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

Annotation of /Sprout/SproutDBD.xml

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.47 - (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 :     </Field>
11 :     <Field name="species" type="name-string">
12 : parrello 1.8 <Notes>Species of the relevant organism.</Notes>
13 :     </Field>
14 : parrello 1.1 <Field name="unique-characterization" type="medium-string">
15 : parrello 1.8 <Notes>The unique characterization identifies the particular organism instance from which the
16 :     genome is taken. It is possible to have in the database more than one genome for a
17 : parrello 1.1 particular species, and every individual organism has variations in its DNA.</Notes>
18 :     </Field>
19 :     <Field name="access-code" type="key-string">
20 : parrello 1.8 <Notes>The access code determines which users can look at the data relating to this genome.
21 :     Each user is associated with a set of access codes. In order to view a genome, one of
22 :     the user's access codes must match this value.</Notes>
23 :     </Field>
24 : parrello 1.15 <Field name="complete" type="boolean">
25 :     <Notes>TRUE if the genome is complete, else FALSE</Notes>
26 :     </Field>
27 : parrello 1.8 <Field name="taxonomy" type="text">
28 :     <Notes>The taxonomy string contains the full taxonomy of the organism, while individual elements
29 :     separated by semi-colons (and optional white space), starting with the domain and ending with
30 :     the disambiguated genus and species (which is the organism's scientific name plus an
31 :     identifying string).</Notes>
32 :     </Field>
33 : parrello 1.37 <Field name="primary-group" type="name-string">
34 :     <Notes>The primary NMPDR group for this organism. There is always exactly one NMPDR group
35 :     (either based on the organism name or the default value "Supporting"), whereas there can be
36 :     multiple named groups or even none.</Notes>
37 :     </Field>
38 : parrello 1.8 <Field name="group-name" type="name-string" relation="GenomeGroups">
39 :     <Notes>The group identifies a special grouping of organisms that would be displayed on a particular
40 :     page or of particular interest to a research group or web site. A single genome can belong to multiple
41 :     such groups or none at all.</Notes>
42 :     </Field>
43 : parrello 1.1 </Fields>
44 :     <Indexes>
45 : parrello 1.45 <Index>
46 : parrello 1.1 <Notes>This index allows the applications to find all genomes associated with
47 :     a specific access code, so that a complete list of the genomes users can view
48 :     may be generated.</Notes>
49 :     <IndexFields>
50 :     <IndexField name="access-code" order="ascending" />
51 :     <IndexField name="genus" order="ascending" />
52 :     <IndexField name="species" order="ascending" />
53 :     <IndexField name="unique-characterization" order="ascending" />
54 :     </IndexFields>
55 :     </Index>
56 : parrello 1.45 <Index>
57 : parrello 1.37 <Notes>This index allows the applications to find all genomes associated with
58 :     a specific primary (NMPDR) group.</Notes>
59 :     <IndexFields>
60 :     <IndexField name="primary-group" order="ascending" />
61 :     <IndexField name="genus" order="ascending" />
62 :     <IndexField name="species" order="ascending" />
63 :     <IndexField name="unique-characterization" order="ascending" />
64 :     </IndexFields>
65 :     </Index>
66 : parrello 1.45 <Index>
67 : parrello 1.1 <Notes>This index allows the applications to find all genomes for a particular
68 :     species.</Notes>
69 :     <IndexFields>
70 :     <IndexField name="genus" order="ascending" />
71 :     <IndexField name="species" order="ascending" />
72 :     <IndexField name="unique-characterization" order="ascending" />
73 :     </IndexFields>
74 :     </Index>
75 :     </Indexes>
76 :     </Entity>
77 :     <Entity name="Source" keyType="medium-string">
78 :     <Notes>A [i]source[/i] describes a place from which genome data was taken. This can be an organization
79 :     or a paper citation.</Notes>
80 :     <Fields>
81 :     <Field name="URL" type="string" relation="SourceURL">
82 : parrello 1.8 <Notes>URL the paper cited or of the organization's web site. This field optional.</Notes>
83 :     </Field>
84 : parrello 1.1 <Field name="description" type="text">
85 : parrello 1.8 <Notes>Description the source. The description can be a street address or a citation.</Notes>
86 :     </Field>
87 : parrello 1.1 </Fields>
88 :     </Entity>
89 :     <Entity name="Contig" keyType="name-string">
90 :     <Notes>A [i]contig[/i] is a contiguous run of residues. The contig's ID consists of the
91 :     genome ID followed by a name that identifies which contig this is for the parent genome. As
92 :     is the case with all keys in this database, the individual components are separated by a
93 :     period.
94 :     [p]A contig can contain over a million residues. For performance reasons, therefore,
95 :     the contig is split into multiple pieces called [i]sequences[/i]. The sequences
96 :     contain the characters that represent the residues as well as data on the quality of
97 :     the residue identification.</Notes>
98 :     </Entity>
99 :     <Entity name="Sequence" keyType="name-string">
100 :     <Notes>A [i]sequence[/i] is a continuous piece of a [i]contig[/i]. Contigs are split into
101 :     sequences so that we don't have to have the entire contig in memory when we are
102 :     manipulating it. The key of the sequence is the contig ID followed by the index of
103 :     the begin point.</Notes>
104 :     <Fields>
105 :     <Field name="sequence" type="text">
106 : parrello 1.8 <Notes>String consisting of the residues. Each residue is described by a single
107 :     character in the string.</Notes>
108 :     </Field>
109 : parrello 1.1 <Field name="quality-vector" type="text">
110 : parrello 1.9 <Notes>String describing the quality data for each base pair. Individual values will
111 : parrello 1.8 be separated by periods. The value represents negative exponent of the probability
112 :     of error. Thus, for example, a quality of 30 indicates the probability of error is
113 :     10^-30. A higher quality number a better chance of a correct match. It is possible
114 : parrello 1.9 that the quality data is not known for a sequence. If that is the case, the quality
115 : parrello 1.8 vector will contain the [b]unknown[/b].</Notes>
116 :     </Field>
117 : parrello 1.1 </Fields>
118 :     </Entity>
119 : parrello 1.25 <Entity name="Feature" keyType="id-string">
120 : parrello 1.1 <Notes>A [i]feature[/i] is a part of a genome that is of special interest. Features
121 :     may be spread across multiple contigs of a genome, but never across more than
122 :     one genome. Features can be assigned to roles via spreadsheet cells,
123 :     and are the targets of annotation.</Notes>
124 :     <Fields>
125 :     <Field name="feature-type" type="string">
126 : parrello 1.8 <Notes>Code indicating the type of this feature.</Notes>
127 :     </Field>
128 : parrello 1.14 <Field name="alias" type="medium-string" relation="FeatureAlias">
129 : parrello 1.9 <Notes>Alternative name for this feature. A feature can have many aliases.</Notes>
130 : parrello 1.8 </Field>
131 : parrello 1.1 <Field name="translation" type="text" relation="FeatureTranslation">
132 : parrello 1.8 <Notes>[i](optional)[/i] A translation of this feature's residues into character
133 :     codes, formed by concatenating the pieces of the feature together. For a
134 :     protein encoding group, this is the protein characters. For other types
135 :     it is the DNA characters.</Notes>
136 :     </Field>
137 : parrello 1.1 <Field name="upstream-sequence" type="text" relation="FeatureUpstream">
138 : parrello 1.8 <Notes>Upstream sequence the feature. This includes residues preceding the feature as well as some of
139 :     the feature's initial residues.</Notes>
140 :     </Field>
141 : parrello 1.42 <Field name="assignment" type="text">
142 :     <Notes>Default functional assignment for this feature.</Notes>
143 :     </Field>
144 : parrello 1.1 <Field name="active" type="boolean">
145 : parrello 1.11 <Notes>TRUE if this feature is still considered valid, FALSE if it has been logically deleted.</Notes>
146 : parrello 1.8 </Field>
147 : parrello 1.41 <Field name="keywords" type="text" searchable="1">
148 :     <Notes>This is a list of search keywords for the feature. It includes the
149 :     functional assignment, subsystem roles, and special properties.</Notes>
150 : parrello 1.36 </Field>
151 : parrello 1.8 <Field name="link" type="text" relation="FeatureLink">
152 :     <Notes>Web hyperlink for this feature. A feature have no hyperlinks or it can have many. The
153 :     links are to other websites that have useful about the gene that the feature represents, and
154 :     are coded as raw HTML, using [b]&lt;a href="[i]link[/i]"&gt;[i]text[/i]&lt;/a&gt;[/b] notation.</Notes>
155 :     </Field>
156 : parrello 1.41 <Field name="conservation" type="float" relation="FeatureConservation">
157 :     <Notes>A number between 0 and 1 that indicates the degree to which this feature's DNA is
158 :     conserved in related genomes. A value of 1 indicates perfect conservation. A value less
159 :     than 1 is a reflect of the degree to which gap characters interfere in the alignment
160 :     between the feature and its close relatives.</Notes>
161 :     </Field>
162 : parrello 1.45 <Field name="essential" type="text" relation="FeatureEssential" special="property_search">
163 :     <Notes>A value indicating the essentiality of the feature, coded as HTML. In most
164 :     cases, this will be a word describing whether the essentiality is confirmed (essential)
165 :     or potential (potential-essential), hyperlinked to the document from which the
166 :     essentiality was curated. If a feature is not essential, this field will have no
167 :     values; otherwise, it may have multiple values.</Notes>
168 :     </Field>
169 :     <Field name="virulent" type="text" relation="FeatureVirulent" special="property_search">
170 :     <Notes>A value indicating the virulence of the feature, coded as HTML. In most
171 :     cases, this will be a phrase or SA number hyperlinked to the document from which
172 :     the virulence information was curated. If the feature is not virulent, this field
173 :     will have no values; otherwise, it may have multiple values.</Notes>
174 :     </Field>
175 :     <Field name="iedb" type="text" relation="FeatureIEDB" special="property_search">
176 :     <Notes>A value indicating whether or not the feature can be found in the
177 :     Immune Epitope Database. If the feature has not been matched to that database,
178 :     this field will have no values. Otherwise, it will have an epitope name and/or
179 :     sequence, hyperlinked to the database.</Notes>
180 :     </Field>
181 : parrello 1.1 </Fields>
182 : parrello 1.8 <Indexes>
183 :     <Index>
184 :     <Notes>This index allows the user to find the feature corresponding to
185 :     the specified alias name.</Notes>
186 :     <IndexFields>
187 :     <IndexField name="alias" order="ascending" />
188 :     </IndexFields>
189 :     </Index>
190 :     </Indexes>
191 : parrello 1.1 </Entity>
192 : parrello 1.27 <Entity name="SynonymGroup" keyType="id-string">
193 :     <Notes>A [i]synonym group[/i] represents a group of features. Substantially identical features
194 :     are mapped to the same synonym group, and this information is used to expand similarities.</Notes>
195 :     </Entity>
196 : parrello 1.1 <Entity name="Role" keyType="string">
197 :     <Notes>A [i]role[/i] describes a biological function that may be fulfilled by a feature.
198 :     One of the main goals of the database is to record the roles of the various features.</Notes>
199 : parrello 1.8 <Fields>
200 : parrello 1.18 <Field name="EC" type="string" relation="RoleEC">
201 :     <Notes>EC code for this role.</Notes>
202 : parrello 1.8 </Field>
203 : parrello 1.15 <Field name="abbr" type="name-string">
204 :     <Notes>Abbreviated name for the role, generally non-unique, but useful
205 :     in column headings for HTML tables.</Notes>
206 :     </Field>
207 : parrello 1.8 </Fields>
208 : parrello 1.18 <Indexes>
209 :     <Index>
210 :     <Notes>This index allows the user to find the role corresponding to
211 :     an EC number.</Notes>
212 :     <IndexFields>
213 :     <IndexField name="EC" order="ascending" />
214 :     </IndexFields>
215 :     </Index>
216 :     </Indexes>
217 : parrello 1.1 </Entity>
218 :     <Entity name="Annotation" keyType="name-string">
219 :     <Notes>An [i]annotation[/i] contains supplementary information about a feature. Annotations
220 : parrello 1.8 are currently the only objects that may be inserted directly into the database. All other
221 : parrello 1.24 information is loaded from data exported by the SEED.</Notes>
222 : parrello 1.8 <Fields>
223 :     <Field name="time" type="date">
224 :     <Notes>Date and time of the annotation.</Notes>
225 :     </Field>
226 :     <Field name="annotation" type="text">
227 :     <Notes>Text of the annotation.</Notes>
228 :     </Field>
229 : parrello 1.1 </Fields>
230 : parrello 1.26 <Indexes>
231 :     <Index>
232 :     <Notes>This index allows the user to find recent annotations.</Notes>
233 :     <IndexFields>
234 :     <IndexField name="time" order="descending" />
235 :     </IndexFields>
236 :     </Index>
237 :     </Indexes>
238 : parrello 1.1 </Entity>
239 : parrello 1.15 <Entity name="Reaction" keyType="key-string">
240 :     <Notes>A [i]reaction[/i] is a chemical process catalyzed by a protein. The reaction ID
241 :     is generally a small number preceded by a letter.</Notes>
242 :     <Fields>
243 :     <Field name="url" type="string" relation="ReactionURL">
244 :     <Notes>HTML string containing a link to a web location that describes the
245 :     reaction. This field is optional.</Notes>
246 :     </Field>
247 :     <Field name="rev" type="boolean">
248 :     <Notes>TRUE if this reaction is reversible, else FALSE</Notes>
249 :     </Field>
250 :     </Fields>
251 :     </Entity>
252 :     <Entity name="Compound" keyType="name-string">
253 :     <Notes>A [i]compound[/i] is a chemical that participates in a reaction.
254 :     All compounds have a unique ID and may also have one or more names.</Notes>
255 :     <Fields>
256 :     <Field name="name-priority" type="int" relation="CompoundName">
257 :     <Notes>Priority of a compound name. The name with the loweset
258 :     priority is the main name of this compound.</Notes>
259 :     </Field>
260 :     <Field name="name" type="name-string" relation="CompoundName">
261 :     <Notes>Descriptive name for the compound. A compound may
262 :     have several names.</Notes>
263 :     </Field>
264 :     <Field name="cas-id" type="name-string" relation="CompoundCAS">
265 :     <Notes>Chemical Abstract Service ID for this compound (optional).</Notes>
266 :     </Field>
267 : parrello 1.19 <Field name="label" type="name-string">
268 :     <Notes>Name used in reaction display strings.
269 :     It is the same as the name possessing a priority of 1, but it is placed
270 :     here to speed up the query used to create the display strings.</Notes>
271 :     </Field>
272 : parrello 1.15 </Fields>
273 :     <Indexes>
274 :     <Index>
275 :     <Notes>This index allows the user to find the compound corresponding to
276 :     the specified name.</Notes>
277 :     <IndexFields>
278 :     <IndexField name="name" order="ascending" />
279 :     </IndexFields>
280 :     </Index>
281 :     <Index>
282 : parrello 1.17 <Notes>This index allows the user to find the compound corresponding to
283 :     the specified CAS ID.</Notes>
284 :     <IndexFields>
285 :     <IndexField name="cas-id" order="ascending" />
286 :     </IndexFields>
287 :     </Index>
288 :     <Index>
289 : parrello 1.15 <Notes>This index allows the user to access the compound names in
290 :     priority order.</Notes>
291 :     <IndexFields>
292 :     <IndexField name="id" order="ascending" />
293 :     <IndexField name="name-priority" order="ascending" />
294 :     </IndexFields>
295 :     </Index>
296 :     </Indexes>
297 :     </Entity>
298 : parrello 1.5 <Entity name="Subsystem" keyType="string">
299 : parrello 1.1 <Notes>A [i]subsystem[/i] is a collection of roles that work together in a cell. Identification of subsystems
300 :     is an important tool for recognizing parallel genetic features in different organisms.</Notes>
301 : parrello 1.15 <Fields>
302 :     <Field name="curator" type="string">
303 :     <Notes>Name of the person currently in charge of the subsystem.</Notes>
304 :     </Field>
305 :     <Field name="notes" type="text">
306 :     <Notes>Descriptive notes about the subsystem.</Notes>
307 :     </Field>
308 : parrello 1.28 <Field name="classification" type="string" relation="SubsystemClass">
309 : parrello 1.44 <Notes>Classification string, colon-delimited. This string organizes the
310 : parrello 1.42 subsystems into a hierarchy.</Notes>
311 : parrello 1.28 </Field>
312 : parrello 1.15 </Fields>
313 :     </Entity>
314 :     <Entity name="RoleSubset" keyType="string">
315 :     <Notes>A [i]role subset[/i] is a named collection of roles in a particular subsystem. The
316 :     subset names are generally very short, non-unique strings. The ID of the parent
317 :     subsystem is prefixed to the subset ID in order to make it unique.</Notes>
318 :     </Entity>
319 :     <Entity name="GenomeSubset" keyType="string">
320 :     <Notes>A [i]genome subset[/i] is a named collection of genomes that participate
321 :     in a particular subsystem. The subset names are generally very short, non-unique
322 :     strings. The ID of the parent subsystem is prefixed to the subset ID in order
323 :     to make it unique.</Notes>
324 : parrello 1.1 </Entity>
325 : parrello 1.24 <Entity name="SSCell" keyType="hash-string">
326 : parrello 1.1 <Notes>Part of the process of locating and assigning features is creating a spreadsheet of
327 :     genomes and roles to which features are assigned. A [i]spreadsheet cell[/i] represents one
328 :     of the positions on the spreadsheet.</Notes>
329 :     </Entity>
330 :     <Entity name="SproutUser" keyType="name-string">
331 :     <Notes>A [i]user[/i] is a person who can make annotations and view data in the database. The
332 :     user object is keyed on the user's login name.</Notes>
333 :     <Fields>
334 : parrello 1.8 <Field name="description" type="string">
335 :     <Notes>Full name or description of this user.</Notes>
336 :     </Field>
337 : parrello 1.1 <Field name="access-code" type="key-string" relation="UserAccess">
338 : parrello 1.8 <Notes>Access code possessed by this
339 : parrello 1.1 user. A user can have many access codes; a genome is accessible to the user if its
340 :     access code matches any one of the user's access codes.</Notes>
341 : parrello 1.8 </Field>
342 : parrello 1.1 </Fields>
343 :     </Entity>
344 : parrello 1.8 <Entity name="Property" keyType="int">
345 :     <Notes>A [i]property[/i] is a type of assertion that could be made about the properties of
346 :     a particular feature. Each property instance is a key/value pair and can be associated
347 :     with many different features. Conversely, a feature can be associated with many key/value
348 :     pairs, even some that notionally contradict each other. For example, there can be evidence
349 :     that a feature is essential to the organism's survival and evidence that it is superfluous.</Notes>
350 :     <Fields>
351 :     <Field name="property-name" type="name-string">
352 :     <Notes>Name of this property.</Notes>
353 :     </Field>
354 :     <Field name="property-value" type="string">
355 :     <Notes>Value associated with this property. For each property
356 :     name, there must by a property record for all of its possible
357 :     values.</Notes>
358 :     </Field>
359 :     </Fields>
360 :     <Indexes>
361 :     <Index>
362 :     <Notes>This index enables the application to find all values for a specified property
363 :     name, or any given name/value pair.</Notes>
364 :     <IndexFields>
365 :     <IndexField name="property-name" order="ascending" />
366 :     <IndexField name="property-value" order="ascending" />
367 :     </IndexFields>
368 :     </Index>
369 :     </Indexes>
370 :     </Entity>
371 :     <Entity name="Diagram" keyType="name-string">
372 :     <Notes>A functional diagram describes the chemical reactions, often comprising a single
373 :     subsystem. A diagram is identified by a short name and contains a longer descriptive name.
374 :     The actual diagram shows which functional roles guide the reactions along with the inputs
375 :     and outputs; the database, however, only indicate which roles belong to a particular
376 :     map.</Notes>
377 :     <Fields>
378 :     <Field name="name" type="text">
379 :     <Notes>Descriptive name of this diagram.</Notes>
380 :     </Field>
381 :     </Fields>
382 :     </Entity>
383 :     <Entity name="ExternalAliasOrg" keyType="name-string">
384 :     <Notes>An external alias is a feature name for a functional assignment that is not a
385 :     FIG ID. Functional assignments for external aliases are kept in a separate section of
386 :     the database. This table contains a description of the relevant organism for an
387 :     external alias functional assignment.</Notes>
388 :     <Fields>
389 :     <Field name="org" type="text">
390 :     <Notes>Descriptive name of the target organism for this external alias.</Notes>
391 :     </Field>
392 :     </Fields>
393 :     </Entity>
394 :     <Entity name="ExternalAliasFunc" keyType="name-string">
395 :     <Notes>An external alias is a feature name for a functional assignment that is not a
396 :     FIG ID. Functional assignments for external aliases are kept in a separate section of
397 :     the database. This table contains the functional role for the external alias functional
398 :     assignment.</Notes>
399 :     <Fields>
400 :     <Field name="func" type="text">
401 :     <Notes>Functional role for this external alias.</Notes>
402 :     </Field>
403 :     </Fields>
404 :     </Entity>
405 : parrello 1.29 <Entity name="Coupling" keyType="id-string">
406 : parrello 1.6 <Notes>A coupling is a relationship between two features. The features are
407 :     physically close on the contig, and there is evidence that they generally
408 :     belong together. The key of this entity is formed by combining the coupled
409 : parrello 1.8 feature IDs with a space.</Notes>
410 : parrello 1.6 <Fields>
411 :     <Field name="score" type="int">
412 :     <Notes>A number based on the set of PCHs (pairs of close homologs). A PCH
413 :     indicates that two genes near each other on one genome are very similar to
414 :     genes near each other on another genome. The score only counts PCHs for which
415 :     the genomes are very different. (In other words, we have a pairing that persists
416 :     between different organisms.) A higher score implies a stronger meaning to the
417 :     clustering.</Notes>
418 :     </Field>
419 :     </Fields>
420 :     </Entity>
421 : parrello 1.30 <Entity name="PCH" keyType="counter">
