Content uploaded by Douglas C Youvan
Author content
All content in this area was uploaded by Douglas C Youvan on Oct 25, 2023
Content may be subject to copyright.
2
3
Kyte-Doolittle Hydropathy Scale
4
import numpy as np
from scipy.spatial.distance import hamming, pdist
from scipy.cluster.hierarchy import linkage, dendrogram
import matplotlib.pyplot as plt
import matplotlib as mpl
# Use the "viridis" colormap
cmap = plt.get_cmap('viridis')
# Create mappable object for the colormap
norm = mpl.colors.Normalize(vmin=-4.5, vmax=4.5)
sm = plt.cm.ScalarMappable(cmap=cmap, norm=norm)
sm.set_array([])
# Define a custom colormap
colors = [(1, 0, 0), (0, 0, 1)] # deep red to deep blue
cm_name = 'custom_div_cmap'
cm = mpl.colors.LinearSegmentedColormap.from_list(cm_name,
colors, N=100)
# Create mappable object for the new colormap
norm = mpl.colors.Normalize(vmin=-4.5, vmax=4.5)
5
sm = plt.cm.ScalarMappable(cmap=cm, norm=norm)
sm.set_array([])
# Step 1: Representing the Genetic Code
genetic_code = {
'ATA': 'I', 'ATC': 'I', 'ATT': 'I', 'ATG': 'M',
'ACA': 'T', 'ACC': 'T', 'ACG': 'T', 'ACT': 'T',
'AAC': 'N', 'AAT': 'N', 'AAA': 'K', 'AAG': 'K',
'AGC': 'S', 'AGT': 'S', 'AGA': 'R', 'AGG': 'R',
'CTA': 'L', 'CTC': 'L', 'CTG': 'L', 'CTT': 'L',
'CCA': 'P', 'CCC': 'P', 'CCG': 'P', 'CCT': 'P',
'CAC': 'H', 'CAT': 'H', 'CAA': 'Q', 'CAG': 'Q',
'CGA': 'R', 'CGC': 'R', 'CGG': 'R', 'CGT': 'R',
'GTA': 'V', 'GTC': 'V', 'GTG': 'V', 'GTT': 'V',
'GCA': 'A', 'GCC': 'A', 'GCG': 'A', 'GCT': 'A',
'GAC': 'D', 'GAT': 'D', 'GAA': 'E', 'GAG': 'E',
'GGA': 'G', 'GGC': 'G', 'GGG': 'G', 'GGT': 'G',
'TCA': 'S', 'TCC': 'S', 'TCG': 'S', 'TCT': 'S',
'TTC': 'F', 'TTT': 'F', 'TTA': 'L', 'TTG': 'L',
'TAC': 'Y', 'TAT': 'Y', 'TAA': '_', 'TAG': '_',
'TGC': 'C', 'TGT': 'C', 'TGA': '_', 'TGG': 'W',
}
6
# Replace _ with X for stop codons
for codon, aa in genetic_code.items():
if aa == '_':
genetic_code[codon] = 'X'
# Step 2: Calculate Pairwise Distances
def nucleotide_distance(codon1, codon2):
return hamming(list(codon1), list(codon2))
def functional_distance(codon1, codon2):
return 0 if genetic_code[codon1] == genetic_code[codon2] else
1
codons = list(genetic_code.keys())
distance_matrix = np.zeros((64, 64))
for i in range(64):
for j in range(64):
distance_matrix[i][j] = nucleotide_distance(codons[i],
codons[j]) + functional_distance(codons[i], codons[j])
# Convert square distance matrix to condensed form
condensed_distance_matrix = pdist(distance_matrix)
7
# Step 3: Hierarchical Clustering
linked = linkage(condensed_distance_matrix, method='single')
# Create a new list of labels with single-letter codes
new_labels = [genetic_code[codon] + ' (' + codon + ')' for codon in
codons]
# Plot the dendrogram
fig, ax = plt.subplots(figsize=(10, 14))
dendrogram(linked, orientation="left", labels=new_labels,
color_threshold=0)
# ... [Previous code remains unchanged]
# Define the Kyte-Doolittle hydropathy values and coloring
function
hydropathy_values = {
'A': 1.8, 'R': -4.5, 'N': -3.5, 'D': -3.5, 'C': 2.5,
'Q': -3.5, 'E': -3.5, 'G': -0.4, 'H': -3.2, 'I': 4.5,
'L': 3.8, 'K': -3.9, 'M': 1.9, 'F': 2.8, 'P': -1.6,
'S': -0.8, 'T': -0.7, 'W': -0.9, 'Y': -1.3, 'V': 4.2,
'X': 0 # for stop codons, neutral value
}
8
# Define a custom colormap
colors = [(1, 0, 0), (0, 0, 1)] # deep red to deep blue
cm_name = 'custom_div_cmap'
cm = mpl.colors.LinearSegmentedColormap.from_list(cm_name,
colors, N=100)
# Create mappable object for the new colormap
norm = mpl.colors.Normalize(vmin=-4.5, vmax=4.5)
sm = plt.cm.ScalarMappable(cmap=cm, norm=norm)
sm.set_array([])
# Adjust the color mapping
for label in ax.get_ymajorticklabels():
label_text = label.get_text().split()[0] # Extract the amino acid
if label_text in hydropathy_values:
value = hydropathy_values[label_text]
color = sm.to_rgba(value)
label.set_color(color)
plt.title('Hierarchical Clustering of Genetic Codons')
plt.xlabel('Distance')
9
plt.tight_layout()
plt.show()
import matplotlib.pyplot as plt
import numpy as np
# Define the Kyte-Doolittle scale values range
norm = plt.Normalize(-4.5, 4.5)
# Use the viridis colormap
cmap = plt.get_cmap('viridis')
sm = plt.cm.ScalarMappable(cmap=cmap, norm=norm)
sm.set_array([])
# Create a new axis for the colorbar
cax = plt.axes([0.1, 0.1, 0.8, 0.8])
cbar = plt.colorbar(sm, cax=cax, orientation='vertical')
10
cbar.set_label('Kyte-Doolittle Hydropathy Value', rotation=270,
labelpad=20)
cbar.set_ticks(np.linspace(-4.5, 4.5, 19)) # Set ticks from -4.5 to
4.5 with an interval of 0.5
cbar.ax.tick_params(labelsize=10)
plt.show()