python-katlas 0.0.7__py3-none-any.whl → 0.0.9__py3-none-any.whl

katlas/__init__.py

@@ -1 +1 @@
-__version__ = "0.0.6"
+__version__ = "0.0.8"

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'),
@@ -47,8 +49,6 @@ d = { 'settings': { 'branch': 'main',
                              'katlas.core.get_ttest': ('core.html#get_ttest', 'katlas/core.py'),
                              'katlas.core.get_unique_site': ('core.html#get_unique_site', 'katlas/core.py'),
                              'katlas.core.multiply': ('core.html#multiply', 'katlas/core.py'),
-                             'katlas.core.multiply.__init__': ('core.html#multiply.__init__', 'katlas/core.py'),
-                             'katlas.core.multiply.func': ('core.html#multiply.func', 'katlas/core.py'),
                              'katlas.core.multiply_func': ('core.html#multiply_func', 'katlas/core.py'),
                              'katlas.core.predict_kinase': ('core.html#predict_kinase', 'katlas/core.py'),
                              'katlas.core.predict_kinase_df': ('core.html#predict_kinase_df', '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
@@ -12,7 +14,6 @@ from tqdm import tqdm
 from scipy.stats import chi2
 from typing import Callable
 from functools import partial
-from joblib import Parallel, delayed
 from scipy.stats import ttest_ind
 from statsmodels.stats.multitest import multipletests
 
@@ -177,7 +178,7 @@ 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 +188,17 @@ 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:
@@ -362,35 +374,30 @@ def multiply_func(values, # list of values, possibilities of amino acids at cert
     return log_sum
 
 # %% ../nbs/00_core.ipynb 33
-class multiply:
+def multiply(values, kinase, num_dict=Data.get_num_dict()):
     "Multiply values, consider the dynamics of scale factor, which is PSPA random aa number."
-    def __init__(self):
-        self.num_dict = Data.get_num_dict()
-        
-    def func(self, values, kinase):
-        
-        # Check if any values are less than or equal to zero
-        if np.any(np.array(values) == 0):
-            return np.nan
-        
-        else:
-            # Retrieve the divide factor from the dictionary
-            self.divide = self.num_dict[kinase]
 
-            # Using the logarithmic property: log(a*b) = log(a) + log(b)
-            # Compute the sum of the logarithms of the values and the divide factor
-            log_sum = np.sum(np.log2(values)) + (len(values) - 1) * np.log2(self.divide)
+    # Check if any values are less than or equal to zero
+    if np.any(np.array(values) == 0):
+        return np.nan
+    else:
+        # Retrieve the divide factor from the dictionary
+        divide_factor = num_dict[kinase]
+
+        # Using the logarithmic property: log(a*b) = log(a) + log(b)
+        # Compute the sum of the logarithms of the values and the divide factor
+        log_sum = np.sum(np.log2(values)) + (len(values) - 1) * np.log2(divide_factor)
 
-            return log_sum
+        return log_sum
 
-# %% ../nbs/00_core.ipynb 37
+# %% ../nbs/00_core.ipynb 36
 def sumup(values, # list of values, possibilities of amino acids at certain positions
           kinase=None, 
          ):
     "Sum up the possibilities of the amino acids at each position in a phosphorylation site sequence"
     return sum(values)
 
-# %% ../nbs/00_core.ipynb 40
+# %% ../nbs/00_core.ipynb 39
 def predict_kinase(input_string: str, # site sequence
                    ref: pd.DataFrame, # reference dataframe for scoring
                    func: Callable, # function to calculate score
@@ -442,18 +449,18 @@ def predict_kinase(input_string: str, # site sequence
         
