def _charge(seq, ph=7.0, amide=False):
"""Calculates charge of a single sequence. The method used is first described by Bjellqvist. In the case of
amidation, the value for the 'Cterm' pKa is 15 (and Cterm is added to the pos_pks dictionary.
The pKa scale is extracted from: http://www.hbcpnetbase.com/ (CRC Handbook of Chemistry and Physics, 96th ed).
**pos_pks** = {'Nterm': 9.38, 'K': 10.67, 'R': 12.10, 'H': 6.04}
**neg_pks** = {'Cterm': 2.15, 'D': 3.71, 'E': 4.15, 'C': 8.14, 'Y': 10.10}
:param ph: {float} pH at which to calculate peptide charge.
:param amide: {boolean} whether the sequences have an amidated C-terminus.
:return: {array} descriptor values in the attribute :py:attr:`descriptor
"""
if amide:
pos_pks = {'Nterm': 9.38, 'K': 10.67, 'R': 12.10, 'H': 6.04}
neg_pks = {'Cterm': 15., 'D': 3.71, 'E': 4.15, 'C': 8.14, 'Y': 10.10}
else:
pos_pks = {'Nterm': 9.38, 'K': 10.67, 'R': 12.10, 'H': 6.04}
neg_pks = {'Cterm': 2.15, 'D': 3.71, 'E': 4.15, 'C': 8.14, 'Y': 10.10}
aa_content = count_aas(seq, scale='absolute')
aa_content['Nterm'] = 1.0
aa_content['Cterm'] = 1.0
pos_charge = 0.0
for aa, pK in pos_pks.items():
c_r = 10**(pK - ph)
partial_charge = c_r / (c_r + 1.0)
pos_charge += aa_content[aa] * partial_charge
neg_charge = 0.0
for aa, pK in neg_pks.items():
c_r = 10**(ph - pK)
partial_charge = c_r / (c_r + 1.0)
neg_charge += aa_content[aa] * partial_charge
return round(pos_charge - neg_charge, 3)
def calc_aa_freq(self, plot=True, color='#83AF9B', filename=None):
"""Method to get the frequency of every amino acid in the library. If the library consists of sub-libraries,
the frequencies of these are calculated independently.
:param plot: {bool} whether the amino acid frequencies should be plotted in a histogram.
:param color: {str} color of the plot
:param filename: {str} filename to save the plot to, if None, the plot is shown
:return: {numpy.ndarray} amino acid frequencies in the attribute :py:attr:`aafreq`. The values are oredered
alphabetically.
:Example:
>>> g = GlobalAnalysis(sequences) # sequences being a list / array of amino acid sequences
>>> g.calc_aa_freq()
>>> g.aafreq
array([[ 0.08250071, 0. , 0.02083928, 0.0159863 , 0.1464459 ,
0.04795889, 0.06622895, 0.0262632 , 0.12988867, 0. ,
0.09192121, 0.03111619, 0.01712818, 0.04852983, 0.05937768,
0.07079646, 0.04396232, 0.0225521 , 0.05994862, 0.01855552]])
.. image:: ../docs/static/AA_dist.png
:height: 300px
"""
for l in range(self.library.shape[0]):
concatseq = ''.join(self.library[l])
d_aa = count_aas(concatseq)
self.aafreq[l] = [d_aa[a] for a in self.AAs]
if plot:
fig, ax = plt.subplots()
for a in range(20):
plt.bar(a, self.aafreq[l, a], 0.9, color=color)
plt.xlim([-0.75, 19.75])
plt.ylim([0, max(self.aafreq[l, :]) + 0.05])
plt.xticks(range(20), d_aa.keys(), fontweight='bold')
plt.ylabel('Amino Acid Frequency', fontweight='bold')
plt.title('Amino Acid Distribution',
fontsize=16,
fontweight='bold')
# only left and bottom axes, no box
ax.spines['right'].set_visible(False)
ax.spines['top'].set_visible(False)
ax.xaxis.set_ticks_position('bottom')
ax.yaxis.set_ticks_position('left')
if filename:
plt.savefig(filename)
else:
plt.show()
def plot_aa_distr(sequences, color='#83AF9B', filename=None):
"""Method to plot the amino acid distribution of a given list of sequences
