python-katlas 0.0.9__tar.gz → 0.1.1__tar.gz

{python-katlas-0.0.9/python_katlas.egg-info → python-katlas-0.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: python-katlas
-Version: 0.0.9
+Version: 0.1.1
 Summary: tools for predicting kinome specificities
 Home-page: https://github.com/sky1ove/python-katlas
 Author: lily
@@ -60,6 +60,13 @@ helpful to your research.
   phosphoproteome](https://www.nature.com/articles/s41587-019-0344-3),
   and [CPTAC](https://pdc.cancer.gov/pdc/cptac-pancancer) /
   [LinkedOmics](https://academic.oup.com/nar/article/46/D1/D956/4607804)
+  
+  
+## Web applications
+
+Users can now run the analysis directly on the web without needing to code. 
+
+Check out our latest web: [kinase-atlas.com](https://kinase-atlas.com/)
 
 ## Tutorials on Colab
 
@@ -67,20 +74,16 @@ helpful to your research.
       sequence](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_01_sinlge_input.ipynb)
 - 2.  [High throughput substrate scoring on phosphoproteomics
       dataset](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_02_high_throughput.ipynb)
-- 3.  [Query a protein’s phosphorylation sites and predict their
-      upstream
-      kinases](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_03_query_gene.ipynb)
-- 4.  [Kinase enrichment analysis for AKT
-      inhibitor](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_04a_enrichment_AKTi.ipynb)
-      / [Kinase enrichment analysis for EGFR
-      inhibitor](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_04b_enrichment_EGFRi.ipynb)
+- 3.  [Kinase enrichment analysis for AKT
+      inhibitor](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_03a_enrichment_AKTi.ipynb)
+
 
 ## Install
 
-Install the latest version through git
+Install the latest version through pip
 
 ``` python
-!pip install git+https://github.com/sky1ove/katlas.git -Uqq
+pip install python-katlas -Uq
 ```
 
 ## Import

{python-katlas-0.0.9 → python-katlas-0.1.1}/README.md

@@ -38,6 +38,13 @@ helpful to your research.
   phosphoproteome](https://www.nature.com/articles/s41587-019-0344-3),
   and [CPTAC](https://pdc.cancer.gov/pdc/cptac-pancancer) /
   [LinkedOmics](https://academic.oup.com/nar/article/46/D1/D956/4607804)
+  
+  
+## Web applications
+
+Users can now run the analysis directly on the web without needing to code. 
+
+Check out our latest web: [kinase-atlas.com](https://kinase-atlas.com/)
 
 ## Tutorials on Colab
 
@@ -45,20 +52,16 @@ helpful to your research.
       sequence](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_01_sinlge_input.ipynb)
 - 2.  [High throughput substrate scoring on phosphoproteomics
       dataset](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_02_high_throughput.ipynb)
-- 3.  [Query a protein’s phosphorylation sites and predict their
-      upstream
-      kinases](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_03_query_gene.ipynb)
-- 4.  [Kinase enrichment analysis for AKT
-      inhibitor](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_04a_enrichment_AKTi.ipynb)
-      / [Kinase enrichment analysis for EGFR
-      inhibitor](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_04b_enrichment_EGFRi.ipynb)
+- 3.  [Kinase enrichment analysis for AKT
+      inhibitor](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_03a_enrichment_AKTi.ipynb)
+
 
 ## Install
 
-Install the latest version through git
+Install the latest version through pip
 
 ``` python
-!pip install git+https://github.com/sky1ove/katlas.git -Uqq
+pip install python-katlas -Uq
 ```
 
 ## Import

python-katlas-0.1.1/katlas/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.0"

{python-katlas-0.0.9 → python-katlas-0.1.1}/katlas/_modidx.py

@@ -46,13 +46,12 @@ d = { 'settings': { 'branch': 'main',
                              'katlas.core.get_one_kinase': ('core.html#get_one_kinase', 'katlas/core.py'),
                              'katlas.core.get_pct': ('core.html#get_pct', 'katlas/core.py'),
                              'katlas.core.get_pct_df': ('core.html#get_pct_df', 'katlas/core.py'),
-                             'katlas.core.get_ttest': ('core.html#get_ttest', 'katlas/core.py'),
+                             'katlas.core.get_pvalue': ('core.html#get_pvalue', '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_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.query_gene': ('core.html#query_gene', 'katlas/core.py'),
                              'katlas.core.raw2norm': ('core.html#raw2norm', 'katlas/core.py'),
                              'katlas.core.sumup': ('core.html#sumup', 'katlas/core.py')},
             'katlas.dl': { 'katlas.dl.CNN1D_1': ('dl.html#cnn1d_1', 'katlas/dl.py'),

{python-katlas-0.0.9 → python-katlas-0.1.1}/katlas/core.py

@@ -6,7 +6,7 @@
 __all__ = ['param_PSPA_st', 'param_PSPA_y', 'param_PSPA', 'param_CDDM', 'param_CDDM_upper', 'Data', 'CPTAC', 'convert_string',
            'checker', 'STY2sty', 'cut_seq', 'get_dict', 'multiply_func', 'multiply', 'sumup', 'predict_kinase',
            'predict_kinase_df', 'get_pct', 'get_pct_df', 'get_unique_site', 'extract_site_seq', 'get_freq',
-           'query_gene', 'get_ttest', 'get_metaP', 'raw2norm', 'get_one_kinase']
+           'get_pvalue', 'get_metaP', 'raw2norm', 'get_one_kinase']
 
 # %% ../nbs/00_core.ipynb 4
 import math, pandas as pd, numpy as np
@@ -14,7 +14,7 @@ from tqdm import tqdm
 from scipy.stats import chi2
 from typing import Callable
 from functools import partial
-from scipy.stats import ttest_ind
+from scipy.stats import ttest_ind, mannwhitneyu, wilcoxon
 from statsmodels.stats.multitest import multipletests
 
 # %% ../nbs/00_core.ipynb 7
@@ -451,17 +451,18 @@ def predict_kinase(input_string: str, # site sequence
 
 # %% ../nbs/00_core.ipynb 41
 # PSPA
-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}
+param_PSPA_st = {'ref':Data.get_pspa_st_norm().astype('float32'), 'func':multiply} # Johnson et al. Nature official
+param_PSPA_y = {'ref':Data.get_pspa_tyr_norm().astype('float32'), 'func':multiply}
+param_PSPA = {'ref':Data.get_pspa_all_norm().astype('float32'), '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
+param_CDDM = {'ref':Data.get_cddm().astype('float32'), 'func':sumup}
+param_CDDM_upper = {'ref':Data.get_cddm_upper().astype('float32'), 'func':sumup, 'to_upper':True} # specific for all uppercase
 
-# %% ../nbs/00_core.ipynb 45
+# %% ../nbs/00_core.ipynb 46
 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')
     
@@ -493,12 +494,20 @@ def predict_kinase_df(df, seq_col, ref, func, to_lower=False, to_upper=False):
     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
     
-    merged_df = input_keys_df.merge(ref_T, left_on='key', right_index=True, how='inner')
+    input_keys_df = input_keys_df.set_index('key')
+    
+    
+    print('Merging reference')
+    merged_df = input_keys_df.merge(ref_T, left_index=True, right_index=True, how='inner')
+
+    print('Finish merging')
     
     if func == sumup:
-        grouped_df = merged_df.drop(columns=['key']).groupby('input_index').sum()
+        grouped_df = merged_df.groupby('input_index').sum()
         out = grouped_df.reindex(df.index)
          
     elif func==multiply:
@@ -514,7 +523,7 @@ def predict_kinase_df(df, seq_col, ref, func, to_lower=False, to_upper=False):
             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)
+            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')
@@ -541,7 +550,7 @@ def predict_kinase_df(df, seq_col, ref, func, to_lower=False, to_upper=False):
     # Return results as a DataFrame
     return out
 
-# %% ../nbs/00_core.ipynb 54
+# %% ../nbs/00_core.ipynb 53
 def get_pct(site,ref,func,pct_ref):
     
     "Replicate the precentile results from The Kinase Library."
@@ -566,7 +575,7 @@ def get_pct(site,ref,func,pct_ref):
     final.columns=['log2(score)','percentile']
     return final
 
-# %% ../nbs/00_core.ipynb 60
+# %% ../nbs/00_core.ipynb 59
 def get_pct_df(score_df, # output from predict_kinase_df 
                pct_ref, # a reference df for percentile calculation
               ):
@@ -591,7 +600,7 @@ def get_pct_df(score_df, # output from predict_kinase_df
     
     return percentiles_df
 
-# %% ../nbs/00_core.ipynb 65
+# %% ../nbs/00_core.ipynb 64
 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
@@ -607,7 +616,7 @@ def get_unique_site(df:pd.DataFrame = None,# dataframe that contains phosphoryla
     
     return unique
 
-# %% ../nbs/00_core.ipynb 68
+# %% ../nbs/00_core.ipynb 67
 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
@@ -633,7 +642,7 @@ def extract_site_seq(df: pd.DataFrame, # dataframe that contains protein sequenc
         
     return np.array(data)
 
