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

# In[1]:


from chembl_webresource_client.unichem import unichem_client as unichem


# ## Get src_compound_ids from src_compound_id

# Obtain a list of all `src_compound_ids` from all sources which are **CURRENTLY** assigned to the same structure as a currently assigned query `src_compound_id`. The output will include query `src_compound_id` if it is a valid `src_compound_id` with a current assignment.

# In[2]:


ret = unichem.get('CHEMBL12',1)


# In[3]:


len(ret)


# In[4]:


ret


# Note also, that by adding an additional (optional) argument (a valid `src_id`), then results will be restricted to only the source specified with this optional argument.

# In[5]:


ret = unichem.get('CHEMBL12',1,2)


# In[6]:


len(ret)


# In[7]:


ret


# ## Get all src_compound_ids from src_compound_id 

# Obtain a list of *all* `src_compound_ids` from all sources (including **BOTH** current **AND** obsolete assignments) to the same structure as a currently assigned query `src_compound_id`. The output will include query `src_compound_id` if it is a valid `src_compound_id` with a current assignment.

# In[8]:


ret = unichem.get('CHEMBL12', 1, all=True)


# In[9]:


len(ret)


# In[10]:


ret


# Note also, that by adding an additional (optional) argument (a valid `src_id`), then results will be restricted to only the source specified with this optional argument.

# In[11]:


ret = unichem.get('CHEMBL12', 1, 2, all=True)


# In[12]:


len(ret)


# In[13]:


ret


# ## Get mapping

# Obtain a full mapping between two sources. Uses only currently assigned `src_compound_ids` from both sources. 

# In[14]:


ret = unichem.map(4,1)


# In[15]:


len(ret)


# In[16]:


ret[0]


# ## Get src_compound_ids from InChI Key

# Obtain a list of all `src_compound_ids` (from all sources) which are **CURRENTLY** assigned to a query InChIKey

# In[17]:


ret = unichem.get('AAOVKJBEBIDNHE-UHFFFAOYSA-N')


# In[18]:


len(ret)


# In[19]:


ret


# ## Get src_compound_ids all from InChIKey 

# Obtain a list of *all* `src_compound_ids` (from all sources) which have current **AND** obsolete assignments to a query InChIKey

# In[20]:


ret = unichem.get('AAOVKJBEBIDNHE-UHFFFAOYSA-N', all=True)


# In[21]:


len(ret)


# In[22]:


ret


# ## Get all src_ids 

# Obtain all `src_ids` currently in UniChem

# In[23]:


ret = unichem.src()


# In[24]:


len(ret)


# In[25]:


ret


# ## Get source infomation 

# Obtain *all* information on a source by querying with a source id (`src_id`).

# In[26]:


ret = unichem.src(1)


# In[27]:


len(ret)


# In[28]:


ret


# ## Get structure

# Obtain structure(s) **CURRENTLY** assigned to a query `src_compound_id`.

# In[29]:


ret = unichem.structure('CHEMBL12',1)


# In[30]:


len(ret)


# In[31]:


ret


# ## Get all structures 

# Obtain structure(s) with current **AND** obsolete assignments to a query `src_compound_id`.

# In[32]:


ret = unichem.structure('CHEMBL12',1, all=True)


# In[33]:


len(ret)


# In[34]:


ret


# ## Get URL for src_compound_ids from src_compound_id 

# Obtain a list of URLs for all `src_compound_ids`, from a specified source (the `to_src_id`), which are **CURRENTLY** assigned to the same structure as a currently assigned query `src_compound_id`. Method only applicable for sources which support direct URLs to `src_compound_id` pages.
# 

# In[35]:


ret = unichem.get('CHEMBL12',1, 2, url=True)


# In[36]:


len(ret)


# In[37]:


ret


# Method also applicable for `to_src_id`'s where the hyperlink is constructed from auxiliary data [and not from the `src_compound_id`] as per example below.

# In[38]:


ret = unichem.get('CHEMBL490',1, 15, url=True)


# In[39]:


len(ret)


# In[40]:


ret


# ## Get src_compound_ids all from obsolete src_compound_id 

# Obtain a list of all `src_compound_ids` from all sources with **BOTH** current **AND** obsolete to the same structure with an obsolete assignment to the query `src_compound_id`. The output will include query `src_compound_id` if it is a valid `src_compound_id` with an obsolete assignment.
# 

# ret = unichem.get('DB07699',2)

# In[41]:


len(ret)


# In[42]:


ret


# Note also, that by adding an additional (optional) argument (a valid `src_id`), then results will be restricted to only the source specified with this optional argument.

# In[43]:


ret = unichem.get('DB07699',2,1)


# In[44]:


len(ret)


# In[45]:


ret


# ## Get verbose src_compound_ids from InChIKey

# Obtain all `src_compound_ids` (from all sources) which are **CURRENTLY** assigned to a query InChIKey. However, these are returned as part of the following data structure: A list of sources containing these `src_compound_ids`, including source description, base_id_url, etc. One element in this list is a list of the `src_compound_ids` currently assigned to the query InChIKey.

# In[46]:


ret = unichem.get('AAOVKJBEBIDNHE-UHFFFAOYSA-N', verbose=True)


# In[47]:


len(ret)


# In[48]:


ret


# ## Get auxiliary mappings 

# For a single source, obtain a mapping between all current `src_compound_ids` to their corresponding auxiliary data. See [FAQ](https://www.ebi.ac.uk/unichem/info/faq#faq13) for an explanation of *auxiliary data*.

# In[49]:


ret = unichem.map(20)


# In[50]:


len(ret)


# In[51]:


ret[0]


# ## Get Connectivity data from InChIKey

# For the explanation of `a`-`h` arguments, please refer to the [documentation](https://www.ebi.ac.uk/unichem/info/widesearchInfo).

# In[52]:


ret = unichem.connectivity('QJVHTELASVOWBE-YBABNSIOSA-N', c=4, h=1)


# In[53]:


len(ret['1'])


# In[54]:


ret['1'][1]


# In[55]:


ret = unichem.connectivity('QJVHTELASVOWBE-YBABNSIOSA-N',a=1,c=3)


# In[56]:


len(ret['1'])


# In[57]:


len(ret['1'][0]['src_matches'])


# In[58]:


ret['1'][0]['src_matches'][3]


# In[59]:


ret = unichem.connectivity('QJVHTELASVOWBE',a=1,c=3)


# In[60]:


len(ret['1'])


# In[61]:


len(ret['1'][0]['src_matches'])


# In[62]:


ret['1'][0]['src_matches'][5]


# ## Get Connectivity data from src_compound_id 

# For the explanation of `a`-`h` arguments, please refer to the [documentation](https://www.ebi.ac.uk/unichem/info/widesearchInfo).

# In[63]:


ret = unichem.connectivity('CHEMBL121',1,c=4,h=1)


# In[64]:


len(ret['1'])


# In[65]:


ret['1'][1]


# In[66]:


ret = unichem.connectivity('CHEMBL121',1)


# In[67]:


len(ret['1'])


# In[68]:


len(ret['1'][0]['src_matches'])


# In[69]:


ret['1'][0]['src_matches']


# ## Get InChI from InChIKey 

# Obtain InChI for InChIKey

# In[70]:


ret = unichem.inchiFromKey('AAOVKJBEBIDNHE-UHFFFAOYSA-N')


# In[71]:


ret