.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "examples/gallery/sequence/homology/luxa_comparison.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_examples_gallery_sequence_homology_luxa_comparison.py>`
        to download the full example code.

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_examples_gallery_sequence_homology_luxa_comparison.py:


Fetching and aligning a protein from different species
======================================================

.. currentmodule:: biotite.sequence.align

This script creates a multiple sequence alignment of the bacterial
luciferase gene *luxA* using the :func:`align_multiple()` function
provided by *Biotite*.

.. GENERATED FROM PYTHON SOURCE LINES 11-55



.. image-sg:: /examples/gallery/sequence/homology/images/sphx_glr_luxa_comparison_001.png
   :alt: luxa comparison
   :srcset: /examples/gallery/sequence/homology/images/sphx_glr_luxa_comparison_001.png, /examples/gallery/sequence/homology/images/sphx_glr_luxa_comparison_001_2_00x.png 2.00x
   :class: sphx-glr-single-img





.. code-block:: Python


    # Code source: Patrick Kunzmann
    # License: BSD 3 clause

    import matplotlib.pyplot as plt
    import biotite.database.entrez as entrez
    import biotite.sequence as seq
    import biotite.sequence.align as align
    import biotite.sequence.graphics as graphics
    import biotite.sequence.io.fasta as fasta

    # Search for protein products of LexA gene in UniProtKB/Swiss-Prot database
    query = entrez.SimpleQuery("luxA", "Gene Name") & entrez.SimpleQuery(
        "srcdb_swiss-prot", "Properties"
    )
    uids = entrez.search(query, db_name="protein")
    fasta_file = fasta.FastaFile.read(
        entrez.fetch_single_file(uids, None, db_name="protein", ret_type="fasta")
    )

    ids = []
    sequences = []
    for header, seq_str in fasta_file.items():
        # Extract the UniProt Entry name from header
        identifier = header.split("|")[-1].split()[0]
        ids.append(identifier)
        sequences.append(seq.ProteinSequence(seq_str))

    matrix = align.SubstitutionMatrix.std_protein_matrix()
    alignment, order, tree, distances = align.align_multiple(
        sequences, matrix, gap_penalty=(-10, -1), terminal_penalty=False
    )
    # Order alignment according to the guide tree
    alignment = alignment[:, order]
    ids = [ids[i] for i in order]

    fig = plt.figure(figsize=(8.0, 20.0))
    ax = fig.add_subplot(111)
    graphics.plot_alignment_type_based(
        ax, alignment, labels=ids, show_numbers=True, spacing=2.0, color_scheme="blossom"
    )
    fig.tight_layout()

    plt.show()


.. _sphx_glr_download_examples_gallery_sequence_homology_luxa_comparison.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: luxa_comparison.ipynb <luxa_comparison.ipynb>`

    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: luxa_comparison.py <luxa_comparison.py>`

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: luxa_comparison.zip <luxa_comparison.zip>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_