python-katlas 0.0.6__py3-none-any.whl → 0.0.8__py3-none-any.whl

katlas/__init__.py

@@ -1 +1 @@
-__version__ = "0.0.3"
+__version__ = "0.0.7"

katlas/_modidx.py

@@ -19,6 +19,8 @@ d = { 'settings': { 'branch': 'main',
                              'katlas.core.Data.get_cddm_others_info': ('core.html#data.get_cddm_others_info', 'katlas/core.py'),
                              'katlas.core.Data.get_cddm_upper': ('core.html#data.get_cddm_upper', 'katlas/core.py'),
                              'katlas.core.Data.get_combine': ('core.html#data.get_combine', 'katlas/core.py'),
+                             'katlas.core.Data.get_combine_site_phosphorylated': ( 'core.html#data.get_combine_site_phosphorylated',
+                                                                                   'katlas/core.py'),
                              'katlas.core.Data.get_combine_site_psp_ochoa': ('core.html#data.get_combine_site_psp_ochoa', 'katlas/core.py'),
                              'katlas.core.Data.get_cptac_ensembl_site': ('core.html#data.get_cptac_ensembl_site', 'katlas/core.py'),
                              'katlas.core.Data.get_cptac_gene_site': ('core.html#data.get_cptac_gene_site', 'katlas/core.py'),

katlas/core.py

@@ -1,3 +1,5 @@
+"""Core functions in Katlas library"""
+
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/00_core.ipynb.
 
 # %% auto 0
@@ -177,7 +179,7 @@ class Data:
         return Data.fetch_data(Data.OCHOA_URL)
     
     # combine ochoa and PSP low throughput data
-    COMBINE_PSP_OCHOA_URL = "https://github.com/sky1ove/katlas/raw/main/dataset/phosphosites/combine_site_ochoa_psp.parquet"
+    COMBINE_PSP_OCHOA_URL = "https://github.com/sky1ove/katlas/raw/main/dataset/phosphosites/combine_site_psp_ochoa.parquet"
     @staticmethod
     def get_combine_site_psp_ochoa():
         "Combined Ochoa and PhosphoSitePlus"
@@ -187,6 +189,17 @@ class Data:
         df.columns = [int(col) if col.lstrip('-').isdigit() else col for col in df.columns]
         return df
     
+    # combine ochoa and PSP low throughput data
+    P_COMBINE_PSP_OCHOA_URL = "https://github.com/sky1ove/katlas/raw/main/dataset/phosphosites/phosphorylated_combine_site.parquet"
+    @staticmethod
+    def get_combine_site_phosphorylated():
+        "Combined Ochoa and PhosphoSitePlus with phosphorylation status"
+        df = Data.fetch_data(Data.P_COMBINE_PSP_OCHOA_URL)
+        
+        #Convert the number in the column name into integer
+        df.columns = [int(col) if col.lstrip('-').isdigit() else col for col in df.columns]
+        return df
+    
 
 # %% ../nbs/00_core.ipynb 12
 class CPTAC:
@@ -395,6 +408,7 @@ def predict_kinase(input_string: str, # site sequence
                    ref: pd.DataFrame, # reference dataframe for scoring
                    func: Callable, # function to calculate score
                    to_lower: bool=False, # convert capital STY to lower case
+                   to_upper: bool=False, # convert all letter to uppercase
                    verbose=True
                    ):
     "Predict kinase given a phosphorylation site sequence"
@@ -408,6 +422,10 @@ def predict_kinase(input_string: str, # site sequence
     # If to_lower is True, convert STY in the sequence to lower case
     if to_lower:
         input_string = STY2sty(input_string)
+        
+    # If to_upper is True, convert the sequence to all uppercase
+    if to_upper:
+        input_string = input_string.upper()
     
     results = [] # Initialize a list to store the scores for each kinase
     
@@ -446,10 +464,10 @@ param_PSPA = {'ref':Data.get_pspa_all_norm(), 'func':multiply().func}
 
 # Kinase-substrate dataset, CDDM
 param_CDDM = {'ref':Data.get_cddm(), 'func':sumup}
-param_CDDM_upper = {'ref':Data.get_cddm_upper(), 'func':sumup} # specific for all uppercase
+param_CDDM_upper = {'ref':Data.get_cddm_upper(), 'func':sumup, 'to_upper':True} # specific for all uppercase
 
 # %% ../nbs/00_core.ipynb 46
-def predict_kinase_df(df, seq_col, ref, func, to_lower=False):
+def predict_kinase_df(df, seq_col, ref, func, to_lower=False, to_upper=False):
     print('input dataframe has a length', df.shape[0])
     print('Preprocessing')
     
@@ -466,6 +484,9 @@ def predict_kinase_df(df, seq_col, ref, func, to_lower=False):
     if to_lower:
         df[seq_col] = df[seq_col].apply(STY2sty)
         
+    if to_upper:
+        df[seq_col] = df[seq_col].str.upper()
+        
     # Adjust sequence lengths to match the reference matrix's expected inputs
     max_value = ref.columns.str[:-1].astype(int).max() # Get the highest position index from the reference columns
     min_value = ref.columns.str[:-1].astype(int).min() # Get the lowest position index

katlas/dl.py

@@ -1,3 +1,5 @@
+"""A collection of deep learning tools via Fastai"""
+
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/04_DL.ipynb.
 
 # %% auto 0

katlas/feature.py

@@ -1,3 +1,5 @@
+"""A collection of tools to extract features from SMILES, proteins, etc."""
+
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/01_feature.ipynb.
 
 # %% auto 0

katlas/plot.py

@@ -1,3 +1,5 @@
+"""A collection of plot functions"""
+
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/02_plot.ipynb.
 
 # %% auto 0

katlas/train.py

@@ -1,3 +1,5 @@
+"""A collection of machine learning tools"""
+
 # AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/03_ML.ipynb.
 
 # %% auto 0

{python_katlas-0.0.6.dist-info → python_katlas-0.0.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: python-katlas
-Version: 0.0.6
+Version: 0.0.8
 Summary: tools for predicting kinome specificities
 Home-page: https://github.com/sky1ove/python-katlas
 Author: lily

python_katlas-0.0.8.dist-info/RECORD

@@ -0,0 +1,14 @@
+katlas/__init__.py,sha256=R9xOYoYrWKcfO5zvTeGC3m_eDNOvxMd8CocQs2tLufo,22
+katlas/_modidx.py,sha256=W8FiqZd2da7DE4nVJaoG56fLD8I1fkmfyXQwHqOFYZg,11245
+katlas/core.py,sha256=8jPQS49qIitfbfyQOCljcql8K05aTCWKHjMCXcdcwWs,35871
+katlas/dl.py,sha256=gV-rwTLU9IudwFyNJKo-MP8nmOzhqURZQt3rJalHoG8,10903
+katlas/feature.py,sha256=Wv94R0hnAovErifV2x5ky8uvRMNSGPjnS4ivyWVoZps,11548
+katlas/imports.py,sha256=-ZphRU8K1KspxMpgRxisE0OskrCw3S8JR8tvmeXBRY0,147
+katlas/plot.py,sha256=_bzvMwxzAjXg0Zxb5Sv7bfCIopxJegjCA-DutjrLybo,23668
+katlas/train.py,sha256=OhiR2ev1UhPBBSWLncwfNjy_UImSmB_kVhZp7DyCQ50,7671
+python_katlas-0.0.8.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+python_katlas-0.0.8.dist-info/METADATA,sha256=86tumS-YaIzTRrU7Tu7xcA0WlYbsdn1zhCAUC9Ba7OE,15482
+python_katlas-0.0.8.dist-info/WHEEL,sha256=EVRjI69F5qVjm_YgqcTXPnTAv3BfSUr0WVAHuSP3Xoo,92
+python_katlas-0.0.8.dist-info/entry_points.txt,sha256=SF3xDlCmE84ECTBIMDo_FNg1aXGX2-lXkCvH5o4VgpM,34
+python_katlas-0.0.8.dist-info/top_level.txt,sha256=pKBKw9KOSJgnnFkoilkDij_iJ_tJbIO4XnrSXIleqNc,7
+python_katlas-0.0.8.dist-info/RECORD,,

python_katlas-0.0.6.dist-info/RECORD

@@ -1,14 +0,0 @@
-katlas/__init__.py,sha256=4GZKi13lDTD25YBkGakhZyEQZWTER_OWQMNPoH_UM2c,22
-katlas/_modidx.py,sha256=COjpHUccTtv9jU9ifJgAn1uHwwYCpwyyFpM_ifl42Ew,11010
-katlas/core.py,sha256=sJLUQJugXKjN6B71esnYDmB3GcdX8YcFxvfIm1EdrAM,34959
-katlas/dl.py,sha256=Rm1EO6oGTiHpqp4EA2xAvbIUnh608FPYOdzndRGKVkc,10849
-katlas/feature.py,sha256=3zgTuCnXqH1e0LGZ2Hkvan852PiaIHxj27cg_TJfKzo,11471
-katlas/imports.py,sha256=-ZphRU8K1KspxMpgRxisE0OskrCw3S8JR8tvmeXBRY0,147
-katlas/plot.py,sha256=vB3gv0aaCNERW1CtdDWqM4jIZOx1auGWwi_1I22xBa0,23630
-katlas/train.py,sha256=s0ucsZVaixCTZPz-XAI2J7zQDeGkiYEJKOc2dFTYsAc,7625
-python_katlas-0.0.6.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-python_katlas-0.0.6.dist-info/METADATA,sha256=Q6mxI66o2dpBZMo_VV3m2jUrYCUunUJMk3elyR4CW7o,15482
-python_katlas-0.0.6.dist-info/WHEEL,sha256=EVRjI69F5qVjm_YgqcTXPnTAv3BfSUr0WVAHuSP3Xoo,92
-python_katlas-0.0.6.dist-info/entry_points.txt,sha256=SF3xDlCmE84ECTBIMDo_FNg1aXGX2-lXkCvH5o4VgpM,34
-python_katlas-0.0.6.dist-info/top_level.txt,sha256=pKBKw9KOSJgnnFkoilkDij_iJ_tJbIO4XnrSXIleqNc,7
-python_katlas-0.0.6.dist-info/RECORD,,