-# %% ../nbs/00_core.ipynb 73
+# %% ../nbs/00_core.ipynb 72
 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
@@ -674,35 +683,16 @@ def get_freq(df_k: pd.DataFrame, # a dataframe for a single kinase that contains
     
     return paper,full
 
-# %% ../nbs/00_core.ipynb 77
-def query_gene(df,gene):
-    
-    "Query gene in the phosphoproteomics dataset"
-    
-    # query gene in the dataframe
-    df_gene = df[df.gene_site.str.contains(f'{gene}_')]
-    
-    # sort dataframe based on position
-    sort_position = df_gene.gene_site.str.split('_').str[-1].str[1:].astype(int).sort_values().index
-    df_gene = df_gene.loc[sort_position]
-    
-    return df_gene
-
-# %% ../nbs/00_core.ipynb 81
-def get_ttest(df, 
+# %% ../nbs/00_core.ipynb 76
+def get_pvalue(df,
               columns1, # list of column names for group1
               columns2, # list of column names for group2
+              test_method = 'mann_whitney', # 'student_t', 'mann_whitney', 'wilcoxon'
               FC_method = 'median', # or mean
-              alpha=0.05, # significance level in multipletests for p_adj
-              correction_method='fdr_bh', # method in multipletests for p_adj
              ):
-    """
-    Performs t-tests and calculates log2 fold change between two groups of columns in a DataFrame.
-    NaN p-values are excluded from the multiple testing correction.
 
-    Returns:
-    DataFrame: Results including log2FC, p-values, adjusted p-values, significance, signed log10 P value, and signed log10 Padj
-    """
+    "Performs statistical tests and calculates difference between the median or mean of two groups of columns."
+
     group1 = df[columns1]
     group2 = df[columns2]
 
@@ -717,24 +707,36 @@ def get_ttest(df,
     # As phosphoproteomics data has already been log transformed, we can directly use subtraction
     FCs = m2 - m1
 
-    # Perform t-tests and handle NaN p-values    
-    t_results = [ttest_ind(group1.loc[idx], group2.loc[idx], nan_policy='omit') for idx in tqdm(df.index, desc="Computing t-tests")]
+    # Perform the chosen test and handle NaN p-values
+    if test_method == 'student_t': # data is normally distributed, non-paired
+        test_func = ttest_ind
+    elif test_method == 'mann_whitney': # not normally distributed, non-paired, mann_whitney considers the rank, ignore the differences
+        test_func = mannwhitneyu
+    elif test_method == 'wilcoxon': # not normally distributed, paired
+        test_func = wilcoxon
+
+    t_results = []
+    for idx in tqdm(df.index, desc=f"Computing {test_method} tests"):
+        try:
+            if test_method == 'wilcoxon': # as wilcoxon is paired, if lack a paired sample, just give nan, as default nanpolicy is propagate (gives nan if nan in input)
+                stat, pvalue = test_func(group1.loc[idx], group2.loc[idx])
+            else:
+                stat, pvalue = test_func(group1.loc[idx], group2.loc[idx], nan_policy='omit')
+        except ValueError:  # Handle cases with insufficient data
+            pvalue = np.nan
+        t_results.append(pvalue)
 
     # Exclude NaN p-values before multiple testing correction
-    p_values = [result.pvalue if result.pvalue is not np.nan else np.nan for result in t_results]
-    valid_p_values = np.array(p_values, dtype=float)  # Ensure the correct data type
+    p_values = np.array(t_results, dtype=float)  # Ensure the correct data type
+    valid_p_values = p_values[~np.isnan(p_values)]
 
-    # valid_p_values = np.array(p_values)
-    valid_p_values = valid_p_values[~np.isnan(valid_p_values)]
-    
     # Adjust for multiple testing on valid p-values only
-    reject, pvals_corrected, _, _ = multipletests(valid_p_values, alpha=alpha, method=correction_method)
-    
+    reject, pvals_corrected, _, _ = multipletests(valid_p_values, alpha=0.05, method='fdr_bh')
+
     # Create a full list of corrected p-values including NaNs
-    full_pvals_corrected = np.empty_like(p_values)
-    full_pvals_corrected[:] = np.nan
+    full_pvals_corrected = np.full_like(p_values, np.nan)
     np.place(full_pvals_corrected, ~np.isnan(p_values), pvals_corrected)
-    
+
     # Adjust the significance accordingly
     full_reject = np.zeros_like(p_values, dtype=bool)
     np.place(full_reject, ~np.isnan(p_values), reject)
@@ -743,22 +745,21 @@ def get_ttest(df,
     results = pd.DataFrame({
         'log2FC': FCs,
         'p_value': p_values,
-        'p_adj': full_pvals_corrected,
-        'significant': full_reject
+        'p_adj': full_pvals_corrected
     })
 
     results['p_value'] = results['p_value'].astype(float)
-    
+
     def get_signed_logP(r,p_col):
         log10 = -np.log10(r[p_col])
         return -log10 if r['log2FC']<0 else log10
-    
+
     results['signed_logP'] = results.apply(partial(get_signed_logP,p_col='p_value'),axis=1)
     results['signed_logPadj'] = results.apply(partial(get_signed_logP,p_col='p_adj'),axis=1)
-    
+
     return results
 
-# %% ../nbs/00_core.ipynb 82
+# %% ../nbs/00_core.ipynb 77
 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)"
@@ -770,7 +771,7 @@ def get_metaP(p_values):
 
     return score
 
-# %% ../nbs/00_core.ipynb 85
+# %% ../nbs/00_core.ipynb 80
 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 
             ):
@@ -793,7 +794,7 @@ def raw2norm(df: pd.DataFrame, # single kinase's df has position as index, and s
     
     return df2
 
-# %% ../nbs/00_core.ipynb 87
+# %% ../nbs/00_core.ipynb 82
 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

{python-katlas-0.0.9 → python-katlas-0.1.1}/katlas/dl.py

@@ -6,7 +6,7 @@
 __all__ = ['def_device', 'seed_everything', 'GeneralDataset', 'get_sampler', 'MLP_1', 'CNN1D_1', 'init_weights', 'lin_wn',
            'conv_wn', 'CNN1D_2', 'train_dl', 'train_dl_cv', 'predict_dl']
 
-# %% ../nbs/04_DL.ipynb 4
+# %% ../nbs/04_DL.ipynb 5
 from fastbook import *
 import fastcore.all as fc,torch.nn.init as init
 from fastai.callback.training import GradientClip
@@ -22,7 +22,7 @@ from sklearn.model_selection import *
 from sklearn.metrics import mean_squared_error
 from scipy.stats import spearmanr,pearsonr
 
-# %% ../nbs/04_DL.ipynb 6
+# %% ../nbs/04_DL.ipynb 7
 def seed_everything(seed=123):
     random.seed(seed)
     os.environ['PYTHONHASHSEED'] = str(seed)
@@ -32,10 +32,10 @@ def seed_everything(seed=123):
     torch.backends.cudnn.deterministic = True
     torch.backends.cudnn.benchmark = False
 
-# %% ../nbs/04_DL.ipynb 8
+# %% ../nbs/04_DL.ipynb 9
 def_device = 'mps' if torch.backends.mps.is_available() else 'cuda' if torch.cuda.is_available() else 'cpu'
 
-# %% ../nbs/04_DL.ipynb 13
+# %% ../nbs/04_DL.ipynb 14
 class GeneralDataset:
     def __init__(self, 
                  df, # a dataframe of values
@@ -62,7 +62,7 @@ class GeneralDataset:
             y = torch.Tensor(self.y[index])
             return X, y
 
-# %% ../nbs/04_DL.ipynb 17
+# %% ../nbs/04_DL.ipynb 18
 def get_sampler(info,col):
     
     "For imbalanced data, get higher weights for less-represented samples"
@@ -82,7 +82,7 @@ def get_sampler(info,col):
     
     return sampler
 
-# %% ../nbs/04_DL.ipynb 23
+# %% ../nbs/04_DL.ipynb 24
 def MLP_1(num_features, 
           num_targets,
           hidden_units = [512, 218],
@@ -112,7 +112,7 @@ def MLP_1(num_features,
     
     return model
 
-# %% ../nbs/04_DL.ipynb 29
+# %% ../nbs/04_DL.ipynb 30
 class CNN1D_1(Module):
     
     def __init__(self, 
@@ -137,12 +137,12 @@ class CNN1D_1(Module):
         x = self.fc2(x)
         return x
 
-# %% ../nbs/04_DL.ipynb 33
+# %% ../nbs/04_DL.ipynb 34
 def init_weights(m, leaky=0.):
     "Initiate any Conv layer with Kaiming norm."
     if isinstance(m, (nn.Conv1d,nn.Conv2d,nn.Conv3d)): init.kaiming_normal_(m.weight, a=leaky)
 
-# %% ../nbs/04_DL.ipynb 34
+# %% ../nbs/04_DL.ipynb 35
 def lin_wn(ni,nf,dp=0.1,act=nn.SiLU):
     "Weight norm of linear."
     layers =  nn.Sequential(
@@ -152,7 +152,7 @@ def lin_wn(ni,nf,dp=0.1,act=nn.SiLU):
     if act: layers.append(act())
     return layers
 
-# %% ../nbs/04_DL.ipynb 35
+# %% ../nbs/04_DL.ipynb 36
 def conv_wn(ni, nf, ks=3, stride=1, padding=1, dp=0.1,act=nn.ReLU):
     "Weight norm of conv."
     layers =  nn.Sequential(
@@ -162,7 +162,7 @@ def conv_wn(ni, nf, ks=3, stride=1, padding=1, dp=0.1,act=nn.ReLU):
     if act: layers.append(act())
     return layers
 
