2.3 Targets for metabolites in the model
============================================

Load a model from the BiGG database
-----------------------------------

.. code:: ipython3

    from cameo import models



.. raw:: html

    





.. raw:: html

    




.. code:: ipython3

    model = models.bigg.iJO1366

Annotate the model with metabolite information
----------------------------------------------

.. code:: ipython3

    from marsi.cobra.utils import annotate_model


.. parsed-literal::

    Looking for local setup.cfg
    Not available [Errno 2] No such file or directory: 'setup.cfg'


.. parsed-literal::

    /Users/joaca/Documents/repositories/marsi/marsi/io/bigg.py:23 FutureWarning: from_csv is deprecated. Please use read_csv(...) instead. Note that some of the default arguments are different, so please refer to the documentation for from_csv when changing your function calls


.. code:: ipython3

    annotate_model(model)



.. raw:: html

    <p>Failed to display Jupyter Widget of type <code>HBox</code>.</p>
    <p>
      If you're reading this message in Jupyter Notebook or JupyterLab, it may mean
      that the widgets JavaScript is still loading. If this message persists, it
      likely means that the widgets JavaScript library is either not installed or
      not enabled. See the <a href="https://ipywidgets.readthedocs.io/en/stable/user_install.html">Jupyter
      Widgets Documentation</a> for setup instructions.
    </p>
    <p>
      If you're reading this message in another notebook frontend (for example, a static
      rendering on GitHub or <a href="https://nbviewer.jupyter.org/">NBViewer</a>),
      it may mean that your frontend doesn't currently support widgets.
    </p>



.. code:: ipython3

    model.metabolites.aacald_c.annotation




.. parsed-literal::

    {'inchi': 'InChI=1S/C2H5NO/c3-1-2-4/h2H,1,3H2'}



.. code:: ipython3

    from cameo.flux_analysis.analysis import find_essential_metabolites

.. code:: ipython3

    essential_metabolites = find_essential_metabolites(model)

.. code:: ipython3

    non_essential_metabolites = [met for met in model.metabolites 
                                 if met not in essential_metabolites and met.id.endswith("_c")]

.. code:: ipython3

    analogues = {}

.. code:: ipython3

    from marsi.chemistry.molecule import Molecule
    from marsi.chemistry.common import dynamic_fingerprint_cut
    from marsi.nearest_neighbors import search_closest_compounds


.. parsed-literal::

    /Users/joaca/Documents/repositories/marsi/marsi/chemistry/rdkit.py:25 DeprecationWarning: The rdkit.Chem.MCS module is deprecated; please use rdkit.Chem.rdFMCS instead.


.. code:: ipython3

    import os
    from pandas import DataFrame

.. code:: ipython3

    for met in non_essential_metabolites:
        if met.id in ["23dhb_c", "3dhguln_c", "3hpp_c"] or met.id.endswith("coa_c"):  # These chemicals are currently
                                                                                      # breaking the software when 
                                                                                      # running in a loop like this.
                                                                          
            continue
        if 'inchi' in met.annotation and met.id not in analogues:
            name = "%s_analogues.csv" % met.id
            if os.path.exists(name):
                analogues[met.id] = DataFrame.from_csv(name, sep="\t")
            else:
                molecule = Molecule.from_inchi(met.annotation['inchi'])
                fp_cut = dynamic_fingerprint_cut(molecule.num_atoms)
                analogues[met.id] = search_closest_compounds(molecule, fp_cut=fp_cut)
                analogues[met.id].to_csv(name, sep='\t')

.. code:: ipython3

    len(analogues), len([m for m in non_essential_metabolites if 'inchi' in m.annotation])




.. parsed-literal::

    (47, 479)



.. code:: ipython3

    from pandas import DataFrame

.. code:: ipython3

    df = DataFrame(columns=["metabolite name", "number of hits", "number of hits (50% similarity)"])

.. code:: ipython3

    for met_id, hits in analogues.items():
        if len(hits) > 0:
            name = model.metabolites.query(met_id)[0].name
            df.loc[met_id] = [name, len(hits), len(hits[hits.structural_score > 0.5])]