:param sequences: {list} list of sequences to calculate the amino acid distribution fore
:param color: {str} color to be used (matplotlib style / hex)
:param filename: {str} location / filename where to save the plot to. *default = None* --> show the plot
:Example:
>>> plot_aa_distr(['KLLKLLKKLLKLLK', 'WWRRWWRAARWWRRWWRR', 'ACDEFGHKLCMNPQRSTVWY', 'GGGGGIIKLWGGGGGGGGGGGGG'])
.. image:: ../docs/static/AA_dist.png
:height: 300px
.. versionadded:: v2.2.5
"""
concatseq = ''.join(sequences)
aa = count_aas(concatseq, scale='relative')
fig, ax = plt.subplots()
for a in range(20):
plt.bar(a, aa.values()[a], 0.9, color=color)
plt.xlim([-0.75, 19.75])
plt.ylim([0, max(aa.values()) + 0.05])
plt.xticks(range(20), aa.keys(), fontweight='bold')
plt.ylabel('Amino Acid Frequency', fontweight='bold')
plt.title('Amino Acid Distribution', fontsize=16, fontweight='bold')
# only left and bottom axes, no box
ax.spines['right'].set_visible(False)
ax.spines['top'].set_visible(False)
ax.xaxis.set_ticks_position('bottom')
ax.yaxis.set_ticks_position('left')
if filename:
plt.savefig(filename, dpi=300)
else:
plt.show()
def plot_summary(self, filename=None, colors=None, plot=True):
"""Method to generate a visual summary of different characteristics of the given library. The class methods
are used with their standard options.
:param filename: {str} path to save the generated plot to.
:param colors: {str / list} color or list of colors to use for plotting. e.g. '#4E395D', 'red', 'k'
:param plot: {boolean} whether the plot should be created or just the features are calculated
:return: visual summary (plot) of the library characteristics (if ``plot=True``).
:Example:
>>> g = GlobalAnalysis([seqs1, seqs2, seqs3]) # seqs being lists / arrays of sequences
>>> g.plot_summary()
.. image:: ../docs/static/summary.png
:height: 600px
"""
# calculate all global properties
self.calc_len()
self.calc_aa_freq(plot=False)
self.calc_charge(ph=7.4, amide=True)
self.calc_H()
self.calc_uH()
if plot:
# plot settings
fig, axes = plt.subplots(nrows=2, ncols=3, figsize=(25, 15))
((ax2, ax5, ax1), (ax3, ax4, ax6)) = axes
plt.suptitle('Summary', fontweight='bold', fontsize=16.)
labels = self.libnames
if not colors:
colors = [
'#FA6900', '#69D2E7', '#542437', '#53777A', '#CCFC8E',
'#9CC4E4'
]
num = len(labels)
for a in [ax1, ax2, ax3, ax4, ax5, ax6]:
# only left and bottom axes, no box
a.spines['right'].set_visible(False)
a.spines['top'].set_visible(False)
a.xaxis.set_ticks_position('bottom')
a.yaxis.set_ticks_position('left')
# 1 length box plot
box = ax1.boxplot(self.len, notch=1, vert=1, patch_artist=True)
plt.setp(box['whiskers'], color='black')
plt.setp(box['medians'],
linestyle='-',
linewidth=1.5,
color='black')
for p, patch in enumerate(box['boxes']):
patch.set(facecolor=colors[p], edgecolor='black', alpha=0.8)
ax1.set_ylabel('Sequence Length', fontweight='bold', fontsize=14.)
ax1.set_xticks([x + 1 for x in range(len(labels))])
ax1.set_xticklabels(labels, fontweight='bold')
# 2 AA bar plot
d_aa = count_aas('')
hands = [
mpatches.Patch(label=labels[i], facecolor=colors[i], alpha=0.8)
for i in range(len(labels))
]
w = .9 / num # bar width
offsets = np.arange(start=-w, step=w,
stop=num * w) # bar offsets if many libs
for i, l in enumerate(self.aafreq):
for a in range(20):
ax2.bar(a - offsets[i],
l[a],
w,
color=colors[i],
alpha=0.8)
ax2.set_xlim([-1., 20.])
