[Bio] / Sprout / SproutDBD.xml Repository:
ViewVC logotype

Annotation of /Sprout/SproutDBD.xml

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.18 - (view) (download) (as text)

1 : parrello 1.1 <?xml version="1.0" encoding="utf-8" ?>
2 :     <Database>
3 :     <Title>Sprout Genome and Subsystem Database</Title>
4 :     <Entities>
5 :     <Entity name="Genome" keyType="name-string">
6 :     <Notes>A [i]genome[/i] contains the sequence data for a particular individual organism.</Notes>
7 :     <Fields>
8 :     <Field name="genus" type="name-string">
9 :     <Notes>Genus of the relevant organism.</Notes>
10 :     <DataGen pass="1">RandParam('streptococcus', 'staphyloccocus', 'felis', 'homo', 'ficticio', 'strangera', 'escherischia', 'carborunda')</DataGen>
11 :     </Field>
12 :     <Field name="species" type="name-string">
13 : parrello 1.8 <Notes>Species of the relevant organism.</Notes>
14 : parrello 1.1 <DataGen pass="1">StringGen('PKVKVKVKVKV')</DataGen>
15 : parrello 1.8 </Field>
16 : parrello 1.1 <Field name="unique-characterization" type="medium-string">
17 : parrello 1.8 <Notes>The unique characterization identifies the particular organism instance from which the
18 :     genome is taken. It is possible to have in the database more than one genome for a
19 : parrello 1.1 particular species, and every individual organism has variations in its DNA.</Notes>
20 : parrello 1.8 <DataGen>StringGen('PKVKVK999')</DataGen>
21 : parrello 1.1 </Field>
22 :     <Field name="access-code" type="key-string">
23 : parrello 1.8 <Notes>The access code determines which users can look at the data relating to this genome.
24 :     Each user is associated with a set of access codes. In order to view a genome, one of
25 :     the user's access codes must match this value.</Notes>
26 :     <DataGen>RandParam('low','medium','high')</DataGen>
27 :     </Field>
28 : parrello 1.15 <Field name="complete" type="boolean">
29 :     <Notes>TRUE if the genome is complete, else FALSE</Notes>
30 :     </Field>
31 : parrello 1.8 <Field name="taxonomy" type="text">
32 :     <Notes>The taxonomy string contains the full taxonomy of the organism, while individual elements
33 :     separated by semi-colons (and optional white space), starting with the domain and ending with
34 :     the disambiguated genus and species (which is the organism's scientific name plus an
35 :     identifying string).</Notes>
36 :     <DataGen pass="2">join('; ', (RandParam('bacteria', 'archaea', 'eukaryote', 'virus', 'environmental'),
37 :     ListGen('PKVKVKVK', 5), $this->{genus}, $this->{species}))</DataGen>
38 :     </Field>
39 :     <Field name="group-name" type="name-string" relation="GenomeGroups">
40 :     <Notes>The group identifies a special grouping of organisms that would be displayed on a particular
41 :     page or of particular interest to a research group or web site. A single genome can belong to multiple
42 :     such groups or none at all.</Notes>
43 :     </Field>
44 : parrello 1.1 </Fields>
45 :     <Indexes>
46 :     <Index>
47 :     <Notes>This index allows the applications to find all genomes associated with
48 :     a specific access code, so that a complete list of the genomes users can view
49 :     may be generated.</Notes>
50 :     <IndexFields>
51 :     <IndexField name="access-code" order="ascending" />
52 :     <IndexField name="genus" order="ascending" />
53 :     <IndexField name="species" order="ascending" />
54 :     <IndexField name="unique-characterization" order="ascending" />
55 :     </IndexFields>
56 :     </Index>
57 :     <Index Unique="false">
58 :     <Notes>This index allows the applications to find all genomes for a particular
59 :     species.</Notes>
60 :     <IndexFields>
61 :     <IndexField name="genus" order="ascending" />
62 :     <IndexField name="species" order="ascending" />
63 :     <IndexField name="unique-characterization" order="ascending" />
64 :     </IndexFields>
65 :     </Index>
66 :     </Indexes>
67 :     </Entity>
68 :     <Entity name="Source" keyType="medium-string">
69 :     <Notes>A [i]source[/i] describes a place from which genome data was taken. This can be an organization
70 :     or a paper citation.</Notes>
71 :     <Fields>
72 :     <Field name="URL" type="string" relation="SourceURL">
73 : parrello 1.8 <Notes>URL the paper cited or of the organization's web site. This field optional.</Notes>
74 :     <DataGen>"http://www.conservativecat.com/Ferdy/TestTarget.php?Source=" . $this->{id}</DataGen>
75 :     </Field>
76 : parrello 1.1 <Field name="description" type="text">
77 : parrello 1.8 <Notes>Description the source. The description can be a street address or a citation.</Notes>
78 :     <DataGen>$this->{id} . ': ' . StringGen(IntGen(50,200))</DataGen>
79 :     </Field>
80 : parrello 1.1 </Fields>
81 :     </Entity>
82 :     <Entity name="Contig" keyType="name-string">
83 :     <Notes>A [i]contig[/i] is a contiguous run of residues. The contig's ID consists of the
84 :     genome ID followed by a name that identifies which contig this is for the parent genome. As
85 :     is the case with all keys in this database, the individual components are separated by a
86 :     period.