422 : parrello 1.6 <Notes>A PCH (physically close homolog) connects a clustering (which is a
423 :     pair of physically close features on a contig) to a second pair of physically
424 :     close features that are similar to the first. Essentially, the PCH is a
425 :     relationship between two clusterings in which the first clustering's features
426 :     are similar to the second clustering's features. The simplest model for
427 :     this would be to simply relate clusterings to each other; however, not all
428 :     physically close pairs qualify as clusterings, so we relate a clustering to
429 : parrello 1.30 a pair of features. The key a unique ID number.</Notes>
430 : parrello 1.6 <Fields>
431 :     <Field name="used" type="boolean">
432 :     <Notes>TRUE if this PCH is used in scoring the attached clustering,
433 :     else FALSE. If a clustering has a PCH for a particular genome and many
434 :     similar genomes are present, then a PCH will probably exist for the
435 :     similar genomes as well. When this happens, only one of the PCHs will
436 :     be scored: the others are considered duplicates of the same evidence.</Notes>
437 :     </Field>
438 :     </Fields>
439 :     </Entity>
440 : parrello 1.31 <Entity name="Family" keyType="id-string">
441 :     <Notes>A family is a group of homologous PEGs believed to have the same function. Protein
442 :     families provide a mechanism for verifying the accuracy of functional assignments
443 :     and are also used in determining phylogenetic trees.</Notes>
444 :     <Fields>
445 : parrello 1.32 <Field name="function" type="text">
446 : parrello 1.31 <Notes>The functional assignment expected for all PEGs in this family.</Notes>
447 :     </Field>
448 : parrello 1.33 <Field name="size" type="int">
449 : parrello 1.31 <Notes>The number of proteins in this family. This may be larger than the
450 :     number of PEGs included in the family, since the family may also contain external
451 :     IDs.</Notes>
452 :     </Field>
453 :     </Fields>
454 :     </Entity>
455 : parrello 1.1 </Entities>
456 :     <Relationships>
457 : parrello 1.34 <Relationship name="IsFamilyForFeature" from="Family" to="Feature" arity="MM">
458 : parrello 1.31 <Notes>This relationship connects a protein family to all of its PEGs and connects
459 :     each PEG to all of its protein families.</Notes>
460 :     </Relationship>
461 : parrello 1.6 <Relationship name="ParticipatesInCoupling" from="Feature" to="Coupling" arity="MM">
462 :     <Notes>This relationship connects a feature to all the functional couplings
463 :     in which it participates. A functional coupling is a recognition of the fact
464 :     that the features are close to each other on a chromosome, and similar
465 :     features in other genomes also tend to be close.</Notes>
466 :     <Fields>
467 :     <Field name="pos" type="int">
468 :     <Notes>Ordinal position of the feature in the coupling. Currently,
469 :     this is either "1" or "2".</Notes>
470 :     </Field>
471 :     </Fields>
472 :     <ToIndex>
473 :     <Notes>This index enables the application to view the features of
474 :     a coupling in the proper order. The order influences the way the
475 :     PCHs are examined.</Notes>
476 :     <IndexFields>
477 :     <IndexField name="pos" order="ascending" />
478 :     </IndexFields>
479 :     </ToIndex>
480 :     </Relationship>
481 : parrello 1.27 <Relationship name="IsSynonymGroupFor" from="SynonymGroup" to="Feature" arity="1M">
482 :     <Notes>This relation connects a synonym group to the features that make it
483 :     up.</Notes>
484 :     </Relationship>
485 : parrello 1.24 <Relationship name="HasFeature" from="Genome" to="Feature" arity="1M">
486 :     <Notes>This relationship connects a genome to all of its features. This
487 :     relationship is redundant in a sense, because the genome ID is part
488 :     of the feature ID; however, it makes the creation of certain queries more
489 :     convenient because you can drag in filtering information for a feature's
490 :     genome.</Notes>
491 :     <Fields>
492 :     <Field name="type" type="key-string">
493 :     <Notes>Feature type (eg. peg, rna)</Notes>
494 :     </Field>
495 :     </Fields>
496 : parrello 1.38 <FromIndex>
497 : parrello 1.24 <Notes>This index enables the application to view the features of a
498 :     Genome sorted by type.</Notes>
499 :     <IndexFields>
500 :     <IndexField name="type" order="ascending" />
501 :     </IndexFields>
502 : parrello 1.38 </FromIndex>
503 : parrello 1.24 </Relationship>
504 : parrello 1.6 <Relationship name="IsEvidencedBy" from="Coupling" to="PCH" arity="1M">
505 :     <Notes>This relationship connects a functional coupling to the physically
506 :     close homologs (PCHs) which affirm that the coupling is meaningful.</Notes>
507 :     </Relationship>
508 :     <Relationship name="UsesAsEvidence" from="PCH" to="Feature" arity="MM">
509 :     <Notes>This relationship connects a PCH to the features that represent its
510 :     evidence. Each PCH is connected to a parent coupling that relates two features
511 :     on a specific genome. The PCH's evidence that the parent coupling is functional
512 :     is the existence of two physically close features on a different genome that
513 :     correspond to the features in the coupling. Those features are found on the
514 :     far side of this relationship.</Notes>
515 :     <Fields>
516 :     <Field name="pos" type="int">
517 :     <Notes>Ordinal position of the feature in the coupling that corresponds
518 :     to our target feature. There is a one-to-one correspondence between the
519 :     features connected to the PCH by this relationship and the features
520 :     connected to the PCH's parent coupling. The ordinal position is used
521 :     to decode that relationship. Currently, this field is either "1" or
522 :     "2".</Notes>
523 :     </Field>
524 :     </Fields>
525 :     <FromIndex>
526 :     <Notes>This index enables the application to view the features of
527 :     a PCH in the proper order.</Notes>
528 :     <IndexFields>
529 :     <IndexField name="pos" order="ascending" />
530 :     </IndexFields>
531 :     </FromIndex>
532 :     </Relationship>
533 : parrello 1.1 <Relationship name="HasContig" from="Genome" to="Contig" arity="1M">
534 :     <Notes>This relationship connects a genome to the contigs that contain the actual genetic
535 :     information.</Notes>
536 :     </Relationship>
537 :     <Relationship name="ComesFrom" from="Genome" to="Source" arity="MM">
538 :     <Notes>This relationship connects a genome to the sources that mapped it. A genome can
539 :     come from a single source or from a cooperation among multiple sources.</Notes>
540 :     </Relationship>
541 :     <Relationship name="IsMadeUpOf" from="Contig" to="Sequence" arity="1M">
542 :     <Notes>A contig is stored in the database as an ordered set of sequences. By splitting the
543 :     contig into sequences, we get a performance boost from only needing to keep small portions
544 :     of a contig in memory at any one time. This relationship connects the contig to its
545 :     constituent sequences.</Notes>
546 :     <Fields>
547 :     <Field name="len" type="int">
548 : parrello 1.15 <Notes>Length of the sequence.</Notes>
549 :     </Field>
550 : parrello 1.1 <Field name="start-position" type="int">
551 : parrello 1.15 <Notes>Index (1-based) of the point in the contig where this
552 :     sequence starts.</Notes>
553 :     </Field>
554 : parrello 1.1 </Fields>
555 :     <FromIndex>
556 :     <Notes>This index enables the application to find all of the sequences in
557 : parrello 1.8 a contig in order, and makes it easier to find a particular residue section.</Notes>
558 : parrello 1.1 <IndexFields>
559 :     <IndexField name="start-position" order="ascending" />
560 :     <IndexField name="len" order="ascending" />
561 :     </IndexFields>
562 :     </FromIndex>
563 :     </Relationship>
564 :     <Relationship name="IsTargetOfAnnotation" from="Feature" to="Annotation" arity="1M">
565 :     <Notes>This relationship connects a feature to its annotations.</Notes>
566 :     </Relationship>
567 :     <Relationship name="MadeAnnotation" from="SproutUser" to="Annotation" arity="1M">
568 :     <Notes>This relationship connects an annotation to the user who made it.</Notes>
569 :     </Relationship>
570 :     <Relationship name="ParticipatesIn" from="Genome" to="Subsystem" arity="MM">
571 :     <Notes>This relationship connects subsystems to the genomes that use
572 :     it. If the subsystem has been curated for the genome, then the subsystem's roles will also be
573 :     connected to the genome features through the [b]SSCell[/b] object.</Notes>
574 : parrello 1.15 <Fields>
575 :     <Field name="variant-code" type="key-string">
576 : parrello 1.20 <Notes>Code indicating the subsystem variant to which this
577 : parrello 1.15 genome belongs. Each subsystem can have multiple variants. A variant
578 : parrello 1.20 code of [b]-1[/b] indicates that the genome does not have a functional
579 :     variant of the subsystem. A variant code of [b]0[/b] indicates that
580 :     the genome's participation is considered iffy.</Notes>
581 : parrello 1.15 </Field>
582 :     </Fields>
583 :     <ToIndex>
584 :     <Notes>This index enables the application to find all of the genomes using
585 :     a subsystem in order by variant code, which is how we wish to display them
586 :     in the spreadsheets.</Notes>
587 :     <IndexFields>
588 :     <IndexField name="variant-code" order="ascending" />
589 :     </IndexFields>
590 :     </ToIndex>
591 : parrello 1.1 </Relationship>
592 :     <Relationship name="OccursInSubsystem" from="Role" to="Subsystem" arity="MM">
593 :     <Notes>This relationship connects roles to the subsystems that implement them. </Notes>
594 : parrello 1.15 <Fields>
595 :     <Field name="column-number" type="int">
596 :     <Notes>Column number for this role in the specified subsystem's
597 :     spreadsheet.</Notes>
598 :     </Field>
599 :     </Fields>
600 :     <ToIndex>
601 :     <Notes>This index enables the application to see the subsystem roles
602 :     in column order. The ordering of the roles is usually significant,
603 :     so it is important to preserve it.</Notes>
604 :     <IndexFields>
605 :     <IndexField name="column-number" order="ascending" />
606 :     </IndexFields>
607 :     </ToIndex>
608 : parrello 1.1 </Relationship>
609 :     <Relationship name="IsGenomeOf" from="Genome" to="SSCell" arity="1M">
610 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
611 :     genome for the spreadsheet column.</Notes>
612 :     </Relationship>
613 :     <Relationship name="IsRoleOf" from="Role" to="SSCell" arity="1M">
614 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
615 :     role for the spreadsheet row.</Notes>
616 :     </Relationship>
617 :     <Relationship name="ContainsFeature" from="SSCell" to="Feature" arity="MM">
618 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
619 :     features assigned to it.</Notes>
620 : parrello 1.15 <Fields>
621 :     <Field name="cluster-number" type="int">
622 :     <Notes>ID of this feature's cluster. Clusters represent families of
623 :     related proteins participating in a subsystem.</Notes>
624 :     </Field>
625 :     </Fields>
626 :     </Relationship>
627 :     <Relationship name="IsAComponentOf" from="Compound" to="Reaction" arity="MM">
628 :     <Notes>This relationship connects a reaction to the compounds that participate
629 :     in it.</Notes>
630 :     <Fields>
631 :     <Field name="product" type="boolean">
632 :     <Notes>TRUE if the compound is a product of the reaction, FALSE if
633 :     it is a substrate. When a reaction is written on paper in
634 :     chemical notation, the substrates are left of the arrow and the
635 :     products are to the right. Sorting on this field will cause
636 :     the substrates to appear first, followed by the products. If the
637 :     reaction is reversible, then the notion of substrates and products
638 :     is not at intuitive; however, a value here of FALSE still puts the
639 :     compound left of the arrow and a value of TRUE still puts it to the
640 :     right.</Notes>
641 :     </Field>
642 : parrello 1.19 <Field name="stoichiometry" type="key-string">
643 : parrello 1.15 <Notes>Number of molecules of the compound that participate in a
644 :     single instance of the reaction. For example, if a reaction
645 : parrello 1.19 produces two water molecules, the stoichiometry of water for the
646 : parrello 1.15 reaction would be two. When a reaction is written on paper in
647 : parrello 1.19 chemical notation, the stoichiometry is the number next to the
648 : parrello 1.15 chemical formula of the compound.</Notes>
649 :     </Field>
650 :     <Field name="main" type="boolean">
651 :     <Notes>TRUE if this compound is one of the main participants in
652 :     the reaction, else FALSE. It is permissible for none of the
653 :     compounds in the reaction to be considered main, in which
654 :     case this value would be FALSE for all of the relevant
655 :     compounds.</Notes>
656 :     </Field>
657 :     <Field name="loc" type="key-string">
658 :     <Notes>An optional character string that indicates the relative
659 :     position of this compound in the reaction's chemical formula. The
660 :     location affects the way the compounds present as we cross the
661 :     relationship from the reaction side. The product/substrate flag
662 :     comes first, then the value of this field, then the main flag.
663 :     The default value is an empty string; however, the empty string
664 :     sorts first, so if this field is used, it should probably be
665 :     used for every compound in the reaction.</Notes>
666 :     </Field>
667 : parrello 1.19 <Field name="discriminator" type="int">
668 :     <Notes>A unique ID for this record. The discriminator does not
669 :     provide any useful data, but it prevents identical records from
670 :     being collapsed by the SELECT DISTINCT command used by ERDB to
671 :     retrieve data.</Notes>
672 :     </Field>
673 : parrello 1.15 </Fields>
674 :     <ToIndex>
675 :     <Notes>This index presents the compounds in the reaction in the
676 :     order they should be displayed when writing it in chemical notation.
677 :     All the substrates appear before all the products, and within that
678 :     ordering, the main compounds appear first.</Notes>
679 : parrello 1.19 <IndexFields>
680 :     <IndexField name="product" order="ascending" />
681 :     <IndexField name="loc" order="ascending" />
682 :     <IndexField name="main" order="descending" />
683 :     </IndexFields>
684 : parrello 1.15 </ToIndex>
685 : parrello 1.1 </Relationship>
686 :     <Relationship name="IsLocatedIn" from="Feature" to="Contig" arity="MM">
687 :     <Notes>This relationship connects a feature to the contig segments that work together
688 :     to effect it. The segments are numbered sequentially starting from 1. The database is
689 :     required to place an upper limit on the length of each segment. If a segment is longer
690 :     than the maximum, it can be broken into smaller bits.
691 :     [p]The upper limit enables applications to locate all features that contain a specific
692 :     residue. For example, if the upper limit is 100 and we are looking for a feature that
693 :     contains residue 234 of contig [b]ABC[/b], we can look for features with a begin point
694 :     between 135 and 333. The results can then be filtered by direction and length of the
695 :     segment.</Notes>
696 :     <Fields>
697 :     <Field name="locN" type="int">
698 : parrello 1.8 <Notes>Sequence number of this segment.</Notes>
699 :     </Field>
700 : parrello 1.1 <Field name="beg" type="int">
701 : parrello 1.8 <Notes>Index (1-based) of the first residue in the contig that
702 :     belongs to the segment.</Notes>
703 :     </Field>
704 : parrello 1.1 <Field name="len" type="int">
705 : parrello 1.8 <Notes>Number of residues in the segment. A length of 0 identifies
706 :     a specific point between residues. This is the point before the residue if the direction
707 :     is forward and the point after the residue if the direction is backward.</Notes>
708 :     </Field>
709 : parrello 1.1 <Field name="dir" type="char">
710 : parrello 1.8 <Notes>Direction of the segment: [b]+[/b] if it is forward and
711 :     [b]-[/b] if it is backward.</Notes>
712 :     </Field>
713 : parrello 1.1 </Fields>
714 : parrello 1.45 <FromIndex>
715 : parrello 1.1 <Notes>This index allows the application to find all the segments of a feature in
716 : parrello 1.8 the proper order.</Notes>
717 : parrello 1.1 <IndexFields>
718 :     <IndexField name="locN" order="ascending" />
719 :     </IndexFields>
720 :     </FromIndex>
721 :     <ToIndex>
722 :     <Notes>This index is the one used by applications to find all the feature
723 :     segments that contain a specific residue.</Notes>
724 :     <IndexFields>
725 :     <IndexField name="beg" order="ascending" />
726 :     </IndexFields>
727 :     </ToIndex>
728 :     </Relationship>
729 : parrello 1.8 <Relationship name="HasProperty" from="Feature" to="Property" arity="MM">
730 :     <Notes>This relationship connects a feature to its known property values.