-# %% ../nbs/04_DL.ipynb 36
+# %% ../nbs/04_DL.ipynb 37
 class CNN1D_2(nn.Module):
     
     def __init__(self, ni, nf, amp_scale = 16):
@@ -212,7 +212,7 @@ class CNN1D_2(nn.Module):
 
         return x
 
-# %% ../nbs/04_DL.ipynb 40
+# %% ../nbs/04_DL.ipynb 41
 def train_dl(df, 
             feat_col, 
             target_col,
@@ -275,7 +275,7 @@ def train_dl(df,
     
     return target, pred
 
-# %% ../nbs/04_DL.ipynb 45
+# %% ../nbs/04_DL.ipynb 46
 @fc.delegates(train_dl)
 def train_dl_cv(df, 
                 feat_col, 
@@ -325,7 +325,7 @@ def train_dl_cv(df,
     
     return oof, metrics
 
-# %% ../nbs/04_DL.ipynb 53
+# %% ../nbs/04_DL.ipynb 54
 def predict_dl(df, 
                feat_col, 
                target_col,

{python-katlas-0.0.9 → python-katlas-0.1.1}/katlas/feature.py

@@ -5,7 +5,7 @@
 # %% auto 0
 __all__ = ['get_rdkit', 'get_morgan', 'get_esm', 'get_t5', 'get_t5_bfd', 'reduce_feature', 'remove_hi_corr', 'preprocess']
 
-# %% ../nbs/01_feature.ipynb 4
+# %% ../nbs/01_feature.ipynb 5
 from fastbook import *
 import torch,re,joblib,gc,esm
 from tqdm.notebook import tqdm; tqdm.pandas()
@@ -30,7 +30,7 @@ from umap.umap_ import UMAP
 
 set_config(transform_output="pandas")
 
-# %% ../nbs/01_feature.ipynb 7
+# %% ../nbs/01_feature.ipynb 8
 def get_rdkit(df: pd.DataFrame, # a dataframe that contains smiles
               col:str = "SMILES", # colname of smile
               normalize: bool = True, # normalize features using StandardScaler()
@@ -49,7 +49,7 @@ def get_rdkit(df: pd.DataFrame, # a dataframe that contains smiles
     # feature_df = feature_df.reset_index()
     return feature_df
 
-# %% ../nbs/01_feature.ipynb 11
+# %% ../nbs/01_feature.ipynb 12
 def get_morgan(df: pd.DataFrame, # a dataframe that contains smiles
                col: str = "SMILES", # colname of smile
                radius=3
@@ -61,7 +61,7 @@ def get_morgan(df: pd.DataFrame, # a dataframe that contains smiles
     fp_df.columns = "morgan_" + fp_df.columns.astype(str)
     return fp_df
 
-# %% ../nbs/01_feature.ipynb 15
+# %% ../nbs/01_feature.ipynb 16
 def get_esm(df:pd.DataFrame, # a dataframe that contains amino acid sequence
             col: str = 'sequence', # colname of amino acid sequence
             model_name: str = "esm2_t33_650M_UR50D", # Name of the ESM model to use for the embeddings.
@@ -128,7 +128,7 @@ def get_esm(df:pd.DataFrame, # a dataframe that contains amino acid sequence
 
         return df_feature
 
-# %% ../nbs/01_feature.ipynb 19
+# %% ../nbs/01_feature.ipynb 20
 def get_t5(df: pd.DataFrame, 
            col: str = 'sequence'
            ):
@@ -170,7 +170,7 @@ def get_t5(df: pd.DataFrame,
     
     return T5_feature
 
-# %% ../nbs/01_feature.ipynb 22
+# %% ../nbs/01_feature.ipynb 23
 def get_t5_bfd(df:pd.DataFrame, 
                col: str = 'sequence'
                ):
@@ -212,7 +212,7 @@ def get_t5_bfd(df:pd.DataFrame,
     
     return T5_feature
 
-# %% ../nbs/01_feature.ipynb 26
+# %% ../nbs/01_feature.ipynb 27
 def reduce_feature(df: pd.DataFrame, 
                    method: str='pca', # dimensionality reduction method, accept both capital and lower case
                    complexity: int=20, # None for PCA; perfplexity for TSNE, recommend: 30; n_neigbors for UMAP, recommend: 15
@@ -258,7 +258,7 @@ def reduce_feature(df: pd.DataFrame,
 
     return embedding_df
 
-# %% ../nbs/01_feature.ipynb 29
+# %% ../nbs/01_feature.ipynb 30
 def remove_hi_corr(df: pd.DataFrame, 
                    thr: float=0.98 # threshold
                    ):
@@ -278,7 +278,7 @@ def remove_hi_corr(df: pd.DataFrame,
     
     return df
 
-# %% ../nbs/01_feature.ipynb 33
+# %% ../nbs/01_feature.ipynb 34
 def preprocess(df: pd.DataFrame,
                thr: float=0.98):
     

{python-katlas-0.0.9 → python-katlas-0.1.1}/katlas/plot.py

@@ -7,7 +7,7 @@ __all__ = ['set_sns', 'get_color_dict', 'logo_func', 'get_logo', 'get_logo2', 'p
            'plot_cluster', 'plot_bokeh', 'plot_count', 'plot_bar', 'plot_group_bar', 'plot_box', 'plot_corr',
            'draw_corr', 'get_AUCDF', 'plot_confusion_matrix']
 
-# %% ../nbs/02_plot.ipynb 4
+# %% ../nbs/02_plot.ipynb 5
 import joblib,logomaker
 import fastcore.all as fc, pandas as pd, numpy as np, seaborn as sns
 from adjustText import adjust_text
@@ -32,14 +32,14 @@ from bokeh.layouts import column
 from bokeh.palettes import Category20_20
 from itertools import cycle
 
-# %% ../nbs/02_plot.ipynb 6
+# %% ../nbs/02_plot.ipynb 7
 def set_sns():
     "Set seaborn resolution for notebook display"
     sns.set(rc={"figure.dpi":300, 'savefig.dpi':300})
     sns.set_context('notebook')
     sns.set_style("ticks")
 
-# %% ../nbs/02_plot.ipynb 7
+# %% ../nbs/02_plot.ipynb 8
 def get_color_dict(categories, # list of names to assign color
                    palette: str='tab20', # choose from sns.color_palette
                    ):
@@ -49,7 +49,7 @@ def get_color_dict(categories, # list of names to assign color
     color_map = {category: next(color_cycle) for category in categories}
     return color_map
 
-# %% ../nbs/02_plot.ipynb 11
+# %% ../nbs/02_plot.ipynb 12
 def logo_func(df:pd.DataFrame, # a dataframe that contains ratios for each amino acid at each position
               title: str='logo', # title of the motif logo
              ):
@@ -81,7 +81,7 @@ def logo_func(df:pd.DataFrame, # a dataframe that contains ratios for each amino
     logo.ax.set_yticks([])
     logo.ax.set_title(title)
 
-# %% ../nbs/02_plot.ipynb 12
+# %% ../nbs/02_plot.ipynb 13
 def get_logo(df: pd.DataFrame, # stacked Dataframe with kinase as index, substrates as columns
              kinase: str, # a specific kinase name in index
              ):
@@ -120,7 +120,7 @@ def get_logo(df: pd.DataFrame, # stacked Dataframe with kinase as index, substra
     # plot logo
     logo_func(ratio2, kinase)
 
-# %% ../nbs/02_plot.ipynb 16
+# %% ../nbs/02_plot.ipynb 17
 def get_logo2(full: pd.DataFrame, # a dataframe that contains the full matrix of a kinase, with index as amino acid, and columns as positions
               title: str = 'logo', # title of the graph
               ):
@@ -159,7 +159,7 @@ def get_logo2(full: pd.DataFrame, # a dataframe that contains the full matrix of
 
     logo_func(ratio2,title)
 
-# %% ../nbs/02_plot.ipynb 19
+# %% ../nbs/02_plot.ipynb 20
 @fc.delegates(sns.scatterplot)
 def plot_rank(sorted_df: pd.DataFrame, # a sorted dataframe
               x: str, # column name for x axis
@@ -203,7 +203,7 @@ def plot_rank(sorted_df: pd.DataFrame, # a sorted dataframe
 
     plt.tight_layout()
 
-# %% ../nbs/02_plot.ipynb 23
+# %% ../nbs/02_plot.ipynb 24
 @fc.delegates(sns.histplot)
 def plot_hist(df: pd.DataFrame, # a dataframe that contain values for plot
               x: str, # column name of values
@@ -220,7 +220,7 @@ def plot_hist(df: pd.DataFrame, # a dataframe that contain values for plot
     plt.figure(figsize=figsize)
     sns.histplot(data=df,x=x,**hist_params,**kwargs)
 
-# %% ../nbs/02_plot.ipynb 27
+# %% ../nbs/02_plot.ipynb 28
 @fc.delegates(sns.heatmap)
 def plot_heatmap(matrix, # a matrix of values
                  title: str='heatmap', # title of the heatmap
@@ -235,7 +235,7 @@ def plot_heatmap(matrix, # a matrix of values
     sns.heatmap(matrix, cmap=cmap, annot=False,**kwargs)
     plt.title(title)
 
-# %% ../nbs/02_plot.ipynb 31
+# %% ../nbs/02_plot.ipynb 32
 @fc.delegates(sns.scatterplot)
 def plot_2d(X: pd.DataFrame, # a dataframe that has first column to be x, and second column to be y
             **kwargs, # arguments for sns.scatterplot
@@ -244,7 +244,7 @@ def plot_2d(X: pd.DataFrame, # a dataframe that has first column to be x, and se
     plt.figure(figsize=(7,7))
     sns.scatterplot(data = X,x=X.columns[0],y=X.columns[1],alpha=0.7,**kwargs)
 
