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

# # Intersect bed on features

# Based on notebook 04 - but separating out to see if there is difference between hypo and hyper methylated.

# <img src="http://eagle.fish.washington.edu/cnidarian/skitch/half-shell___Lab_notebook_of_Steven_Roberts_1ACECD10.png" alt="half-shell___Lab_notebook_of_Steven_Roberts_1ACECD10.png"/>

# In[2]:


get_ipython().system('date')


# In[20]:


get_ipython().run_line_magic('pylab', 'inline')
import scipy.stats as stats


# Feature (from nb -03)    
# 
# **tldr** 4 "new" tracks
# <img src="http://eagle.fish.washington.edu/cnidarian/skitch/IGV_and_Directory_Listing_of__halfshell_2015-02-hs-bedgraph__1AA51F1B.png" width =100% alt="IGV_and_Directory_Listing_of__halfshell_2015-02-hs-bedgraph__1AA51F1B.png"/>
# ```
# /Users/sr320/data-genomic/tentacle/Cuffdiff_geneexp.sig.gtf
# /Users/sr320/data-genomic/tentacle/rebuilt.gtf
# /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-housekeeping.gff
# /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-env-response.gff
# ```

# # DEGs

# `-wb	Write the original entry in B for each overlap. Useful for knowing what A overlaps. Restricted by -f and -r.`

# tldr
# 
# <img src="http://eagle.fish.washington.edu/cnidarian/skitch/Screenshot_4_3_15__7_22_AM_1ACED994.png" alt="Screenshot_4_3_15__7_22_AM_1ACED994.png"/>

# ## Separating HYPO and HYPER

# In[1]:


get_ipython().system('head ./data/2014.07.02.colson/genomeBrowserTracks/logFC_HS-preHS/2014.07.02.2M_sig.bedGraph')


# In[1]:


get_ipython().system('fgrep -c "-" ./data/2014.07.02.colson/genomeBrowserTracks/logFC_HS-preHS/2014.07.02.2M_sig.bedGraph')



# In[3]:


get_ipython().system('fgrep "-" ./data/2014.07.02.colson/genomeBrowserTracks/logFC_HS-preHS/2014.07.02.2M_sig.bedGraph | head')


# In[4]:


get_ipython().system('fgrep "-"  ./data/2014.07.02.colson/genomeBrowserTracks/logFC_HS-preHS/2014.07.02.2M_sig.bedGraph  > /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hypo.bedGraph')
get_ipython().system('head /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hypo.bedGraph')


# In[6]:


get_ipython().system('fgrep "-"  ./data/2014.07.02.colson/genomeBrowserTracks/logFC_HS-preHS/2014.07.02.4M_sig.bedGraph  > /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hypo.bedGraph')
get_ipython().system('head /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hypo.bedGraph')


# In[7]:


get_ipython().system('fgrep "-"  ./data/2014.07.02.colson/genomeBrowserTracks/logFC_HS-preHS/2014.07.02.6M_sig.bedGraph  > /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hypo.bedGraph')
get_ipython().system('head /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hypo.bedGraph')


# In[ ]:





# In[ ]:





# In[ ]:





# ### HYPO

# In[5]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hypo.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cuffdiff_geneexp.sig.gtf  | cut -f 6  | sort | uniq -c')


# In[9]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hypo.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cuffdiff_geneexp.sig.gtf  | cut -f 6  | sort | uniq -c')


# In[10]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hypo.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cuffdiff_geneexp.sig.gtf  | cut -f 6  | sort | uniq -c')


# In[10]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/git-repos/paper-Temp-stress/ipynb/data/array-design/OID40453_probe_locations.gff  -b /Users/sr320/data-genomic/tentacle/Cuffdiff_geneexp.sig.gtf  | cut -f 11  | sort | uniq -c')


# In[21]:


# Enter the data comparing Oyster 2 then Probes
obs = array([[726, 7224], [117460, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# In[22]:


# Enter the data comparing Oyster 4 then Probes
obs = array([[426, 6560], [117460, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# In[23]:


# Enter the data comparing Oyster 6 then Probes
obs = array([[372, 7645], [117460, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# ## HYPER

# In[13]:


get_ipython().system('fgrep -v "-"  ./data/2014.07.02.colson/genomeBrowserTracks/logFC_HS-preHS/2014.07.02.2M_sig.bedGraph  > /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hyper.bedGraph')
get_ipython().system('head /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hyper.bedGraph')
get_ipython().system('wc -l /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hyper.bedGraph')


# In[12]:


get_ipython().system('fgrep -v "-"  ./data/2014.07.02.colson/genomeBrowserTracks/logFC_HS-preHS/2014.07.02.4M_sig.bedGraph  > /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hyper.bedGraph')
get_ipython().system('head /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hyper.bedGraph')
get_ipython().system('wc -l /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hyper.bedGraph')


# In[14]:


get_ipython().system('fgrep -v "-"  ./data/2014.07.02.colson/genomeBrowserTracks/logFC_HS-preHS/2014.07.02.6M_sig.bedGraph  > /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hyper.bedGraph')
get_ipython().system('head /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hyper.bedGraph')
get_ipython().system('wc -l /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hyper.bedGraph')


# In[15]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hyper.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cuffdiff_geneexp.sig.gtf  | cut -f 6  | sort | uniq -c')


# In[16]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hyper.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cuffdiff_geneexp.sig.gtf  | cut -f 6  | sort | uniq -c')


# In[17]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hyper.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cuffdiff_geneexp.sig.gtf  | cut -f 6  | sort | uniq -c')


# In[18]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/git-repos/paper-Temp-stress/ipynb/data/array-design/OID40453_probe_locations.gff  -b /Users/sr320/data-genomic/tentacle/Cuffdiff_geneexp.sig.gtf  | cut -f 11  | sort | uniq -c')


# In[24]:


# Enter the data comparing Oyster 2 then Probes
obs = array([[154, 2803], [117460, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# In[25]:


# Enter the data comparing Oyster 2 then Probes
obs = array([[278, 3587], [117460, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# In[26]:


# Enter the data comparing Oyster 2 then Probes
obs = array([[260, 4044], [117460, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# In[ ]:





# In[ ]:





# In[ ]:





# # Rebuilt (new gtf based on RNAseq data)

# In[15]:


get_ipython().system('intersectbed  -wb  -a ./data/2014.07.02.colson/genomeBrowserTracks/logFC_HS-preHS/2014.07.02.2M_sig.bedGraph  -b /Users/sr320/data-genomic/tentacle/rebuilt.gtf  | cut -f 6  | sort | uniq -c')


# In[16]:


get_ipython().system('intersectbed  -wb  -a ./data/2014.07.02.colson/genomeBrowserTracks/logFC_HS-preHS/2014.07.02.4M_sig.bedGraph  -b /Users/sr320/data-genomic/tentacle/rebuilt.gtf  | cut -f 6  | sort | uniq -c')


# In[17]:


get_ipython().system('intersectbed  -wb  -a ./data/2014.07.02.colson/genomeBrowserTracks/logFC_HS-preHS/2014.07.02.6M_sig.bedGraph  -b /Users/sr320/data-genomic/tentacle/rebuilt.gtf  | cut -f 6  | sort | uniq -c')


# In[18]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/git-repos/paper-Temp-stress/ipynb/data/array-design/OID40453_probe_locations.gff  -b /Users/sr320/data-genomic/tentacle/rebuilt.gtf  | cut -f 11  | sort | uniq -c')


# In[39]:


# Enter the data comparing Oyster 2 then Probes
obs = array([[8768, 10028], [1197818, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# In[40]:


# Enter the data comparing Oyster 4 then Probes
obs = array([[7694, 10148], [1197818, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# In[41]:


# Enter the data comparing Oyster 6 then Probes
obs = array([[6160, 11690], [1197818, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# # Housekeeping Genes

# Separating out hypo and hyper

# <img src="http://eagle.fish.washington.edu/cnidarian/skitch/Screenshot_4_3_15__7_23_AM_1ACED9DD.png" alt="Screenshot_4_3_15__7_23_AM_1ACED9DD.png"/>

# In[29]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hypo.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-housekeeping.gff  | cut -f 6  | sort | uniq -c')
get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hyper.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-housekeeping.gff  | cut -f 6  | sort | uniq -c')


# In[30]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hypo.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-housekeeping.gff  | cut -f 6  | sort | uniq -c')
get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hyper.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-housekeeping.gff  | cut -f 6  | sort | uniq -c')


