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

# # sourmash: working with private collections of signatures
# 
# ### Running this notebook.
# 
# You can run this notebook interactively via mybinder; click on this button:
# [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/dib-lab/sourmash/master?filepath=doc%2Fsourmash-collections.ipynb)
# 
# A rendered version of this notebook is available at [sourmash.readthedocs.io](https://sourmash.readthedocs.io) under "Tutorials and notebooks".
# 
# You can also get this notebook from the [doc/ subdirectory of the sourmash github repository](https://github.com/dib-lab/sourmash/tree/master/doc). See [binder/environment.yaml](https://github.com/dib-lab/sourmash/blob/master/binder/environment.yml) for installation dependencies.
# 
# ### What is this?
# 
# This is a Jupyter Notebook using Python 3. If you are running this via [binder](https://mybinder.org), you can use Shift-ENTER to run cells, and double click on code cells to edit them.
# 
# Contact: C. Titus Brown, ctbrown@ucdavis.edu. Please [file issues on GitHub](https://github.com/dib-lab/sourmash/issues/) if you have any questions or comments!

# ## download a bunch of genomes

# In[1]:


get_ipython().system('mkdir -p big_genomes')
get_ipython().system('curl -L https://osf.io/8uxj9/?action=download | (cd big_genomes && tar xzf -)')


# ## compute signatures for each file

# In[2]:


get_ipython().system('cd big_genomes/ && sourmash compute -k 31 --scaled=1000 --name-from-first *.fa')


# ## Compare them all

# In[3]:


get_ipython().system('sourmash compare big_genomes/*.sig -o compare_all.mat')
get_ipython().system('sourmash plot compare_all.mat')


# In[4]:


from IPython.display import Image
Image(filename='compare_all.mat.matrix.png') 


# ## make a fast(er) search database for all of them

# In[5]:


get_ipython().system('sourmash index -k 31 all-genomes big_genomes/*.sig')


# You can now use this to search, and gather.

# In[6]:


get_ipython().system('sourmash search shew_os185.fa.sig all-genomes --threshold=0.001')


# In[7]:


# (make fake metagenome again, just in case)
get_ipython().system('cat genomes/*.fa > fake-metagenome.fa')
get_ipython().system('sourmash compute -k 31 --scaled=1000 fake-metagenome.fa')


# In[8]:


get_ipython().system('sourmash gather fake-metagenome.fa.sig all-genomes')


# # build a database with taxonomic information --
# 
# for this, we need to provide a metadata file that contains accession => tax information.

# In[9]:


import pandas
df = pandas.read_csv('podar-lineage.csv')
df


# In[10]:


get_ipython().system('sourmash lca index podar-lineage.csv taxdb big_genomes/*.sig  -C 3 --split-identifiers')


# This database 'taxdb.lca.json' can be used for search and gather as above:

# In[11]:


get_ipython().system('sourmash gather fake-metagenome.fa.sig taxdb.lca.json')


# ...but can also be used for taxonomic summarization:

# In[12]:


get_ipython().system('sourmash lca summarize --query fake-metagenome.fa.sig --db taxdb.lca.json')


# ## A full list of notebooks
# 
# [An introduction to k-mers for genome comparison and analysis](kmers-and-minhash.ipynb)
# 
# [Some sourmash command line examples!](sourmash-examples.ipynb)
# 
# [Working with private collections of signatures.](sourmash-collections.ipynb)