1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
|
"""module contains code integration correlation implemented in rust here
https://github.com/Alexanderlacuna/correlation_rust
"""
import subprocess
import json
import os
from gn3.computations.qtlreaper import create_output_directory
from gn3.random import random_string
from gn3.settings import CORRELATION_COMMAND
from gn3.settings import TMPDIR
def generate_input_files(dataset: list[str],
output_dir: str = TMPDIR) -> tuple[str, str]:
"""function generates outputfiles and inputfiles"""
tmp_dir = f"{output_dir}/correlation"
create_output_directory(tmp_dir)
tmp_file = os.path.join(tmp_dir, f"{random_string(10)}.txt")
with open(tmp_file, "w", encoding="utf-8") as file_writer:
file_writer.write("\n".join(dataset))
return (tmp_dir, tmp_file)
def generate_json_file(
tmp_dir, tmp_file, method, delimiter, x_vals) -> tuple[str, str]:
"""generating json input file required by cargo"""
tmp_json_file = os.path.join(tmp_dir, f"{random_string(10)}.json")
output_file = os.path.join(tmp_dir, f"{random_string(10)}.txt")
with open(tmp_json_file, "w", encoding="utf-8") as outputfile:
json.dump({
"method": method,
"file_path": tmp_file,
"x_vals": x_vals,
"sample_values": "bxd1",
"output_file": output_file,
"file_delimiter": delimiter
}, outputfile)
return (output_file, tmp_json_file)
def run_correlation(
dataset, trait_vals: str, method: str, delimiter: str,
corr_type: str = "sample", top_n: int = 500):
"""entry function to call rust correlation"""
#pylint: disable=too-many-arguments
(tmp_dir, tmp_file) = generate_input_files(dataset)
(output_file, json_file) = generate_json_file(
tmp_dir=tmp_dir, tmp_file=tmp_file, method=method, delimiter=delimiter,
x_vals=trait_vals)
command_list = [CORRELATION_COMMAND, json_file, TMPDIR]
subprocess.run(command_list, check=True)
return parse_correlation_output(output_file, corr_type, top_n)
def parse_correlation_output(result_file: str,
corr_type: str, top_n: int = 500) -> dict:
"""parse file output """
#current types are sample and tissue
def __parse_line__(line):
(trait_name, corr_coeff, p_val, num_overlap) = line.rstrip().split(",")
if corr_type == "sample":
return (trait_name, {
"num_overlap": num_overlap,
"corr_coefficient": corr_coeff,
"p_value": p_val
})
if corr_type == "tissue":
return (
trait_name,
{
"tissue_corr": corr_coeff,
"tissue_number": num_overlap,
"tissue_p_val": p_val,
# The fields below are mandatory
"p_value": p_val,
"num_overlap": num_overlap,
"corr_coefficient": corr_coeff
})
return tuple(trait_name, {})
with open(result_file, "r", encoding="utf-8") as file_reader:
return dict([
__parse_line__(line)
for idx, line in enumerate(file_reader) if idx < top_n])
return {}
def get_samples(all_samples: dict[str, str],
base_samples: list[str],
excluded: list[str]):
"""filter null samples and excluded samples"""
data = {}
if base_samples:
fls = [
sm for sm in base_samples if sm not in excluded]
for sample in fls:
if sample in all_samples:
smp_val = all_samples[sample].strip()
if smp_val.lower() != "x":
data[sample] = float(smp_val)
return data
return({key: float(val.strip()) for (key, val) in all_samples.items()
if key not in excluded and val.lower().strip() != "x"})
def get_sample_corr_data(sample_type: str,
all_samples: dict[str, str],
dataset_samples: list[str]) -> dict[str, str]:
"""dependeing on the sample_type fetch the correct sample data """
if sample_type == "samples_primary":
data = get_samples(all_samples=all_samples,
base_samples=dataset_samples, excluded=[])
elif sample_type == "samples_other":
data = get_samples(
all_samples=all_samples,
base_samples=[],
excluded=dataset_samples)
else:
data = get_samples(
all_samples=all_samples, base_samples=[], excluded=[])
return data
def parse_tissue_corr_data(symbol_name: str,
symbol_dict: dict,
dataset_symbols: dict,
dataset_vals: dict):
"""parset tissue data input"""
results = None
if symbol_name and symbol_name.lower() in symbol_dict:
x_vals = [float(val) for val in symbol_dict[symbol_name.lower()]]
data = []
for (trait, symbol) in dataset_symbols.items():
try:
corr_vals = dataset_vals.get(symbol.lower())
if corr_vals:
corr_vals = [str(trait)] + corr_vals
data.append(",".join([str(x) for x in corr_vals]))
except AttributeError:
pass
results = (x_vals, data)
return results
|
