def unaligned_error_list(length, error_p):
e_dict = {}
error_rate = {
(0, 0.4): "match",
(0.4, 0.7): "mis",
(0.7, 0.85): "ins",
(0.85, 1): "del"
}
pos = 0
last_is_ins = False
while pos < length:
p = random.random()
for k_error in error_rate.keys():
if k_error[0] <= p < k_error[1]:
error_type = error_rate[k_error]
break
if error_type == "match":
step = 1
elif error_type == "mis":
step = mm.pois_geom(error_p["mis"][0], error_p["mis"][2],
error_p["mis"][3])
e_dict[pos] = ["mis", step]
elif error_type == "ins":
step = mm.wei_geom(error_p["ins"][0], error_p["ins"][1],
error_p["ins"][2], error_p["ins"][3])
if last_is_ins:
e_dict[pos + 0.1][1] += step
else:
e_dict[pos + 0.1] = ["ins", step]
last_is_ins = True
else:
step = mm.wei_geom(error_p["del"][0], error_p["del"][1],
error_p["del"][2], error_p["del"][3])
e_dict[pos] = ["del", step]
if error_type != "ins":
pos += step
last_is_ins = False
if pos > length:
length = pos
return length, e_dict
def unaligned_error_list(length, error_p):
e_dict = {}
error_rate = {(0, 0.4): "match", (0.4, 0.7): "mis", (0.7, 0.85): "ins", (0.85, 1): "del"}
pos = 0
last_is_ins = False
while pos < length:
p = random.random()
for k_error in error_rate.keys():
if k_error[0] <= p < k_error[1]:
error_type = error_rate[k_error]
break
if error_type == "match":
step = 1
elif error_type == "mis":
step = mm.pois_geom(error_p["mis"][0], error_p["mis"][2], error_p["mis"][3])
e_dict[pos] = ["mis", step]
elif error_type == "ins":
step = mm.wei_geom(error_p["ins"][0], error_p["ins"][1], error_p["ins"][2], error_p["ins"][3])
if last_is_ins:
e_dict[pos + 0.1][1] += step
else:
e_dict[pos + 0.1] = ["ins", step]
last_is_ins = True
else:
step = mm.wei_geom(error_p["del"][0], error_p["del"][1], error_p["del"][2], error_p["del"][3])
e_dict[pos] = ["del", step]
if error_type != "ins":
pos += step
last_is_ins = False
if pos > length:
length = pos
return length, e_dict
def error_list(m_ref, m_model, m_ht_list, error_p, trans_p):
# l_old is the original length, and l_new is used to control the new length after introducing errors
l_new = m_ref
pos = 0
e_dict = {}
middle_ref = m_ref
prev_error = "start"
# The first match come from m_ht_list
p = random.random()
k1 = list(m_ht_list.keys())[0]
for k2, v2 in m_ht_list[k1].items():
if k2[0] < p <= k2[1]:
prev_match = int(np.floor((p - k2[0])/(k2[1] - k2[0]) * (v2[1] - v2[0]) + v2[0]))
if prev_match < 2:
prev_match = 2
pos += prev_match
# Select an error, then the step size, and then a match and so on so forth.
while pos < middle_ref:
# pick the error based on Markov chain
p = random.random()
for k in trans_p[prev_error].keys():
if k[0] <= p < k[1]:
error = trans_p[prev_error][k]
break
if error == "mis":
step = mm.pois_geom(error_p["mis"][0], error_p["mis"][2], error_p["mis"][3])
elif error == "ins":
step = mm.wei_geom(error_p[error][0], error_p[error][1], error_p[error][2], error_p[error][3])
l_new += step
else:
step = mm.wei_geom(error_p[error][0], error_p[error][1], error_p[error][2], error_p[error][3])
l_new -= step
if error != "ins":
e_dict[pos] = [error, step]
pos += step
if pos >= middle_ref:
l_new += pos - middle_ref
middle_ref = pos
else:
e_dict[pos - 0.5] = [error, step]
prev_error = error
# Randomly select a match length
for k1 in m_model.keys():
if k1[0] <= prev_match < k1[1]:
break
p = random.random()
for k2, v2 in m_model[k1].items():
if k2[0] < p <= k2[1]:
step = int(np.floor((p - k2[0])/(k2[1] - k2[0]) * (v2[1] - v2[0]) + v2[0]))
break
# there are no two 0 base matches together
if prev_match == 0 and step == 0:
step = 1
prev_match = step
if pos + prev_match > middle_ref:
l_new += pos + prev_match - middle_ref
middle_ref = pos + prev_match
pos += prev_match
if prev_match == 0:
prev_error += "0"
return l_new, middle_ref, e_dict
def error_list(m_ref, m_model, m_ht_list, error_p, trans_p):
# l_old is the original length, and l_new is used to control the new length after introducing errors
l_new = m_ref
pos = 0
e_dict = {}
middle_ref = m_ref
prev_error = "start"
# The first match come from m_ht_list
p = random.random()
k1 = m_ht_list.keys()[0]
for k2, v2 in m_ht_list[k1].items():
if k2[0] < p <= k2[1]:
prev_match = int(np.floor((p - k2[0]) / (k2[1] - k2[0]) * (v2[1] - v2[0]) + v2[0]))
if prev_match < 2:
prev_match = 2
pos += prev_match
# Select an error, then the step size, and then a match and so on so forth.
while pos < middle_ref:
# pick the error based on Markov chain
p = random.random()
for k in trans_p[prev_error].keys():
if k[0] <= p < k[1]:
error = trans_p[prev_error][k]
break
if error == "mis":
step = mm.pois_geom(error_p["mis"][0], error_p["mis"][2], error_p["mis"][3])
elif error == "ins":
step = mm.wei_geom(error_p[error][0], error_p[error][1], error_p[error][2], error_p[error][3])
l_new += step
else:
step = mm.wei_geom(error_p[error][0], error_p[error][1], error_p[error][2], error_p[error][3])
l_new -= step
if error != "ins":
e_dict[pos] = [error, step]
pos += step
if pos >= middle_ref:
l_new += pos - middle_ref
middle_ref = pos
else:
e_dict[pos - 0.5] = [error, step]
prev_error = error
# Randomly select a match length
for k1 in m_model.keys():
if k1[0] <= prev_match < k1[1]:
break
p = random.random()
for k2, v2 in m_model[k1].items():
if k2[0] < p <= k2[1]:
step = int(np.floor((p - k2[0]) / (k2[1] - k2[0]) * (v2[1] - v2[0]) + v2[0]))
break
# there are no two 0 base matches together
if prev_match == 0 and step == 0:
step = 1
prev_match = step
if pos + prev_match > middle_ref:
l_new += pos + prev_match - middle_ref
middle_ref = pos + prev_match
pos += prev_match
if prev_match == 0:
prev_error += "0"
return l_new, middle_ref, e_dict
def error_list(m_ref, m_list, m_ht_list, error_p):
# l_old is the original length, and l_new is used to control the new length after introducing errors
l_new = m_ref
pos = 0
e_dict = {}
errors = {(0, 0.51027): "mis", (0.51027, 0.72467): "ins", (0.72467, 1): "del"}
transition_pr = {"mis": {(0, 0.50105): "mis", (0.50105, 0.72018): "ins", (0.72018, 1): "del"},
"ins": {(0, 0.52186): "mis", (0.52186, 0.82170): "ins", (0.82170, 1): "del"},
"del": {(0, 0.51752): "mis", (0.51752, 0.65589): "ins", (0.65589, 1): "del"}}
middle_ref = m_ref
last_error = ""
# The first match and last match come from m_ht_list
p = random.random()
for k in m_ht_list.keys():
if k[0] <= p < k[1]:
step = m_ht_list[k]
break
pos += step
p = random.random()
for k in m_ht_list.keys():
if k[0] <= p < k[1]:
last_match = m_ht_list[k]
break
# Select an error, then the step size, and then a match and so on so forth.
while pos < middle_ref - last_match:
if last_error == "":
# the first error of a read is randomly selected based on the rate of different errors.
p = random.random()
for k in errors.keys():
if k[0] <= p < k[1]:
error = errors[k]
break
else:
if step != 0:
# the rest errors are selected based on Markov chain
p = random.random()
for k in transition_pr[last_error].keys():
if k[0] <= p < k[1]:
error = transition_pr[last_error][k]
break
# if there are two consecutive errors, if the first one is mis, the second can be ins or del
elif last_error == "mis":
p = random.random()
if p <= 0.44386:
error = "ins"
else:
error = "del"
# if the first one is ins or del, the following one can only be a mis
elif last_error in ["ins", "del"]:
error = "mis"
if error == "mis":
step = mm.pois_geom(error_p["mis"][0], error_p["mis"][2], error_p["mis"][3])
else:
step = mm.wei_geom(error_p[error][0], error_p[error][1], error_p[error][2], error_p[error][3])
if error == "ins":
l_new += step
else:
l_new -= step
if error != "ins":
e_dict[pos] = [error, step]
pos += step
if pos >= middle_ref - last_match:
l_new += pos + last_match - middle_ref
middle_ref = pos + last_match
break
else:
e_dict[pos - 0.5] = [error, step]
if pos == middle_ref - last_match:
break
last_error = error
# Randomly select a match length
p = random.random()
for k in m_list.keys():
if k[0] <= p < k[1]:
step = m_list[k]
break
if pos + step > middle_ref - last_match:
l_new += pos + step + last_match - middle_ref
middle_ref = pos + step + last_match
pos += step
return l_new, middle_ref, e_dict