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

Annotation of /Sprout/NewSproutDBD.xml

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.1 - (view) (download) (as text)

1 : parrello 1.1 <Database>
2 :     <Title>Sprout Genome and Subsystem Database</Title>
3 :     <Notes>The Sprout database contains the genetic data for all complete organisms in the SeedEnvironment.
4 :     The data that is not in Sprout-- attributes, similarities, couplings-- is stored on external
5 :     servers available to the Sprout software. The Sprout database is reloaded approximately once
6 :     per month. There is significant redundancy in the Sprout database because it has been
7 :     optimized for searching. In particular, the Feature table contains an extra copy of the
8 :     feature's functional role and a list of possible search terms.</Notes>
9 :     <Entities>
10 :     <Entity name="Genome" keyType="string">
11 :     <DisplayInfo theme="nmpdr" col="3" row="1" />
12 :     <Notes>A Genome contains the sequence data for a particular individual organism.</Notes>
13 :     <Fields>
14 :     <Field name="genus" type="string">
15 :     <Notes>Genus of the relevant organism.</Notes>
16 :     </Field>
17 :     <Field name="species" type="string">
18 :     <Notes>Species of the relevant organism.</Notes>
19 :     </Field>
20 :     <Field name="unique-characterization" type="string" default="">
21 :     <Notes>The unique characterization identifies the particular organism instance from which the
22 :     genome is taken. It is possible to have in the database more than one genome for a
23 :     particular species, and every individual organism has variations in its DNA.</Notes>
24 :     </Field>
25 :     <Field name="scientific-name" type="string">
26 :     <Notes>Scientific name of this genome, usually consisting of the genus,
27 :     species, and unique characterization.</Notes>
28 :     </Field>
29 :     <Field name="version" type="string">
30 :     <Notes>Version string for this genome, generally consisting of the genome ID followed
31 :     by a period and a string of digits.</Notes>
32 :     </Field>
33 :     <Field name="complete" type="boolean">
34 :     <Notes>TRUE if the genome is complete, else FALSE</Notes>
35 :     </Field>
36 :     <Field name="dna-size" type="counter">
37 :     <Notes>number of base pairs in the genome</Notes>
38 :     </Field>
39 :     <Field name="taxonomy" type="text">
40 :     <Notes>The taxonomy string contains the full taxonomy of the organism, with individual elements
41 :     separated by semi-colons (and optional white space), starting with the domain and ending with
42 :     the disambiguated genus and species (which is the organism's scientific name plus an
43 :     identifying string).</Notes>
44 :     </Field>
45 :     <Field name="primary-group" type="string">
46 :     <Notes>The primary NMPDR group for this organism. There is always exactly one NMPDR group
47 :     per organism (either based on the organism name or a default value for supporting
48 :     genomes). In general, more data is kept on organisms in NMPDR groups than on supporting
49 :     organisms.</Notes>
50 :     </Field>
51 :     <Field name="contigs" type="int">
52 :     <Notes>Number of contigs for this organism.</Notes>
53 :     </Field>
54 :     <Field name="pegs" type="int">
55 :     <Notes>Number of protein encoding genes for this organism</Notes>
56 :     </Field>
57 :     <Field name="rnas" type="int">
58 :     <Notes>Number of RNA features found for this organism.</Notes>
59 :     </Field>
60 :     <Field name="endospore" type="semi-boolean">
61 :     <Notes>Y/N/? flag indicating whether or not this organism produces endospores.</Notes>
62 :     </Field>
63 :     <Field name="gc-content" type="float">
64 :     <Notes>Percentage of the genome that consists of G and C base pairs.</Notes>
65 :     </Field>
66 :     <Field name="habitat" type="string">
67 :     <Notes>Preferred habitat of organism.</Notes>
68 :     </Field>
69 :     <Field name="gram-stain" type="semi-boolean">
70 :     <Notes>Gram stain behaviour of organism-- positive, negative, or unknown.</Notes>
71 :     </Field>
72 :     <Field name="motility" type="semi-boolean">
73 :     <Notes>Y/N/? flag indicating whether or not this organism can move under
74 :     its own power.</Notes>
75 :     </Field>
76 :     <Field name="oxygen" type="string">
77 :     <Notes>Indication of this organism's behavior relating to environmental oxygen.</Notes>
78 :     </Field>
79 :     <Field name="temperature-min" type="float">
80 :     <Notes>Minimum optimal temperature for this organism, in degrees Celsius.</Notes>
81 :     </Field>
82 :     <Field name="temperature-max" type="float">
83 :     <Notes>Maximum optimal temperature for this organism, in degrees Celsius.</Notes>
84 :     </Field>
85 :     <Field name="pathogenic" type="semi-boolean">
86 :     <Notes>Y/N/? flag indicating whether or not this organism is pathogenic.</Notes>
87 :     </Field>
88 :     <Field name="salinity" type="string">
89 :     <Notes>Indication of this organism's behavior relating to environmental
90 :     salinity.</Notes>
91 :     </Field>
92 :     <Field name="optimal-temperature-range" type="string">
93 :     <Notes>Indication of this organism's behavior relating to environmental
94 :     temperature.</Notes>
95 :     </Field>
96 :     </Fields>
97 :     <Indexes>
98 :     <Index>
99 :     <Notes>This index allows the applications to find all genomes associated with
100 :     a specific primary (NMPDR) group.</Notes>
101 :     <IndexFields>
102 :     <IndexField name="primary-group" order="ascending" />
103 :     <IndexField name="genus" order="ascending" />
104 :     <IndexField name="species" order="ascending" />
105 :     <IndexField name="unique-characterization" order="ascending" />
106 :     </IndexFields>
107 :     </Index>
108 :     <Index>
109 :     <Notes>This index allows the applications to retrieve all genomes by genus and species
110 :     groupings.</Notes>
111 :     <IndexFields>
112 :     <IndexField name="genus" order="ascending" />
113 :     <IndexField name="species" order="ascending" />
114 :     <IndexField name="unique-characterization" order="ascending" />
115 :     </IndexFields>
116 :     </Index>
117 :     <Index>
118 :     <Notes>This index allows the applications to search for genome by scientific
119 :     name.</Notes>
120 :     <IndexFields>
121 :     <IndexField name="scientific-name" order="ascending" />
122 :     </IndexFields>
123 :     </Index>
124 :     </Indexes>
125 :     </Entity>
126 :     <Entity name="ProteinFamily" keyType="string">
127 :     <Notes>A protein family represents a group of proteins with related
128 :     functions. Some protein families are downloaded from the PFAM database
129 :     and some are FIGfams. The protein family keys all begin with the letters
130 :     PF and the FIGfams with the letters FIG.</Notes>
131 :     <Fields>
132 :     <Field name="common-name" type="string" relation="ProteinFamilyName">
133 :     <Notes>Ontological name for the protein family. Not all families
134 :     have ontological names.</Notes>
135 :     </Field>
136 :     </Fields>
137 :     <Indexes>
138 :     <Index>
139 :     <Notes>This index allows the user to locate protein families
140 :     by name.</Notes>
141 :     <IndexFields>
142 :     <IndexField name="common-name" order="ascending" />
143 :     </IndexFields>
144 :     </Index>
145 :     </Indexes>
146 :     </Entity>
147 :     <Entity name="Host" keyType="string">
148 :     <Notes>A host is a particular type of creature in which an organism has
149 :     pathogenic behavior. Hosts can be specific (Human) or general
150 :     (Animal).</Notes>
151 :     </Entity>
152 :     <Entity name="CDD" keyType="string">
153 :     <Notes>A CDD is a protein domain designator. It represents the shape of a molecular unit
154 :     on a feature's protein. The ID is six-digit string assigned by the public
155 :     Conserved Domain Database. A CDD can occur on multiple features and a feature
156 :     generally has multiple CDDs.</Notes>
157 :     </Entity>
158 :     <Entity name="Source" keyType="string">
159 :     <Notes>A source describes a place from which genome data was taken. This can be an organization
160 :     or a paper citation.</Notes>
161 :     <Fields>
162 :     <Field name="URL" type="string" relation="SourceURL">
163 :     <Notes>URL the paper cited or of the organization's web site. This field optional.</Notes>
164 :     </Field>
165 :     <Field name="description" type="text">
166 :     <Notes>Description of the source. The description can be a street address or a citation.</Notes>
167 :     </Field>
168 :     </Fields>
169 :     </Entity>
170 :     <Entity name="Contig" keyType="string">
171 :     <DisplayInfo theme="nmpdr" col="1" row="1" />
172 :     <Notes>A contig is a contiguous run of residues. The contig's ID consists of the
173 :     genome ID followed by a name that identifies which contig this is for the parent genome. As
174 :     is the case with all keys in this database, the individual components are separated by a
175 :     period. A contig can contain over a million residues. For performance reasons, therefore,
176 :     the contig is split into multiple pieces called sequences. The sequences
177 :     contain the characters that represent the residues as well as data on the quality of
178 :     the residue identification.</Notes>
179 :     </Entity>
180 :     <Entity name="Sequence" keyType="string">
181 :     <Notes>A sequence is a continuous piece of a contig. Contigs are split into
182 :     sequences so that we don't have to have the entire contig in memory when we are
183 :     manipulating it. The key of the sequence is the contig ID followed by the index of
184 :     the begin point.</Notes>
185 :     <Fields>
186 :     <Field name="sequence" type="dna">
187 :     <Notes>String consisting of the residues (base pairs). Each residue is described by a single
188 :     character in the string.</Notes>
189 :     </Field>
190 :     <Field name="quality-vector" type="text">
191 :     <Notes>String describing the quality data for each base pair. Individual values will
192 :     be separated by periods. The value represents negative exponent of the probability
193 :     of error. Thus, for example, a quality of 30 indicates the probability of error is
194 :     10^-30. A higher quality number indicates a better chance of a correct match. It is
195 :     possible that the quality data is not known for a sequence. If that is the case, the
196 :     quality vector will contain the string "unknown".</Notes>
197 :     </Field>
198 :     </Fields>
199 :     </Entity>
200 :     <Entity name="Keyword" keyType="string">
201 :     <Notes>A keyword is a word that can be used to search the feature table. This entity
202 :     contains the keyword's stem, its phonetic form, and the number of features that
203 :     can be found by searching for the word.</Notes>
204 :     <Fields>
205 :     <Field name="stem" type="string">
206 :     <Notes>The stem of a keyword is a normalized form that is independent of parts
207 :     of speech. The actual keywords stored in the database search index are stems.</Notes>
208 :     </Field>
209 :     <Field name="phonex" type="string">
210 :     <Notes>A _phonex_ is a string that identifies the phonetic characteristics of the
211 :     word stem. This can be used to find alternative spellings if an matching word is not
212 :     present.</Notes>
213 :     </Field>
214 :     </Fields>
215 :     <Indexes>
216 :     <Index>
217 :     <Notes>This index allows the user to find words by stem.</Notes>
218 :     <IndexFields>
219 :     <IndexField name="stem" order="ascending" />
220 :     </IndexFields>
221 :     </Index>
222 :     <Index>
223 :     <Notes>This index allows the user to find words by phonex.</Notes>
224 :     <IndexFields>
225 :     <IndexField name="phonex" order="ascending" />
226 :     </IndexFields>
227 :     </Index>
228 :     </Indexes>
229 :     </Entity>
230 :     <Entity name="ExternalDatabase" keyType="string">
231 :     <Notes>An external database identifies a biological database surveyed by PIR International
232 :     as part of an effort to determine which features are essentially identical between bioinformatics
233 :     organizations. Each feature in the database will have zero or more corresponding IDs that are
234 :     captured from the PIR data. Each corresponding ID is represented in a relationship between an external
235 :     database and the feature itself.</Notes>
236 :     </Entity>
237 :     <Entity name="Feature" keyType="string">
238 :     <DisplayInfo theme="nmpdr" col="3" row="3" />
239 :     <Notes>A feature (sometimes also called a "gene" is a part of a genome that is of special interest. Features
240 :     may be spread across multiple contigs of a genome, but never across more than
241 :     one genome. Features can be assigned to roles via spreadsheet cells,
242 :     and are the targets of annotation. Each feature in the database has a unique FigId.</Notes>
243 :     <Fields>
244 :     <Field name="feature-type" type="string">
245 :     <Notes>Code indicating the type of this feature. Among the codes currently
246 :     supported are "peg" for a protein encoding gene, "bs" for a
247 :     binding site, "opr" for an operon, and so forth.</Notes>
248 :     </Field>
249 :     <Field name="translation" type="text" relation="FeatureTranslation">
250 :     <Notes>(optional) A translation of this feature's residues into
251 :     protein character codes, formed by concatenating the pieces
252 :     of the feature together. Only protein encoding genes have
253 :     translations.</Notes>
254 :     </Field>
255 :     <Field name="upstream-sequence" type="text" relation="FeatureUpstream">
256 :     <Notes>Upstream sequence for the feature. This includes residues preceding the feature as
257 :     well as some of the feature's initial residues.</Notes>
258 :     </Field>
259 :     <Field name="assignment" type="text">
260 :     <Notes>Default functional assignment for this feature.</Notes>
261 :     </Field>
262 :     <Field name="assignment-maker" type="string">
263 :     <Notes>name of the user who made the functional assignment</Notes>
264 :     </Field>
265 :     <Field name="assignment-quality" type="char">
266 :     <Notes>quality of the functional assignment, usually a space, but may be W (indicating weak) or X
267 :     (indicating experimental)</Notes>
268 :     </Field>
269 :     <Field name="keywords" type="text" searchable="1">
270 :     <Notes>This is a list of search keywords for the feature. It includes the
271 :     functional assignment, subsystem roles, and special properties.</Notes>
272 :     </Field>
273 :     <Field name="link" type="text" relation="FeatureLink">
274 :     <Notes>Web hyperlink for this feature. A feature can have no hyperlinks or it can have many. The
275 :     links are to other websites that have useful about the gene that the feature represents, and
276 :     are coded as raw HTML.</Notes>
277 :     </Field>
278 :     <Field name="essential" type="link" relation="FeatureEssential" special="property_search">
279 :     <Notes>A value indicating the essentiality of the feature, coded as HTML. In most
280 :     cases, this will be a word describing whether the essentiality is confirmed (essential)
281 :     or potential (potential-essential), hyperlinked to the document from which the
282 :     essentiality was curated. If a feature is not essential, this field will have no
283 :     values; otherwise, it may have multiple values.</Notes>
284 :     </Field>
285 :     <Field name="virulent" type="link" relation="FeatureVirulent" special="property_search">
286 :     <Notes>A value indicating the virulence of the feature, coded as HTML. In most
287 :     cases, this will be a phrase or SA number hyperlinked to the document from which
288 :     the virulence information was curated. If the feature is not virulent, this field
289 :     will have no values; otherwise, it may have multiple values.</Notes>
290 :     </Field>
291 :     <Field name="iedb" type="link" relation="FeatureIEDB" special="property_search">
292 :     <Notes>A value indicating whether or not the feature can be found in the
293 :     Immune Epitope Database. If the feature has not been matched to that database,
294 :     this field will have no values. Otherwise, it will have an epitope name and/or
295 :     sequence, hyperlinked to the database.</Notes>
296 :     </Field>
297 :     <Field name="location-string" type="text">
298 :     <Notes>Location of the feature, expressed as a comma-delimited list of Sprout location
299 :     strings. This gives us a fast mechanism for extracting the feature location. Otherwise,
300 :     we have to painstakingly paste together the IsLocatedIn records, which are themselves
301 :     designed to help look for features in a particular region rather than to find the location
302 :     of a feature.</Notes>
303 :     </Field>
304 :     <Field name="signal-peptide" type="string">
305 :     <Notes>The signal peptide location for this feature. This is expressed as start and end
306 :     numbers with a hyphen for the relevant amino acids. So, "1-22" would indicate a signal
307 :     peptide at the beginning of the feature's protein and extending through 22 amino acid
308 :     positions. An empty string means no signal peptide is present.</Notes>
309 :     </Field>
310 :     <Field name="transmembrane-map" type="text">
311 :     <Notes>A map indicating which sections of a protein will be embedded in a membrane.
312 :     This is expressed as a comma-separated list of as start and end numbers with hyphens
313 :     for the relevant amino acids. So, "10-12, 40-60" would indicate that there are two
314 :     sections of the protein that become embedded in a membrane: the 10th through 12th
315 :     amino acids, and the 40th through the 60th. An empty string means no
316 :     transmembrane regions are known.</Notes>
317 :     </Field>
318 :     <Field name="similar-to-human" type="boolean">
319 :     <Notes>TRUE if this feature generates a protein that is similar to one found in humans,
320 :     else FALSE</Notes>
321 :     </Field>
322 :     <Field name="isoelectric-point" type="float">
323 :     <Notes>pH in the surrounding medium at which the charge on a protein is neutral.
324 :     If the pH of the medium is lower than this value, the protein will have a net
325 :     positive charge. If the pH of the medium is higher, then the protein will have a
326 :     net negative charge.</Notes>
327 :     </Field>
328 :     <Field name="molecular-weight" type="float">
329 :     <Notes>Molecular weight of this feature's protein, in daltons. A weight of 0
330 :     indicates that no protein is created.</Notes>
331 :     </Field>
332 :     <Field name="sequence-length" type="counter">
333 :     <Notes>Number of base pairs in this feature.</Notes>
334 :     </Field>
335 :     <Field name="locked" type="boolean">
336 :     <Notes>TRUE if a feature's assignment is locked. A locked feature's functional
337 :     role cannot be changed by automated programs.</Notes>
338 :     </Field>
339 :     <Field name="in-genbank" type="boolean">
340 :     <Notes>TRUE if a feature can be found in GenBank, else FALSE</Notes>
341 :     </Field>
342 :     <Field name="conserved-neighbors" type="int">
343 :     <Notes>number of coupled features</Notes>
344 :     </Field>
345 :     <Field name="transmembrane-domain-count" type="int">
346 :     <Notes>number of sections in the feature's protein that
347 :     become embedded in the cell membrane</Notes>
348 :     </Field>
349 :     <Field name="ec" type="string" relation="FeatureEC">
350 :     <Notes>An EC number associated with this feature.</Notes>
351 :     </Field>
352 :     </Fields>
353 :     <Indexes>
354 :     <Index>
355 :     <Notes>This index supports looking up features by EC
356 :     number.</Notes>
357 :     <IndexFields>
358 :     <IndexField name="ec" order="ascending" />
359 :     </IndexFields>
360 :     </Index>
361 :     </Indexes>
362 :     </Entity>
363 :     <Entity name="FeatureAlias" keyType="string">
364 :     <Notes>Alternative names for features. A feature can have many aliases. In general,
365 :     each alias corresponds to only one feature, but there are many exceptions to this rule.</Notes>
366 :     </Entity>
367 :     <Entity name="SproutUser" keyType="string">
368 :     <Notes>A user is a person who can make annotations and view data in the database. The
369 :     user object is keyed on the user's login name.</Notes>
370 :     <Fields>
371 :     <Field name="description" type="string">
372 :     <Notes>Full name or description of this user.</Notes>
373 :     </Field>
374 :     </Fields>
375 :     </Entity>
376 :     <Entity name="SynonymGroup" keyType="string">
377 :     <Notes>A synonym group represents a group of features. Features that represent substantially
378 :     identical proteins or DNA sequences are mapped to the same synonym group, and this information is
379 :     used to expand similarities.</Notes>
380 :     </Entity>
381 :     <Entity name="Role" keyType="string">
382 :     <DisplayInfo theme="web" col="7" row="3" />
383 :     <Notes>A role describes a biological function that may be fulfilled by a feature.
384 :     One of the main goals of the database is to record the roles of the various features.</Notes>
385 :     </Entity>
386 :     <Entity name="RoleEC" keyType="string">
387 :     <Notes>EC code for a role.</Notes>
388 :     </Entity>
389 :     <Entity name="Annotation" keyType="string">
390 :     <DisplayInfo theme="seed" col="1" row="3" />
391 :     <Notes>An annotation contains supplementary information about a feature. The most
392 :     important type of annotation is the assignment of a functional role; however,
393 :     other types of annotations are also possible.</Notes>
394 :     <Fields>
395 :     <Field name="time" type="date">
396 :     <Notes>Date and time of the annotation.</Notes>
397 :     </Field>
398 :     <Field name="annotation" type="text">
399 :     <Notes>Text of the annotation.</Notes>
400 :     </Field>
401 :     </Fields>
402 :     <Indexes>
403 :     <Index>
404 :     <Notes>This index allows the user to find recent annotations.</Notes>
405 :     <IndexFields>
406 :     <IndexField name="time" order="descending" />
407 :     </IndexFields>
408 :     </Index>
409 :     </Indexes>
410 :     </Entity>
411 :     <Entity name="Reaction" keyType="string">
412 :     <DisplayInfo theme="web" col="7" row="5" />
413 :     <Notes>A reaction is a chemical process catalyzed by a protein. The reaction ID
414 :     is generally a small number preceded by a letter.</Notes>
415 :     <Fields>
416 :     <Field name="url" type="string" relation="ReactionURL">
417 :     <Notes>HTML string containing a link to a web location that describes the
418 :     reaction. This field is optional.</Notes>
419 :     </Field>
420 :     <Field name="rev" type="boolean">
421 :     <Notes>TRUE if this reaction is reversible, else FALSE</Notes>
422 :     </Field>
423 :     </Fields>
424 :     </Entity>
425 :     <Entity name="Compound" keyType="string">
426 :     <DisplayInfo theme="web" col="7" row="7" />
427 :     <Notes>A compound is a chemical that participates in a reaction.
428 :     All compounds have a unique ID and may also have one or more names.</Notes>
429 :     <Fields>
430 :     <Field name="label" type="string">
431 :     <Notes>Name used in reaction display strings. This is the same as the name
432 :     possessing a priority of 1, but it is placed here to speed up the query
433 :     used to create the display strings.</Notes>
434 :     </Field>
435 :     </Fields>
436 :     </Entity>
437 :     <Entity name="CompoundName" keyType="string">
438 :     <Notes>A compound name is a common name for the chemical represented by a
439 :     compound.</Notes>
440 :     </Entity>
441 :     <Entity name="CompoundCAS" keyType="string">
442 :     <Notes>This entity represents the Chemical Abstract Service ID for a
443 :     compound. Each Compound has at most one CAS ID.</Notes>
444 :     </Entity>
445 :     <Entity name="Subsystem" keyType="string">
446 :     <DisplayInfo theme="seed" col="5" row="1" />
447 :     <Notes>A subsystem is a collection of roles that work together in a cell. Identification of subsystems
448 :     is an important tool for recognizing parallel genetic features in different organisms.</Notes>
449 :     <Fields>
450 :     <Field name="version" type="int">
451 :     <Notes>Version number for the subsystem. This value is incremented each time the subsystem
452 :     is backed up.</Notes>
453 :     </Field>
454 :     <Field name="curator" type="string">
455 :     <Notes>Name of the person currently in charge of the subsystem.</Notes>
456 :     </Field>
457 :     <Field name="notes" type="text">
458 :     <Notes>Descriptive notes about the subsystem.</Notes>
459 :     </Field>
460 :     <Field name="description" type="text">
461 :     <Notes>Description of the subsystem's function in the cell.</Notes>
462 :     </Field>
463 :     <Field name="classification" type="string" relation="SubsystemClass">
464 :     <Notes>Classification string, colon-delimited. This string organizes the
465 :     subsystems into a hierarchy.</Notes>
466 :     </Field>
467 :     <Field name="hope-curation-notes" type="text" relation="SubsystemHopeNotes">
468 :     <Notes>Text description of how the scenarios were curated.</Notes>
469 :     </Field>
470 :     </Fields>
471 :     </Entity>
472 :     <Entity name="RoleSubset" keyType="string">
473 :     <Notes>A role subset is a named collection of roles in a particular subsystem. The
474 :     subset names are generally very short, non-unique strings. The ID of the parent
475 :     subsystem is prefixed to the subset ID in order to make it unique.</Notes>
476 :     </Entity>
477 :     <Entity name="GenomeSubset" keyType="string">
478 :     <Notes>A genome subset is a named collection of genomes that participate
479 :     in a particular subsystem. The subset names are generally very short, non-unique
480 :     strings. The ID of the parent subsystem is prefixed to the subset ID in order
481 :     to make it unique.</Notes>
482 :     </Entity>
483 :     <Entity name="SSCell" keyType="hash-string">
484 :     <DisplayInfo theme="seed" col="5" row="3" />
485 :     <Notes>Part of the process of subsystem annotation of features
486 :     is creating a spreadsheet of genomes and roles to which features are assigned.
487 :     A spreadsheet cell represents one of the positions on the spreadsheet.</Notes>
488 :     <Fields>
489 :     <Field name="column-number" type="int">
490 :     <Notes>Column number of this cell. This value is put here to
491 :     improve the performance of an essential query.</Notes>
492 :     </Field>
493 :     </Fields>
494 :     </Entity>
495 :     <Entity name="Property" keyType="int">
496 :     <Notes>A property is a type of assertion that could be made about the properties of
497 :     a particular feature. Each property instance is a key/value pair and can be associated
498 :     with many different features. Conversely, a feature can be associated with many key/value
499 :     pairs, even some that notionally contradict each other. For example, there can be evidence
500 :     that a feature is essential to the organism's survival and evidence that it is superfluous.</Notes>
501 :     <Fields>
502 :     <Field name="property-name" type="string">
503 :     <Notes>Name of this property.</Notes>
504 :     </Field>
505 :     <Field name="property-value" type="text">
506 :     <Notes>Value associated with this property. For each property
507 :     name, there must by a property record for all of its possible
508 :     values.</Notes>
509 :     </Field>
510 :     </Fields>
511 :     <Indexes>
512 :     <Index>
513 :     <Notes>This index enables the application to find all values for a specified property
514 :     name, or any given name/value pair.</Notes>
515 :     <IndexFields>
516 :     <IndexField name="property-name" order="ascending" />
517 :     <IndexField name="property-value" order="ascending" />
518 :     </IndexFields>
519 :     </Index>
520 :     </Indexes>
521 :     </Entity>
522 :     <Entity name="Diagram" keyType="string">
523 :     <DisplayInfo theme="web" col="7" row="1" />
524 :     <Notes>A functional diagram describes a network of chemical reactions, often comprising a single
525 :     subsystem. A diagram is identified by a short name and contains a longer descriptive name.
526 :     The actual diagram shows which functional roles guide the reactions along with the inputs
527 :     and outputs; the database, however, only indicates which roles belong to a particular
528 :     diagram's map.</Notes>
529 :     <Fields>
530 :     <Field name="name" type="text">
531 :     <Notes>Descriptive name of this diagram.</Notes>
532 :     </Field>
533 :     </Fields>
534 :     </Entity>
535 :     <Entity name="PDB" keyType="string">
536 :     <DisplayInfo theme="web" col="3" row="5" />
537 :     <Notes>A PDB is a protein data bank entry containing information that can be used
538 :     to determine the shape of the protein and the energies required to dock with it.
539 :     The ID is the four-character name used on the PDB web site.</Notes>
540 :     <Fields>
541 :     <Field name="docking-count" type="int">
542 :     <Notes>The number of ligands that have been docked against this PDB.</Notes>
543 :     </Field>
544 :     </Fields>
545 :     <Indexes>
546 :     <Index>
547 :     <IndexFields>
548 :     <IndexField name="docking-count" order="descending" />
549 :     <IndexField name="id" order="ascending" />
550 :     </IndexFields>
551 :     </Index>
552 :     </Indexes>
553 :     </Entity>
554 :     <Entity name="Ligand" keyType="string">
555 :     <DisplayInfo theme="web" col="3" row="7" />
556 :     <Notes>A Ligand is a chemical of interest in computing docking energies against a PDB.
557 :     The ID of the ligand is an 8-digit ID number in the ZINC database.</Notes>
558 :     <Fields>
559 :     <Field name="name" type="long-string">
560 :     <Notes>Chemical name of this ligand.</Notes>
561 :     </Field>
562 :     </Fields>
563 :     </Entity>
564 :     <Entity name="CellLocation" keyType="string">
565 :     <Notes>A section of the cell in which a protein might be found. This includes the cell wall or
566 :     membrane, outside the cell, inside the cell, and so forth.</Notes>
567 :     </Entity>
568 :     <Entity name="Scenario" keyType="string">
569 :     <Notes>A scenario used to verify the validity of subsystem assignments. Each
570 :     scenario converrts input compounds to output compounds using reactions.
571 :     The scenario may use all of the reactions controlled by a subsystem or only
572 :     some, and may also incorporate additional reactions.</Notes>
573 :     </Entity>
574 :     </Entities>
575 :     <Relationships>
576 :     <Relationship name="IsPathogenicIn" from="Genome" to="Host" arity="MM">
577 :     <Notes>This relationship connects a genome to a host in which it is
578 :     pathogenic. Many genomes do not have a pathogenic host; some have
579 :     multiple hosts.</Notes>
580 :     </Relationship>
581 :     <Relationship name="IsFamilyForFeature" from="ProteinFamily" to="Feature"
582 :     arity="MM" converse="IsInFamily">
583 :     <Notes>This relationship connects a feature to its protein
584 :     families.</Notes>
585 :     <Fields>
586 :     <Field name="range" type="string">
587 :     <Notes>Location in the feature of the matching protein.</Notes>
588 :     </Field>
589 :     </Fields>
590 :     </Relationship>
591 :     <Relationship name="Catalyzes" from="Role" to="Reaction" arity="MM"
592 :     converse="IsCatalyzedBy">
593 :     <DisplayInfo theme="web" />
594 :     <Notes>This relationship connects a role to the reactions it catalyzes.
595 :     The purpose of a role is to create proteins that trigger certain
596 :     chemical reactions. A single reaction can be triggered by many roles,
597 :     and a role can trigger many reactions.</Notes>
598 :     </Relationship>
599 :     <Relationship name="ExcludesReaction" from="Scenario" to="Reaction" arity="MM">
600 :     <Notes>This relationship connects a scenario to reactions of the parent
601 :     subsystem that do not participate in it.</Notes>
602 :     </Relationship>
603 :     <Relationship name="IncludesReaction" from="Scenario" to="Reaction" arity="MM">
604 :     <Notes>This relationship connects a scenario to reactions that participate
605 :     in it but are not part of the parent subsystem.</Notes>
606 :     </Relationship>
607 :     <Relationship name="HasScenario" from="Subsystem" to="Scenario" arity="MM">
608 :     <Notes>This relationship connects a role to the scenarios used to
609 :     validate it.</Notes>
610 :     </Relationship>
611 :     <Relationship name="IsInputFor" from="Compound" to="Scenario" arity="MM">
612 :     <Notes>This relationship connects a scenario to its input compounds.</Notes>
613 :     </Relationship>
614 :     <Relationship name="IsOutputOf" from="Compound" to="Scenario" arity="MM">
615 :     <Notes>This relationship connects a scenario to its output compounds</Notes>
616 :     <Fields>
617 :     <Field name="auxiliary" type="boolean">
618 :     <Notes>TRUE if this is an auxiliary output compound, FALSE if it is a
619 :     main output compound.</Notes>
620 :     </Field>
621 :     </Fields>
622 :     </Relationship>
623 :     <Relationship name="IsOnDiagram" from="Scenario" to="Diagram" arity="MM">
624 :     <Notes>This relationship connects a scenario to related diagrams.</Notes>
625 :     </Relationship>
626 :     <Relationship name="IsPossiblePlaceFor" from="CellLocation" to="Feature" arity="MM">
627 :     <Notes>This relationship connects a feature with the various places in a cell that the feature
628 :     might be found. The confidence factor is included as intersection data.</Notes>
629 :     <Fields>
630 :     <Field name="confidence" type="float">
631 :     <Notes>Confidence that the protein will be found in this location, expressed as a
632 :     value from 0 to 10.</Notes>
633 :     </Field>
634 :     </Fields>
635 :     </Relationship>
636 :     <Relationship name="IsPresentOnProteinOf" from="CDD" to="Feature" arity="MM">
637 :     <Notes>This relationship connects a feature to its CDD protein domains. The
638 :     match score is included as intersection data.</Notes>
639 :     <Fields>
640 :     <Field name="score" type="float">
641 :     <Notes>This is the match score between the feature and the CDD. A
642 :     lower score is a better match.</Notes>
643 :     </Field>
644 :     </Fields>
645 :     <FromIndex>
646 :     <IndexFields>
647 :     <IndexField name="score" order="ascending" />
648 :     </IndexFields>
649 :     </FromIndex>
650 :     </Relationship>
651 :     <Relationship name="IsIdentifiedByCAS" from="Compound" to="CompoundCAS" arity="MM">
652 :     <Notes>Relates a compound's CAS ID to the compound itself. Every CAS ID is
653 :     associated with a compound, and some are associated with two compounds, but not
654 :     all compounds have CAS IDs.</Notes>
655 :     </Relationship>
656 :     <Relationship name="IsIdentifiedByEC" from="Role" to="RoleEC" arity="MM">
657 :     <Notes>Relates a role to its EC number. Every EC number is associated with a
658 :     role, but not all roles have EC numbers.</Notes>
659 :     </Relationship>
660 :     <Relationship name="IsAliasOf" from="FeatureAlias" to="Feature" arity="MM">
661 :     <Notes>Connects an alias to the feature it represents. Every alias connects
662 :     to at least 1 feature, and a feature connects to many aliases.</Notes>
663 :     </Relationship>
664 :     <Relationship name="HasCompoundName" from="Compound" to="CompoundName" arity="MM">
665 :     <Notes>Connects a compound to its names. A compound generally has several
666 :     names</Notes>
667 :     <Fields>
668 :     <Field name="priority" type="int">
669 :     <Notes>Priority of this name, with 1 being the highest priority, 2
670 :     the next highest, and so forth.</Notes>
671 :     </Field>
672 :     </Fields>
673 :     <FromIndex>
674 :     <Notes>This index enables the application to view the names of a compound
675 :     in priority order.</Notes>
676 :     <IndexFields>
677 :     <IndexField name="priority" order="ascending" />
678 :     </IndexFields>
679 :     </FromIndex>
680 :     </Relationship>
681 :     <Relationship name="IsProteinForFeature" from="PDB" to="Feature" arity="MM">
682 :     <DisplayInfo caption="Is Protein\nFor Feature" theme="web" />
683 :     <Notes>Relates a PDB to features that produce highly similar proteins.</Notes>
684 :     <Fields>
685 :     <Field name="score" type="float">
686 :     <Notes>Similarity score for the comparison between the feature and
687 :     the PDB protein. A lower score indicates a better match.</Notes>
688 :     </Field>
689 :     <Field name="start-location" type="int">
690 :     <Notes>Starting location within the feature of the matching region.</Notes>
691 :     </Field>
692 :     <Field name="end-location" type="int">
693 :     <Notes>Ending location within the feature of the matching region.</Notes>
694 :     </Field>
695 :     </Fields>
696 :     <ToIndex>
697 :     <Notes>This index enables the application to view the PDBs of a
698 :     feature in order from the closest match to the furthest.</Notes>
699 :     <IndexFields>
700 :     <IndexField name="score" order="ascending" />
701 :     </IndexFields>
702 :     </ToIndex>
703 :     <FromIndex>
704 :     <Notes>This index enables the application to view the features of
705 :     a PDB in order from the closest match to the furthest.</Notes>
706 :     <IndexFields>
707 :     <IndexField name="score" order="ascending" />
708 :     </IndexFields>
709 :     </FromIndex>
710 :     </Relationship>
711 :     <Relationship name="DocksWith" from="PDB" to="Ligand" arity="MM">
712 :     <DisplayInfo caption="Docks With" theme="web" />
713 :     <Notes>Indicates that a docking result exists between a PDB and a ligand. The
714 :     docking result describes the energy required for the ligand to dock with
715 :     the protein described by the PDB. A lower energy indicates the ligand has a
716 :     good chance of disabling the protein. At the current time, only the best
717 :     docking results are kept.</Notes>
718 :     <Fields>
719 :     <Field name="reason" type="string">
720 :     <Notes>Indication of the reason for determining the docking result.
721 :     A value of =Random= indicates the docking was attempted as a part
722 :     of a random survey used to determine the docking characteristics of the
723 :     PDB. A value of =Rich= indicates the docking was attempted because
724 :     a low-energy docking result was predicted for the ligand with respect
725 :     to the PDB.</Notes>
726 :     </Field>
727 :     <Field name="tool" type="string">
728 :     <Notes>Name of the tool used to produce the docking result.</Notes>
729 :     </Field>
730 :     <Field name="total-energy" type="float">
731 :     <Notes>Total energy required for the ligand to dock with the PDB
732 :     protein, in kcal/mol. A negative value means energy is released.</Notes>
733 :     </Field>
734 :     <Field name="vanderwaals-energy" type="float">
735 :     <Notes>Docking energy in kcal/mol that results from the geometric fit
736 :     (Van der Waals force) between the PDB and the ligand.</Notes>
737 :     </Field>
738 :     <Field name="electrostatic-energy" type="float">
739 :     <Notes>Docking energy in kcal/mol that results from the movement of
740 :     electrons (electrostatic force) between the PDB and the ligand.</Notes>
741 :     </Field>
742 :     </Fields>
743 :     <FromIndex>
744 :     <Notes>This index enables the application to view a PDB's docking results from
745 :     the lowest energy (best docking) to highest energy (worst docking).</Notes>
746 :     <IndexFields>
747 :     <IndexField name="total-energy" order="ascending" />
748 :     </IndexFields>
749 :     </FromIndex>
750 :     <ToIndex>
751 :     <Notes>This index enables the application to view a ligand's docking results from
752 :     the lowest energy (best docking) to highest energy (worst docking).</Notes>
753 :     </ToIndex>
754 :     </Relationship>
755 :     <Relationship name="IsAlsoFoundIn" from="Feature" to="ExternalDatabase" arity="MM">
756 :     <Notes>This relationship connects a feature to external databases that contain
757 :     essentially identical features. The name used in the external database is stored
758 :     in the relationship as intersection data.</Notes>
759 :     <Fields>
760 :     <Field name="alias" type="string">
761 :     <Notes>ID of the feature in the specified external database.</Notes>
762 :     </Field>
763 :     </Fields>
764 :     <Indexes>
765 :     <Index>
766 :     <Notes>This index allows direct access to features by external ID.</Notes>
767 :     <IndexFields>
768 :     <IndexField name="alias" order="ascending" />
769 :     </IndexFields>
770 :     </Index>
771 :     </Indexes>
772 :     </Relationship>
773 :     <Relationship name="IsSynonymGroupFor" from="SynonymGroup" to="Feature" arity="MM">
774 :     <Notes>This relation connects a synonym group to the features that make it
775 :     up.</Notes>
776 :     </Relationship>
777 :     <Relationship name="HasFeature" from="Genome" to="Feature" arity="1M" converse="IsInGenome">
778 :     <DisplayInfo theme="nmpdr" caption="Has\nFeature" />
779 :     <Notes>This relationship connects a genome to all of its features. This
780 :     relationship is redundant in a sense, because the genome ID is part
781 :     of the feature ID; however, it makes the creation of certain queries more
782 :     convenient because you can drag in filtering information for a feature's
783 :     genome.</Notes>
784 :     <Fields>
785 :     <Field name="type" type="string">
786 :     <Notes>Feature type (eg. peg, rna)</Notes>
787 :     </Field>
788 :     </Fields>
789 :     <FromIndex>
790 :     <Notes>This index enables the application to view the features of a
791 :     Genome sorted by type.</Notes>
792 :     <IndexFields>
793 :     <IndexField name="type" order="ascending" />
794 :     </IndexFields>
795 :     </FromIndex>
796 :     </Relationship>
797 :     <Relationship name="HasContig" from="Genome" to="Contig" arity="1M">
798 :     <DisplayInfo caption="Is Part Of" theme="nmpdr" />
799 :     <Notes>This relationship connects a genome to the contigs that contain the actual genetic
800 :     information.</Notes>
801 :     </Relationship>
802 :     <Relationship name="ComesFrom" from="Genome" to="Source" arity="MM">
803 :     <Notes>This relationship connects a genome to the sources that mapped it. A genome can
804 :     come from a single source or from a cooperation among multiple sources.</Notes>
805 :     </Relationship>
806 :     <Relationship name="IsMadeUpOf" from="Contig" to="Sequence" arity="1M">
807 :     <Notes>A contig is stored in the database as an ordered set of sequences. By splitting the
808 :     contig into sequences, we get a performance boost from only needing to keep small portions
809 :     of a contig in memory at any one time. This relationship connects the contig to its
810 :     constituent sequences.</Notes>
811 :     <Fields>
812 :     <Field name="len" type="int">
813 :     <Notes>Length of the sequence.</Notes>
814 :     </Field>
815 :     <Field name="start-position" type="int">
816 :     <Notes>Index (1-based) of the point in the contig where this
817 :     sequence starts.</Notes>
818 :     </Field>
819 :     </Fields>
820 :     <FromIndex>
821 :     <Notes>This index enables the application to find all of the sequences in
822 :     a contig in order, and makes it easier to find a particular residue section.</Notes>
823 :     <IndexFields>
824 :     <IndexField name="start-position" order="ascending" />
825 :     <IndexField name="len" order="ascending" />
826 :     </IndexFields>
827 :     </FromIndex>
828 :     </Relationship>
829 :     <Relationship name="IsTargetOfAnnotation" from="Feature" to="Annotation" arity="1M">
830 :     <DisplayInfo caption="Targets" theme="seed" />
831 :     <Notes>This relationship connects a feature to its annotations.</Notes>
832 :     </Relationship>
833 :     <Relationship name="MadeAnnotation" from="SproutUser" to="Annotation" arity="1M">
834 :     <Notes>This relationship connects an annotation to the user who made it.</Notes>
835 :     </Relationship>
836 :     <Relationship name="ParticipatesIn" from="Genome" to="Subsystem" arity="MM">
837 :     <DisplayInfo caption="\nParticipates\nIn" theme="seed" />
838 :     <Notes>This relationship connects subsystems to the genomes that use
839 :     it. If the subsystem has been curated for the genome, then the subsystem's roles will also be
840 :     connected to the genome features through the *SSCell* object.</Notes>
841 :     <Fields>
842 :     <Field name="variant-code" type="string">
843 :     <Notes>Code indicating the subsystem variant to which this
844 :     genome belongs. Each subsystem can have multiple variants. A variant
845 :     code of -1 indicates that the genome does not have a functional
846 :     variant of the subsystem. A variant code of 0 indicates that
847 :     the genome's participation is considered iffy.</Notes>
848 :     </Field>
849 :     </Fields>
850 :     <ToIndex>
851 :     <Notes>This index enables the application to find all of the genomes using
852 :     a subsystem in order by variant code, which is how we wish to display them
853 :     in the spreadsheets.</Notes>
854 :     <IndexFields>
855 :     <IndexField name="variant-code" order="ascending" />
856 :     </IndexFields>
857 :     </ToIndex>
858 :     </Relationship>
859 :     <Relationship name="OccursInSubsystem" from="Role" to="Subsystem" arity="MM">
860 :     <DisplayInfo caption="Uses" theme="seed" />
861 :     <Notes>This relationship connects roles to the subsystems that implement them.</Notes>
862 :     <Fields>
863 :     <Field name="abbr" type="string">
864 :     <Notes>Abbreviated name for the role, generally non-unique, but useful
865 :     in column headings for HTML tables.</Notes>
866 :     </Field>
867 :     <Field name="column-number" type="int">
868 :     <Notes>Column number for this role in the specified subsystem's
869 :     spreadsheet.</Notes>
870 :     </Field>
871 :     <Field name="auxiliary" type="boolean">
872 :     <Notes>If TRUE, then this role is ancillary to the purpose of the subsystem.
873 :     If FALSE, it is essential to its metabolic pathway.</Notes>
874 :     </Field>
875 :     <Field name="hope-reaction-note" type="text">
876 :     <Notes>A description of the status of a role in relation to the
877 :     reactions it produces as determined by the scenarios. If present,
878 :     will indicate if the role has been determined to be auxiliary,
879 :     if it has been examined to verify an automatic assignment, and so
880 :     forth.</Notes>
881 :     </Field>
882 :     </Fields>
883 :     <ToIndex>
884 :     <Notes>This index enables the application to see the subsystem roles
885 :     in column order. The ordering of the roles is usually significant,
886 :     so it is important to preserve it.</Notes>
887 :     <IndexFields>
888 :     <IndexField name="column-number" order="ascending" />
889 :     </IndexFields>
890 :     </ToIndex>
891 :     </Relationship>
892 :     <Relationship name="IsGenomeOf" from="Genome" to="SSCell" arity="1M">
893 :     <DisplayInfo caption="Is Row Of" theme="seed" />
894 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
895 :     genome for the spreadsheet column.</Notes>
896 :     </Relationship>
897 :     <Relationship name="IsRoleOf" from="Role" to="SSCell" arity="1M">
898 :     <DisplayInfo caption="Is In\nColumn\nFor" theme="seed" />
899 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
900 :     role for the spreadsheet row.</Notes>
901 :     </Relationship>
902 :     <Relationship name="ContainsFeature" from="SSCell" to="Feature" arity="MM">
903 :     <DisplayInfo caption="Is\nContained\nIn" theme="seed" />
904 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
905 :     features assigned to it.</Notes>
906 :     <Fields>
907 :     <Field name="cluster-number" type="int">
908 :     <Notes>ID of this feature's cluster. Clusters represent families of
909 :     related proteins participating in a subsystem.</Notes>
910 :     </Field>
911 :     </Fields>
912 :     </Relationship>
913 :     <Relationship name="IsAComponentOf" from="Compound" to="Reaction" arity="MM">
914 :     <DisplayInfo caption="Involves" theme="web" />
915 :     <Notes>This relationship connects a reaction to the compounds that participate
916 :     in it.</Notes>
917 :     <Fields>
918 :     <Field name="product" type="boolean">
919 :     <Notes>TRUE if the compound is a product of the reaction, FALSE if
920 :     it is a substrate. When a reaction is written on paper in
921 :     chemical notation, the substrates are left of the arrow and the
922 :     products are to the right. Sorting on this field will cause
923 :     the substrates to appear first, followed by the products. If the
924 :     reaction is reversible, then the notion of substrates and products
925 :     is not at intuitive; however, a value here of FALSE still puts the
926 :     compound left of the arrow and a value of TRUE still puts it to the
927 :     right.</Notes>
928 :     </Field>
929 :     <Field name="stoichiometry" type="string">
930 :     <Notes>Number of molecules of the compound that participate in a
931 :     single instance of the reaction. For example, if a reaction
932 :     produces two water molecules, the stoichiometry of water for the
933 :     reaction would be two. When a reaction is written on paper in
934 :     chemical notation, the stoichiometry is the number next to the
935 :     chemical formula of the compound.</Notes>
936 :     </Field>
937 :     <Field name="main" type="boolean">
938 :     <Notes>TRUE if this compound is one of the main participants in
939 :     the reaction, else FALSE. It is permissible for none of the
940 :     compounds in the reaction to be considered main, in which
941 :     case this value would be FALSE for all of the relevant
942 :     compounds.</Notes>
943 :     </Field>
944 :     <Field name="loc" type="string">
945 :     <Notes>An optional character string that indicates the relative
946 :     position of this compound in the reaction's chemical formula. The
947 :     location affects the way the compounds present as we cross the
948 :     relationship from the reaction side. The product/substrate flag
949 :     comes first, then the value of this field, then the main flag.
950 :     The default value is an empty string; however, the empty string
951 :     sorts first, so if this field is used, it should probably be
952 :     used for every compound in the reaction.</Notes>
953 :     </Field>
954 :     <Field name="discriminator" type="int">
955 :     <Notes>A unique ID for this record. The discriminator does not
956 :     provide any useful data, but it prevents identical records from
957 :     being collapsed by the SELECT DISTINCT command used by ERDB to
958 :     retrieve data.</Notes>
959 :     </Field>
960 :     </Fields>
961 :     <ToIndex>
962 :     <Notes>This index presents the compounds in the reaction in the
963 :     order they should be displayed when writing it in chemical notation.
964 :     All the substrates appear before all the products, and within that
965 :     ordering, the main compounds appear first.</Notes>
966 :     <IndexFields>
967 :     <IndexField name="product" order="ascending" />
968 :     <IndexField name="loc" order="ascending" />
969 :     <IndexField name="main" order="descending" />
970 :     </IndexFields>
971 :     </ToIndex>
972 :     </Relationship>
973 :     <Relationship name="IsLocatedIn" from="Feature" to="Contig" arity="MM">
974 :     <DisplayInfo caption="Is\nLocation\nOf" theme="nmpdr" />
975 :     <Notes>This relationship connects a feature to the contig segments that work together
976 :     to effect it. The segments are numbered sequentially starting from 1. The database is
977 :     required to place an upper limit on the length of each segment. If a segment is longer
978 :     than the maximum, it can be broken into smaller bits. The upper limit enables applications
979 :     to locate all features that contain a specific residue. For example, if the upper limit
980 :     is 100 and we are looking for a feature that contains residue 234 of contig *ABC*, we
981 :     can look for features with a begin point between 135 and 333. The results can then be
982 :     filtered by direction and length of the segment.</Notes>
983 :     <Fields>
984 :     <Field name="locN" type="int">
985 :     <Notes>Sequence number of this segment.</Notes>
986 :     </Field>
987 :     <Field name="beg" type="int">
988 :     <Notes>Index (1-based) of the first residue in the contig that
989 :     belongs to the segment.</Notes>
990 :     </Field>
991 :     <Field name="len" type="int">
992 :     <Notes>Number of residues in the segment. A length of 0 identifies
993 :     a specific point between residues. This is the point before the residue if the direction
994 :     is forward and the point after the residue if the direction is backward.</Notes>
995 :     </Field>
996 :     <Field name="dir" type="char">
997 :     <Notes>Direction of the segment: =+= if it is forward and
998 :     =-= if it is backward.</Notes>
999 :     </Field>
1000 :     </Fields>
1001 :     <FromIndex>
1002 :     <Notes>This index allows the application to find all the segments of a feature in
1003 :     the proper order.</Notes>
1004 :     <IndexFields>
1005 :     <IndexField name="locN" order="ascending" />
1006 :     </IndexFields>
1007 :     </FromIndex>
1008 :     <ToIndex>
1009 :     <Notes>This index is the one used by applications to find all the feature
1010 :     segments that contain a specific residue.</Notes>
1011 :     <IndexFields>
1012 :     <IndexField name="beg" order="ascending" />
1013 :     </IndexFields>
1014 :     </ToIndex>
1015 :     </Relationship>
1016 :     <Relationship name="HasProperty" from="Feature" to="Property" arity="MM">
1017 :     <Notes>This relationship connects a feature to its known property values.
1018 :     The relationship contains text data that indicates the paper or organization
1019 :     that discovered evidence that the feature possesses the property. So, for
1020 :     example, if two papers presented evidence that a feature is essential,
1021 :     there would be an instance of this relationship for both.</Notes>
1022 :     <Fields>
1023 :     <Field name="evidence" type="text">
1024 :     <Notes>URL or citation of the paper or
1025 :     institution that reported evidence of the relevant feature possessing
1026 :     the specified property value.</Notes>
1027 :     </Field>
1028 :     </Fields>
1029 :     </Relationship>
1030 :     <Relationship name="RoleOccursIn" from="Role" to="Diagram" arity="MM">
1031 :     <DisplayInfo caption="Shows" theme="web" />
1032 :     <Notes>This relationship connects a role to the diagrams on which it
1033 :     appears. A role frequently identifies an enzyme, and can appear in many
1034 :     diagrams. A diagram generally contains many different roles.</Notes>
1035 :     </Relationship>
1036 :     <Relationship name="HasSSCell" from="Subsystem" to="SSCell" arity="1M">
1037 :     <DisplayInfo caption="Is Container Of" theme="seed" />
1038 :     <Notes>This relationship connects a subsystem to the spreadsheet cells
1039 :     used to analyze and display it. The cells themselves can be thought of
1040 :     as a grid with Roles on one axis and Genomes on the other. The
1041 :     various features of the subsystem are then assigned to the cells.</Notes>
1042 :     </Relationship>
1043 :     <Relationship name="IsTrustedBy" from="SproutUser" to="SproutUser" arity="MM">
1044 :     <Notes>This relationship identifies the users trusted by each
1045 :     particular user. When viewing functional assignments, the
1046 :     assignment displayed is the most recent one by a user trusted
1047 :     by the current user. The current user implicitly trusts himself.
1048 :     If no trusted users are specified in the database, the user
1049 :     also implicitly trusts the user =FIG=.</Notes>
1050 :     </Relationship>
1051 :     <Relationship name="ConsistsOfRoles" from="RoleSubset" to="Role" arity="MM">
1052 :     <Notes>This relationship connects a role subset to the roles that it covers.
1053 :     A subset is, essentially, a named group of roles belonging to a specific
1054 :     subsystem, and this relationship effects that. Note that will a role
1055 :     may belong to many subsystems, a subset belongs to only one subsystem,
1056 :     and all roles in the subset must have that subsystem in common.</Notes>
1057 :     </Relationship>
1058 :     <Relationship name="ConsistsOfGenomes" from="GenomeSubset" to="Genome" arity="MM">
1059 :     <Notes>This relationship connects a subset to the genomes that it covers.
1060 :     A subset is, essentially, a named group of genomes participating in a specific
1061 :     subsystem, and this relationship effects that. Note that while a genome
1062 :     may belong to many subsystems, a subset belongs to only one subsystem,
1063 :     and all genomes in the subset must have that subsystem in common.</Notes>
1064 :     </Relationship>
1065 :     <Relationship name="HasRoleSubset" from="Subsystem" to="RoleSubset" arity="1M">
1066 :     <Notes>This relationship connects a subsystem to its constituent
1067 :     role subsets. Note that some roles in a subsystem may not belong to a
1068 :     subset, so the relationship between roles and subsystems cannot be
1069 :     derived from the relationships going through the subset.</Notes>
1070 :     </Relationship>
1071 :     <Relationship name="HasGenomeSubset" from="Subsystem" to="GenomeSubset" arity="1M">
1072 :     <Notes>This relationship connects a subsystem to its constituent
1073 :     genome subsets. Note that some genomes in a subsystem may not belong to a
1074 :     subset, so the relationship between genomes and subsystems cannot be
1075 :     derived from the relationships going through the subset.</Notes>
1076 :     </Relationship>
1077 :     <Relationship name="HasRoleInSubsystem" from="Feature" to="Subsystem" arity="MM">
1078 :     <Notes>This relationship connects a feature to the subsystems in which it
1079 :     participates. This is technically redundant information, but it is used
1080 :     so often that it gets its own table for performance reasons.</Notes>
1081 :     <Fields>
1082 :     <Field name="genome" type="string">
1083 :     <Notes>ID of the genome containing the feature</Notes>
1084 :     </Field>
1085 :     <Field name="type" type="string">
1086 :     <Notes>Feature type (eg. peg, rna)</Notes>
1087 :     </Field>
1088 :     </Fields>
1089 :     <ToIndex>
1090 :     <Notes>This index enables the application to view the features of a
1091 :     subsystem sorted by genome and feature type.</Notes>
1092 :     <IndexFields>
1093 :     <IndexField name="genome" order="ascending" />
1094 :     <IndexField name="type" order="ascending" />
1095 :     </IndexFields>
1096 :     </ToIndex>
1097 :     </Relationship>
1098 :     </Relationships>
1099 :     <Shapes>
1100 :     <Shape type="oval" name="Pins">
1101 :     <DisplayInfo theme="nmpdr" col="1" row="4.5" fixed="1" />
1102 :     <Notes>The Pin Server provides information about functional couplings between features.</Notes>
1103 :     </Shape>
1104 :     <Shape type="oval" name="Sims">
1105 :     <DisplayInfo theme="nmpdr" col="1.5" row="5" fixed="1" />
1106 :     <Notes>The Similarity Server contains a high-performance custom database of similarities between features.</Notes>
1107 :     </Shape>
1108 :     <Shape type="oval" name="BBHs">
1109 :     <DisplayInfo theme="nmpdr" col="2" row="5.5" fixed="1" />
1110 :     <Notes>For each feature, the BBH Server has that feature's bidirectional best hits in other genomes.</Notes>
1111 :     </Shape>
1112 :     <Shape type="arrow" name="WebServices" from="Sims" to="Feature">
1113 :     <DisplayInfo caption=" " theme="nmpdr" col="2.5" row="4" />
1114 :     <Notes>HTTP services are used to transmit data between the servers and the
1115 :     NMPDR.</Notes>
1116 :     </Shape>
1117 :     </Shapes>
1118 :     </Database>

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3