     return out.round(3)  # Return the scores rounded to three decimal places
 
-# %% ../nbs/00_core.ipynb 42
+# %% ../nbs/00_core.ipynb 41
 # PSPA
-param_PSPA_st = {'ref':Data.get_pspa_st_norm(), 'func':multiply().func} # Johnson et al. Nature official
-param_PSPA_y = {'ref':Data.get_pspa_tyr_norm(), 'func':multiply().func}
-param_PSPA = {'ref':Data.get_pspa_all_norm(), 'func':multiply().func}
+param_PSPA_st = {'ref':Data.get_pspa_st_norm(), 'func':multiply} # Johnson et al. Nature official
+param_PSPA_y = {'ref':Data.get_pspa_tyr_norm(), 'func':multiply}
+param_PSPA = {'ref':Data.get_pspa_all_norm(), 'func':multiply}
 
 
 # Kinase-substrate dataset, CDDM
 param_CDDM = {'ref':Data.get_cddm(), 'func':sumup}
 param_CDDM_upper = {'ref':Data.get_cddm_upper(), 'func':sumup, 'to_upper':True} # specific for all uppercase
 
-# %% ../nbs/00_core.ipynb 46
+# %% ../nbs/00_core.ipynb 45
 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')
@@ -481,29 +488,60 @@ def predict_kinase_df(df, seq_col, ref, func, to_lower=False, to_upper=False):
     
     print('Finish preprocessing')
     
-    results = []
-    # Extract numerical part of reference DataFrame columns, sort them
-    num = list(set(ref.columns.str[:-1].astype(int)))
-    num.sort()
-    print(f'Calculating position: {num}')
-    # Transform reference DataFrame to a dictionary and clean up NaN values
-    ref_dict = ref.T.to_dict()
-    ref_dict = {
-        outer_k: {inner_k: val for inner_k, val in outer_v.items() if not pd.isna(val)}
-        for outer_k, outer_v in ref_dict.items()}
     
-    # Function to process each kinase with its dictionary, using parallel processing
-    def process_kinase(kinase, r_dict):
-        return [func(np.array([r_dict.get(key) for key in get_dict(input_string) if key in r_dict]), kinase) for input_string in df[seq_col]]
+    # wide form to long form
+    df['keys'] = df['site_seq'].apply(get_dict)
+    input_keys_df  = df[['keys']].explode('keys').reset_index()
+    input_keys_df.columns = ['input_index', 'key']
+    ref_T = ref.T
     
-    # Process all kinases in parallel, using tqdm for progress tracking
-    results = Parallel(n_jobs=-1)(delayed(process_kinase)(kinase, r_dict) for kinase, r_dict in tqdm(ref_dict.items()))
+    merged_df = input_keys_df.merge(ref_T, left_on='key', right_index=True, how='inner')
     
-    # Return results as a DataFrame
-    return pd.DataFrame(results, index=ref.index, columns=df.index).T
+    if func == sumup:
+        grouped_df = merged_df.drop(columns=['key']).groupby('input_index').sum()
+        out = grouped_df.reindex(df.index)
+         
+    elif func==multiply:
+        # Get the list of kinases and num_dict
+        kinases = ref_T.columns
+        num_dict = Data.get_num_dict()
+        
+        out = {}
+        for kinase in tqdm(kinases):
+            divide_factor = num_dict[kinase]
+            # Extract data for this kinase
+            kinase_df = merged_df[['input_index', kinase]].copy()
+            kinase_df = kinase_df.rename(columns={kinase: 'value'})
+
+            # Compute log_value
+            kinase_df['log_value'] = np.log2(kinase_df['value'],where=kinase_df['value']>0)
+
+            # Group by 'input_index' and compute sum and count
+            grouped = kinase_df.dropna().groupby('input_index')
+            sum_log_values = grouped['log_value'].sum()
+            len_values = grouped['log_value'].count()
 
+            # Compute log_sum using the formula
+            log_sum = sum_log_values + (len_values - 1) * np.log2(divide_factor)
 
