Development

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.1.5
+current_version = 0.2.0
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<build>\d+))?

.gitignore

@@ -141,3 +141,5 @@ alphabase/logs
 *sidebar.yml
 *_proc
 *_quarto.yml
+# .gitconfig is now autogenerated
+.gitconfig

README.md

@@ -7,7 +7,7 @@ AlphaBase
 <img src="https://github.com/MannLabs/alphabase/workflows/Default%20installation%20and%20tests/badge.svg" /></a>
 <a href="https://github.com/MannLabs/alphabase/workflows/Publish%20on%20PyPi%20and%20release%20on%20GitHub/badge.svg" alt="GUI and PyPi releases">
 <img src="https://github.com/MannLabs/alphabase/workflows/Publish%20on%20PyPi%20and%20release%20on%20GitHub/badge.svg"/></a>
-<a href="https://pypi.org/project/peptdeep" alt="pypi">
+<a href="https://pypi.org/project/alphabase" alt="pypi">
 <img src="https://img.shields.io/pypi/v/alphabase" /></a>
 <a href="https://pypi.org/project/alphabase" alt="release">
 <img src="https://img.shields.io/pypi/dm/alphabase?color=blue&label=pip%20downloads"/></a>

alphabase/__init__.py

@@ -2,7 +2,7 @@
 
 
 __project__ = "alphabase"
-__version__ = "0.1.5"
+__version__ = "0.2.0"
 __license__ = "Apache"
 __description__ = "An open-source Python package of the AlphaPept ecosystem"
 __author__ = "Mann Labs"

alphabase/_modidx.py

@@ -347,6 +347,8 @@
                                                                                                                              'alphabase/psm_reader/psm_reader.py'),
                                                  'alphabase.psm_reader.psm_reader.PSMReaderBase._translate_score': ( 'psm_reader/psm_reader.html#psmreaderbase._translate_score',
                                                                                                                      'alphabase/psm_reader/psm_reader.py'),
+                                                 'alphabase.psm_reader.psm_reader.PSMReaderBase.add_modification_mapping': ( 'psm_reader/psm_reader.html#psmreaderbase.add_modification_mapping',
+                                                                                                                             'alphabase/psm_reader/psm_reader.py'),
                                                  'alphabase.psm_reader.psm_reader.PSMReaderBase.filter_psm_by_modifications': ( 'psm_reader/psm_reader.html#psmreaderbase.filter_psm_by_modifications',
                                                                                                                                 'alphabase/psm_reader/psm_reader.py'),
                                                  'alphabase.psm_reader.psm_reader.PSMReaderBase.import_file': ( 'psm_reader/psm_reader.html#psmreaderbase.import_file',

alphabase/constants/const_files/protease.yaml

@@ -20,6 +20,7 @@ enterokinase:  '(?<=[DE]{3})K'
 factor xa:  '(?<=[AFGILTVM][DE]G)R'
 formic acid:  'D'
 glutamyl endopeptidase:  'E'
+glu-c: 'E'
 granzyme b:  '(?<=IEP)D'
 hydroxylamine:  'N(?=G)'
 iodosobenzoic acid:  'W'
@@ -36,6 +37,6 @@ thrombin:  '((?<=G)R(?=G))|((?<=[AFGILTVM][AFGILTVWA]P)R(?=[^DE][^DE]))'
 trypsin_full:  '([KR](?=[^P]))|((?<=W)K(?=P))|((?<=M)R(?=P))'
 trypsin_exception:  '((?<=[CD])K(?=D))|((?<=C)K(?=[HY]))|((?<=C)R(?=K))|((?<=R)R(?=[HR]))'
 trypsin:  '([KR](?=[^P]))'
-trypsin/P:  '([KR])'
+trypsin/p:  '([KR])'
 non-specific:  '()'
 no-cleave: '_'

alphabase/peptide/fragment.py

@@ -142,8 +142,8 @@ def init_fragment_by_precursor_dataframe(
 ):
     '''
     Init zero fragment dataframe for the `precursor_df`. If 
-    the `reference_fragment_df` is provided, it will generate 
-    the dataframe based on the reference. Otherwise it 
+    the `reference_fragment_df` is provided, the result dataframe's 
+    length will be the same as reference_fragment_df. Otherwise it 
     generates the dataframe from scratch.
 
     Parameters
@@ -184,7 +184,9 @@ def init_fragment_by_precursor_dataframe(
     #     we can just `del precursor_df['frag_start_idx']` before call this function.
     '''
     if 'frag_start_idx' not in precursor_df.columns:
-        fragment_df, start_indices, end_indices = init_zero_fragment_dataframe(
+        (
+            fragment_df, start_indices, end_indices
+        ) = init_zero_fragment_dataframe(
             precursor_df.nAA.values,
             charged_frag_types,
             dtype=dtype
@@ -211,12 +213,12 @@ def init_fragment_by_precursor_dataframe(
                     if _fr in reference_fragment_df.columns
                 ]]
             else:
-                fragment_df = init_fragment_dataframe_from_other(
-                    reference_fragment_df[[
-                        _fr for _fr in charged_frag_types 
-                        if _fr in reference_fragment_df.columns
-                    ]],
-                    dtype=dtype
+                fragment_df = pd.DataFrame(
+                    np.zeros((
+                        len(reference_fragment_df), 
+                        len(charged_frag_types)
+                    )),
+                    columns = charged_frag_types
                 )
     return fragment_df
 
@@ -602,11 +604,12 @@ def create_fragment_mz_dataframe(
                     if _fr in reference_fragment_df.columns
                 ]]
             else:
-                fragment_mz_df = init_fragment_dataframe_from_other(
-                    reference_fragment_df[[
-                        _fr for _fr in charged_frag_types 
-                        if _fr in reference_fragment_df.columns
-                    ]]
+                fragment_mz_df = pd.DataFrame(
+                    np.zeros((
+                        len(reference_fragment_df), 
+                        len(charged_frag_types)
+                    )),
+                    columns = charged_frag_types
                 )
         else:
             fragment_mz_df = init_fragment_by_precursor_dataframe(

alphabase/protein/fasta.py

@@ -204,9 +204,9 @@ def __init__(self,
         self.n_miss_cleave = max_missed_cleavages
         self.peptide_length_min = peptide_length_min
         self.peptide_length_max = peptide_length_max
-        if protease in protease_dict:
+        if protease.lower() in protease_dict:
             self.regex_pattern = re.compile(
-                protease_dict[protease]
+                protease_dict[protease.lower()]
             )
         else:
             self.regex_pattern = re.compile(

alphabase/psm_reader/psm_reader.py

@@ -169,6 +169,16 @@ def __init__(self,
     def psm_df(self)->pd.DataFrame:
         return self._psm_df
 
+    def add_modification_mapping(self, modification_mapping:dict):
+        if (
+            modification_mapping is None or
+             len(modification_mapping) == 0
+        ):
+            return
+
+        self.modification_mapping.update(modification_mapping)
+        self.set_modification_mapping(self.modification_mapping)
+
     def set_modification_mapping(self, modification_mapping:dict):
         if modification_mapping is None:
             self._init_modification_mapping()
@@ -444,7 +454,7 @@ def filter_psm_by_modifications(self, include_mod_set = set([
         self._psm_df.reset_index(drop=True, inplace=True)
 
 
-# %% ../../nbdev_nbs/psm_reader/psm_reader.ipynb 16
+# %% ../../nbdev_nbs/psm_reader/psm_reader.ipynb 18
 class PSMReaderProvider:
     def __init__(self):
         self.reader_dict = {}

nbdev_nbs/constants/aa.ipynb

@@ -630,15 +630,6 @@
    "display_name": "Python 3.8.3 ('base')",
    "language": "python",
    "name": "python3"
-  },
-  "language_info": {
-   "name": "python",
-   "version": "3.8.3"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "8a3b27e141e49c996c9b863f8707e97aabd49c4a7e8445b9b783b34e4a21a9b2"
-   }
   }
  },
  "nbformat": 4,

nbdev_nbs/constants/element.ipynb

@@ -333,15 +333,6 @@
    "display_name": "Python 3.8.3 ('base')",
    "language": "python",
    "name": "python3"
-  },
-  "language_info": {
-   "name": "python",
-   "version": "3.8.3"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "8a3b27e141e49c996c9b863f8707e97aabd49c4a7e8445b9b783b34e4a21a9b2"
-   }
   }
  },
  "nbformat": 4,