# In[31]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hypo.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-housekeeping.gff  | cut -f 6  | sort | uniq -c')
get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hyper.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-housekeeping.gff  | cut -f 6  | sort | uniq -c')


# In[26]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/git-repos/paper-Temp-stress/ipynb/data/array-design/OID40453_probe_locations.gff  -b /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-housekeeping.gff  | cut -f 11  | sort | uniq -c')


# In[42]:


# Enter the data comparing Oyster 2 then Probes
obs = array([[3210, 10028], [251970, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# In[43]:


# Enter the data comparing Oyster 4 then Probes
obs = array([[3369, 10148], [251970, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# In[47]:


# Enter the data comparing Oyster 6 then Probes
obs = array([[3819, 11690], [251970, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# In[ ]:





# In[ ]:





# # Environmental Response Genes

# separating Hypo and Hyper

# tldr
# <img src="http://eagle.fish.washington.edu/cnidarian/skitch/Screenshot_4_3_15__7_28_AM_1ACEDB27.png" alt="Screenshot_4_3_15__7_28_AM_1ACEDB27.png"/>

# In[ ]:





# In[33]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hypo.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-env-response.gff  | cut -f 6  | sort | uniq -c')
get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hyper.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-env-response.gff  | cut -f 6  | sort | uniq -c')


# In[34]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hypo.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-env-response.gff  | cut -f 6  | sort | uniq -c')
get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hyper.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-env-response.gff  | cut -f 6  | sort | uniq -c')


# In[35]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hypo.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-env-response.gff  | cut -f 6  | sort | uniq -c')
get_ipython().system('intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hyper.bedGraph  -b /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-env-response.gff  | cut -f 6  | sort | uniq -c')


# In[27]:


get_ipython().system('intersectbed  -wb  -a /Users/sr320/git-repos/paper-Temp-stress/ipynb/data/array-design/OID40453_probe_locations.gff  -b /Users/sr320/data-genomic/tentacle/Cgigas_v9_gene-env-response.gff  | cut -f 11  | sort | uniq -c')


# In[45]:


# Enter the data comparing Oyster 2 then Probes
obs = array([[2809, 10028], [190475, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# In[48]:


# Enter the data comparing Oyster 4 then Probes
obs = array([[2738, 10148], [190475, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# In[49]:


# Enter the data comparing Oyster 6 then Probes
obs = array([[3216, 11690], [190475, 697753]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# # TE-Blast

# <img src="http://eagle.fish.washington.edu/cnidarian/skitch/Screenshot_4_3_15__7_42_AM_1ACEDE69.png" alt="Screenshot_4_3_15__7_42_AM_1ACEDE69.png"/>

# In[37]:


get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hypo.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_v9_tracks/Cgigas_v9_TE-WUBLASTX.gff  | cut -f 6  | sort | uniq -c | sed '/#/d'")
get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hyper.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_v9_tracks/Cgigas_v9_TE-WUBLASTX.gff  | cut -f 6  | sort | uniq -c | sed '/#/d'")


# In[38]:


get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hypo.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_v9_tracks/Cgigas_v9_TE-WUBLASTX.gff  | cut -f 6  | sort | uniq -c | sed '/#/d'")
get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hyper.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_v9_tracks/Cgigas_v9_TE-WUBLASTX.gff  | cut -f 6  | sort | uniq -c | sed '/#/d'")


# In[39]:


get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hypo.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_v9_tracks/Cgigas_v9_TE-WUBLASTX.gff  | cut -f 6  | sort | uniq -c | sed '/#/d'")
get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hyper.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_v9_tracks/Cgigas_v9_TE-WUBLASTX.gff  | cut -f 6  | sort | uniq -c | sed '/#/d'")


# # Promoter

# <img src="http://eagle.fish.washington.edu/cnidarian/skitch/Screenshot_4_3_15__7_48_AM_1ACEDFD9.png" alt="Screenshot_4_3_15__7_48_AM_1ACEDFD9.png"/>

# In[40]:


get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hypo.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_v9_tracks/Cgigas_v9_1k5p_gene_promoter.gff  | cut -f 6,7  | sort | uniq -c | sed '/#/d'")
get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hyper.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_v9_tracks/Cgigas_v9_1k5p_gene_promoter.gff  | cut -f 6,7  | sort | uniq -c | sed '/#/d'")