-# %% ../nbs/02_plot.ipynb 33
+# %% ../nbs/02_plot.ipynb 34
 def plot_cluster(df: pd.DataFrame, # a dataframe of values that is waited for dimensionality reduction
                  method: str='pca', # dimensionality reduction method, choose from pca, umap, and tsne
                  hue: str=None, # colname of color
@@ -269,7 +269,7 @@ def plot_cluster(df: pd.DataFrame, # a dataframe of values that is waited for di
         texts = [plt.text(embedding_df[x_col][i], embedding_df[y_col][i], name_list[i],fontsize=8) for i in range(len(embedding_df))]
         adjust_text(texts, arrowprops=dict(arrowstyle='-', color='black'))
 
-# %% ../nbs/02_plot.ipynb 37
+# %% ../nbs/02_plot.ipynb 38
 def plot_bokeh(X:pd.DataFrame, # a dataframe of two columns from dimensionality reduction
                idx, # pd.Series or list that indicates identities for searching box
                hue:None, # pd.Series or list that indicates category for each sample
@@ -367,7 +367,7 @@ def plot_bokeh(X:pd.DataFrame, # a dataframe of two columns from dimensionality
     layout = column(autocomplete, p)
     show(layout)
 
-# %% ../nbs/02_plot.ipynb 40
+# %% ../nbs/02_plot.ipynb 41
 def plot_count(cnt, # from df['x'].value_counts()
                tick_spacing: float= None, # tick spacing for x axis
                palette: str='tab20'):
@@ -383,7 +383,7 @@ def plot_count(cnt, # from df['x'].value_counts()
     if tick_spacing is not None:
         ax.xaxis.set_major_locator(MultipleLocator(tick_spacing))
 
-# %% ../nbs/02_plot.ipynb 42
+# %% ../nbs/02_plot.ipynb 43
 @fc.delegates(sns.barplot)
 def plot_bar(df, 
              value, # colname of value
@@ -438,7 +438,7 @@ def plot_bar(df,
     
     plt.gca().spines[['right', 'top']].set_visible(False)
 
-# %% ../nbs/02_plot.ipynb 45
+# %% ../nbs/02_plot.ipynb 46
 @fc.delegates(sns.barplot)
 def plot_group_bar(df, 
                    value_cols,  # list of column names for values, the order depends on the first item
@@ -481,7 +481,7 @@ def plot_group_bar(df,
     plt.gca().spines[['right', 'top']].set_visible(False)
     plt.legend(fontsize=fontsize) # if change legend location, use loc='upper right'
 
-# %% ../nbs/02_plot.ipynb 48
+# %% ../nbs/02_plot.ipynb 49
 @fc.delegates(sns.boxplot)
 def plot_box(df,
              value, # colname of value
@@ -523,7 +523,7 @@ def plot_box(df,
     # plt.gca().spines[['right', 'top']].set_visible(False)
     
 
-# %% ../nbs/02_plot.ipynb 51
+# %% ../nbs/02_plot.ipynb 52
 @fc.delegates(sns.regplot)
 def plot_corr(x, # x axis values, or colname of x axis
               y, # y axis values, or colname of y axis
@@ -560,7 +560,7 @@ def plot_corr(x, # x axis values, or colname of x axis
             transform=plt.gca().transAxes, 
              ha='center', va='center')
 
-# %% ../nbs/02_plot.ipynb 55
+# %% ../nbs/02_plot.ipynb 56
 def draw_corr(corr):
     
     "plot heatmap from df.corr()"
@@ -572,7 +572,7 @@ def draw_corr(corr):
     plt.figure(figsize=(20, 16))  # Set the figure size
     sns.heatmap(corr, annot=True, cmap='coolwarm', vmin=-1, vmax=1, mask=mask, fmt='.2f')
 
-# %% ../nbs/02_plot.ipynb 59
+# %% ../nbs/02_plot.ipynb 60
 def get_AUCDF(df,col, reverse=False,plot=True,xlabel='Rank of reported kinase'):
     
     "Plot CDF curve and get relative area under the curve"
@@ -637,7 +637,7 @@ def get_AUCDF(df,col, reverse=False,plot=True,xlabel='Rank of reported kinase'):
         
     return AUCDF
 
-# %% ../nbs/02_plot.ipynb 62
+# %% ../nbs/02_plot.ipynb 63
 def plot_confusion_matrix(target, # pd.Series 
                           pred, # pd.Series
                           class_names:list=['0','1'],

{python-katlas-0.0.9 → python-katlas-0.1.1}/katlas/train.py

@@ -5,7 +5,7 @@
 # %% auto 0
 __all__ = ['get_splits', 'split_data', 'score_each', 'train_ml', 'train_ml_cv', 'predict_ml']
 
