# We can apply this tree style to a random tree as follows.
t = ete3.Tree()
t.populate(10)
t.render("%%inline", tree_style=ts)
# distance based methods to phylogenetic reconstruction
# for the next approach, we will rely on computing the distances between the sequences.
# We will use dissimilarity distance between two objects x and y. Literature on this can be found online, for now
# we are going to show the code.
from skbio import DistanceMatrix
dm = DistanceMatrix([[0.0, 1.0, 2.0], [1.0, 0.0, 3.0], [2.0, 3.0, 0.0]],
ids=['a', 'b', 'c'])
_ = dm.plot(cmap='Greens')
# We will use the scikit-bio to create a skbio.distancematrix object. These objects can be viewed as heatmaps.
from BioinformaticsCode.algorithms import kmer_distance
kmer_dm = DistanceMatrix.from_iterable(sequences,
metric=kmer_distance,
key='id')
_ = kmer_dm.plot(cmap='Greens', title='3mer distances between sequences')
kmer_dm.plot
List_Of_Name.append(array_of_frequencies[i, :])
for j in range(line):
heatmap[i][j] = np.linalg.norm(array_of_frequencies[i, :] -
array_of_frequencies[j, :])
f, ax = plt.subplots()
ax = sns.heatmap(heatmap)
plt.show()
return heatmap
#CreateProfiles("bact","/home/roselyne/Bureau/BIM-info/GENOM/Database",7)
output = np.load("Frequency_vector_for_database.npy")
df = Tuples2DF(output, [1, 2, 3])
heatmap = plot_Distance_Matrix_Between_Species(df)
ids = list(df['Name'])
dm = DistanceMatrix(heatmap, ids)
tree_str = nj(dm, result_constructor=str)
print(tree_str[:55], "...")
fig = dm.plot(title='Distance Matrix - kmer from 1 to 3')
fig.savefig('Distance_Matrix_kmer_1To3.png')
file = open("tree_nw_format_kmer_1To3.txt", 'w')
file.write(tree_str)
file.close