# In[41]:


get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hypo.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_v9_tracks/Cgigas_v9_1k5p_gene_promoter.gff  | cut -f 6,7  | sort | uniq -c | sed '/#/d'")
get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hyper.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_v9_tracks/Cgigas_v9_1k5p_gene_promoter.gff  | cut -f 6,7  | sort | uniq -c | sed '/#/d'")


# !intersectbed \
# -wb \
# -a /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hypo.bedGraph \
# -b /Volumes/web-1/trilobite/Crassostrea_gigas_v9_tracks/Cgigas_v9_1k5p_gene_promoter.gff \
# | cut -f 6,7 \
# | sort | uniq -c | sed '/#/d'
# !intersectbed \
# -wb \
# -a /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hyper.bedGraph \
# -b /Volumes/web-1/trilobite/Crassostrea_gigas_v9_tracks/Cgigas_v9_1k5p_gene_promoter.gff \
# | cut -f 6,7 \
# | sort | uniq -c | sed '/#/d'

# # Chi2 test to compare hypo v hyper?

# In[43]:


# Enter the data comparing Oyster ALL hypo versus hyper -HOUSEKEEPING
obs = array([[6527, 21429], [3871, 10434]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# In[44]:


# Enter the data comparing Oyster ALL hypo versus hyper -DEGS
obs = array([[1524, 21429], [692, 10434]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# In[45]:


# Enter the data comparing Oyster ALL hypo versus hyper -TE blast
obs = array([[760, 21429], [45, 10434]])

# Calculate the chi-square test
chi2_corrected = stats.chi2_contingency(obs, correction=True)
chi2_uncorrected = stats.chi2_contingency(obs, correction=False)

# Print the result
print('CHI SQUARE')
print('The corrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_corrected[0], chi2_corrected[1]))
print('The uncorrected chi2 value is {0:5.3f}, with p={1:5.3f}'.format(chi2_uncorrected[0], chi2_uncorrected[1]))


# <img src="http://eagle.fish.washington.edu/cnidarian/skitch/Screenshot_4_3_15__8_07_AM_1ACEE442.png" alt="Screenshot_4_3_15__8_07_AM_1ACEE442.png"/>

# # Hypo v Hyper on Ensembl gff - gives data on gene body, and repeats

# In[48]:


get_ipython().system('echo "hypo"')
get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hypo.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_ensembl_tracks/Crassostrea_gigas.GCA_000297895.1.25.sorted.gff3  | cut -f 6,7  | sort | uniq -c | sed '/#/d'")
get_ipython().system('echo "hyper"')
get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.2M_sig.hyper.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_ensembl_tracks/Crassostrea_gigas.GCA_000297895.1.25.sorted.gff3  | cut -f 6,7  | sort | uniq -c | sed '/#/d'")


# In[50]:


get_ipython().system('echo "hypo"')
get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hypo.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_ensembl_tracks/Crassostrea_gigas.GCA_000297895.1.25.sorted.gff3  | cut -f 6,7  | sort | uniq -c | sed '/#/d'")
get_ipython().system('echo "hyper"')
get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.4M_sig.hyper.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_ensembl_tracks/Crassostrea_gigas.GCA_000297895.1.25.sorted.gff3  | cut -f 6,7  | sort | uniq -c | sed '/#/d'")


# In[49]:


get_ipython().system('echo "hypo"')
get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hypo.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_ensembl_tracks/Crassostrea_gigas.GCA_000297895.1.25.sorted.gff3  | cut -f 6,7  | sort | uniq -c | sed '/#/d'")
get_ipython().system('echo "hyper"')
get_ipython().system("intersectbed  -wb  -a /Users/sr320/data-genomic/tentacle/2014.07.02.6M_sig.hyper.bedGraph  -b /Volumes/web-1/trilobite/Crassostrea_gigas_ensembl_tracks/Crassostrea_gigas.GCA_000297895.1.25.sorted.gff3  | cut -f 6,7  | sort | uniq -c | sed '/#/d'")


# In[51]:


get_ipython().system("intersectbed  -wb  -a /Users/sr320/git-repos/paper-Temp-stress/ipynb/data/array-design/OID40453_probe_locations.gff  -b /Volumes/web-1/trilobite/Crassostrea_gigas_ensembl_tracks/Crassostrea_gigas.GCA_000297895.1.25.sorted.gff3  | cut -f 11,12  | sort | uniq -c | sed '/#/d'")


# In[ ]: