Newer
Older
import numpy as np
import pandas as pd
from loess.loess_1d import loess_1d
from dataloader import RT_Dataset
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
"A": 1,
"C": 2,
"D": 3,
"E": 4,
"F": 5,
"G": 6,
"H": 7,
"I": 8,
"K": 9,
"L": 10,
"M": 11,
"N": 12,
"P": 13,
"Q": 14,
"R": 15,
"S": 16,
"T": 17,
"V": 18,
"W": 19,
"Y": 20,
"CaC": 21,
"OxM": 22
}
ALPHABET_UNMOD_REV = {v: k for k, v in ALPHABET_UNMOD.items()}
def numerical_to_alphabetical(arr):
seq = ''
for i in range(len(arr)):
seq+=ALPHABET_UNMOD_REV[arr[i]]
return seq
def align(dataset, reference):
seq_ref = reference['sequence']
seq_common = dataset['Sequence']
seq_ref = seq_ref.tolist()
seq_common = seq_common.tolist()
seq_ref = [tuple(l) for l in seq_ref]
seq_common = [tuple(l) for l in seq_common]
ind_dict_ref = dict((k, i) for i, k in enumerate(seq_ref))
inter = set(ind_dict_ref).intersection(seq_common)
ind_dict_ref = [ind_dict_ref[x] for x in inter]
indices_common = dict((k, i) for i, k in enumerate(seq_common))
indices_common = [indices_common[x] for x in inter]
rt_ref = reference['irt'][ind_dict_ref].reset_index()
rt_data = dataset['Retention time'][indices_common].reset_index()
xout, yout, wout = loess_1d(np.array(rt_data['Retention time'].tolist()), np.array(rt_ref['irt'].tolist()),
xnew=dataset['Retention time'],
degree=1, frac=0.5,
npoints=None, rotate=False, sigy=None)
dataset['Retention time'] = yout
return dataset
data_ori = RT_Dataset(None, 'database/data_train.csv', 'train', 25).data
data_ori['sequence'] = data_ori['sequence'].map(numerical_to_alphabetical)
data_train = load_data('msms/msms16_01.txt').reset_index(drop=True)
# data_train = pd.read_pickle('database/data_DIA_16_01.pkl').reset_index(drop=True)
data_align = align(data_train, data_ori)
data_align.to_pickle('database/data_DIA_16_01_aligned.pkl')
data_train = load_data('msms/msms17_01.txt').reset_index(drop=True)
# data_train = pd.read_pickle('database/data_DIA_17_01.pkl').reset_index(drop=True)
data_align = align(data_train, data_ori)
data_align.to_pickle('database/data_DIA_17_01_aligned.pkl')
data_train = load_data('msms/msms20_01.txt').reset_index(drop=True)
# data_train = pd.read_pickle('database/data_DIA_20_01.pkl').reset_index(drop=True)
data_align = align(data_train, data_ori)
data_align.to_pickle('database/data_DIA_20_01_aligned.pkl')
data_train = load_data('msms/msms23_01.txt').reset_index(drop=True)
# data_train = pd.read_pickle('database/data_DIA_23_01.pkl').reset_index(drop=True)
data_align = align(data_train, data_ori)
data_align.to_pickle('database/data_DIA_23_01_aligned.pkl')
data_train = load_data('msms/msms24_01.txt').reset_index(drop=True)
# data_train = pd.read_pickle('database/data_DIA_24_01.pkl').reset_index(drop=True)
data_align = align(data_train, data_ori)
data_align.to_pickle('database/data_DIA_24_01_aligned.pkl')
data_train = load_data('msms/msms30_01.txt').reset_index(drop=True)
# data_train = pd.read_pickle('database/data_DIA_30_01.pkl').reset_index(drop=True)
data_align.to_pickle('database/data_DIA_30_01_aligned.pkl')
# plt.scatter(data_train['Retention time'], data_align['Retention time'], s=1)
# plt.savefig('test_align_2.png')
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
#
#
# dataset_ref = pd.read_pickle('database/data_01_16_DIA_ISA_55.pkl')
# data_ref = Common_Dataset(dataset_ref, 25).data
# dataset_2 = pd.read_pickle('database/data_01_20_DIA_ISA_55.pkl')
# data_2 = Common_Dataset(dataset_2, 25).data
# dataset_3 = pd.read_pickle('database/data_01_17_DIA_ISA_55.pkl')
# data_3 = Common_Dataset(dataset_3, 25).data
# dataset_4 = pd.read_pickle('database/data_01_23_DIA_ISA_55.pkl')
# data_4 = Common_Dataset(dataset_4, 25).data
# data_align_3 = align(data_3, data_ref)
# data_align_4 = align(data_4, data_ref)
#
# data = pd.concat([data_ref, data_2, data_align_3, data_align_4], ignore_index=True)
# data = data.drop(columns='index')
# data['Sequence'] = data['Sequence'].map(numerical_to_alphabetical)
# num_data = data.shape[0]
# train_num = np.floor(num_data*0.8)
# train_size=0
# list_train=[]
# list_test=[]
# groups = data.groupby('Sequence')
# for seq, gr in groups:
#
# train_size+= gr.shape[0]
#
# if train_size>train_num:
# list_test.append(gr)
# else:
# list_train.append(gr)
#
#
# dataset_train = pd.concat(list_train, ignore_index=True)
# dataset_test = pd.concat(list_test, ignore_index=True)
# dataset_train.to_pickle('database/data_DIA_ISA_55_train.pkl')
# dataset_train.to_pickle('database/data_DIA_ISA_55_test.pkl')