ax2.set_ylim([0, 1.05 * np.max(self.aafreq)])
ax2.set_xticks(range(20))
ax2.set_xticklabels(d_aa.keys(), fontweight='bold')
ax2.set_ylabel('Fraction', fontweight='bold', fontsize=14.)
ax2.set_xlabel('Amino Acids', fontweight='bold', fontsize=14.)
ax2.legend(handles=hands, labels=labels)
# 3 hydophobicity violin plot
for i, l in enumerate(self.H):
vplot = ax3.violinplot(l,
positions=[i + 1],
widths=0.5,
showmeans=True,
showmedians=False)
# crappy adaptions of violin dictionary elements
vplot['cbars'].set_edgecolor('black')
vplot['cmins'].set_edgecolor('black')
vplot['cmeans'].set_edgecolor('black')
vplot['cmaxes'].set_edgecolor('black')
vplot['cmeans'].set_linestyle('--')
for pc in vplot['bodies']:
pc.set_facecolor(colors[i])
pc.set_alpha(0.8)
pc.set_edgecolor('black')
pc.set_linewidth(1.5)
pc.set_alpha(0.7)
pc.set_label(labels[i])
ax3.set_xticks([x + 1 for x in range(len(labels))])
ax3.set_xticklabels(labels, fontweight='bold')
ax3.set_ylabel('Global Hydrophobicity',
fontweight='bold',
fontsize=14.)
# 4 hydrophobic moment violin plot
for i, l in enumerate(self.uH):
vplot = ax4.violinplot(l,
positions=[i + 1],
widths=0.5,
showmeans=True,
showmedians=False)
# crappy adaptions of violin dictionary elements
vplot['cbars'].set_edgecolor('black')
vplot['cmins'].set_edgecolor('black')
vplot['cmeans'].set_edgecolor('black')
vplot['cmaxes'].set_edgecolor('black')
vplot['cmeans'].set_linestyle('--')
for pc in vplot['bodies']:
pc.set_facecolor(colors[i])
pc.set_alpha(0.8)
pc.set_edgecolor('black')
pc.set_linewidth(1.5)
pc.set_alpha(0.7)
pc.set_label(labels[i])
ax4.set_xticks([x + 1 for x in range(len(labels))])
ax4.set_xticklabels(labels, fontweight='bold')
ax4.set_ylabel('Global Hydrophobic Moment',
fontweight='bold',
fontsize=14.)
# 5 charge histogram
if self.shapes: # if the library consists of different sized sub libraries
bwidth = 1. / len(self.shapes)
for i, c in enumerate(self.charge):
counts, bins = np.histogram(c,
range=[-5, 20],
bins=25,
normed=True)
ax5.bar(bins[1:] + i * bwidth,
counts,
bwidth,
color=colors[i],
label=labels[i],
alpha=0.8)
# ax5.hist(c, bins, alpha=0.7, align=alignments[i], rwidth=0.95 / len(self.shapes), histtype='bar',
# normed=1, label=labels[i], color=colors[i])
else:
ax5.hist(self.charge,
25,
normed=1,
alpha=0.8,
align='left',
rwidth=0.95,
histtype='bar',
label=labels,
color=colors[:num])
ax5.set_xlabel('Global Charge', fontweight='bold', fontsize=14.)
ax5.set_ylabel('Fraction', fontweight='bold', fontsize=14.)
