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
188
189
190
191
192
193
194
195
196
197
198
199
|
# Genbank XML parser
from collections import namedtuple
import dateutil
from dateutil.parser import parse as dateparse
from dateutil.tz import gettz
import os
import re
import sys
import types
import xml.etree.ElementTree as ET
class GBError(Exception):
pass
"""
Example of an output JSON:
{
"id": "placeholder",
"host": {
"host_species": "http://purl.obolibrary.org/obo/NCBITaxon_9606"
},
"sample": {
"sample_id": "MT890462.1",
"source_database_accession": [
"http://identifiers.org/insdc/MT890462.1#sequence"
],
"collection_location": "http://www.wikidata.org/entity/Q649",
"collection_date": "2020-04-17",
"collecting_institution": "N.A.Kovtun Clinical Hospital 1 of Departament of President Affairs"
},
"virus": {
"virus_strain": "SARS-CoV-2/human/RUS/20200417_10/2020",
"virus_species": "http://purl.obolibrary.org/obo/NCBITaxon_2697049"
},
"technology": {
"assembly_method": "http://purl.obolibrary.org/obo/GENEPIO_0001628",
"alignment_protocol": "bowtie2 v. 2.3.4",
"sample_sequencing_technology": [
"http://purl.obolibrary.org/obo/OBI_0000759"
]
},
"submitter": {
"authors": [
"Blagodatskikh,K.A."
],
"submitter_name": [
"R&D"
],
"submitter_address": "Pirogov Russian National Research Medical University, Ostrovityanova 1, Moscow 117997, Russia"
}
}
Note: missing data should be None! Do not fill in other data by
'guessing'.
When data is malformed an warning should be issued.
"""
def get_metadata(id, gbseq):
host = types.SimpleNamespace()
sample = types.SimpleNamespace()
submitter = types.SimpleNamespace()
technology = types.SimpleNamespace()
warnings = []
def warn(msg):
print(f"WARNING: {msg}",file=sys.stderr)
warnings.append(msg)
def fetch(msg, xpath):
try:
n = gbseq.find(xpath).text
return n
except AttributeError:
warn("Missing "+msg)
host.host_species = "http://purl.obolibrary.org/obo/NCBITaxon_9606"
sample.sample_id = id
sample.database = "https://www.ncbi.nlm.nih.gov/genbank/"
sample.source_database_accession = f"http://identifiers.org/insdc/{id}#sequence"
# <GBQualifier>
# <GBQualifier_name>country</GBQualifier_name>
# <GBQualifier_value>USA: Cruise_Ship_1, California</GBQualifier_value>
# </GBQualifier>
sample.collection_location = "FIXME"
submitter.authors = [n.text for n in gbseq.findall(".//GBAuthor")]
# <GBReference_journal>Submitted (28-OCT-2020) MDU-PHL, The Peter
# Doherty Institute for Infection and Immunity, 792 Elizabeth
# Street, Melbourne, Vic 3000, Australia
# </GBReference_journal>
try:
n = gbseq.find(".//GBReference_journal").text
# print(n,file=sys.stderr)
if n != 'Unpublished':
institute,address = n.split(',',1)
submitter.submitter_name = institute.split(') ')[1]
submitter.submitter_address = address.strip()
except AttributeError:
pass
except ValueError:
submitter.additional_submitter_information = n
pass
try:
n = gbseq.find("./GBSeq_comment").text
except AttributeError:
pass
if 'Assembly-Data' in n:
# print(n,file=sys.stderr)
# the following is wrong (de novo by default)
# technology.assembly_method = 'http://purl.obolibrary.org/obo/GENEPIO_0001628'
p = re.compile(r'.*Assembly Method :: ([^;]+).*')
m = p.match(n)
if m: technology.alignment_protocol = m.group(1)
p = re.compile(r'.*Coverage :: ([^;]+).*')
m = p.match(n)
if m: technology.sequencing_coverage = m.group(1)
p = re.compile(r'.*Sequencing Technology :: ([^;]+).*')
m = p.match(n)
if m: technology.sample_sequencing_technology = m.group(1).strip()
# --- Dates
n = gbseq.find("./GBSeq_create-date")
creation_date = dateparse(n.text).date()
n = gbseq.find("./GBSeq_update-date")
update_date = dateparse(n.text).date()
n = gbseq.find(".//GBQualifier/GBQualifier_name/[.='collection_date']/../GBQualifier_value")
try:
date = dateparse(n.text).date()
sample.collection_date = str(date)
except dateutil.parser._parser.ParserError as e:
warn("No collection_date: ",str(e))
sample.collection_date = None
except AttributeError:
warn("Missing collection_date")
sample.collection_date = None
# --- Host info
# - Homo sapiens
# - Homo sapiens; female
# - Homo sapiens; female 63
# - Homo sapiens; female; age 40
# - Homo sapiens; gender: F; age: 61
# - Homo sapiens; gender: M; age: 68
# - Homo sapiens; hospitalized patient
# - Homo sapiens; male
# - Homo sapiens; male; 63
# - Homo sapiens; male; age 29
# - Homo sapiens; symptomatic
n = fetch("host_species", ".//GBQualifier/GBQualifier_name/[.='host']/../GBQualifier_value")
if n:
list = n.split('; ')
species = list[0]
host.host_species = species
if species != "Homo sapiens":
warn(f"Species not understood: {species}")
if len(list)>1:
sex = list[1]
if 'male' in sex or 'gender: M' in sex: host.host_sex = 'male'
if 'female' in sex or 'gender: F' in sex: host.host_sex = 'female'
if len(list)>2:
age = list[2]
p = re.compile(r'[^\d]+(\d+)')
m = p.match(n)
print(m.group(1))
if m:
host.host_age = int(m.group(1))
host.host_age_unit = 'http://purl.obolibrary.org/obo/UO_0000036'
# sys.exit(1)
info = {
'id': 'placeholder',
'update_date': str(update_date),
'host': host.__dict__,
'sample': sample.__dict__,
#'virus': virus,
'technology': technology.__dict__,
'submitter': submitter.__dict__,
'warnings': warnings,
}
print(info)
return True,info
def get_sequence(id, gbseq):
seq = None
count = 0
for gbseq_sequence in gbseq.findall('./GBSeq_sequence'):
count += 1
if count > 1:
raise GBError(f"Expected one sequence for {id}")
seq = gbseq_sequence.text.upper()
print(f"SEQ: size={len(seq)}",seq[0:30])
if len(seq) < 20_000:
raise GBError(f"Sequence too short")
return seq
|
