#!/usr/bin/env python
# coding: utf-8

# # Overview of CyTOF Data
# The original data was given as two tab-separated matrices
# * ``Plasma.txt`` (original name: 160202_CGI002_Plasma_Plasma_singlets.fcs_raw_events.txt)
# * ``PMA.txt`` (original name: 160202_CGI002_PMA_PMA_singlets.fcs_raw_events.txt)
# 
# These files had individual cell measurements as rows and dimensions (e.g. antibodies) as columns. I only kept the dimensions of interest surface marker and phospho marker antibody columns/dimensions and renamed these files ``Plasma_clean.txt`` and ``PMA_clean.txt``.
# 

# In[1]:


import pandas as pd
import numpy as np

from clustergrammer_widget import *
net = Network()


# In[2]:


net.load_file('../cytof_data/Plasma_CT.txt')
df_plasma = net.export_df()


# In[3]:


net.load_df(df_plasma)
df_plasma.shape


# In[4]:


net.normalize(axis='col', norm_type='zscore', keep_orig=False)


# In[5]:


net.downsample(ds_type='kmeans', axis='row', num_samples=1000)
net.dat['mat'].shape


# In[6]:


# clip z-scores since we do not are about extreme outliers
net.clip(-10,10)


# In[7]:


net.make_clust(views=[])
clustergrammer_widget(network=net.widget())


# # PMA

# In[12]:


net.load_file('../cytof_data/PMA_CT.txt')
df_pma = net.export_df()


# In[13]:


net.load_df(df_pma)
df_pma.shape


# In[14]:


net.normalize(axis='col', norm_type='zscore', keep_orig=False)
net.downsample(ds_type='kmeans', axis='row', num_samples=1000)
net.dat['mat'].shape
net.clip(-10,10)


# In[15]:


net.make_clust(views=[])
clustergrammer_widget(network=net.widget())


# # Merge Plasma and PMA

# In[12]:


df_plasma.shape    


# In[13]:


df_pma.shape


# In[14]:


df_merge = pd.concat([df_plasma, df_pma])


# In[15]:


df_merge.shape


# In[16]:


net.load_df(df_merge)


# In[17]:


net.normalize(axis='col', norm_type='zscore', keep_orig=False)
net.downsample(ds_type='kmeans', axis='row', num_samples=1000)
net.clip(-10,10)
net.dat['mat'].shape


# In[18]:


net.make_clust(views=[])
clustergrammer_widget(network=net.widget())


# ## Merged Results
# 
# The above heatmap mixes both surface markers and phosphorylation markers. We can see that PMA treated cells have higher levels of phospohrylation of 
# * pCREB
# * PMAPKAP2
# * pERK12
# * pp38
# 
# and higher levels of the CD14 surface marker.
# 
# We want to also see how our cells cluster based on phosphorylation markers only and surface markers only.

# In[ ]: