Sphinx doc

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.2.0
+current_version = 0.2.1
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<build>\d+))?
@@ -15,6 +15,8 @@ serialize =
 
 [bumpversion:file:./settings.ini]
 
+[bumpversion:file:./docs/conf.py]
+
 [bumpversion:file:./release/one_click_linux_gui/control]
 
 [bumpversion:file:./release/one_click_linux_gui/create_installer_linux.sh]

.gitignore

@@ -70,6 +70,7 @@ instance/
 
 # Sphinx documentation
 docs/_build/
+docs/build/
 
 # PyBuilder
 target/
@@ -138,7 +139,7 @@ alphabase/logs
 
 # nbdev2
 *.gitattributes
-*_docs*
+_docs*
 # *_quarto.yml
 # *sidebar.yml
 *_proc*

.readthedocs.yaml

@@ -0,0 +1,27 @@
+# .readthedocs.yaml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+   configuration: docs/conf.py
+
+# Optionally build your docs in additional formats such as PDF
+formats: all
+
+conda:
+  environment: misc/conda_dev_env.yaml
+
+# # Optionally set the version of Python and requirements required to build your docs
+# python:
+#   version: 3.8
+#   install:
+#     - requirements: requirements/requirements.txt
+#     - method: pip
+#       path: .
+#       extra_requirements:
+#         - plotting
+#         - development

README.md

@@ -36,19 +36,13 @@ please see [GitHub Pages](https://mannlabs.github.io/alphabase/)
 
 ## About
 
-An open-source Python package of the AlphaPept ecosystem from the [Mann
-Labs at the Max Planck Institute of
-Biochemistry](https://www.biochem.mpg.de/mann) and the [University of
-Copenhagen](https://www.cpr.ku.dk/research/proteomics/mann/). It
-provides basic functionalities for AlphaPept ecosystem.
+The infrastructure package of AlphaX ecosystem for MS proteomics.
 
 ------------------------------------------------------------------------
 
 ## License
 
-AlphaBase was developed by the [Mann Labs at the Max Planck Institute of
-Biochemistry](https://www.biochem.mpg.de/mann) and the [University of
-Copenhagen](https://www.cpr.ku.dk/research/proteomics/mann/) and is
+AlphaBase was developed by the [Mann Labs at the Max Planck Institute of Biochemistry](https://www.biochem.mpg.de/mann) and the [University of Copenhagen](https://www.cpr.ku.dk/research/proteomics/mann/) and is
 freely available with an [Apache License](LICENSE.txt). External Python
 packages (available in the [requirements](requirements) folder) have
 their own licenses, which can be consulted on their respective websites.

alphabase/__init__.py

@@ -2,7 +2,7 @@
 
 
 __project__ = "alphabase"
-__version__ = "0.2.0"
+__version__ = "0.2.1"
 __license__ = "Apache"
 __description__ = "An open-source Python package of the AlphaPept ecosystem"
 __author__ = "Mann Labs"

alphabase/constants/aa.py

@@ -1,32 +1,25 @@
-# AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbdev_nbs/constants/aa.ipynb.
-
-# %% auto 0
-__all__ = ['AA_CHEM', 'AA_ASCII_MASS', 'AA_DF', 'AA_formula', 'reset_AA_mass', 'reset_AA_df', 'calc_sequence_mass',
-           'calc_AA_masses_for_same_len_seqs', 'calc_sequence_masses_for_same_len_seqs',
-           'calc_AA_masses_for_var_len_seqs']
-
-# %% ../../nbdev_nbs/constants/aa.ipynb 2
 import os
 import pandas as pd
 import numpy as np
 
 from typing import Union, Tuple
 
-from ..yaml_utils import load_yaml
+from alphabase.yaml_utils import load_yaml
 
 from alphabase.constants.element import (
     calc_mass_from_formula, 
     MASS_H2O, parse_formula,
 )
 
-from ._const import CONST_FILE_FOLDER
+from alphabase.constants._const import CONST_FILE_FOLDER
 
-# %% ../../nbdev_nbs/constants/aa.ipynb 3
+# We use all 128 ASCII code to represent amino acids for flexible extensions in the future.
+# The amino acid masses are stored in 128-lengh array :py:data:`AA_ASCII_MASS`. 
+# If an ASCII code is not in `AA_CHEM`, the mass will be set as a large value to disable MS search.
 AA_CHEM:dict = load_yaml(
     os.path.join(CONST_FILE_FOLDER, 'amino_acid.yaml')
 )
 
-# %% ../../nbdev_nbs/constants/aa.ipynb 5
 def reset_AA_mass()->np.ndarray:
     """AA mass in np.array with shape (128,)"""
     AA_ASCII_MASS = np.ones(128)*1e8
@@ -53,14 +46,13 @@ def reset_AA_df():
 #: 128-len AA dataframe
 AA_DF:pd.DataFrame = reset_AA_df()
 
-#: AA to formula dict of dict. For example: {'K': {'C': n, 'O': m, ...}}
+# AA to formula dict of dict. For example: {'K': {'C': n, 'O': m, ...}}
 AA_formula:dict = {}
 for aa, formula, mass in AA_DF.values:
     AA_formula[aa] = dict(
         parse_formula(formula)
     )
 
-# %% ../../nbdev_nbs/constants/aa.ipynb 8
 def calc_sequence_mass(
     sequence: str
 )->np.ndarray:
@@ -77,7 +69,6 @@ def calc_sequence_mass(
     '''
     return AA_ASCII_MASS[np.array(sequence,'c').view(np.int8)]
 
-# %% ../../nbdev_nbs/constants/aa.ipynb 10
 def calc_AA_masses_for_same_len_seqs(
     sequence_array: np.ndarray
 )->np.ndarray:
@@ -132,7 +123,6 @@ def calc_sequence_masses_for_same_len_seqs(
     )+MASS_H2O
 
 
-# %% ../../nbdev_nbs/constants/aa.ipynb 19
 def calc_AA_masses_for_var_len_seqs(
     sequence_array: np.ndarray
 )->np.ndarray:

alphabase/constants/atom.py

@@ -1 +1 @@
-from .element import *
+from alphabase.constants.element import *

alphabase/constants/const_files/protease.yaml

@@ -36,7 +36,8 @@ thermolysin:  '[^DE](?=[AFILMV])'
 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_not_p:  '([KR](?=[^P]))'
+trypsin:  '([KR])'
 trypsin/p:  '([KR])'
 non-specific:  '()'
 no-cleave: '_'

alphabase/constants/const_files/psm_reader.yaml

@@ -23,8 +23,6 @@ alphapept:
 maxquant:
   reader_type: maxquant
   rt_unit: minute
-  mod_sep: '()'
-  underscore_for_ncterm: True
   fixed_C57: True
   column_mapping:
     'sequence': 'Sequence'
@@ -51,33 +49,27 @@ maxquant:
     'Acetyl@Protein N-term': 
       - '_(Acetyl (Protein N-term))'
       - '_(ac)'
-      - '_(UniMod:1)'
     'Carbamidomethyl@C': 
       - 'C(Carbamidomethyl (C))'
-      - 'C(UniMod:4)'
     'Oxidation@M': 
       - 'M(Oxidation (M))'
       - 'M(ox)'
-      - 'M(UniMod:35)'
     'Phospho@S': 
       - 'S(Phospho (S))'
       - 'S(Phospho (ST))'
       - 'S(Phospho (STY))'
       - 'S(ph)'
-      - 'S(UniMod:21)'
       - 'pS'
     'Phospho@T': 
       - 'T(Phospho (T))'
       - 'T(Phospho (ST))'
       - 'T(Phospho (STY))'
       - 'T(ph)'
-      - 'T(UniMod:21)'
       - 'pT'
     'Phospho@Y': 
       - 'Y(Phospho (Y))'
       - 'Y(Phospho (STY))'
       - 'Y(ph)'
-      - 'Y(UniMod:21)'
       - 'pY'
     'Deamidated@N': ['N(Deamidation (NQ))','N(de)']
     'Deamidated@Q': ['Q(Deamidation (NQ))','Q(de)']
@@ -145,8 +137,6 @@ msfragger_pepxml:
 diann:
   reader_type: diann
   rt_unit: minute
-  mod_sep: '()'
-  underscore_for_ncterm: False
   fixed_C57: False
   csv_sep: "\t"
   column_mapping:
@@ -166,8 +156,6 @@ diann:
 spectronaut_report:
   reader_type: spectronaut_report
   rt_unit: minute
-  mod_sep: '[]'
-  underscore_for_ncterm: True
   fixed_C57: False
   csv_sep: ','
   column_mapping:
@@ -177,11 +165,10 @@ spectronaut_report:
     'genes': 'PG.Genes'
     'uniprot_ids': 'PG.UniProtIds'
     'charge': 'charge'
+  modification_mapping: 'maxquant'
 spectronaut:
   reader_type: spectronaut
   rt_unit: irt
-  mod_sep: '[]'
-  underscore_for_ncterm: True
   fixed_C57: False
   csv_sep: "\t"
   mod_seq_columns:

alphabase/constants/element.py

@@ -1,28 +1,18 @@
-# AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbdev_nbs/constants/element.ipynb.
-
-# %% auto 0
-__all__ = ['common_const_dict', 'MASS_PROTON', 'MASS_ISOTOPE', 'MAX_ISOTOPE_LEN', 'EMPTY_DIST', 'CHEM_INFO_DICT',
-           'CHEM_MONO_MASS', 'CHEM_ISOTOPE_DIST', 'CHEM_MONO_IDX', 'MASS_H2O', 'MASS_NH3', 'truncate_isotope',
-           'reset_elements', 'load_elem_yaml', 'parse_formula', 'calc_mass_from_formula']
-
-# %% ../../nbdev_nbs/constants/element.ipynb 2
 import os
 import numpy as np
 import numba
 
-from ..yaml_utils import load_yaml
+from alphabase.yaml_utils import load_yaml
 
-from ._const import CONST_FILE_FOLDER
+from alphabase.constants._const import CONST_FILE_FOLDER
 
-# %% ../../nbdev_nbs/constants/element.ipynb 3
 common_const_dict:dict = load_yaml(
     os.path.join(CONST_FILE_FOLDER, 'common_constants.yaml')
 )
 
 MASS_PROTON:float = common_const_dict['MASS_PROTON']
 MASS_ISOTOPE:float = common_const_dict['MASS_ISOTOPE']
 
-# %% ../../nbdev_nbs/constants/element.ipynb 5
 MAX_ISOTOPE_LEN = common_const_dict['MAX_ISOTOPE_LEN']
 EMPTY_DIST = np.zeros(MAX_ISOTOPE_LEN)
 EMPTY_DIST[0] = 1
@@ -75,7 +65,6 @@ def truncate_isotope(
             trunc_start = len(isotopes)-MAX_ISOTOPE_LEN-1
     return mono_idx-trunc_start-1, trunc_start+1, trunc_end
 
-# %% ../../nbdev_nbs/constants/element.ipynb 7
 #: chemical element information in dict defined by `nist_element.yaml`
 CHEM_INFO_DICT = {}
 
@@ -164,7 +153,6 @@ def load_elem_yaml(yaml_file:str):
     )
 )
 
-# %% ../../nbdev_nbs/constants/element.ipynb 9
 def parse_formula(
     formula:str
 )->list:

alphabase/constants/isotope.py

@@ -1,9 +1,3 @@
-# AUTOGENERATED! DO NOT EDIT! File to edit: ../../nbdev_nbs/constants/isotope.ipynb.
-
-# %% auto 0
-__all__ = ['abundance_convolution', 'one_element_dist', 'formula_dist', 'IsotopeDistribution']
-
-# %% ../../nbdev_nbs/constants/isotope.ipynb 3
 import numba
 import numpy as np
 import typing
@@ -14,7 +8,6 @@
     truncate_isotope, parse_formula
 )
 
-# %% ../../nbdev_nbs/constants/isotope.ipynb 4
 @numba.njit
 def abundance_convolution(
     d1:np.ndarray,
@@ -55,7 +48,6 @@ def abundance_convolution(
     mono_idx, start, end = truncate_isotope(ret, mono_idx)
     return ret[start:end], mono_idx
 
-# %% ../../nbdev_nbs/constants/isotope.ipynb 6
 @numba.njit
 def one_element_dist(
     elem: str,
@@ -125,7 +117,6 @@ def formula_dist(
         calc_dist, mono_idx = abundance_convolution(calc_dist, mono_idx, _dist, _mono)
     return calc_dist, mono_idx
 
-# %% ../../nbdev_nbs/constants/isotope.ipynb 23
 def _calc_one_elem_cum_dist(
     element_cum_dist:np.ndarray, 
     element_cum_mono:np.ndarray
@@ -154,7 +145,6 @@ def _calc_one_elem_cum_dist(
             element_cum_mono[1]
         )
 
-# %% ../../nbdev_nbs/constants/isotope.ipynb 24
 class IsotopeDistribution:
     def __init__(self, 
         max_elem_num_dict:dict = {