87 :     [p]A contig can contain over a million residues. For performance reasons, therefore,
88 :     the contig is split into multiple pieces called [i]sequences[/i]. The sequences
89 :     contain the characters that represent the residues as well as data on the quality of
90 :     the residue identification.</Notes>
91 :     </Entity>
92 :     <Entity name="Sequence" keyType="name-string">
93 :     <Notes>A [i]sequence[/i] is a continuous piece of a [i]contig[/i]. Contigs are split into
94 :     sequences so that we don't have to have the entire contig in memory when we are
95 :     manipulating it. The key of the sequence is the contig ID followed by the index of
96 :     the begin point.</Notes>
97 :     <Fields>
98 :     <Field name="sequence" type="text">
99 : parrello 1.8 <Notes>String consisting of the residues. Each residue is described by a single
100 :     character in the string.</Notes>
101 :     <DataGen>RandChars("ACGT", IntGen(100,400))</DataGen>
102 :     </Field>
103 : parrello 1.1 <Field name="quality-vector" type="text">
104 : parrello 1.9 <Notes>String describing the quality data for each base pair. Individual values will
105 : parrello 1.8 be separated by periods. The value represents negative exponent of the probability
106 :     of error. Thus, for example, a quality of 30 indicates the probability of error is
107 :     10^-30. A higher quality number a better chance of a correct match. It is possible
108 : parrello 1.9 that the quality data is not known for a sequence. If that is the case, the quality
109 : parrello 1.8 vector will contain the [b]unknown[/b].</Notes>
110 :     <DataGen>unknown</DataGen>
111 :     </Field>
112 : parrello 1.1 </Fields>
113 :     </Entity>
114 :     <Entity name="Feature" keyType="name-string">
115 :     <Notes>A [i]feature[/i] is a part of a genome that is of special interest. Features
116 :     may be spread across multiple contigs of a genome, but never across more than
117 :     one genome. Features can be assigned to roles via spreadsheet cells,
118 :     and are the targets of annotation.</Notes>
119 :     <Fields>
120 :     <Field name="feature-type" type="string">
121 : parrello 1.8 <Notes>Code indicating the type of this feature.</Notes>
122 :     <DataGen>RandParam('peg','rna')</DataGen>
123 :     </Field>
124 : parrello 1.14 <Field name="alias" type="medium-string" relation="FeatureAlias">
125 : parrello 1.9 <Notes>Alternative name for this feature. A feature can have many aliases.</Notes>
126 : parrello 1.8 <DataGen testCount="3">StringGen('Pgi|99999', 'Puni|XXXXXX', 'PAAAAAA999')</DataGen>
127 :     </Field>
128 : parrello 1.1 <Field name="translation" type="text" relation="FeatureTranslation">
129 : parrello 1.8 <Notes>[i](optional)[/i] A translation of this feature's residues into character
130 :     codes, formed by concatenating the pieces of the feature together. For a
131 :     protein encoding group, this is the protein characters. For other types
132 :     it is the DNA characters.</Notes>
133 :     <DataGen testCount="0"></DataGen>
134 :     </Field>
135 : parrello 1.1 <Field name="upstream-sequence" type="text" relation="FeatureUpstream">
136 : parrello 1.8 <Notes>Upstream sequence the feature. This includes residues preceding the feature as well as some of
137 :     the feature's initial residues.</Notes>
138 :     <DataGen testCount="0"></DataGen>
139 :     </Field>
140 : parrello 1.1 <Field name="active" type="boolean">
141 : parrello 1.11 <Notes>TRUE if this feature is still considered valid, FALSE if it has been logically deleted.</Notes>
142 : parrello 1.8 <DataGen>1</DataGen>
143 :     </Field>
144 :     <Field name="link" type="text" relation="FeatureLink">
145 :     <Notes>Web hyperlink for this feature. A feature have no hyperlinks or it can have many. The
146 :     links are to other websites that have useful about the gene that the feature represents, and
147 :     are coded as raw HTML, using [b]&lt;a href="[i]link[/i]"&gt;[i]text[/i]&lt;/a&gt;[/b] notation.</Notes>
148 :     <DataGen testCount="3">'http://www.conservativecat.com/Ferdy/TestTarget.php?Source=' . $this->{id} .
149 :     "&amp;Number=" . IntGen(1,99)</DataGen>
150 :     </Field>
151 : parrello 1.1 </Fields>
152 : parrello 1.8 <Indexes>
153 :     <Index>
154 :     <Notes>This index allows the user to find the feature corresponding to
155 :     the specified alias name.</Notes>
156 :     <IndexFields>
157 :     <IndexField name="alias" order="ascending" />
158 :     </IndexFields>
159 :     </Index>
160 :     </Indexes>
161 : parrello 1.1 </Entity>
162 :     <Entity name="Role" keyType="string">
163 :     <Notes>A [i]role[/i] describes a biological function that may be fulfilled by a feature.
164 :     One of the main goals of the database is to record the roles of the various features.</Notes>
165 : parrello 1.8 <Fields>
166 : parrello 1.18 <Field name="EC" type="string" relation="RoleEC">
167 :     <Notes>EC code for this role.</Notes>
168 : parrello 1.8 <DataGen testCount="1">StringGen(IntGen(20,40)) . "(" . $this->{id} . ")"</DataGen>
169 :     </Field>
170 : parrello 1.15 <Field name="abbr" type="name-string">
171 :     <Notes>Abbreviated name for the role, generally non-unique, but useful
172 :     in column headings for HTML tables.</Notes>
173 :     </Field>
174 : parrello 1.8 </Fields>
175 : parrello 1.18 <Indexes>
176 :     <Index>
177 :     <Notes>This index allows the user to find the role corresponding to
178 :     an EC number.</Notes>
179 :     <IndexFields>
180 :     <IndexField name="EC" order="ascending" />
181 :     </IndexFields>
182 :     </Index>
183 :     </Indexes>
184 : parrello 1.1 </Entity>
185 :     <Entity name="Annotation" keyType="name-string">
186 :     <Notes>An [i]annotation[/i] contains supplementary information about a feature. Annotations
187 : parrello 1.8 are currently the only objects that may be inserted directly into the database. All other
188 :     information is loaded from data exported by the SEED.
189 :     [p]Each annotation is associated with a target [b]Feature[/b]. The key of the annotation
190 :     is the target feature ID followed by a timestamp.</Notes>
191 :     <Fields>
192 :     <Field name="time" type="date">
193 :     <Notes>Date and time of the annotation.</Notes>
194 :     </Field>
195 :     <Field name="annotation" type="text">
196 :     <Notes>Text of the annotation.</Notes>
197 :     </Field>
198 : parrello 1.1 </Fields>
199 :     </Entity>
200 : parrello 1.15 <Entity name="Reaction" keyType="key-string">
201 :     <Notes>A [i]reaction[/i] is a chemical process catalyzed by a protein. The reaction ID
202 :     is generally a small number preceded by a letter.</Notes>
203 :     <Fields>
204 :     <Field name="url" type="string" relation="ReactionURL">
205 :     <Notes>HTML string containing a link to a web location that describes the
206 :     reaction. This field is optional.</Notes>
207 :     </Field>
208 :     <Field name="rev" type="boolean">
209 :     <Notes>TRUE if this reaction is reversible, else FALSE</Notes>
210 :     </Field>
211 :     </Fields>
212 :     </Entity>
213 :     <Entity name="Compound" keyType="name-string">
214 :     <Notes>A [i]compound[/i] is a chemical that participates in a reaction.
215 :     All compounds have a unique ID and may also have one or more names.</Notes>
216 :     <Fields>
217 :     <Field name="name-priority" type="int" relation="CompoundName">
218 :     <Notes>Priority of a compound name. The name with the loweset
219 :     priority is the main name of this compound.</Notes>
220 :     </Field>
221 :     <Field name="name" type="name-string" relation="CompoundName">
222 :     <Notes>Descriptive name for the compound. A compound may
223 :     have several names.</Notes>
224 :     </Field>
225 :     <Field name="cas-id" type="name-string" relation="CompoundCAS">
226 :     <Notes>Chemical Abstract Service ID for this compound (optional).</Notes>
227 :     </Field>
228 :     </Fields>
229 :     <Indexes>
230 :     <Index>
231 :     <Notes>This index allows the user to find the compound corresponding to
232 :     the specified name.</Notes>
233 :     <IndexFields>
234 :     <IndexField name="name" order="ascending" />
235 :     </IndexFields>
236 :     </Index>
237 :     <Index>
238 : parrello 1.17 <Notes>This index allows the user to find the compound corresponding to
239 :     the specified CAS ID.</Notes>
240 :     <IndexFields>
241 :     <IndexField name="cas-id" order="ascending" />
242 :     </IndexFields>
243 :     </Index>
244 :     <Index>
245 : parrello 1.15 <Notes>This index allows the user to access the compound names in
246 :     priority order.</Notes>
247 :     <IndexFields>
248 :     <IndexField name="id" order="ascending" />
249 :     <IndexField name="name-priority" order="ascending" />
250 :     </IndexFields>
251 :     </Index>
252 :     </Indexes>
253 :     </Entity>
254 : parrello 1.5 <Entity name="Subsystem" keyType="string">
255 : parrello 1.1 <Notes>A [i]subsystem[/i] is a collection of roles that work together in a cell. Identification of subsystems
256 :     is an important tool for recognizing parallel genetic features in different organisms.</Notes>
257 : parrello 1.15 <Fields>
258 :     <Field name="curator" type="string">
259 :     <Notes>Name of the person currently in charge of the subsystem.</Notes>
260 :     </Field>
261 :     <Field name="notes" type="text">
262 :     <Notes>Descriptive notes about the subsystem.</Notes>
263 :     </Field>
264 :     </Fields>
265 :     </Entity>
266 :     <Entity name="RoleSubset" keyType="string">
267 :     <Notes>A [i]role subset[/i] is a named collection of roles in a particular subsystem. The
268 :     subset names are generally very short, non-unique strings. The ID of the parent
269 :     subsystem is prefixed to the subset ID in order to make it unique.</Notes>
270 :     </Entity>
271 :     <Entity name="GenomeSubset" keyType="string">
272 :     <Notes>A [i]genome subset[/i] is a named collection of genomes that participate
273 :     in a particular subsystem. The subset names are generally very short, non-unique
274 :     strings. The ID of the parent subsystem is prefixed to the subset ID in order
275 :     to make it unique.</Notes>
276 : parrello 1.1 </Entity>
277 : parrello 1.13 <Entity name="SSCell" keyType="medium-string">
278 : parrello 1.1 <Notes>Part of the process of locating and assigning features is creating a spreadsheet of
279 :     genomes and roles to which features are assigned. A [i]spreadsheet cell[/i] represents one
280 :     of the positions on the spreadsheet.</Notes>
281 :     </Entity>
282 :     <Entity name="SproutUser" keyType="name-string">
283 :     <Notes>A [i]user[/i] is a person who can make annotations and view data in the database. The
284 :     user object is keyed on the user's login name.</Notes>
285 :     <Fields>
286 : parrello 1.8 <Field name="description" type="string">
287 :     <Notes>Full name or description of this user.</Notes>
288 :     </Field>
289 : parrello 1.1 <Field name="access-code" type="key-string" relation="UserAccess">
290 : parrello 1.8 <Notes>Access code possessed by this
291 : parrello 1.1 user. A user can have many access codes; a genome is accessible to the user if its
292 :     access code matches any one of the user's access codes.</Notes>
293 : parrello 1.8 <DataGen testCount="2">RandParam('low', 'medium', 'high')</DataGen>
294 :     </Field>
295 : parrello 1.1 </Fields>
296 :     </Entity>
297 : parrello 1.8 <Entity name="Property" keyType="int">
298 :     <Notes>A [i]property[/i] is a type of assertion that could be made about the properties of
299 :     a particular feature. Each property instance is a key/value pair and can be associated
300 :     with many different features. Conversely, a feature can be associated with many key/value
301 :     pairs, even some that notionally contradict each other. For example, there can be evidence
302 :     that a feature is essential to the organism's survival and evidence that it is superfluous.</Notes>
303 :     <Fields>
304 :     <Field name="property-name" type="name-string">
305 :     <Notes>Name of this property.</Notes>
306 :     </Field>
307 :     <Field name="property-value" type="string">
308 :     <Notes>Value associated with this property. For each property
309 :     name, there must by a property record for all of its possible
310 :     values.</Notes>
311 :     </Field>
312 :     </Fields>
313 :     <Indexes>
314 :     <Index>
315 :     <Notes>This index enables the application to find all values for a specified property
316 :     name, or any given name/value pair.</Notes>
317 :     <IndexFields>
318 :     <IndexField name="property-name" order="ascending" />
319 :     <IndexField name="property-value" order="ascending" />
320 :     </IndexFields>
321 :     </Index>
322 :     </Indexes>
323 :     </Entity>
324 :     <Entity name="Diagram" keyType="name-string">
325 :     <Notes>A functional diagram describes the chemical reactions, often comprising a single
326 :     subsystem. A diagram is identified by a short name and contains a longer descriptive name.
327 :     The actual diagram shows which functional roles guide the reactions along with the inputs
328 :     and outputs; the database, however, only indicate which roles belong to a particular
329 :     map.</Notes>
330 :     <Fields>
331 :     <Field name="name" type="text">
332 :     <Notes>Descriptive name of this diagram.</Notes>
333 :     </Field>
334 :     </Fields>
335 :     </Entity>
336 :     <Entity name="ExternalAliasOrg" keyType="name-string">
337 :     <Notes>An external alias is a feature name for a functional assignment that is not a
338 :     FIG ID. Functional assignments for external aliases are kept in a separate section of
339 :     the database. This table contains a description of the relevant organism for an
340 :     external alias functional assignment.</Notes>
341 :     <Fields>
342 :     <Field name="org" type="text">
343 :     <Notes>Descriptive name of the target organism for this external alias.</Notes>
344 :     </Field>
345 :     </Fields>
346 :     </Entity>
347 :     <Entity name="ExternalAliasFunc" keyType="name-string">
348 :     <Notes>An external alias is a feature name for a functional assignment that is not a
349 :     FIG ID. Functional assignments for external aliases are kept in a separate section of
350 :     the database. This table contains the functional role for the external alias functional
351 :     assignment.</Notes>
352 :     <Fields>
353 :     <Field name="func" type="text">
354 :     <Notes>Functional role for this external alias.</Notes>
355 :     </Field>
356 :     </Fields>
357 :     </Entity>
358 : parrello 1.6 <Entity name="Coupling" keyType="medium-string">
359 :     <Notes>A coupling is a relationship between two features. The features are
360 :     physically close on the contig, and there is evidence that they generally
361 :     belong together. The key of this entity is formed by combining the coupled
362 : parrello 1.8 feature IDs with a space.</Notes>
363 : parrello 1.6 <Fields>
364 :     <Field name="score" type="int">
365 :     <Notes>A number based on the set of PCHs (pairs of close homologs). A PCH
366 :     indicates that two genes near each other on one genome are very similar to
367 :     genes near each other on another genome. The score only counts PCHs for which
368 :     the genomes are very different. (In other words, we have a pairing that persists
369 :     between different organisms.) A higher score implies a stronger meaning to the
370 :     clustering.</Notes>
371 :     </Field>
372 :     </Fields>
373 :     </Entity>
374 :     <Entity name="PCH" keyType="string">
375 :     <Notes>A PCH (physically close homolog) connects a clustering (which is a
376 :     pair of physically close features on a contig) to a second pair of physically
377 :     close features that are similar to the first. Essentially, the PCH is a
378 :     relationship between two clusterings in which the first clustering's features
379 :     are similar to the second clustering's features. The simplest model for
380 :     this would be to simply relate clusterings to each other; however, not all
381 :     physically close pairs qualify as clusterings, so we relate a clustering to
382 :     a pair of features. The key is the clustering key followed by the IDs
383 :     of the features in the second pair.</Notes>
384 :     <Fields>
385 :     <Field name="used" type="boolean">
386 :     <Notes>TRUE if this PCH is used in scoring the attached clustering,
387 :     else FALSE. If a clustering has a PCH for a particular genome and many
388 :     similar genomes are present, then a PCH will probably exist for the
389 :     similar genomes as well. When this happens, only one of the PCHs will
390 :     be scored: the others are considered duplicates of the same evidence.</Notes>
391 :     </Field>
392 :     </Fields>
393 :     </Entity>
394 : parrello 1.1 </Entities>
395 :     <Relationships>
396 : parrello 1.6 <Relationship name="ParticipatesInCoupling" from="Feature" to="Coupling" arity="MM">
397 :     <Notes>This relationship connects a feature to all the functional couplings
398 :     in which it participates. A functional coupling is a recognition of the fact
399 :     that the features are close to each other on a chromosome, and similar
400 :     features in other genomes also tend to be close.</Notes>
401 :     <Fields>
402 :     <Field name="pos" type="int">
403 :     <Notes>Ordinal position of the feature in the coupling. Currently,
404 :     this is either "1" or "2".</Notes>
405 :     </Field>
406 :     </Fields>
407 :     <ToIndex>
408 :     <Notes>This index enables the application to view the features of
409 :     a coupling in the proper order. The order influences the way the
410 :     PCHs are examined.</Notes>
411 :     <IndexFields>
412 :     <IndexField name="pos" order="ascending" />
413 :     </IndexFields>
414 :     </ToIndex>
415 :     </Relationship>
416 :     <Relationship name="IsEvidencedBy" from="Coupling" to="PCH" arity="1M">
417 :     <Notes>This relationship connects a functional coupling to the physically
418 :     close homologs (PCHs) which affirm that the coupling is meaningful.</Notes>
419 :     </Relationship>
420 :     <Relationship name="UsesAsEvidence" from="PCH" to="Feature" arity="MM">
421 :     <Notes>This relationship connects a PCH to the features that represent its
422 :     evidence. Each PCH is connected to a parent coupling that relates two features
423 :     on a specific genome. The PCH's evidence that the parent coupling is functional
424 :     is the existence of two physically close features on a different genome that
425 :     correspond to the features in the coupling. Those features are found on the
426 :     far side of this relationship.</Notes>
427 :     <Fields>
428 :     <Field name="pos" type="int">
429 :     <Notes>Ordinal position of the feature in the coupling that corresponds
430 :     to our target feature. There is a one-to-one correspondence between the
431 :     features connected to the PCH by this relationship and the features
432 :     connected to the PCH's parent coupling. The ordinal position is used
433 :     to decode that relationship. Currently, this field is either "1" or
434 :     "2".</Notes>
435 :     </Field>
436 :     </Fields>
437 :     <FromIndex>
438 :     <Notes>This index enables the application to view the features of
439 :     a PCH in the proper order.</Notes>
440 :     <IndexFields>
441 :     <IndexField name="pos" order="ascending" />
442 :     </IndexFields>
443 :     </FromIndex>
444 :     </Relationship>
445 : parrello 1.1 <Relationship name="HasContig" from="Genome" to="Contig" arity="1M">
446 :     <Notes>This relationship connects a genome to the contigs that contain the actual genetic
447 :     information.</Notes>
448 :     </Relationship>
449 :     <Relationship name="ComesFrom" from="Genome" to="Source" arity="MM">
450 :     <Notes>This relationship connects a genome to the sources that mapped it. A genome can
451 :     come from a single source or from a cooperation among multiple sources.</Notes>
452 :     </Relationship>
453 :     <Relationship name="IsMadeUpOf" from="Contig" to="Sequence" arity="1M">
454 :     <Notes>A contig is stored in the database as an ordered set of sequences. By splitting the
455 :     contig into sequences, we get a performance boost from only needing to keep small portions
456 :     of a contig in memory at any one time. This relationship connects the contig to its
457 :     constituent sequences.</Notes>
458 :     <Fields>
459 :     <Field name="len" type="int">
460 : parrello 1.15 <Notes>Length of the sequence.</Notes>
461 :     </Field>
462 : parrello 1.1 <Field name="start-position" type="int">
463 : parrello 1.15 <Notes>Index (1-based) of the point in the contig where this
464 :     sequence starts.</Notes>
465 :     </Field>
466 : parrello 1.1 </Fields>
467 :     <FromIndex>
468 :     <Notes>This index enables the application to find all of the sequences in
469 : parrello 1.8 a contig in order, and makes it easier to find a particular residue section.</Notes>
470 : parrello 1.1 <IndexFields>
471 :     <IndexField name="start-position" order="ascending" />
472 :     <IndexField name="len" order="ascending" />
473 :     </IndexFields>
474 :     </FromIndex>
475 :     </Relationship>
476 :     <Relationship name="IsTargetOfAnnotation" from="Feature" to="Annotation" arity="1M">
477 :     <Notes>This relationship connects a feature to its annotations.</Notes>
478 :     </Relationship>
479 :     <Relationship name="MadeAnnotation" from="SproutUser" to="Annotation" arity="1M">
480 :     <Notes>This relationship connects an annotation to the user who made it.</Notes>
481 :     </Relationship>
482 :     <Relationship name="ParticipatesIn" from="Genome" to="Subsystem" arity="MM">
483 :     <Notes>This relationship connects subsystems to the genomes that use
484 :     it. If the subsystem has been curated for the genome, then the subsystem's roles will also be
485 :     connected to the genome features through the [b]SSCell[/b] object.</Notes>
486 : parrello 1.15 <Fields>
487 :     <Field name="variant-code" type="key-string">
488 :     <Notes>Numeric code indicating the subsystem variant to which this
489 :     genome belongs. Each subsystem can have multiple variants. A variant
490 :     code of [b]-1[/b] indicates that the genome's roles apply to all
491 :     variants. A variant code of [b]0[/b] indicates that the genome's
492 :     participation is considered iffy.</Notes>
493 :     </Field>
494 :     </Fields>
495 :     <ToIndex>
496 :     <Notes>This index enables the application to find all of the genomes using
497 :     a subsystem in order by variant code, which is how we wish to display them
498 :     in the spreadsheets.</Notes>
499 :     <IndexFields>
500 :     <IndexField name="variant-code" order="ascending" />
501 :     </IndexFields>
502 :     </ToIndex>
503 : parrello 1.1 </Relationship>
504 :     <Relationship name="OccursInSubsystem" from="Role" to="Subsystem" arity="MM">
505 :     <Notes>This relationship connects roles to the subsystems that implement them. </Notes>
506 : parrello 1.15 <Fields>
507 :     <Field name="column-number" type="int">
508 :     <Notes>Column number for this role in the specified subsystem's
509 :     spreadsheet.</Notes>
510 :     </Field>
511 :     </Fields>
512 :     <ToIndex>
513 :     <Notes>This index enables the application to see the subsystem roles
514 :     in column order. The ordering of the roles is usually significant,
515 :     so it is important to preserve it.</Notes>
516 :     <IndexFields>
517 :     <IndexField name="column-number" order="ascending" />
518 :     </IndexFields>
519 :     </ToIndex>
520 : parrello 1.1 </Relationship>
521 :     <Relationship name="IsGenomeOf" from="Genome" to="SSCell" arity="1M">
522 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
523 :     genome for the spreadsheet column.</Notes>
524 :     </Relationship>
525 :     <Relationship name="IsRoleOf" from="Role" to="SSCell" arity="1M">
526 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
527 :     role for the spreadsheet row.</Notes>
528 :     </Relationship>
529 :     <Relationship name="ContainsFeature" from="SSCell" to="Feature" arity="MM">
530 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
531 :     features assigned to it.</Notes>
532 : parrello 1.15 <Fields>
533 :     <Field name="cluster-number" type="int">
534 :     <Notes>ID of this feature's cluster. Clusters represent families of
535 :     related proteins participating in a subsystem.</Notes>
536 :     </Field>
537 :     </Fields>
538 :     </Relationship>
539 :     <Relationship name="IsAComponentOf" from="Compound" to="Reaction" arity="MM">
540 :     <Notes>This relationship connects a reaction to the compounds that participate
541 :     in it.</Notes>
542 :     <Fields>
543 :     <Field name="product" type="boolean">
544 :     <Notes>TRUE if the compound is a product of the reaction, FALSE if
545 :     it is a substrate. When a reaction is written on paper in
546 :     chemical notation, the substrates are left of the arrow and the
547 :     products are to the right. Sorting on this field will cause
548 :     the substrates to appear first, followed by the products. If the
549 :     reaction is reversible, then the notion of substrates and products
550 :     is not at intuitive; however, a value here of FALSE still puts the
551 :     compound left of the arrow and a value of TRUE still puts it to the
552 :     right.</Notes>
553 :     </Field>
554 : parrello 1.16 <Field name="stoichometry" type="key-string">
555 : parrello 1.15 <Notes>Number of molecules of the compound that participate in a
556 :     single instance of the reaction. For example, if a reaction
557 :     produces two water molecules, the stoichometry of water for the
558 :     reaction would be two. When a reaction is written on paper in
559 :     chemical notation, the stoichometry is the number next to the
560 :     chemical formula of the compound.</Notes>
561 :     </Field>
562 :     <Field name="main" type="boolean">
563 :     <Notes>TRUE if this compound is one of the main participants in
564 :     the reaction, else FALSE. It is permissible for none of the
565 :     compounds in the reaction to be considered main, in which
566 :     case this value would be FALSE for all of the relevant
567 :     compounds.</Notes>
568 :     </Field>
569 :     <Field name="loc" type="key-string">
570 :     <Notes>An optional character string that indicates the relative
571 :     position of this compound in the reaction's chemical formula. The
572 :     location affects the way the compounds present as we cross the
573 :     relationship from the reaction side. The product/substrate flag
574 :     comes first, then the value of this field, then the main flag.
575 :     The default value is an empty string; however, the empty string
576 :     sorts first, so if this field is used, it should probably be
577 :     used for every compound in the reaction.</Notes>
578 :     </Field>
579 :     </Fields>
580 :     <ToIndex>
581 :     <Notes>This index presents the compounds in the reaction in the
582 :     order they should be displayed when writing it in chemical notation.
583 :     All the substrates appear before all the products, and within that
584 :     ordering, the main compounds appear first.</Notes>
585 :     <IndexField name="product" order="ascending" />
586 :     <IndexField name="loc" order="ascending" />
587 :     <IndexField name="main" order="descending" />
588 :     </ToIndex>
589 : parrello 1.1 </Relationship>
590 :     <Relationship name="IsLocatedIn" from="Feature" to="Contig" arity="MM">
591 :     <Notes>This relationship connects a feature to the contig segments that work together
592 :     to effect it. The segments are numbered sequentially starting from 1. The database is
593 :     required to place an upper limit on the length of each segment. If a segment is longer
594 :     than the maximum, it can be broken into smaller bits.
595 :     [p]The upper limit enables applications to locate all features that contain a specific
596 :     residue. For example, if the upper limit is 100 and we are looking for a feature that
597 :     contains residue 234 of contig [b]ABC[/b], we can look for features with a begin point
598 :     between 135 and 333. The results can then be filtered by direction and length of the
599 :     segment.</Notes>
600 :     <Fields>
601 :     <Field name="locN" type="int">
602 : parrello 1.8 <Notes>Sequence number of this segment.</Notes>
603 :     </Field>
604 : parrello 1.1 <Field name="beg" type="int">
605 : parrello 1.8 <Notes>Index (1-based) of the first residue in the contig that
606 :     belongs to the segment.</Notes>
607 :     </Field>
608 : parrello 1.1 <Field name="len" type="int">
609 : parrello 1.8 <Notes>Number of residues in the segment. A length of 0 identifies
610 :     a specific point between residues. This is the point before the residue if the direction
611 :     is forward and the point after the residue if the direction is backward.</Notes>
612 :     </Field>
613 : parrello 1.1 <Field name="dir" type="char">
614 : parrello 1.8 <Notes>Direction of the segment: [b]+[/b] if it is forward and
615 :     [b]-[/b] if it is backward.</Notes>
616 :     </Field>
617 : parrello 1.1 </Fields>
618 :     <FromIndex Unique="false">
619 :     <Notes>This index allows the application to find all the segments of a feature in
620 : parrello 1.8 the proper order.</Notes>
621 : parrello 1.1 <IndexFields>
622 :     <IndexField name="locN" order="ascending" />
623 :     </IndexFields>
624 :     </FromIndex>
625 :     <ToIndex>
626 :     <Notes>This index is the one used by applications to find all the feature
627 :     segments that contain a specific residue.</Notes>
628 :     <IndexFields>
629 :     <IndexField name="beg" order="ascending" />
630 :     </IndexFields>
631 :     </ToIndex>
632 :     </Relationship>
633 :     <Relationship name="IsBidirectionalBestHitOf" from="Feature" to="Feature" arity="MM">
634 :     <Notes>This relationship is one of two that relate features to each other. It
635 :     connects features that are very similar but on separate genomes. A
636 :     bidirectional best hit relationship exists between two features [b]A[/b]
637 :     and [b]B[/b] if [b]A[/b] is the best match for [b]B[/b] on [b]A[/b]'s genome
638 :     and [b]B[/b] is the best match for [b]A[/b] on [b]B[/b]'s genome. </Notes>
639 :     <Fields>
640 :     <Field name="genome" type="name-string">
641 : parrello 1.8 <Notes>ID of the genome containing the target (to) feature.</Notes>
642 :     </Field>
643 :     <Field name="sc" type="float">
644 :     <Notes>score for this relationship</Notes>
645 :     </Field>
646 : parrello 1.1 </Fields>
647 :     <FromIndex>
648 :     <Notes>This index allows the application to find a feature's best hit for
649 : parrello 1.8 a specific target genome.</Notes>
650 : parrello 1.1 <IndexFields>
651 :     <IndexField name="genome" order="ascending" />
652 :     </IndexFields>
653 :     </FromIndex>
654 :     </Relationship>
655 : parrello 1.8 <Relationship name="HasProperty" from="Feature" to="Property" arity="MM">
656 :     <Notes>This relationship connects a feature to its known property values.
657 :     The relationship contains text data that indicates the paper or organization
658 :     that discovered evidence that the feature possesses the property. So, for
659 :     example, if two papers presented evidence that a feature is essential,
660 :     there would be an instance of this relationship for both.</Notes>
661 :     <Fields>
662 :     <Field name="evidence" type="text">
663 :     <Notes>URL or citation of the paper or
664 :     institution that reported evidence of the relevant feature possessing
665 :     the specified property value.</Notes>
666 :     </Field>
667 :     </Fields>
668 :     </Relationship>
669 :     <Relationship name="RoleOccursIn" from="Role" to="Diagram" arity="MM">
670 :     <Notes>This relationship connects a role to the diagrams on which it
671 :     appears. A role frequently identifies an enzyme, and can appear in many
672 :     diagrams. A diagram generally contains many different roles.</Notes>
673 :     </Relationship>
674 :     <Relationship name="HasSSCell" from="Subsystem" to="SSCell" arity="1M">
675 :     <Notes>This relationship connects a subsystem to the spreadsheet cells
676 :     used to analyze and display it. The cells themselves can be thought of
677 :     as a grid with Roles on one axis and Genomes on the other. The
678 :     various features of the subsystem are then assigned to the cells.</Notes>
679 :     </Relationship>
680 :     <Relationship name="IsTrustedBy" from="SproutUser" to="SproutUser" arity="MM">
681 :     <Notes>This relationship identifies the users trusted by each
682 :     particular user. When viewing functional assignments, the
683 :     assignment displayed is the most recent one by a user trusted
684 :     by the current user. The current user implicitly trusts himself.
685 :     If no trusted users are specified in the database, the user
686 :     also implicitly trusts the user [b]FIG[/b].</Notes>
687 :     </Relationship>
688 : parrello 1.15 <Relationship name="ConsistsOfRoles" from="RoleSubset" to="Role" arity="MM">
689 :     <Notes>This relationship connects a role subset to the roles that it covers.
690 :     A subset is, essentially, a named group of roles belonging to a specific
691 :     subsystem, and this relationship effects that. Note that will a role
692 :     may belong to many subsystems, a subset belongs to only one subsystem,
693 :     and all roles in the subset must have that subsystem in common.</Notes>
694 :     </Relationship>
695 :     <Relationship name="ConsistsOfGenomes" from="GenomeSubset" to="Genome" arity="MM">
696 :     <Notes>This relationship connects a subset to the genomes that it covers.
697 :     A subset is, essentially, a named group of genomes participating in a specific
698 :     subsystem, and this relationship effects that. Note that while a genome
699 :     may belong to many subsystems, a subset belongs to only one subsystem,
700 :     and all genomes in the subset must have that subsystem in common.</Notes>
701 :     </Relationship>
702 :     <Relationship name="HasRoleSubset" from="Subsystem" to="RoleSubset" arity="1M">
703 :     <Notes>This relationship connects a subsystem to its constituent
704 :     role subsets. Note that some roles in a subsystem may not belong to a
705 :     subset, so the relationship between roles and subsystems cannot be
706 :     derived from the relationships going through the subset.</Notes>
707 :     </Relationship>
708 :     <Relationship name="HasGenomeSubset" from="Subsystem" to="GenomeSubset" arity="1M">
709 :     <Notes>This relationship connects a subsystem to its constituent
710 :     genome subsets. Note that some genomes in a subsystem may not belong to a
711 :     subset, so the relationship between genomes and subsystems cannot be
712 :     derived from the relationships going through the subset.</Notes>
713 :     </Relationship>
714 :     <Relationship name="Catalyzes" from="Role" to="Reaction" arity="MM">
715 :     <Notes>This relationship connects a role to the reactions it catalyzes.
716 :     The purpose of a role is to create proteins that trigger certain
717 :     chemical reactions. A single reaction can be triggered by many roles,
718 :     and a role can trigger many reactions.</Notes>
719 :     </Relationship>
720 : parrello 1.1 </Relationships>
721 :     </Database>

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3