 
 

{msreport-0.0.24 → msreport-0.0.26}/msreport/plot.py

@@ -718,7 +718,10 @@ def volcano_ma(
         )
 
         ax.set_xlabel(x_variable)
-        ax.set_ylabel(f"{y_variable} [-log10]")
+        if y_variable == pvalue_tag:
+            ax.set_ylabel(f"{y_variable} [-log10]")
+        else:
+            ax.set_ylabel(f"{y_variable} [log2]")
 
     fig.tight_layout()
     return fig, axes
@@ -1075,13 +1078,13 @@ def pvalue_histogram(
         )
 
         # Adjust x- and y-axis
-        ax.set_xlabel(None)
         ax.set_xticks(np.arange(0, 1.01, 0.5))
         ax.tick_params(labelsize=9)
         if plot_number > 0:
             ax.tick_params(axis="y", color="none")
 
-        # Add second label
+        # Add x-label and second y-label
+        ax.set_xlabel(pvalue_tag, fontsize=9)
         ax2 = ax.twinx()
         ax2.set_yticks([])
         ax2.set_ylabel(comparison_group, fontsize=9)

{msreport-0.0.24 → msreport-0.0.26}/msreport/qtable.py

@@ -1,5 +1,5 @@
 from __future__ import annotations
-from typing import Any, Optional
+from typing import Any, Iterable, Optional
 import os
 import warnings
 
@@ -196,8 +196,9 @@ class Qtable:
         columns = helper.find_sample_columns(self.data, tag, samples)
         table = self.get_data(exclude_invalid=exclude_invalid)[columns]
         if samples_as_columns:
-            mapping = _str_to_substr_mapping(columns, samples)
-            table.rename(columns=mapping, inplace=True)
+            sample_to_columns = _match_samples_to_tag_columns(samples, columns, tag)
+            columns_to_samples = {v: k for k, v in sample_to_columns.items()}
+            table.rename(columns=columns_to_samples, inplace=True)
         return table
 
     def make_expression_table(
@@ -502,15 +503,30 @@ def _exclude_invalid(df: pd.DataFrame) -> pd.DataFrame:
     return df[df["Valid"]].copy()
 
 
-def _str_to_substr_mapping(strings, substrings) -> dict[str, str]:
-    """Mapping of strings to substrings.
+def _match_samples_to_tag_columns(
+    samples: Iterable[str],
+    columns: Iterable[str],
+    tag: str,
+) -> dict:
+    """Mapping of samples to columns which contain the sample and the tag.
 
-    Strings point to a matching substring. If multiple substrings are found in a string,
-    only one is reported.
+    Args:
+        samples: A list of sample names.
+        columns: A list of column names.
+        tag: A string that must be present in the column names.
+
+    Returns:
+        A dictionary that maps sample names to column names that contain the sample
+        name and the tag.
     """
+    WHITESPACE_CHARS = " ."
+
     mapping = dict()
-    for sub in substrings:
-        mapping.update({s: sub for s in strings if sub in s})
+    for sample in samples:
+        for col in columns:
+            if col.replace(tag, "").replace(sample, "").strip(WHITESPACE_CHARS) == "":
+                mapping[sample] = col
+                break
     return mapping
 
 

{msreport-0.0.24 → msreport-0.0.26}/msreport/reader.py

@@ -2196,9 +2196,11 @@ def extract_fragpipe_localization_probabilities(localization_entry: str) -> dict
         _, probabilities = msreport.peptidoform.parse_modified_sequence(
             probability_sequence, "(", ")"
         )
-        modification_probabilities[modification] = {
-            site: float(probability) for site, probability in probabilities
-        }
+        if modification not in modification_probabilities:
+            modification_probabilities[modification] = {}
+        modification_probabilities[modification].update(
+            {site: float(probability) for site, probability in probabilities}
+        )
     return modification_probabilities
 
 

{msreport-0.0.24 → msreport-0.0.26}/msreport.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: msreport
-Version: 0.0.24
+Version: 0.0.26
 Summary: Post processing and analysis of quantitative proteomics data
 Author-email: "David M. Hollenstein" <hollenstein.david@gmail.com>
 License: Apache-2.0