ax5.set_xlim(-6, 21)
ax5.text(0.95,
0.8,
b'amide: $true$',
verticalalignment='center',
horizontalalignment='right',
transform=ax5.transAxes,
fontsize=15)
ax5.text(0.95,
0.75,
b'pH: $7.4$',
verticalalignment='center',
horizontalalignment='right',
transform=ax5.transAxes,
fontsize=15)
ax5.legend()
# 6 3D plot
ax6.spines['left'].set_visible(False)
ax6.spines['bottom'].set_visible(False)
ax6.set_xticks([])
ax6.set_yticks([])
ax6 = fig.add_subplot(2, 3, 6, projection='3d')
for i, l in enumerate(range(num)):
xt = self.H[l] # find all values in x for the given target
yt = self.charge[
l] # find all values in y for the given target
zt = self.uH[l] # find all values in y for the given target
ax6.scatter(xt,
yt,
zt,
c=colors[l],
alpha=.8,
s=25,
label=labels[i])
ax6.set_xlabel('H', fontweight='bold', fontsize=14.)
ax6.set_ylabel('Charge', fontweight='bold', fontsize=14.)
ax6.set_zlabel('uH', fontweight='bold', fontsize=14.)
data_c = [item for sublist in self.charge
for item in sublist] # flatten charge data into one list
data_H = [item for sublist in self.H
for item in sublist] # flatten H data into one list
data_uH = [item for sublist in self.uH
for item in sublist] # flatten uH data into one list
ax6.set_xlim([np.min(data_H), np.max(data_H)])
ax6.set_ylim([np.min(data_c), np.max(data_c)])
ax6.set_zlim([np.min(data_uH), np.max(data_uH)])
ax6.legend(loc='best')
if filename:
plt.savefig(filename, dpi=200)
else:
plt.show()
def analyze_generated(self, num, fname='analysis.txt', plot=False):
""" Method to analyze the generated sequences located in `self.generated`.
:param num: {int} wanted number of sequences to sample
:param fname: {str} filename to save analysis info to
:param plot: {bool} whether to plot an overview of descriptors
:return: file with analysis info (distances)
"""
with open(fname, 'w') as f:
print("Analyzing...")
f.write("ANALYSIS OF SAMPLED SEQUENCES\n==============================\n\n")
f.write("Nr. of duplicates in generated sequences: %i\n" % (len(self.generated) - len(set(self.generated))))
count = len(set(self.generated) & set(self.sequences)) # get shared entries in both lists
f.write("%.1f percent of generated sequences are present in the training data.\n" %
((count / len(self.generated)) * 100))
d = GlobalDescriptor(self.generated)
len1 = len(d.sequences)
d.filter_aa('B')
len2 = len(d.sequences)
d.length()
f.write("\n\nLENGTH DISTRIBUTION OF GENERATED DATA:\n\n")
f.write("Number of sequences too short:\t%i\n" % (num - len1))
f.write("Number of invalid (with 'B'):\t%i\n" % (len1 - len2))
f.write("Number of valid unique seqs:\t%i\n" % len2)
f.write("Mean sequence length: \t\t%.1f ± %.1f\n" % (np.mean(d.descriptor), np.std(d.descriptor)))
f.write("Median sequence length: \t\t%i\n" % np.median(d.descriptor))
f.write("Minimal sequence length: \t\t%i\n" % np.min(d.descriptor))
f.write("Maximal sequence length: \t\t%i\n" % np.max(d.descriptor))
descriptor = 'pepcats'
seq_desc = PeptideDescriptor([s[1:].rstrip() for s in self.sequences], descriptor)
seq_desc.calculate_autocorr(7)
gen_desc = PeptideDescriptor(d.sequences, descriptor)
gen_desc.calculate_autocorr(7)
# random comparison set
self.ran = Random(len(self.generated), np.min(d.descriptor), np.max(d.descriptor)) # generate rand seqs
probas = count_aas(''.join(seq_desc.sequences)).values() # get the aa distribution of training seqs
self.ran.generate_sequences(proba=probas)