-# %% ../nbs/03_ML.ipynb 4
+# %% ../nbs/03_ML.ipynb 5
 # katlas
 from .core import Data
 from .feature import *
@@ -29,7 +29,7 @@ from sklearn.ensemble import *
 from sklearn import set_config
 set_config(transform_output="pandas")
 
-# %% ../nbs/03_ML.ipynb 7
+# %% ../nbs/03_ML.ipynb 8
 def get_splits(df: pd.DataFrame, # df contains info for split
                stratified: str=None, # colname to make stratified kfold; sampling from different groups
                group: str=None, # colname to make group kfold; test and train are from different groups
@@ -79,7 +79,7 @@ def get_splits(df: pd.DataFrame, # df contains info for split
     
     return splits
 
-# %% ../nbs/03_ML.ipynb 12
+# %% ../nbs/03_ML.ipynb 13
 def split_data(df: pd.DataFrame, # dataframe of values
                feat_col: list, # feature columns
                target_col: list, # target columns
@@ -95,7 +95,7 @@ def split_data(df: pd.DataFrame, # dataframe of values
     
     return X_train, y_train, X_test, y_test
 
-# %% ../nbs/03_ML.ipynb 16
+# %% ../nbs/03_ML.ipynb 17
 def score_each(target: pd.DataFrame, # target dataframe
               pred: pd.DataFrame, # predicted dataframe
               absolute = True, # if absolute, take average with absolute values for pearson/spearman
@@ -134,7 +134,7 @@ def score_each(target: pd.DataFrame, # target dataframe
     
     return mse,pearson_mean, metrics_df
 
-# %% ../nbs/03_ML.ipynb 21
+# %% ../nbs/03_ML.ipynb 22
 def train_ml(df, # dataframe of values
              feat_col, # feature columns
              target_col, # target columns
@@ -169,7 +169,7 @@ def train_ml(df, # dataframe of values
     
     return y_test, y_pred
 
-# %% ../nbs/03_ML.ipynb 24
+# %% ../nbs/03_ML.ipynb 25
 def train_ml_cv( df, # dataframe of values
                  feat_col, # feature columns
                  target_col,  # target columns
@@ -213,7 +213,7 @@ def train_ml_cv( df, # dataframe of values
     
     return oof, metrics
 
-# %% ../nbs/03_ML.ipynb 31
+# %% ../nbs/03_ML.ipynb 32
 def predict_ml(df, # Dataframe that contains features
                feat_col, # feature columns
                target_col=None,

{python-katlas-0.0.9 → python-katlas-0.1.1/python_katlas.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: python-katlas
-Version: 0.0.9
+Version: 0.1.1
 Summary: tools for predicting kinome specificities
 Home-page: https://github.com/sky1ove/python-katlas
 Author: lily
@@ -60,6 +60,13 @@ helpful to your research.
   phosphoproteome](https://www.nature.com/articles/s41587-019-0344-3),
   and [CPTAC](https://pdc.cancer.gov/pdc/cptac-pancancer) /
   [LinkedOmics](https://academic.oup.com/nar/article/46/D1/D956/4607804)
+  
+  
+## Web applications
+
+Users can now run the analysis directly on the web without needing to code. 
+
+Check out our latest web: [kinase-atlas.com](https://kinase-atlas.com/)
 
 ## Tutorials on Colab
 
@@ -67,20 +74,16 @@ helpful to your research.
       sequence](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_01_sinlge_input.ipynb)
 - 2.  [High throughput substrate scoring on phosphoproteomics
       dataset](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_02_high_throughput.ipynb)
-- 3.  [Query a protein’s phosphorylation sites and predict their
-      upstream
-      kinases](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_03_query_gene.ipynb)
-- 4.  [Kinase enrichment analysis for AKT
-      inhibitor](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_04a_enrichment_AKTi.ipynb)
-      / [Kinase enrichment analysis for EGFR
-      inhibitor](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_04b_enrichment_EGFRi.ipynb)
+- 3.  [Kinase enrichment analysis for AKT
+      inhibitor](https://colab.research.google.com/github/sky1ove/katlas/blob/main/nbs/tutorial_03a_enrichment_AKTi.ipynb)
+
 
 ## Install
 
-Install the latest version through git
+Install the latest version through pip
 
 ``` python
-!pip install git+https://github.com/sky1ove/katlas.git -Uqq
+pip install python-katlas -Uq
 ```
 
 ## Import

{python-katlas-0.0.9 → python-katlas-0.1.1}/settings.ini

@@ -5,7 +5,7 @@
 ### Python library ###
 repo = python-katlas
 lib_name = %(repo)s
-version = 0.0.9
+version = 0.1.1
 min_python = 3.7
 license = apache2
 black_formatting = False

python-katlas-0.0.9/katlas/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.0.8"