731 :     The relationship contains text data that indicates the paper or organization
732 :     that discovered evidence that the feature possesses the property. So, for
733 :     example, if two papers presented evidence that a feature is essential,
734 :     there would be an instance of this relationship for both.</Notes>
735 :     <Fields>
736 :     <Field name="evidence" type="text">
737 :     <Notes>URL or citation of the paper or
738 :     institution that reported evidence of the relevant feature possessing
739 :     the specified property value.</Notes>
740 :     </Field>
741 :     </Fields>
742 :     </Relationship>
743 :     <Relationship name="RoleOccursIn" from="Role" to="Diagram" arity="MM">
744 :     <Notes>This relationship connects a role to the diagrams on which it
745 :     appears. A role frequently identifies an enzyme, and can appear in many
746 :     diagrams. A diagram generally contains many different roles.</Notes>
747 :     </Relationship>
748 :     <Relationship name="HasSSCell" from="Subsystem" to="SSCell" arity="1M">
749 :     <Notes>This relationship connects a subsystem to the spreadsheet cells
750 :     used to analyze and display it. The cells themselves can be thought of
751 :     as a grid with Roles on one axis and Genomes on the other. The
752 :     various features of the subsystem are then assigned to the cells.</Notes>
753 :     </Relationship>
754 :     <Relationship name="IsTrustedBy" from="SproutUser" to="SproutUser" arity="MM">
755 :     <Notes>This relationship identifies the users trusted by each
756 :     particular user. When viewing functional assignments, the
757 :     assignment displayed is the most recent one by a user trusted
758 :     by the current user. The current user implicitly trusts himself.
759 :     If no trusted users are specified in the database, the user
760 :     also implicitly trusts the user [b]FIG[/b].</Notes>
761 :     </Relationship>
762 : parrello 1.15 <Relationship name="ConsistsOfRoles" from="RoleSubset" to="Role" arity="MM">
763 :     <Notes>This relationship connects a role subset to the roles that it covers.
764 :     A subset is, essentially, a named group of roles belonging to a specific
765 :     subsystem, and this relationship effects that. Note that will a role
766 :     may belong to many subsystems, a subset belongs to only one subsystem,
767 :     and all roles in the subset must have that subsystem in common.</Notes>
768 :     </Relationship>
769 :     <Relationship name="ConsistsOfGenomes" from="GenomeSubset" to="Genome" arity="MM">
770 :     <Notes>This relationship connects a subset to the genomes that it covers.
771 :     A subset is, essentially, a named group of genomes participating in a specific
772 :     subsystem, and this relationship effects that. Note that while a genome
773 :     may belong to many subsystems, a subset belongs to only one subsystem,
774 :     and all genomes in the subset must have that subsystem in common.</Notes>
775 :     </Relationship>
776 :     <Relationship name="HasRoleSubset" from="Subsystem" to="RoleSubset" arity="1M">
777 :     <Notes>This relationship connects a subsystem to its constituent
778 :     role subsets. Note that some roles in a subsystem may not belong to a
779 :     subset, so the relationship between roles and subsystems cannot be
780 :     derived from the relationships going through the subset.</Notes>
781 :     </Relationship>
782 :     <Relationship name="HasGenomeSubset" from="Subsystem" to="GenomeSubset" arity="1M">
783 :     <Notes>This relationship connects a subsystem to its constituent
784 :     genome subsets. Note that some genomes in a subsystem may not belong to a
785 :     subset, so the relationship between genomes and subsystems cannot be
786 :     derived from the relationships going through the subset.</Notes>
787 :     </Relationship>
788 :     <Relationship name="Catalyzes" from="Role" to="Reaction" arity="MM">
789 :     <Notes>This relationship connects a role to the reactions it catalyzes.
790 :     The purpose of a role is to create proteins that trigger certain
791 :     chemical reactions. A single reaction can be triggered by many roles,
792 :     and a role can trigger many reactions.</Notes>
793 :     </Relationship>
794 : parrello 1.39 <Relationship name="HasRoleInSubsystem" from="Feature" to="Subsystem" arity="MM">
795 :     <Notes>This relationship connects a feature to the subsystems in which it
796 :     participates. This is technically redundant information, but it is used
797 :     so often that it deserves its own table.</Notes>
798 : parrello 1.40 <Fields>
799 :     <Field name="genome" type="name-string">
800 :     <Notes>ID of the genome containing the feature</Notes>
801 :     </Field>
802 :     <Field name="type" type="key-string">
803 :     <Notes>Feature type (eg. peg, rna)</Notes>
804 :     </Field>
805 :     </Fields>
806 :     <ToIndex>
807 :     <Notes>This index enables the application to view the features of a
808 :     subsystem sorted by genome and feature type.</Notes>
809 :     <IndexFields>
810 :     <IndexField name="genome" order="ascending" />
811 :     <IndexField name="type" order="ascending" />
812 :     </IndexFields>
813 :     </ToIndex>
814 : parrello 1.39 </Relationship>
815 : parrello 1.1 </Relationships>
816 :     </Database>

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3