simple_bioc 0.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +18 -0
- data/Gemfile +4 -0
- data/LICENSE +20 -0
- data/LICENSE.txt +22 -0
- data/README.md +29 -0
- data/Rakefile +8 -0
- data/lib/simple_bioc/annotation.rb +11 -0
- data/lib/simple_bioc/bioc_reader.rb +102 -0
- data/lib/simple_bioc/bioc_writer.rb +93 -0
- data/lib/simple_bioc/collection.rb +15 -0
- data/lib/simple_bioc/document.rb +29 -0
- data/lib/simple_bioc/location.rb +10 -0
- data/lib/simple_bioc/node.rb +12 -0
- data/lib/simple_bioc/node_base.rb +14 -0
- data/lib/simple_bioc/passage.rb +29 -0
- data/lib/simple_bioc/relation.rb +14 -0
- data/lib/simple_bioc/sentence.rb +20 -0
- data/lib/simple_bioc/version.rb +3 -0
- data/lib/simple_bioc.rb +14 -0
- data/simple_bioc.gemspec +27 -0
- data/spec/simple_bioc_spec.rb +14 -0
- data/xml/BioC.dtd +146 -0
- data/xml/PMID-8557975-simplified-sentences-tokens.xml +492 -0
- data/xml/PMID-8557975-simplified-sentences.xml +49 -0
- data/xml/abbr.key +71 -0
- data/xml/abbr.xml +1 -0
- data/xml/ascii.key +29 -0
- data/xml/ascii.xml +3 -0
- data/xml/everything-sentence.xml +1 -0
- data/xml/everything.key +8 -0
- data/xml/everything.xml +1 -0
- data/xml/lemma.key +51 -0
- data/xml/lemma.xml +1 -0
- data/xml/pos.key +49 -0
- data/xml/pos.xml +1 -0
- data/xml/sentence.key +36 -0
- data/xml/sentence.xml +1 -0
- metadata +153 -0
data/xml/BioC.dtd
ADDED
|
@@ -0,0 +1,146 @@
|
|
|
1
|
+
<!-- Combination DTD that will work with any document so far. -->
|
|
2
|
+
|
|
3
|
+
<!--
|
|
4
|
+
|
|
5
|
+
Some believe XML is easily read by humans and that should be
|
|
6
|
+
supported by clearly formatting the elements. In the long run,
|
|
7
|
+
this is destracting. While the only meaningful spaces are in text
|
|
8
|
+
elements and the other spaces can be ignored, current tools add no
|
|
9
|
+
additional space. Formatters and editors may be used to make the
|
|
10
|
+
XML file appear more readable.
|
|
11
|
+
|
|
12
|
+
The possible variety of annotations that one might want to produce
|
|
13
|
+
or use is nearly countless. There is no guarantee that these are
|
|
14
|
+
organized in the nice nested structure required for XML
|
|
15
|
+
elements. Even if they were, it would be nice to more easily
|
|
16
|
+
ignore unwanted annotations. So annotations are recorded in a
|
|
17
|
+
stand off manner, external to the annotated text. The exceptions
|
|
18
|
+
are passages and sentences because of their fundamental place in
|
|
19
|
+
text.
|
|
20
|
+
|
|
21
|
+
The text is expected to be encoded in Unicode, specifically
|
|
22
|
+
utf-8. This is one of the encodings required to be implented by
|
|
23
|
+
XML tools, is portable between big-endian and little-endian
|
|
24
|
+
machines and is a superset of 7-bit ASCII. Code points beyond 127
|
|
25
|
+
may be expressed directly in utf-8 or indirectly using numeric
|
|
26
|
+
entities. Since many tools today still only directly process
|
|
27
|
+
ASCII characters, conversion should be available and
|
|
28
|
+
standardized. Offsets should be in 8 bit code units (bytes) for
|
|
29
|
+
easier processing by naive programs.
|
|
30
|
+
|
|
31
|
+
Nothing final. Just current thoughts.
|
|
32
|
+
|
|
33
|
+
collection: Group of documents, usually from a larger corpus. If
|
|
34
|
+
a group of documents is from several corpora, use several
|
|
35
|
+
collections.
|
|
36
|
+
|
|
37
|
+
source: Name of the source corpus from which the documents were selected
|
|
38
|
+
|
|
39
|
+
date: Date documents extracted from original source. Can be as
|
|
40
|
+
simple as yyyymmdd or an ISO timestamp.
|
|
41
|
+
|
|
42
|
+
key: Separate file describing the types used and any other useful
|
|
43
|
+
information about the data in the file. For example, if a file
|
|
44
|
+
includes part-of-speech tags, this file should describe the
|
|
45
|
+
part-of-speech tags used.
|
|
46
|
+
|
|
47
|
+
infon: key-value pairs. Can record essentially arbitrary
|
|
48
|
+
information. "type" will be a particular common key in the major
|
|
49
|
+
sub elements below. For PubMed references, passage "type" might
|
|
50
|
+
signal "title" or "abstract". For annotations, it might indicate
|
|
51
|
+
"noun phrase", "gene", or "disease". In the programming language
|
|
52
|
+
data structures, infons are typically represented as a map from
|
|
53
|
+
strings to strings. This means keys should be unique within each
|
|
54
|
+
parent element.
|
|
55
|
+
|
|
56
|
+
document: A document in the collection. A single, complete
|
|
57
|
+
stand-alone document as described by it's parent source.
|
|
58
|
+
|
|
59
|
+
id: Typically, the id of the document in the parent
|
|
60
|
+
source. Should at least be unique in the collection.
|
|
61
|
+
|
|
62
|
+
passage: One portion of the document. For now PubMed documents
|
|
63
|
+
have a title and an abstract. Structured abstracts could have
|
|
64
|
+
additional passages. For a full text document, passages could be
|
|
65
|
+
sections such as Introduction, Materials and Methods, or
|
|
66
|
+
Conclusion. Another option would be paragraphs. Passages impose a
|
|
67
|
+
linear structure on the document. Further structure in the
|
|
68
|
+
document can be implied by the infon["type"] value.
|
|
69
|
+
|
|
70
|
+
offset: Where the passage occurs in the parent document. Depending
|
|
71
|
+
on the source corpus, this might be a very relevant number. They
|
|
72
|
+
should be sequential and identify a passage's position in
|
|
73
|
+
the document. Since pubmed is extracted from an XML file, the
|
|
74
|
+
title has an offset of zero, while the abstract is assumed to
|
|
75
|
+
begin after the title and one space.
|
|
76
|
+
|
|
77
|
+
text: The original text of the passage.
|
|
78
|
+
|
|
79
|
+
sentence: One sentence of the passage.
|
|
80
|
+
|
|
81
|
+
offset: A document offset to where the sentence begins in the
|
|
82
|
+
passage. This value is the sum of the passage offset and the local
|
|
83
|
+
offset within the passage.
|
|
84
|
+
|
|
85
|
+
text: The original text of the sentence.
|
|
86
|
+
|
|
87
|
+
annotation: Stand-off annotation
|
|
88
|
+
|
|
89
|
+
id: Used to refer to this annotation in relations.
|
|
90
|
+
|
|
91
|
+
location: Location of the annotated text. Multiple locations
|
|
92
|
+
indicate a multi-span annotation.
|
|
93
|
+
|
|
94
|
+
offset: Document offset to where the annotated text begins in
|
|
95
|
+
the passage or sentence. The value is the sum of the passage or
|
|
96
|
+
sentence offset and the local offset within the passage or
|
|
97
|
+
sentence.
|
|
98
|
+
|
|
99
|
+
length: Length of the annotated text. While unlikely, this could
|
|
100
|
+
be zero to describe an annotation that belongs between two
|
|
101
|
+
characters.
|
|
102
|
+
|
|
103
|
+
text: Unless something else is defined one would be expect the
|
|
104
|
+
annotated text. The length is redundant in this case. Other uses
|
|
105
|
+
for this text could be the normalized ID for a gene in a gene
|
|
106
|
+
database.
|
|
107
|
+
|
|
108
|
+
relation: Relationship between multiple annotations.
|
|
109
|
+
|
|
110
|
+
id: Used to refer to this relation in other relationships.
|
|
111
|
+
|
|
112
|
+
refid: Id of an annotated object or other relation.
|
|
113
|
+
|
|
114
|
+
role: Describes how the referenced annotated object or other
|
|
115
|
+
relation participates in the current relationship. Has a default
|
|
116
|
+
value so can be left out if there is no meaningful value.
|
|
117
|
+
|
|
118
|
+
-->
|
|
119
|
+
|
|
120
|
+
<!ELEMENT collection ( source, date, key, infon*, document+ ) >
|
|
121
|
+
<!ELEMENT source (#PCDATA)>
|
|
122
|
+
<!ELEMENT date (#PCDATA)>
|
|
123
|
+
<!ELEMENT key (#PCDATA)>
|
|
124
|
+
<!ELEMENT infon (#PCDATA)>
|
|
125
|
+
<!ATTLIST infon key CDATA #REQUIRED >
|
|
126
|
+
|
|
127
|
+
<!ELEMENT document ( id, infon*, passage+, relation* ) >
|
|
128
|
+
<!ELEMENT id (#PCDATA)>
|
|
129
|
+
|
|
130
|
+
<!ELEMENT passage ( infon*, offset, ( ( text?, annotation* ) | sentence* ), relation* ) >
|
|
131
|
+
<!ELEMENT offset (#PCDATA)>
|
|
132
|
+
<!ELEMENT text (#PCDATA)>
|
|
133
|
+
|
|
134
|
+
<!ELEMENT sentence ( infon*, offset, text?, annotation*, relation* ) >
|
|
135
|
+
|
|
136
|
+
<!ELEMENT annotation ( infon*, location*, text ) >
|
|
137
|
+
<!ATTLIST annotation id CDATA #IMPLIED >
|
|
138
|
+
<!ELEMENT location EMPTY>
|
|
139
|
+
<!ATTLIST location offset CDATA #REQUIRED >
|
|
140
|
+
<!ATTLIST location length CDATA #REQUIRED >
|
|
141
|
+
|
|
142
|
+
<!ELEMENT relation ( infon*, node* ) >
|
|
143
|
+
<!ATTLIST relation id CDATA #IMPLIED >
|
|
144
|
+
<!ELEMENT node EMPTY>
|
|
145
|
+
<!ATTLIST node refid CDATA #REQUIRED >
|
|
146
|
+
<!ATTLIST node role CDATA "" >
|
|
@@ -0,0 +1,492 @@
|
|
|
1
|
+
<?xml version="1.0" encoding="utf-8"?>
|
|
2
|
+
<!DOCTYPE collection SYSTEM "BioC.dtd">
|
|
3
|
+
<collection>
|
|
4
|
+
<source>PubMed</source>
|
|
5
|
+
<date>20130316</date>
|
|
6
|
+
<key>PMID-8557975-simplified-sentences-tokens.key</key>
|
|
7
|
+
<document>
|
|
8
|
+
<id>8557975</id>
|
|
9
|
+
<passage>
|
|
10
|
+
<infon key="type">abstract</infon>
|
|
11
|
+
<offset>0</offset>
|
|
12
|
+
<sentence>
|
|
13
|
+
<infon key="type">original sentence</infon>
|
|
14
|
+
<offset>70</offset>
|
|
15
|
+
<annotation id="t0">
|
|
16
|
+
<infon key="type">token</infon>
|
|
17
|
+
<location offset="70" length="6"></location>
|
|
18
|
+
<text>Active</text>
|
|
19
|
+
</annotation>
|
|
20
|
+
<annotation id="t1">
|
|
21
|
+
<infon key="type">token</infon>
|
|
22
|
+
<location offset="77" length="5"></location>
|
|
23
|
+
<text>Raf-1</text>
|
|
24
|
+
</annotation>
|
|
25
|
+
<annotation id="t2">
|
|
26
|
+
<infon key="type">token</infon>
|
|
27
|
+
<location offset="83" length="14"></location>
|
|
28
|
+
<text>phosphorylates</text>
|
|
29
|
+
</annotation>
|
|
30
|
+
<annotation id="t3">
|
|
31
|
+
<infon key="type">token</infon>
|
|
32
|
+
<location offset="98" length="3"></location>
|
|
33
|
+
<text>and</text>
|
|
34
|
+
</annotation>
|
|
35
|
+
<annotation id="t4">
|
|
36
|
+
<infon key="type">token</infon>
|
|
37
|
+
<location offset="102" length="9"></location>
|
|
38
|
+
<text>activates</text>
|
|
39
|
+
</annotation>
|
|
40
|
+
<annotation id="t5">
|
|
41
|
+
<infon key="type">token</infon>
|
|
42
|
+
<location offset="112" length="3"></location>
|
|
43
|
+
<text>the</text>
|
|
44
|
+
</annotation>
|
|
45
|
+
<annotation id="t6">
|
|
46
|
+
<infon key="type">token</infon>
|
|
47
|
+
<location offset="116" length="17"></location>
|
|
48
|
+
<text>mitogen-activated</text>
|
|
49
|
+
</annotation>
|
|
50
|
+
<annotation id="t7">
|
|
51
|
+
<infon key="type">token</infon>
|
|
52
|
+
<location offset="134" length="7"></location>
|
|
53
|
+
<text>protein</text>
|
|
54
|
+
</annotation>
|
|
55
|
+
<annotation id="t8">
|
|
56
|
+
<infon key="type">token</infon>
|
|
57
|
+
<location offset="142" length="1"></location>
|
|
58
|
+
<text>(</text>
|
|
59
|
+
</annotation>
|
|
60
|
+
<annotation id="t9">
|
|
61
|
+
<infon key="type">token</infon>
|
|
62
|
+
<location offset="143" length="3"></location>
|
|
63
|
+
<text>MAP</text>
|
|
64
|
+
</annotation>
|
|
65
|
+
<annotation id="t10">
|
|
66
|
+
<infon key="type">token</infon>
|
|
67
|
+
<location offset="146" length="1"></location>
|
|
68
|
+
<text>)</text>
|
|
69
|
+
</annotation>
|
|
70
|
+
<annotation id="t11">
|
|
71
|
+
<infon key="type">token</infon>
|
|
72
|
+
<location offset="148" length="20"></location>
|
|
73
|
+
<text>kinase/extracellular</text>
|
|
74
|
+
</annotation>
|
|
75
|
+
<annotation id="t12">
|
|
76
|
+
<infon key="type">token</infon>
|
|
77
|
+
<location offset="169" length="16"></location>
|
|
78
|
+
<text>signal-regulated</text>
|
|
79
|
+
</annotation>
|
|
80
|
+
<annotation id="t13">
|
|
81
|
+
<infon key="type">token</infon>
|
|
82
|
+
<location offset="186" length="6"></location>
|
|
83
|
+
<text>kinase</text>
|
|
84
|
+
</annotation>
|
|
85
|
+
<annotation id="t14">
|
|
86
|
+
<infon key="type">token</infon>
|
|
87
|
+
<location offset="193" length="6"></location>
|
|
88
|
+
<text>kinase</text>
|
|
89
|
+
</annotation>
|
|
90
|
+
<annotation id="t15">
|
|
91
|
+
<infon key="type">token</infon>
|
|
92
|
+
<location offset="200" length="1"></location>
|
|
93
|
+
<text>1</text>
|
|
94
|
+
</annotation>
|
|
95
|
+
<annotation id="t16">
|
|
96
|
+
<infon key="type">token</infon>
|
|
97
|
+
<location offset="202" length="1"></location>
|
|
98
|
+
<text>(</text>
|
|
99
|
+
</annotation>
|
|
100
|
+
<annotation id="t17">
|
|
101
|
+
<infon key="type">token</infon>
|
|
102
|
+
<location offset="203" length="4"></location>
|
|
103
|
+
<text>MEK1</text>
|
|
104
|
+
</annotation>
|
|
105
|
+
<annotation id="t18">
|
|
106
|
+
<infon key="type">token</infon>
|
|
107
|
+
<location offset="207" length="1"></location>
|
|
108
|
+
<text>)</text>
|
|
109
|
+
</annotation>
|
|
110
|
+
<annotation id="t19">
|
|
111
|
+
<infon key="type">token</infon>
|
|
112
|
+
<location offset="208" length="1"></location>
|
|
113
|
+
<text>,</text>
|
|
114
|
+
</annotation>
|
|
115
|
+
<annotation id="t20">
|
|
116
|
+
<infon key="type">token</infon>
|
|
117
|
+
<location offset="210" length="5"></location>
|
|
118
|
+
<text>which</text>
|
|
119
|
+
</annotation>
|
|
120
|
+
<annotation id="t21">
|
|
121
|
+
<infon key="type">token</infon>
|
|
122
|
+
<location offset="216" length="2"></location>
|
|
123
|
+
<text>in</text>
|
|
124
|
+
</annotation>
|
|
125
|
+
<annotation id="t22">
|
|
126
|
+
<infon key="type">token</infon>
|
|
127
|
+
<location offset="219" length="4"></location>
|
|
128
|
+
<text>turn</text>
|
|
129
|
+
</annotation>
|
|
130
|
+
<annotation id="t23">
|
|
131
|
+
<infon key="type">token</infon>
|
|
132
|
+
<location offset="224" length="14"></location>
|
|
133
|
+
<text>phosphorylates</text>
|
|
134
|
+
</annotation>
|
|
135
|
+
<annotation id="t24">
|
|
136
|
+
<infon key="type">token</infon>
|
|
137
|
+
<location offset="239" length="3"></location>
|
|
138
|
+
<text>and</text>
|
|
139
|
+
</annotation>
|
|
140
|
+
<annotation id="t25">
|
|
141
|
+
<infon key="type">token</infon>
|
|
142
|
+
<location offset="243" length="9"></location>
|
|
143
|
+
<text>activates</text>
|
|
144
|
+
</annotation>
|
|
145
|
+
<annotation id="t26">
|
|
146
|
+
<infon key="type">token</infon>
|
|
147
|
+
<location offset="253" length="3"></location>
|
|
148
|
+
<text>the</text>
|
|
149
|
+
</annotation>
|
|
150
|
+
<annotation id="t27">
|
|
151
|
+
<infon key="type">token</infon>
|
|
152
|
+
<location offset="257" length="3"></location>
|
|
153
|
+
<text>MAP</text>
|
|
154
|
+
</annotation>
|
|
155
|
+
<annotation id="t28">
|
|
156
|
+
<infon key="type">token</infon>
|
|
157
|
+
<location offset="261" length="21"></location>
|
|
158
|
+
<text>kinases/extracellular</text>
|
|
159
|
+
</annotation>
|
|
160
|
+
<annotation id="t29">
|
|
161
|
+
<infon key="type">token</infon>
|
|
162
|
+
<location offset="283" length="6"></location>
|
|
163
|
+
<text>signal</text>
|
|
164
|
+
</annotation>
|
|
165
|
+
<annotation id="t30">
|
|
166
|
+
<infon key="type">token</infon>
|
|
167
|
+
<location offset="290" length="9"></location>
|
|
168
|
+
<text>regulated</text>
|
|
169
|
+
</annotation>
|
|
170
|
+
<annotation id="t31">
|
|
171
|
+
<infon key="type">token</infon>
|
|
172
|
+
<location offset="300" length="7"></location>
|
|
173
|
+
<text>kinases</text>
|
|
174
|
+
</annotation>
|
|
175
|
+
<annotation id="t32">
|
|
176
|
+
<infon key="type">token</infon>
|
|
177
|
+
<location offset="307" length="1"></location>
|
|
178
|
+
<text>,</text>
|
|
179
|
+
</annotation>
|
|
180
|
+
<annotation id="t33">
|
|
181
|
+
<infon key="type">token</infon>
|
|
182
|
+
<location offset="309" length="4"></location>
|
|
183
|
+
<text>ERK1</text>
|
|
184
|
+
</annotation>
|
|
185
|
+
<annotation id="t34">
|
|
186
|
+
<infon key="type">token</infon>
|
|
187
|
+
<location offset="314" length="3"></location>
|
|
188
|
+
<text>and</text>
|
|
189
|
+
</annotation>
|
|
190
|
+
<annotation id="t35">
|
|
191
|
+
<infon key="type">token</infon>
|
|
192
|
+
<location offset="318" length="4"></location>
|
|
193
|
+
<text>ERK2</text>
|
|
194
|
+
</annotation>
|
|
195
|
+
<annotation id="t36">
|
|
196
|
+
<infon key="type">token</infon>
|
|
197
|
+
<location offset="322" length="1"></location>
|
|
198
|
+
<text>.</text>
|
|
199
|
+
</annotation>
|
|
200
|
+
</sentence>
|
|
201
|
+
<sentence>
|
|
202
|
+
<infon key="type">simplified sentence</infon>
|
|
203
|
+
<offset>325</offset>
|
|
204
|
+
<annotation id="t37">
|
|
205
|
+
<infon key="type">token</infon>
|
|
206
|
+
<location offset="325" length="6"></location>
|
|
207
|
+
<text>Active</text>
|
|
208
|
+
</annotation>
|
|
209
|
+
<annotation id="t38">
|
|
210
|
+
<infon key="type">token</infon>
|
|
211
|
+
<location offset="332" length="5"></location>
|
|
212
|
+
<text>Raf-1</text>
|
|
213
|
+
</annotation>
|
|
214
|
+
<annotation id="t39">
|
|
215
|
+
<infon key="type">token</infon>
|
|
216
|
+
<location offset="338" length="14"></location>
|
|
217
|
+
<text>phosphorylates</text>
|
|
218
|
+
</annotation>
|
|
219
|
+
<annotation id="t40">
|
|
220
|
+
<infon key="type">token</infon>
|
|
221
|
+
<location offset="353" length="4"></location>
|
|
222
|
+
<text>MEK1</text>
|
|
223
|
+
</annotation>
|
|
224
|
+
<annotation id="t41">
|
|
225
|
+
<infon key="type">token</infon>
|
|
226
|
+
<location offset="357" length="1"></location>
|
|
227
|
+
<text>.</text>
|
|
228
|
+
</annotation>
|
|
229
|
+
</sentence>
|
|
230
|
+
<sentence>
|
|
231
|
+
<infon key="type">simplified sentence</infon>
|
|
232
|
+
<offset>360</offset>
|
|
233
|
+
<annotation id="t42">
|
|
234
|
+
<infon key="type">token</infon>
|
|
235
|
+
<location offset="360" length="6"></location>
|
|
236
|
+
<text>Active</text>
|
|
237
|
+
</annotation>
|
|
238
|
+
<annotation id="t43">
|
|
239
|
+
<infon key="type">token</infon>
|
|
240
|
+
<location offset="367" length="5"></location>
|
|
241
|
+
<text>Raf-1</text>
|
|
242
|
+
</annotation>
|
|
243
|
+
<annotation id="t44">
|
|
244
|
+
<infon key="type">token</infon>
|
|
245
|
+
<location offset="373" length="9"></location>
|
|
246
|
+
<text>activates</text>
|
|
247
|
+
</annotation>
|
|
248
|
+
<annotation id="t45">
|
|
249
|
+
<infon key="type">token</infon>
|
|
250
|
+
<location offset="383" length="4"></location>
|
|
251
|
+
<text>MEK1</text>
|
|
252
|
+
</annotation>
|
|
253
|
+
<annotation id="t46">
|
|
254
|
+
<infon key="type">token</infon>
|
|
255
|
+
<location offset="387" length="1"></location>
|
|
256
|
+
<text>.</text>
|
|
257
|
+
</annotation>
|
|
258
|
+
</sentence>
|
|
259
|
+
<sentence>
|
|
260
|
+
<infon key="type">simplified sentence</infon>
|
|
261
|
+
<offset>390</offset>
|
|
262
|
+
<annotation id="t47">
|
|
263
|
+
<infon key="type">token</infon>
|
|
264
|
+
<location offset="390" length="4"></location>
|
|
265
|
+
<text>MEK1</text>
|
|
266
|
+
</annotation>
|
|
267
|
+
<annotation id="t48">
|
|
268
|
+
<infon key="type">token</infon>
|
|
269
|
+
<location offset="395" length="2"></location>
|
|
270
|
+
<text>in</text>
|
|
271
|
+
</annotation>
|
|
272
|
+
<annotation id="t49">
|
|
273
|
+
<infon key="type">token</infon>
|
|
274
|
+
<location offset="398" length="4"></location>
|
|
275
|
+
<text>turn</text>
|
|
276
|
+
</annotation>
|
|
277
|
+
<annotation id="t50">
|
|
278
|
+
<infon key="type">token</infon>
|
|
279
|
+
<location offset="403" length="14"></location>
|
|
280
|
+
<text>phosphorylates</text>
|
|
281
|
+
</annotation>
|
|
282
|
+
<annotation id="t51">
|
|
283
|
+
<infon key="type">token</infon>
|
|
284
|
+
<location offset="418" length="4"></location>
|
|
285
|
+
<text>ERK1</text>
|
|
286
|
+
</annotation>
|
|
287
|
+
<annotation id="t52">
|
|
288
|
+
<infon key="type">token</infon>
|
|
289
|
+
<location offset="422" length="1"></location>
|
|
290
|
+
<text>.</text>
|
|
291
|
+
</annotation>
|
|
292
|
+
</sentence>
|
|
293
|
+
<sentence>
|
|
294
|
+
<infon key="type">simplified sentence</infon>
|
|
295
|
+
<offset>425</offset>
|
|
296
|
+
<annotation id="t53">
|
|
297
|
+
<infon key="type">token</infon>
|
|
298
|
+
<location offset="425" length="4"></location>
|
|
299
|
+
<text>MEK1</text>
|
|
300
|
+
</annotation>
|
|
301
|
+
<annotation id="t54">
|
|
302
|
+
<infon key="type">token</infon>
|
|
303
|
+
<location offset="430" length="2"></location>
|
|
304
|
+
<text>in</text>
|
|
305
|
+
</annotation>
|
|
306
|
+
<annotation id="t55">
|
|
307
|
+
<infon key="type">token</infon>
|
|
308
|
+
<location offset="433" length="4"></location>
|
|
309
|
+
<text>turn</text>
|
|
310
|
+
</annotation>
|
|
311
|
+
<annotation id="t56">
|
|
312
|
+
<infon key="type">token</infon>
|
|
313
|
+
<location offset="438" length="14"></location>
|
|
314
|
+
<text>phosphorylates</text>
|
|
315
|
+
</annotation>
|
|
316
|
+
<annotation id="t57">
|
|
317
|
+
<infon key="type">token</infon>
|
|
318
|
+
<location offset="453" length="4"></location>
|
|
319
|
+
<text>ERK2</text>
|
|
320
|
+
</annotation>
|
|
321
|
+
<annotation id="t58">
|
|
322
|
+
<infon key="type">token</infon>
|
|
323
|
+
<location offset="457" length="1"></location>
|
|
324
|
+
<text>.</text>
|
|
325
|
+
</annotation>
|
|
326
|
+
</sentence>
|
|
327
|
+
<sentence>
|
|
328
|
+
<infon key="type">simplified sentence</infon>
|
|
329
|
+
<offset>460</offset>
|
|
330
|
+
<annotation id="t59">
|
|
331
|
+
<infon key="type">token</infon>
|
|
332
|
+
<location offset="460" length="4"></location>
|
|
333
|
+
<text>MEK1</text>
|
|
334
|
+
</annotation>
|
|
335
|
+
<annotation id="t60">
|
|
336
|
+
<infon key="type">token</infon>
|
|
337
|
+
<location offset="465" length="2"></location>
|
|
338
|
+
<text>in</text>
|
|
339
|
+
</annotation>
|
|
340
|
+
<annotation id="t61">
|
|
341
|
+
<infon key="type">token</infon>
|
|
342
|
+
<location offset="468" length="4"></location>
|
|
343
|
+
<text>turn</text>
|
|
344
|
+
</annotation>
|
|
345
|
+
<annotation id="t62">
|
|
346
|
+
<infon key="type">token</infon>
|
|
347
|
+
<location offset="473" length="9"></location>
|
|
348
|
+
<text>activates</text>
|
|
349
|
+
</annotation>
|
|
350
|
+
<annotation id="t63">
|
|
351
|
+
<infon key="type">token</infon>
|
|
352
|
+
<location offset="483" length="4"></location>
|
|
353
|
+
<text>ERK1</text>
|
|
354
|
+
</annotation>
|
|
355
|
+
<annotation id="t64">
|
|
356
|
+
<infon key="type">token</infon>
|
|
357
|
+
<location offset="487" length="1"></location>
|
|
358
|
+
<text>.</text>
|
|
359
|
+
</annotation>
|
|
360
|
+
</sentence>
|
|
361
|
+
<sentence>
|
|
362
|
+
<infon key="type">simplified sentence</infon>
|
|
363
|
+
<offset>489</offset>
|
|
364
|
+
<annotation id="t65">
|
|
365
|
+
<infon key="type">token</infon>
|
|
366
|
+
<location offset="489" length="4"></location>
|
|
367
|
+
<text>MEK1</text>
|
|
368
|
+
</annotation>
|
|
369
|
+
<annotation id="t66">
|
|
370
|
+
<infon key="type">token</infon>
|
|
371
|
+
<location offset="494" length="2"></location>
|
|
372
|
+
<text>in</text>
|
|
373
|
+
</annotation>
|
|
374
|
+
<annotation id="t67">
|
|
375
|
+
<infon key="type">token</infon>
|
|
376
|
+
<location offset="497" length="4"></location>
|
|
377
|
+
<text>turn</text>
|
|
378
|
+
</annotation>
|
|
379
|
+
<annotation id="t68">
|
|
380
|
+
<infon key="type">token</infon>
|
|
381
|
+
<location offset="502" length="9"></location>
|
|
382
|
+
<text>activates</text>
|
|
383
|
+
</annotation>
|
|
384
|
+
<annotation id="t69">
|
|
385
|
+
<infon key="type">token</infon>
|
|
386
|
+
<location offset="512" length="4"></location>
|
|
387
|
+
<text>ERK2</text>
|
|
388
|
+
</annotation>
|
|
389
|
+
<annotation id="t70">
|
|
390
|
+
<infon key="type">token</infon>
|
|
391
|
+
<location offset="516" length="1"></location>
|
|
392
|
+
<text>.</text>
|
|
393
|
+
</annotation>
|
|
394
|
+
</sentence>
|
|
395
|
+
<!-- equ -->
|
|
396
|
+
<!-- Active -->
|
|
397
|
+
<relation id="r0">
|
|
398
|
+
<infon key="type">equ</infon>
|
|
399
|
+
<node refid="t0" role="original"></node>
|
|
400
|
+
<node refid="t37" role="simplified"></node>
|
|
401
|
+
<node refid="t42" role="simplified"></node>
|
|
402
|
+
</relation>
|
|
403
|
+
<!-- RAF-1 -->
|
|
404
|
+
<relation id="r1">
|
|
405
|
+
<infon key="type">equ</infon>
|
|
406
|
+
<node refid="t1" role="original"></node>
|
|
407
|
+
<node refid="t38" role="simplified"></node>
|
|
408
|
+
<node refid="t43" role="simplified"></node>
|
|
409
|
+
</relation>
|
|
410
|
+
<!-- phosphorylates -->
|
|
411
|
+
<relation id="r2">
|
|
412
|
+
<infon key="type">equ</infon>
|
|
413
|
+
<node refid="t2" role="original"></node>
|
|
414
|
+
<node refid="t39" role="simplified"></node>
|
|
415
|
+
</relation>
|
|
416
|
+
<!-- MEK1 -->
|
|
417
|
+
<relation id="r3">
|
|
418
|
+
<infon key="type">equ</infon>
|
|
419
|
+
<node refid="t17" role="original"></node>
|
|
420
|
+
<node refid="t40" role="simplified"></node>
|
|
421
|
+
<node refid="t45" role="simplified"></node>
|
|
422
|
+
<node refid="t47" role="simplified"></node>
|
|
423
|
+
<node refid="t53" role="simplified"></node>
|
|
424
|
+
<node refid="t59" role="simplified"></node>
|
|
425
|
+
<node refid="t65" role="simplified"></node>
|
|
426
|
+
</relation>
|
|
427
|
+
<!-- . -->
|
|
428
|
+
<relation id="r4">
|
|
429
|
+
<infon key="type">equ</infon>
|
|
430
|
+
<node refid="t36" role="original"></node>
|
|
431
|
+
<node refid="t41" role="simplified"></node>
|
|
432
|
+
<node refid="t46" role="simplified"></node>
|
|
433
|
+
<node refid="t52" role="simplified"></node>
|
|
434
|
+
<node refid="t58" role="simplified"></node>
|
|
435
|
+
<node refid="t64" role="simplified"></node>
|
|
436
|
+
<node refid="t70" role="simplified"></node>
|
|
437
|
+
</relation>
|
|
438
|
+
<!-- activates -->
|
|
439
|
+
<relation id="r5">
|
|
440
|
+
<infon key="type">equ</infon>
|
|
441
|
+
<node refid="t4" role="original"></node>
|
|
442
|
+
<node refid="t44" role="simplified"></node>
|
|
443
|
+
</relation>
|
|
444
|
+
<!-- in -->
|
|
445
|
+
<relation id="r6">
|
|
446
|
+
<infon key="type">equ</infon>
|
|
447
|
+
<node refid="t21" role="original"></node>
|
|
448
|
+
<node refid="t48" role="simplified"></node>
|
|
449
|
+
<node refid="t54" role="simplified"></node>
|
|
450
|
+
<node refid="t60" role="simplified"></node>
|
|
451
|
+
<node refid="t66" role="simplified"></node>
|
|
452
|
+
</relation>
|
|
453
|
+
<!-- turn -->
|
|
454
|
+
<relation id="r7">
|
|
455
|
+
<infon key="type">equ</infon>
|
|
456
|
+
<node refid="t22" role="original"></node>
|
|
457
|
+
<node refid="t49" role="simplified"></node>
|
|
458
|
+
<node refid="t55" role="simplified"></node>
|
|
459
|
+
<node refid="t61" role="simplified"></node>
|
|
460
|
+
<node refid="t67" role="simplified"></node>
|
|
461
|
+
</relation>
|
|
462
|
+
<!-- phosphorylates -->
|
|
463
|
+
<relation id="r8">
|
|
464
|
+
<infon key="type">equ</infon>
|
|
465
|
+
<node refid="t23" role="original"></node>
|
|
466
|
+
<node refid="t50" role="simplified"></node>
|
|
467
|
+
<node refid="t56" role="simplified"></node>
|
|
468
|
+
</relation>
|
|
469
|
+
<!-- ERK1 -->
|
|
470
|
+
<relation id="r9">
|
|
471
|
+
<infon key="type">equ</infon>
|
|
472
|
+
<node refid="t33" role="original"></node>
|
|
473
|
+
<node refid="t51" role="simplified"></node>
|
|
474
|
+
<node refid="t63" role="simplified"></node>
|
|
475
|
+
</relation>
|
|
476
|
+
<!-- ERK2 -->
|
|
477
|
+
<relation id="r10">
|
|
478
|
+
<infon key="type">equ</infon>
|
|
479
|
+
<node refid="t35" role="original"></node>
|
|
480
|
+
<node refid="t57" role="simplified"></node>
|
|
481
|
+
<node refid="t69" role="simplified"></node>
|
|
482
|
+
</relation>
|
|
483
|
+
<!-- activates -->
|
|
484
|
+
<relation id="r11">
|
|
485
|
+
<infon key="type">equ</infon>
|
|
486
|
+
<node refid="t25" role="original"></node>
|
|
487
|
+
<node refid="t62" role="simplified"></node>
|
|
488
|
+
<node refid="t68" role="simplified"></node>
|
|
489
|
+
</relation>
|
|
490
|
+
</passage>
|
|
491
|
+
</document>
|
|
492
|
+
</collection>
|