-# %% ../nbs/00_core.ipynb 55
+            # Find all 'input_index' where 'log_value' is NaN
+            nan_input_indices = kinase_df.loc[kinase_df['value']==0, 'input_index'].unique()
+            # Set log_sum at those indices to NaN
+            log_sum.loc[nan_input_indices] = np.nan
+
+            # Assign the computed values to the results DataFrame
+            out[kinase] = log_sum
+
+        out = pd.DataFrame(out).reindex(df.index)
+        
+    else:
+        grouped_df = merged_df.drop(columns=['key']).groupby('input_index').agg(func)
+        out = grouped_df.reindex(df.index)
+        
+    # Return results as a DataFrame
+    return out
+
+# %% ../nbs/00_core.ipynb 54
 def get_pct(site,ref,func,pct_ref):
     
     "Replicate the precentile results from The Kinase Library."
@@ -528,7 +566,7 @@ def get_pct(site,ref,func,pct_ref):
     final.columns=['log2(score)','percentile']
     return final
 
-# %% ../nbs/00_core.ipynb 61
+# %% ../nbs/00_core.ipynb 60
 def get_pct_df(score_df, # output from predict_kinase_df 
                pct_ref, # a reference df for percentile calculation
               ):
@@ -553,7 +591,7 @@ def get_pct_df(score_df, # output from predict_kinase_df
     
     return percentiles_df
 
-# %% ../nbs/00_core.ipynb 66
+# %% ../nbs/00_core.ipynb 65
 def get_unique_site(df:pd.DataFrame = None,# dataframe that contains phosphorylation sites
                     seq_col: str='site_seq', # column name of site sequence
                     id_col: str='gene_site' # column name of site id
@@ -569,7 +607,7 @@ def get_unique_site(df:pd.DataFrame = None,# dataframe that contains phosphoryla
     
     return unique
 
-# %% ../nbs/00_core.ipynb 69
+# %% ../nbs/00_core.ipynb 68
 def extract_site_seq(df: pd.DataFrame, # dataframe that contains protein sequence
                      seq_col: str, # column name of protein sequence
                      position_col: str # column name of position 0
@@ -595,7 +633,7 @@ def extract_site_seq(df: pd.DataFrame, # dataframe that contains protein sequenc
         
     return np.array(data)
 
-# %% ../nbs/00_core.ipynb 74
+# %% ../nbs/00_core.ipynb 73
 def get_freq(df_k: pd.DataFrame, # a dataframe for a single kinase that contains phosphorylation sequence splitted by their position
              aa_order = [i for i in 'PGACSTVILMFYWHKRQNDEsty'], # amino acid to include in the full matrix 
              aa_order_paper = [i for i in 'PGACSTVILMFYWHKRQNDEsty'], # amino acid to include in the partial matrix
@@ -636,7 +674,7 @@ def get_freq(df_k: pd.DataFrame, # a dataframe for a single kinase that contains
     
     return paper,full
 
-# %% ../nbs/00_core.ipynb 78
+# %% ../nbs/00_core.ipynb 77
 def query_gene(df,gene):
     
     "Query gene in the phosphoproteomics dataset"
@@ -650,7 +688,7 @@ def query_gene(df,gene):
     
     return df_gene
 
-# %% ../nbs/00_core.ipynb 82
+# %% ../nbs/00_core.ipynb 81
 def get_ttest(df, 
               columns1, # list of column names for group1
               columns2, # list of column names for group2
@@ -720,7 +758,7 @@ def get_ttest(df,
     
     return results
 
-# %% ../nbs/00_core.ipynb 83
+# %% ../nbs/00_core.ipynb 82
 def get_metaP(p_values):
     
