def test_2(self):
from Bio.SubsMat.MatrixInfo import blosum62
print blosum62
columns = []
points = []
for tup in blosum62.keys():
if not tup[0] in columns:
columns.append(tup[0])
print columns
for x, first in enumerate(columns):
points.append([])
for second in columns:
try:
points[x].append(blosum62[(first,second)])
except KeyError:
points[x].append(blosum62[(second, first)])
for row in points:
print row
with open("inputs/blosum.txt", "w") as file:
file.write("\t".join(columns))
file.write("\n")
for row in points:
file.write("\t".join(map(str, row)))
file.write("\n")
def get_distance_matrix():
aas = sorted({t[0] for t in sorted(blosum62.keys())})
D = np.array([[
blosum62[a, b] if (a, b) in blosum62 else blosum62[b, a] for a in aas
] for b in aas])
D = -(D + min(D.flatten()) + 1)
return D
def sim(ch1, ch2):
""" Similarity between two amino acids.
:param ch1: string
:param ch2: string
:return: int
"""
if (ch1, ch2) in blosum62.keys():
return blosum62[(ch1, ch2)]
else:
return blosum62[(ch2, ch1)]
def return_blosum62_dict():
prot_dic = dict((k, 0) for k in IUPACData.protein_letters)
A = []
Dictblosum = {}
for aa in prot_dic:
for bb in prot_dic:
if (aa, bb) in blosum62.keys():
A.append(blosum62[(aa, bb)])
else:
A.append(blosum62[(bb, aa)])
Dictblosum[aa] = A
A = []
Dictblosum['X'] = [
0, -1, -1, -1, -2, -1, -1, -1, -1, -1, -1, -1, -1, -1, -2, 0, 0, -2,
-1, -1
]
Dictblosum['B'] = [
-2, -1, 3, 4, -3, 0, 1, -1, 0, -3, -4, 0, -3, -3, -2, 0, -1, -4, -3, -3
]
Dictblosum['Z'] = [
-1, 0, 0, 1, -3, 3, 4, -2, 0, -3, -3, 1, -1, -3, -1, 0, -1, -3, -2, -2
]
return Dictblosum
def embed(x_train, y_train, output_csv=None):
max_len = max([len(s) for s in x_train])
aas = sorted({t[0] for t in sorted(blosum62.keys())})
D = get_distance_matrix()
aa_to_embedding = {
aa: embedding[0]
for aa, embedding in zip(
aas,
MDS(n_components=1, dissimilarity='precomputed').fit_transform(D))
}
processed = np.zeros((len(x_train), max_len))
for i, s in enumerate(x_train):
for j, c in enumerate(s):
processed[i, j] = aa_to_embedding[c]
if output_csv:
print('Saving embedded csv')
pd.DataFrame(np.c_[processed, y_train]).to_csv(output_csv,
header=None,
index=False,
float_format='%.3f')
return processed, y_train
from Bio.SubsMat.MatrixInfo import blosum62
mmatch = {}
for i, j in blosum62.keys():
mmatch[i, j] = mmatch[j, i] = blosum62[i, j]
def score(seq1, seq2, gap, match, d_old=None, depth=0):
if not d_old:
d = [[i*gap for i in range(len(seq1)+1)]]
else:
d = [d_old[-1]]
j = depth
for s in seq2:
cur = [(j+1) * gap]
for i, t in enumerate(seq1):
cur.append(max(d[-1][i+1] + gap, d[-1][i] + match[s, t], cur[-1] + gap))
d.append(cur)
j += 1
return d if not d_old else d[1:]
def backtrace(seq1, seq2, score_matrix, gap, match):
i, j = len(seq2), len(seq1)
res1, res2 = [], []
while i != 0 or j != 0:
s, t = seq2[i - 1], seq1[j - 1]
l = [score_matrix[i - 1][j] + gap,
score_matrix[i][j - 1] + gap,
score_matrix[i - 1][j - 1] + match[s, t]]
def create_figures(feature_to_weighted_sums, weight_totals, min_total,
report_dir, filetype):
aa_blosum = set()
for aa1, aa2 in blosum62.keys():
aa_blosum.add(aa1)
aa_blosum.add(aa2)
include_mask = weight_totals >= min_total
p = re.compile(r'aa_to_([A-Z])$')
aa_to_features = {}
for feature_name, weighted_sums in feature_to_weighted_sums.items():