.. code:: ipython3

    df




.. raw:: html

    <div>
    <style scoped>
        .dataframe tbody tr th:only-of-type {
            vertical-align: middle;
        }
    
        .dataframe tbody tr th {
            vertical-align: top;
        }
    
        .dataframe thead th {
            text-align: right;
        }
    </style>
    <table border="1" class="dataframe">
      <thead>
        <tr style="text-align: right;">
          <th></th>
          <th>metabolite name</th>
          <th>number of hits</th>
          <th>number of hits (50% similarity)</th>
        </tr>
      </thead>
      <tbody>
        <tr>
          <th>3hpppn_c</th>
          <td>3-(3-hydroxy-phenyl)propionate</td>
          <td>6298</td>
          <td>4129</td>
        </tr>
        <tr>
          <th>23ddhb_c</th>
          <td>2,3-Dihydro-2,3-dihydroxybenzoate</td>
          <td>2296</td>
          <td>1519</td>
        </tr>
        <tr>
          <th>3hddcoa_c</th>
          <td>(S)-3-Hydroxydodecanoyl-CoA</td>
          <td>6</td>
          <td>0</td>
        </tr>
        <tr>
          <th>2dr5p_c</th>
          <td>2-Deoxy-D-ribose 5-phosphate</td>
          <td>226</td>
          <td>155</td>
        </tr>
        <tr>
          <th>35cgmp_c</th>
          <td>3',5'-Cyclic GMP</td>
          <td>1254</td>
          <td>428</td>
        </tr>
        <tr>
          <th>2amsa_c</th>
          <td>2-Aminomalonate semialdehyde</td>
          <td>1785</td>
          <td>449</td>
        </tr>
        <tr>
          <th>13dpg_c</th>
          <td>3-Phospho-D-glyceroyl phosphate</td>
          <td>346</td>
          <td>200</td>
        </tr>
        <tr>
          <th>23dhba_c</th>
          <td>(2,3-Dihydroxybenzoyl)adenylate</td>
          <td>159</td>
          <td>4</td>
        </tr>
        <tr>
          <th>3ohcoa_c</th>
          <td>3-Oxohexanoyl-CoA</td>
          <td>5</td>
          <td>0</td>
        </tr>
        <tr>
          <th>3dhgulnp_c</th>
          <td>3-keto-L-gulonate-6-phosphate</td>
          <td>65</td>
          <td>48</td>
        </tr>
        <tr>
          <th>2dr1p_c</th>
          <td>2-Deoxy-D-ribose 1-phosphate</td>
          <td>1149</td>
          <td>508</td>
        </tr>
        <tr>
          <th>2pg_c</th>
          <td>D-Glycerate 2-phosphate</td>
          <td>1056</td>
          <td>472</td>
        </tr>
        <tr>
          <th>15dap_c</th>
          <td>1,5-Diaminopentane</td>
          <td>3181</td>
          <td>925</td>
        </tr>
        <tr>
          <th>2mcacn_c</th>
          <td>Cis-2-Methylaconitate</td>
          <td>902</td>
          <td>566</td>
        </tr>
        <tr>
          <th>12ppd__R_c</th>
          <td>(R)-Propane-1,2-diol</td>
          <td>244</td>
          <td>193</td>
        </tr>
        <tr>
          <th>2h3oppan_c</th>
          <td>2-Hydroxy-3-oxopropanoate</td>
          <td>964</td>
          <td>361</td>
        </tr>
        <tr>
          <th>2dh3dgal_c</th>
          <td>2-Dehydro-3-deoxy-D-galactonate</td>
          <td>1902</td>
          <td>890</td>
        </tr>
        <tr>
          <th>3hcinnm_c</th>
          <td>3-hydroxycinnamic acid</td>
          <td>6608</td>
          <td>4684</td>
        </tr>
        <tr>
          <th>1ddecg3p_c</th>
          <td>1-dodecanoyl-sn-glycerol 3-phosphate</td>
          <td>1308</td>
          <td>41</td>
        </tr>
        <tr>
          <th>3hhcoa_c</th>
          <td>(S)-3-Hydroxyhexanoyl-CoA</td>
          <td>4</td>
          <td>0</td>
        </tr>
        <tr>
          <th>2mcit_c</th>
          <td>2-Methylcitrate</td>
          <td>1061</td>
          <td>517</td>
        </tr>
        <tr>
          <th>23doguln_c</th>
          <td>2,3-Dioxo-L-gulonate</td>
          <td>1951</td>
          <td>905</td>
        </tr>
        <tr>
          <th>3oddcoa_c</th>
          <td>3-Oxododecanoyl-CoA</td>
          <td>9</td>
          <td>4</td>
        </tr>
        <tr>
          <th>1tdecg3p_c</th>
          <td>1-tetradecanoyl-sn-glycerol 3-phosphate</td>
          <td>918</td>
          <td>26</td>
        </tr>
        <tr>
          <th>3odcoa_c</th>
          <td>3-Oxodecanoyl-CoA</td>
          <td>12</td>
          <td>4</td>
        </tr>
        <tr>
          <th>23dappa_c</th>
          <td>2,3-diaminopropionate</td>
          <td>3025</td>
          <td>851</td>
        </tr>
        <tr>
          <th>12ppd__S_c</th>
          <td>(S)-Propane-1,2-diol</td>
          <td>1207</td>
          <td>575</td>
        </tr>
        <tr>
          <th>2ddg6p_c</th>
          <td>2-Dehydro-3-deoxy-D-gluconate 6-phosphate</td>
          <td>102</td>
          <td>73</td>
        </tr>
        <tr>
          <th>2tpr3dpcoa_c</th>
          <td>2'-(5''-triphosphoribosyl)-3'-dephospho-CoA</td>
          <td>10</td>
          <td>1</td>
        </tr>
        <tr>
          <th>3hadpcoa_c</th>
          <td>(3S)-3-Hydroxyadipyl-CoA</td>
          <td>2</td>
          <td>0</td>
        </tr>
        <tr>
          <th>3ohdcoa_c</th>
          <td>3-Oxohexadecanoyl-CoA</td>
          <td>3</td>
          <td>0</td>
        </tr>
        <tr>
          <th>2aobut_c</th>
          <td>L-2-Amino-3-oxobutanoate</td>
          <td>2856</td>
          <td>818</td>
        </tr>
        <tr>
          <th>2shchc_c</th>
          <td>2-Succinyl-6-hydroxy-2,4-cyclohexadiene-1-carb...</td>
          <td>319</td>
          <td>182</td>
        </tr>
        <tr>
          <th>2dh3dgal6p_c</th>
          <td>2-Dehydro-3-deoxy-D-galactonate 6-phosphate</td>
          <td>102</td>
          <td>73</td>
        </tr>
        <tr>
          <th>2ddglcn_c</th>
          <td>2-Dehydro-3-deoxy-D-gluconate</td>
          <td>1902</td>
          <td>890</td>
        </tr>
        <tr>
          <th>3hocoa_c</th>
          <td>(S)-3-Hydroxyoctanoyl-CoA</td>
          <td>6</td>
          <td>1</td>
        </tr>
        <tr>
          <th>3ohodcoa_c</th>
          <td>3-Oxooctadecanoyl-CoA</td>
          <td>2</td>
          <td>0</td>
        </tr>
        <tr>
          <th>25dkglcn_c</th>
          <td>2,5-diketo-D-gluconate</td>
          <td>1833</td>
          <td>779</td>
        </tr>
        <tr>
          <th>3hdcoa_c</th>
          <td>(S)-3-Hydroxydecanoyl-CoA</td>
          <td>12</td>
          <td>2</td>
        </tr>
        <tr>
          <th>2pglyc_c</th>
          <td>2-Phosphoglycolate</td>
          <td>1121</td>
          <td>564</td>
        </tr>
      </tbody>
    </table>
    </div>