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

# # Simple query to OcéanIA Platform TARA_R110002003
# ## This example shows how to extract arbitrary biological sub-sequences from a FASTA file available in the OcéanIA Platform

# ### 1. Install oceania-query-fasta package

# In[ ]:


get_ipython().run_line_magic('pip', 'install oceania-query-fasta')


# ### 2. Prepare request params

# In[ ]:


TARA_SAMPLE_ID = "TARA_R110002003"

# REQUEST_PARAMS is a list of tuples that identify subsequences to extract
# each tuple must have the values (sequence_id, start_index, stop_index, sequence_type)
# sequence type accepted values are [raw, complement, reverse_complement], optional value if ommited defaults to "raw".
REQUEST_PARAMS = [
            ("TARA_R110002003_G_scaffold3_1",3290,6293),
            ("TARA_R110002003_G_scaffold3_3",0,327),
            ("TARA_R110002003_G_scaffold3_3",944,2742),
            ("TARA_R110002003_G_scaffold3_4",379,379),
            ("TARA_R110002003_G_scaffold3_4",1530,1669)
        ]


# ### 3. Perform call to the OcéanIA services

# In[ ]:


from oceania import get_sequences_from_fasta

request_result = get_sequences_from_fasta(
    TARA_SAMPLE_ID,
    REQUEST_PARAMS
)

# get_sequences_from_fasta returns a pandas.DataFrame with the extracted sequences
print(request_result)