clean_up_heatmap fix and correct Methyl masses

- correct Methyl masses
- duplicate fix in clean_up_heatmap
- style improvements

.github/pull_request_template.md

@@ -1,5 +1,7 @@
 # ⚠️ IMPORTANT: Branch Strategy
+
 This repository follows a strict branch strategy:
+
 - `master` branch is ONLY for PyPI release mirroring
 - All development PRs MUST target the `dev` branch
 - If your PR targets `master`, it will be flagged and you'll be asked to retarget to `dev`

CHANGELOG.md

@@ -33,12 +33,12 @@
 - `lectin_specificity` now uses our custom `DataFrameSerializer` and is stored as a .json file rather than a .pkl file, to improve long-term stability across versions (034b6ad)
 
 ##### Fixed 🐛
-- Fixed DeprecationWarning in all data-loading functions that used `importlib.resources.open_text` or `.content`
+- Fixed DeprecationWarning in all data-loading functions that used `importlib.resources.open_text` or `.content` (87ea2fc)
 
 #### stats
 ##### Added ✨
 - Added the "random_state" keyword argument to `clr_transformation` to allow users to provide a reproducible RNG seed (b94744e)
-- Added the `JTKTest` class object
+- Added the `JTKTest` class object (87ea2fc)
 
 ##### Changed 🔄
 - For `replace_outliers_winsorization`, in small datasets, the 5% limit is dynamically changed to include at least one datapoint (23d6456)
@@ -47,7 +47,7 @@
 
 ##### Deprecated ⚠️
 - Deprecated `hlm`, `fast_two_sum`, `two_sum`, `expansion_sum`, and `update_cf_for_m_n`, which will all be done in-line instead (e1afe33)
-- Deprecated `jtkdist`, `jtkinit`, `jtkstat`, `jtkx`, which will all be done by the new `JTKTest`
+- Deprecated `jtkdist`, `jtkinit`, `jtkstat`, `jtkx`, which will all be done by the new `JTKTest` (87ea2fc)
 
 ##### Fixed 🐛
 - Fixed DeprecationWarning in `calculate_permanova_stat` for calling nonzero on 0d arrays (23d6456)
@@ -76,6 +76,7 @@
 ##### Fixed 🐛
 - Fixed an edge case in `get_unique_topologies`, in which the absence of a universal replacer sometimes created an empty list that was attempted to be indexed (0c94995)
 - Made sure that `compositions_to_structures` always returns a DataFrame, even if no matches are found (0c94995)
+- Provided correct exact methyl masses in `mass_dict`
 
 #### processing
 ##### Added ✨
@@ -138,7 +139,7 @@
 ##### Changed 🔄
 - `get_glycanova` will now raise a ValueError if fewer than three groups are provided in the input data (f76535e)
 - Improved console drawing quality controlled by `display_svg_with_matplotlib` and image quality in Excel cells using `plot_glycans_excel` (a64f694)
-- The "periods" argument in `get_jtk` is now a keyword argument and has a default value of [12, 24]
+- The "periods" argument in `get_jtk` is now a keyword argument and has a default value of [12, 24] (87ea2fc)
 
 ##### Fixed 🐛
 - Fixed a FutureWarning in `get_lectin_array` by avoiding DataFrame.groupby with axis=1 (f76535e)
@@ -150,7 +151,7 @@
 - Fixed an issue where variance-filtered rows could cause problems in `get_differential_expression` if "monte_carlo = True" (ef3da9c)
 - Fixed an issue in `get_differential_expression` if "sets = True" that caused indexing issues under certain conditions (ef3da9c)
 - Ensured that "effect_size_variance = True" in `get_differential_expression` always formats variances correctly (ef3da9c)
-- Ensured that the combination of "grouped_BH = True", "paired = False", and CLR/ALR in `get_differential_expression` works even when negative values are present
+- Ensured that the combination of "grouped_BH = True", "paired = False", and CLR/ALR in `get_differential_expression` works even when negative values are present (87ea2fc)
 
 #### regex
 ##### Fixed 🐛
@@ -161,6 +162,9 @@
 - Added `get_size_branching_features` to create glycan size and branching level features for downstream analysis (d57b836)
 - Added the "size_branch" option in the "feature_set" keyword argument of `annotate_dataset` and `quantify_motifs`, to analyze glycans by size or level of branching (d57b836)
 