     "Use Fisher's method to calculate a combined p value given a list of p values; this function also allows negative p values (negative correlation)"
@@ -732,7 +770,7 @@ def get_metaP(p_values):
 
     return score
 
-# %% ../nbs/00_core.ipynb 86
+# %% ../nbs/00_core.ipynb 85
 def raw2norm(df: pd.DataFrame, # single kinase's df has position as index, and single amino acid as columns
              PDHK: bool=False, # whether this kinase belongs to PDHK family 
             ):
@@ -755,7 +793,7 @@ def raw2norm(df: pd.DataFrame, # single kinase's df has position as index, and s
     
     return df2
 
-# %% ../nbs/00_core.ipynb 88
+# %% ../nbs/00_core.ipynb 87
 def get_one_kinase(df: pd.DataFrame, #stacked dataframe (paper's raw data)
                    kinase:str, # a specific kinase
                    normalize: bool=False, # normalize according to the paper; special for PDHK1/4

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-0.0.7.dist-info → python_katlas-0.0.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: python-katlas
-Version: 0.0.7
+Version: 0.0.9
 Summary: tools for predicting kinome specificities
 Home-page: https://github.com/sky1ove/python-katlas
 Author: lily
@@ -21,7 +21,6 @@ License-File: LICENSE
 Requires-Dist: statsmodels
 Requires-Dist: fastparquet
 Requires-Dist: tqdm
-Requires-Dist: joblib
 Provides-Extra: dev
 Requires-Dist: nbdev ; extra == 'dev'
 Requires-Dist: pyngrok ; extra == 'dev'

python_katlas-0.0.9.dist-info/RECORD

@@ -0,0 +1,14 @@
+katlas/__init__.py,sha256=wOJN3HxAgnSon5vWYU3Txm2UZ_7tBHDKXUKZIH-mXX8,22
+katlas/_modidx.py,sha256=N4eRU0s8l9NGhHf-PZynH4p87iyw9ksebr7DKd8SLR0,11027
+katlas/core.py,sha256=eSQonCHahRPgSbNGVhrbPlYkhSqarnFWm_-juS4gCY0,36654
+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-0.0.9.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+python_katlas-0.0.9.dist-info/METADATA,sha256=hGnYSHNOMM3r60gt9VcOgo3se2r5H43lJFYciFkJ1_Q,15460
+python_katlas-0.0.9.dist-info/WHEEL,sha256=EVRjI69F5qVjm_YgqcTXPnTAv3BfSUr0WVAHuSP3Xoo,92
+python_katlas-0.0.9.dist-info/entry_points.txt,sha256=SF3xDlCmE84ECTBIMDo_FNg1aXGX2-lXkCvH5o4VgpM,34
+python_katlas-0.0.9.dist-info/top_level.txt,sha256=pKBKw9KOSJgnnFkoilkDij_iJ_tJbIO4XnrSXIleqNc,7
+python_katlas-0.0.9.dist-info/RECORD,,

python_katlas-0.0.7.dist-info/RECORD

@@ -1,14 +0,0 @@
-katlas/__init__.py,sha256=QiiYsv0kcJaB8wCWyT-FnI2b6be87HA-CrrIUn8LQhg,22
-katlas/_modidx.py,sha256=COjpHUccTtv9jU9ifJgAn1uHwwYCpwyyFpM_ifl42Ew,11010
-katlas/core.py,sha256=a4dYSYUSLsixcXmLVJwso3iwHUjlN4XJZ4Vbnr4_I98,35274
-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-0.0.7.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-python_katlas-0.0.7.dist-info/METADATA,sha256=azPEmysqMFYpCJlC4gDDA1Yyprb5914xceAysBb7G5Q,15482
-python_katlas-0.0.7.dist-info/WHEEL,sha256=EVRjI69F5qVjm_YgqcTXPnTAv3BfSUr0WVAHuSP3Xoo,92
-python_katlas-0.0.7.dist-info/entry_points.txt,sha256=SF3xDlCmE84ECTBIMDo_FNg1aXGX2-lXkCvH5o4VgpM,34
-python_katlas-0.0.7.dist-info/top_level.txt,sha256=pKBKw9KOSJgnnFkoilkDij_iJ_tJbIO4XnrSXIleqNc,7
-python_katlas-0.0.7.dist-info/RECORD,,