Newer
Older
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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
"""
Filter and combine various peptide/MHC datasets to derive a composite training set,
optionally including eluted peptides identified by mass-spec.
"""
import sys
import argparse
import os
import pandas
import mhcnames
def normalize_allele_name(s):
try:
return mhcnames.normalize_allele_name(s)
except Exception:
return "UNKNOWN"
parser = argparse.ArgumentParser(usage=__doc__)
parser.add_argument(
"--item",
nargs="+",
action="append",
metavar="PMID FILE, ... FILE",
default=[],
help="Item to curate: PMID and list of files")
parser.add_argument(
"--out",
metavar="OUT.csv",
help="Out file path")
parser.add_argument(
"--debug",
action="store_true",
default=False,
help="Leave user in pdb if PMID is unsupported")
HANDLERS = {}
def load(filenames, **kwargs):
result = {}
for filename in filenames:
if filename.endswith(".csv"):
result[filename] = pandas.read_csv(filename, **kwargs)
elif filename.endswith(".xlsx") or filename.endswith(".xls"):
result[filename] = pandas.read_excel(filename, **kwargs)
else:
result[filename] = filename
return result
def debug(*filenames):
loaded = load(filenames)
import ipdb
ipdb.set_trace()
def handle_pmid_27600516(filename):
df = pandas.read_csv(filename)
sample_to_peptides = {}
current_sample = None
for peptide in df.peptide:
if peptide.startswith("#"):
current_sample = peptide[1:]
sample_to_peptides[current_sample] = []
else:
assert current_sample is not None
sample_to_peptides[current_sample].append(peptide.strip().upper())
rows = []
for (sample, peptides) in sample_to_peptides.items():
for peptide in sorted(set(peptides)):
rows.append([sample, peptide])
result = pandas.DataFrame(rows, columns=["sample_id", "peptide"])
result["sample_type"] = "melanoma_cell_line"
return result
def handle_pmid_23481700(filename):
df = pandas.read_excel(filename)
peptides = df.iloc[10:,0].values
assert peptides[0] == "TPSLVKSTSQL"
assert peptides[-1] == "LPHSVNSKL"
result = pandas.DataFrame({
"peptide": peptides,
})
result["sample_id"] = "23481700"
result["sample_type"] = "B-LCL"
return result
def handle_pmid_24616531(filename):
df = pandas.read_excel(filename, sheetname="EThcD")
peptides = df.Sequence.values
assert peptides[0] == "APFLRIAF"
assert peptides[-1] == "WRQAGLSYIRYSQI"
result = pandas.DataFrame({
"peptide": peptides,
})
result["sample_id"] = "24616531"
result["sample_type"] = "B-lymphoblastoid"
result["cell_line"] = "GR"
result["pulldown_antibody"] = "W6/32"
# Note: this publication lists hla as "HLA-A*01,-03, B*07,-27, and -C*02,-07"
# we are guessing the exact 4 digit alleles based on this.
result["hla"] = "HLA-A*01:01 HLA-A*03:01 HLA-B*07:02 HLA-B*27:05 HLA-C*02:02 HLA-C*07:01"
return result
def handle_pmid_25576301(filename):
df = pandas.read_excel(filename, sheetname="Peptides")
peptides = df.Sequence.values
assert peptides[0] == "AAAAAAAQSVY"
assert peptides[-1] == "YYYNGKAVY"
# TODO TODO
import ipdb ; ipdb.set_trace()
# THIS IS ALL JUNK:
result = pandas.DataFrame({
"peptide": peptides,
})
result["sample_id"] = "24616531"
result["sample_type"] = "B-lymphoblastoid"
result["cell_line"] = "GR"
result["pulldown_antibody"] = "W6/32"
# Note: this publication lists hla as "HLA-A*01,-03, B*07,-27, and -C*02,-07"
# we are guessing the exact 4 digit alleles based on this.
result["hla"] = "HLA-A*01:01 HLA-A*03:01 HLA-B*07:02 HLA-B*27:05 HLA-C*02:02 HLA-C*07:01"
return result
# Hack to add all functions with names like handle_pmid_XXXX to HANDLERS dict.
for (key, value) in list(locals().items()):
if key.startswith("handle_pmid_"):
HANDLERS[key.replace("handle_pmid_", "")] = value
def run():
args = parser.parse_args(sys.argv[1:])
dfs = []
for item_tpl in args.item:
(pmid, filenames) = (item_tpl[0], item_tpl[1:])
print("Processing item", pmid, *[os.path.abspath(f) for f in filenames])
df = None
if pmid in HANDLERS:
df = HANDLERS[pmid](*filenames)
elif args.debug:
debug(*filenames)
else:
raise NotImplementedError(args.pmid)
if df is not None:
df["pmid"] = pmid
print("*** PMID %s: %d peptides ***" % (pmid, len(df)))
print("Counts by sample id:")
print(df.groupby("sample_id").peptide.nunique())
print("")
print("Counts by sample type:")
print(df.groupby("sample_type").peptide.nunique())
print("****************************")
dfs.append(df)
df = pandas.concat(dfs, ignore_index=True)
df.to_csv(args.out, index=False)
print("Wrote: %s" % args.out)
if __name__ == '__main__':
run()