m = p.match(feature_name)
if m:
aa = m[1]
mean_by_heads = np.where(include_mask,
weighted_sums / weight_totals, -1)
feature_vector = mean_by_heads.flatten()
feature_vector = feature_vector[feature_vector != -1]
aa_to_features[aa] = feature_vector
aas = sorted(aa_to_features.keys())
aas_set = set(aas)
print('Excluding following AAs not in feature set', aa_blosum - aas_set)
print('Excluding following AAs not in blosum62', aas_set - aa_blosum)
aa_list = sorted(list(aas_set & aa_blosum))
n_aa = len(aa_list)
corr = np.zeros((n_aa, n_aa))
for i, aa1 in enumerate(aa_list):
vector1 = aa_to_features[aa1]
for j, aa2 in enumerate(aa_list):
if i == j:
corr[i, j] = None
else:
vector2 = aa_to_features[aa2]
corr[i, j], _ = pearsonr(vector1, vector2)
cmap = 'Blues'
ax = sns.heatmap(corr, cmap=cmap, vmin=-0.5)
ax.set_xticklabels(aa_list)
ax.set_yticklabels(aa_list)
plt.savefig(report_dir / f'aa_corr_to.pdf', format=filetype)
plt.close()
blosum = np.zeros((n_aa, n_aa))
for i, aa1 in enumerate(aa_list):
for j, aa2 in enumerate(aa_list):
if i == j:
blosum[i, j] = None
else:
if blosum62.get((aa1, aa2)) is not None:
blosum[i, j] = blosum62.get((aa1, aa2))
else:
blosum[i, j] = blosum62.get((aa2, aa1))
ax = sns.heatmap(blosum, cmap=cmap, vmin=-4, vmax=4)
ax.set_xticklabels(aa_list)
ax.set_yticklabels(aa_list)
plt.savefig(report_dir / f'blosum62.pdf', format=filetype)
plt.close()
corr_scores = []
blos_scores = []
for i in range(n_aa):
for j in range(i):
corr_scores.append(corr[i, j])
blos_scores.append(blosum[i, j])
print('Pearson Correlation between feature corr and blosum',
pearsonr(corr_scores, blos_scores)[0])
if output_csv:
print('Saving embedded csv')
pd.DataFrame(np.c_[processed, y_train]).to_csv(output_csv,
header=None,
index=False,
float_format='%.3f')
return processed, y_train
if __name__ == '__main__':
# x_train, y_train = np.hsplit(pd.read_csv('train.csv', delimiter=',', header=None).to_numpy(), 2)
# x_train, y_train = x_train[:, 0], y_train[:, 0]
# # x_train, y_train = x_train[:, 0], y_train[:, 0]
# x_train = embed(x_train, y_train, 'embedded.csv')
k = 3
aas = sorted({t[0] for t in sorted(blosum62.keys())})
kmer_to_index = {
''.join(kmer): i + 1
for i, kmer in enumerate(product(aas, repeat=k))
}
print(kmer_to_index)
print(len(kmer_to_index))
# print(list(product(aas, repeat=3)))
# product([1,2,3], repeat=3)
# print([1, 2, 3, 4, 5][:-3 + 1])
data = pd.read_csv('train.csv', delimiter=',', header=None).to_numpy()
#
x_train, y_train = data[:, 0], data[:, 1]
print(x_train.shape, y_train.shape)
from Bio.SubsMat.MatrixInfo import blosum62
mmatch = {}
for i, j in blosum62.keys():
mmatch[i, j] = mmatch[j, i] = blosum62[i, j]
def score(seq1, seq2, gap, match, d_old=None, depth=0):
if not d_old:
d = [[i * gap for i in range(len(seq1) + 1)]]
else:
d = [d_old[-1]]
j = depth
for s in seq2:
cur = [(j + 1) * gap]
for i, t in enumerate(seq1):
cur.append(
max(d[-1][i + 1] + gap, d[-1][i] + match[s, t], cur[-1] + gap))
d.append(cur)
j += 1
return d if not d_old else d[1:]
def backtrace(seq1, seq2, score_matrix, gap, match):
i, j = len(seq2), len(seq1)
res1, res2 = [], []
while i != 0 or j != 0:
s, t = seq2[i - 1], seq1[j - 1]
l = [
score_matrix[i - 1][j] + gap, score_matrix[i][j - 1] + gap,