ran_desc = PeptideDescriptor(self.ran.sequences, descriptor)
ran_desc.calculate_autocorr(7)
# amphipathic helices comparison set
self.hel = Helices(len(self.generated), np.min(d.descriptor), np.max(d.descriptor))
self.hel.generate_sequences()
hel_desc = PeptideDescriptor(self.hel.sequences, descriptor)
hel_desc.calculate_autocorr(7)
# distance calculation
f.write("\n\nDISTANCE CALCULATION IN '%s' DESCRIPTOR SPACE\n\n" % descriptor.upper())
desc_dist = distance.cdist(gen_desc.descriptor, seq_desc.descriptor, metric='euclidean')
f.write("Average euclidean distance of sampled to training data:\t%.3f +/- %.3f\n" %
(np.mean(desc_dist), np.std(desc_dist)))
ran_dist = distance.cdist(ran_desc.descriptor, seq_desc.descriptor, metric='euclidean')
f.write("Average euclidean distance if randomly sampled seqs:\t%.3f +/- %.3f\n" %
(np.mean(ran_dist), np.std(ran_dist)))
hel_dist = distance.cdist(hel_desc.descriptor, seq_desc.descriptor, metric='euclidean')
f.write("Average euclidean distance if amphipathic helical seqs:\t%.3f +/- %.3f\n" %
(np.mean(hel_dist), np.std(hel_dist)))
# more simple descriptors
g_seq = GlobalDescriptor(seq_desc.sequences)
g_gen = GlobalDescriptor(gen_desc.sequences)
g_ran = GlobalDescriptor(ran_desc.sequences)
g_hel = GlobalDescriptor(hel_desc.sequences)
g_seq.calculate_all()
g_gen.calculate_all()
g_ran.calculate_all()
g_hel.calculate_all()
sclr = StandardScaler()
sclr.fit(g_seq.descriptor)
f.write("\n\nDISTANCE CALCULATION FOR SCALED GLOBAL DESCRIPTORS\n\n")
desc_dist = distance.cdist(sclr.transform(g_gen.descriptor), sclr.transform(g_seq.descriptor),
metric='euclidean')
f.write("Average euclidean distance of sampled to training data:\t%.2f +/- %.2f\n" %
(np.mean(desc_dist), np.std(desc_dist)))
ran_dist = distance.cdist(sclr.transform(g_ran.descriptor), sclr.transform(g_seq.descriptor),
metric='euclidean')
f.write("Average euclidean distance if randomly sampled seqs:\t%.2f +/- %.2f\n" %
(np.mean(ran_dist), np.std(ran_dist)))
hel_dist = distance.cdist(sclr.transform(g_hel.descriptor), sclr.transform(g_seq.descriptor),
metric='euclidean')
f.write("Average euclidean distance if amphipathic helical seqs:\t%.2f +/- %.2f\n" %
(np.mean(hel_dist), np.std(hel_dist)))
# hydrophobic moments
uh_seq = PeptideDescriptor(seq_desc.sequences, 'eisenberg')
uh_seq.calculate_moment()
uh_gen = PeptideDescriptor(gen_desc.sequences, 'eisenberg')
uh_gen.calculate_moment()
uh_ran = PeptideDescriptor(ran_desc.sequences, 'eisenberg')
uh_ran.calculate_moment()
uh_hel = PeptideDescriptor(hel_desc.sequences, 'eisenberg')
uh_hel.calculate_moment()
f.write("\n\nHYDROPHOBIC MOMENTS\n\n")
f.write("Hydrophobic moment of training seqs:\t%.3f +/- %.3f\n" %
(np.mean(uh_seq.descriptor), np.std(uh_seq.descriptor)))
f.write("Hydrophobic moment of sampled seqs:\t\t%.3f +/- %.3f\n" %
(np.mean(uh_gen.descriptor), np.std(uh_gen.descriptor)))
f.write("Hydrophobic moment of random seqs:\t\t%.3f +/- %.3f\n" %
(np.mean(uh_ran.descriptor), np.std(uh_ran.descriptor)))
f.write("Hydrophobic moment of amphipathic seqs:\t%.3f +/- %.3f\n" %
(np.mean(uh_hel.descriptor), np.std(uh_hel.descriptor)))
if plot:
if self.refs:
a = GlobalAnalysis([uh_seq.sequences, uh_gen.sequences, uh_hel.sequences, uh_ran.sequences],
['training', 'sampled', 'hel', 'ran'])
else:
a = GlobalAnalysis([uh_seq.sequences, uh_gen.sequences], ['training', 'sampled'])
a.plot_summary(filename=fname[:-4] + '.png')