+##### Fixed 🐛
+- Fixed an issue in `clean_up_heatmap` in which, occasionally, duplicate strings were introduced in the output
+
 ### ml
 #### model_training
 ##### Added ✨

glycowork/glycan_data/stats.py

@@ -1,12 +1,11 @@
 import pandas as pd
 import numpy as np
-import math
 import warnings
 from typing import Dict, List, Optional, Tuple, Union
 from collections import Counter
 from sklearn.linear_model import Ridge
 from sklearn.ensemble import RandomForestRegressor
-from scipy.stats import wilcoxon, rankdata, norm, chi2, t, f, entropy, gmean, f_oneway, combine_pvalues, dirichlet, spearmanr, ttest_rel, ttest_ind
+from scipy.stats import rankdata, norm, chi2, t, f, entropy, gmean, f_oneway, combine_pvalues, dirichlet, spearmanr, ttest_rel, ttest_ind
 from scipy.stats.mstats import winsorize
 from scipy.spatial import procrustes
 from scipy.spatial.distance import squareform
@@ -250,10 +249,10 @@ def test(self, values: np.ndarray) -> Tuple[float, int, int, float]:
     best_stats = (1.0, self.periods[0], 0, 0)
     for period in self.periods:
       waveforms_period = self.waveforms[period]
-      for phase in range(len(waveforms_period)):
+      for phase, waveform_phase in enumerate(waveforms_period):
         if phase > 0 and (period+(phase*self.interval) in self.periods or period-(phase*self.interval) in self.periods):
           continue
-        S = (signs * waveforms_period[phase]).sum()
+        S = (signs * waveform_phase).sum()
         if S == 0:
           continue
         jtk = (abs(S) + self.max_stat) / 2

glycowork/motif/annotate.py

@@ -275,16 +275,20 @@ def clean_up_heatmap(
     ) -> pd.DataFrame: # DataFrame with redundant motifs removed
   "Removes redundant motif entries from glycan abundance data while preserving the most informative labels"
   motif_dic = dict(zip(motif_list.motif_name, motif_list.motif))
-  df.index = df.index.to_series().apply(lambda x: motif_dic[x] + ' '*20 if x in motif_dic else x)
+  original_index = df.index.copy()
+  df.index = df.index.to_series().apply(lambda x: motif_dic[x] + ' ' * 20 if x in motif_dic else x)
+  df['_original_position'] = range(len(df))
   # Group the DataFrame by identical rows
-  grouped = df.groupby(list(df.columns))
-  # Find the row with the longest string index within each group and return a new DataFrame
-  max_idx_series = grouped.apply(lambda group: group.index.to_series().str.len().idxmax(), include_groups = False)
-  result = df.loc[max_idx_series].drop_duplicates()
-  result.index = result.index.str.strip()
-  motif_dic = {value: key for key, value in motif_dic.items()}
-  result.index = [motif_dic.get(k, k) for k in result.index]
-  return result
+  grouped = df.groupby(list(df.columns[:-1]), sort = False)
+  # Find the integer indices of rows with the longest string index within each group
+  max_idx_positions = []
+  for _, group in grouped:
+    # Find the row with the longest string index
+    longest_idx = group.index.to_series().str.len().idxmax()
+    # Retrieve the original integer position of this row
+    max_idx_positions.append(group.loc[longest_idx, '_original_position'])
+  df.index = original_index
+  return df.iloc[max_idx_positions].drop_duplicates().drop(['_original_position'], axis = 1)
 
 
 def quantify_motifs(

glycowork/motif/mz_to_composition.csv

@@ -25,4 +25,4 @@ Trifluoroacetic acid,112.9850391,113.0160096,112.9850391,113.0160096,112.9850391
 PCho,165.0555,165.0555,,,,
 red_end,18.0105546,18.0105546,46.0419,46.0419,102.0317,102.0317
 PEtN,123.0628,123.0628,,,,
-Methyl,14.3,14.3,14.3,14.3,,
+Methyl,14.01565,14.0266,14.01565,14.0266,14.01565,14.0266