{msreport-0.0.24 → msreport-0.0.26}/tests/test_helper.py

@@ -19,20 +19,35 @@ class TestFindColumns:
         assert columns == ["Test A", "Test B"]
 
 
-def test_find_sample_columns():
-    df = pd.DataFrame(
-        columns=[
-            "Test",
-            "Test Not_a_sample",
-            "Test Sample_A",
-            "Test Sample_B",
-            "Something else",
-        ]
-    )
-    samples = ["Sample_A", "Sample_B"]
-    tag = "Test"
-    columns = msreport.helper.find_sample_columns(df, tag, samples)
-    assert columns == ["Test Sample_A", "Test Sample_B"]
+class TestFindSampleColumns:
+    def test_find_sample_columns(self):
+        df = pd.DataFrame(
+            columns=[
+                "Tag",
+                "Tag Not_a_sample",
+                "Tag Sample_A",
+                "Tag Sample_B",
+                "Something else",
+            ]
+        )
+        samples = ["Sample_A", "Sample_B"]
+        tag = "Tag"
+        columns = msreport.helper.find_sample_columns(df, tag, samples)
+        assert columns == ["Tag Sample_A", "Tag Sample_B"]
+
+    def test_columns_are_returned_in_order_of_samples(self):
+        df = pd.DataFrame(columns=["Tag Sample_B", "Tag Sample_A"])
+        samples = ["Sample_A", "Sample_B"]
+        tag = "Tag"
+        columns = msreport.helper.find_sample_columns(df, tag, samples)
+        assert columns == ["Tag Sample_A", "Tag Sample_B"]
+
+    def test_correct_mapping_with_samples_that_are_substrings(self):
+        df = pd.DataFrame(columns=["Tag SampleB_1", "Tag B_1"])
+        samples = ["B_1"]
+        tag = "Tag"
+        columns = msreport.helper.find_sample_columns(df, tag, samples)
+        assert columns == ["Tag B_1"]
 
 
 class TestKeepRowsByPartialMatch:

{msreport-0.0.24 → msreport-0.0.26}/tests/test_qtable.py

@@ -84,15 +84,24 @@ class TestExcludeInvalid:
             msreport.qtable._exclude_invalid(df)
 
 
-def test_str_to_substr_mapping():
-    strings = ["Tag SampleB_1", "Tag SampleA_1", "Tag SampleA_2"]
-    substrs = ["SampleA_1", "SampleB_1", "SampleA_2"]
-    true_mapping = {
-        "Tag SampleA_1": "SampleA_1",
-        "Tag SampleA_2": "SampleA_2",
-        "Tag SampleB_1": "SampleB_1",
-    }
-    assert msreport.qtable._str_to_substr_mapping(strings, substrs) == true_mapping
+class TestMatchSamplesToTagColumns:
+    def test_match_samples_to_tag_columns(self):
+        samples = ["SampleA_1", "SampleA_2", "SampleB_1"]
+        columns = ["Tag SampleA_1", "Tag SampleA_2", "Tag SampleB_1"]
+        true_mapping = {
+            "SampleA_1": "Tag SampleA_1",
+            "SampleA_2": "Tag SampleA_2",
+            "SampleB_1": "Tag SampleB_1",
+        }
+        observed_mapping = msreport.qtable._match_samples_to_tag_columns(samples, columns, "Tag")  # fmt:skip
+        assert observed_mapping == true_mapping
+
+    def test_correct_mapping_with_samples_that_are_substrings(self):
+        samples = ["B_1", "SampleB_1"]
+        columns = ["Tag B_1", "Tag SampleB_1"]
+        true_mapping = {"B_1": "Tag B_1", "SampleB_1": "Tag SampleB_1"}
+        observed_mapping = msreport.qtable._match_samples_to_tag_columns(samples, columns, "Tag")  # fmt:skip
+        assert observed_mapping == true_mapping
 
 
 def test_qtable_setup():