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

Annotation of /Sprout/SproutDBD.xml

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.49 - (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 : parrello 1.48 <Field name="version" type="name-string">
20 :     <Notes>version string for this genome, generally consisting of the genome ID followed
21 :     by a period and a string of digits.</Notes>
22 :     </Field>
23 : parrello 1.1 <Field name="access-code" type="key-string">
24 : parrello 1.8 <Notes>The access code determines which users can look at the data relating to this genome.
25 :     Each user is associated with a set of access codes. In order to view a genome, one of
26 :     the user's access codes must match this value.</Notes>
27 :     </Field>
28 : parrello 1.15 <Field name="complete" type="boolean">
29 :     <Notes>TRUE if the genome is complete, else FALSE</Notes>
30 :     </Field>
31 : parrello 1.48 <Field name="dna-size" type="counter">
32 :     <Notes>number of base pairs in the genome</Notes>
33 :     </Field>
34 : parrello 1.8 <Field name="taxonomy" type="text">
35 :     <Notes>The taxonomy string contains the full taxonomy of the organism, while individual elements
36 :     separated by semi-colons (and optional white space), starting with the domain and ending with
37 :     the disambiguated genus and species (which is the organism's scientific name plus an
38 :     identifying string).</Notes>
39 :     </Field>
40 : parrello 1.37 <Field name="primary-group" type="name-string">
41 :     <Notes>The primary NMPDR group for this organism. There is always exactly one NMPDR group
42 :     (either based on the organism name or the default value "Supporting"), whereas there can be
43 :     multiple named groups or even none.</Notes>
44 :     </Field>
45 : parrello 1.8 <Field name="group-name" type="name-string" relation="GenomeGroups">
46 :     <Notes>The group identifies a special grouping of organisms that would be displayed on a particular
47 :     page or of particular interest to a research group or web site. A single genome can belong to multiple
48 :     such groups or none at all.</Notes>
49 :     </Field>
50 : parrello 1.1 </Fields>
51 :     <Indexes>
52 : parrello 1.45 <Index>
53 : parrello 1.1 <Notes>This index allows the applications to find all genomes associated with
54 :     a specific access code, so that a complete list of the genomes users can view
55 :     may be generated.</Notes>
56 :     <IndexFields>
57 :     <IndexField name="access-code" order="ascending" />
58 :     <IndexField name="genus" order="ascending" />
59 :     <IndexField name="species" order="ascending" />
60 :     <IndexField name="unique-characterization" order="ascending" />
61 :     </IndexFields>
62 :     </Index>
63 : parrello 1.45 <Index>
64 : parrello 1.37 <Notes>This index allows the applications to find all genomes associated with
65 :     a specific primary (NMPDR) group.</Notes>
66 :     <IndexFields>
67 :     <IndexField name="primary-group" order="ascending" />
68 :     <IndexField name="genus" order="ascending" />
69 :     <IndexField name="species" order="ascending" />
70 :     <IndexField name="unique-characterization" order="ascending" />
71 :     </IndexFields>
72 :     </Index>
73 : parrello 1.45 <Index>
74 : parrello 1.1 <Notes>This index allows the applications to find all genomes for a particular
75 :     species.</Notes>
76 :     <IndexFields>
77 :     <IndexField name="genus" order="ascending" />
78 :     <IndexField name="species" order="ascending" />
79 :     <IndexField name="unique-characterization" order="ascending" />
80 :     </IndexFields>
81 :     </Index>
82 :     </Indexes>
83 :     </Entity>
84 :     <Entity name="Source" keyType="medium-string">
85 :     <Notes>A [i]source[/i] describes a place from which genome data was taken. This can be an organization
86 :     or a paper citation.</Notes>
87 :     <Fields>
88 :     <Field name="URL" type="string" relation="SourceURL">
89 : parrello 1.8 <Notes>URL the paper cited or of the organization's web site. This field optional.</Notes>
90 :     </Field>
91 : parrello 1.1 <Field name="description" type="text">
92 : parrello 1.8 <Notes>Description the source. The description can be a street address or a citation.</Notes>
93 :     </Field>
94 : parrello 1.1 </Fields>
95 :     </Entity>
96 :     <Entity name="Contig" keyType="name-string">
97 :     <Notes>A [i]contig[/i] is a contiguous run of residues. The contig's ID consists of the
98 :     genome ID followed by a name that identifies which contig this is for the parent genome. As
99 :     is the case with all keys in this database, the individual components are separated by a
100 :     period.
101 :     [p]A contig can contain over a million residues. For performance reasons, therefore,
102 :     the contig is split into multiple pieces called [i]sequences[/i]. The sequences
103 :     contain the characters that represent the residues as well as data on the quality of
104 :     the residue identification.</Notes>
105 :     </Entity>
106 :     <Entity name="Sequence" keyType="name-string">
107 :     <Notes>A [i]sequence[/i] is a continuous piece of a [i]contig[/i]. Contigs are split into
108 :     sequences so that we don't have to have the entire contig in memory when we are
109 :     manipulating it. The key of the sequence is the contig ID followed by the index of
110 :     the begin point.</Notes>
111 :     <Fields>
112 :     <Field name="sequence" type="text">
113 : parrello 1.8 <Notes>String consisting of the residues. Each residue is described by a single
114 :     character in the string.</Notes>
115 :     </Field>
116 : parrello 1.1 <Field name="quality-vector" type="text">
117 : parrello 1.9 <Notes>String describing the quality data for each base pair. Individual values will
118 : parrello 1.8 be separated by periods. The value represents negative exponent of the probability
119 :     of error. Thus, for example, a quality of 30 indicates the probability of error is
120 :     10^-30. A higher quality number a better chance of a correct match. It is possible
121 : parrello 1.9 that the quality data is not known for a sequence. If that is the case, the quality
122 : parrello 1.8 vector will contain the [b]unknown[/b].</Notes>
123 :     </Field>
124 : parrello 1.1 </Fields>
125 :     </Entity>
126 : parrello 1.25 <Entity name="Feature" keyType="id-string">
127 : parrello 1.1 <Notes>A [i]feature[/i] is a part of a genome that is of special interest. Features
128 :     may be spread across multiple contigs of a genome, but never across more than
129 :     one genome. Features can be assigned to roles via spreadsheet cells,
130 :     and are the targets of annotation.</Notes>
131 :     <Fields>
132 :     <Field name="feature-type" type="string">
133 : parrello 1.8 <Notes>Code indicating the type of this feature.</Notes>
134 :     </Field>
135 : parrello 1.14 <Field name="alias" type="medium-string" relation="FeatureAlias">
136 : parrello 1.9 <Notes>Alternative name for this feature. A feature can have many aliases.</Notes>
137 : parrello 1.8 </Field>
138 : parrello 1.1 <Field name="translation" type="text" relation="FeatureTranslation">
139 : parrello 1.8 <Notes>[i](optional)[/i] A translation of this feature's residues into character
140 :     codes, formed by concatenating the pieces of the feature together. For a
141 :     protein encoding group, this is the protein characters. For other types
142 :     it is the DNA characters.</Notes>
143 :     </Field>
144 : parrello 1.1 <Field name="upstream-sequence" type="text" relation="FeatureUpstream">
145 : parrello 1.8 <Notes>Upstream sequence the feature. This includes residues preceding the feature as well as some of
146 :     the feature's initial residues.</Notes>
147 :     </Field>
148 : parrello 1.42 <Field name="assignment" type="text">
149 :     <Notes>Default functional assignment for this feature.</Notes>
150 :     </Field>
151 : parrello 1.1 <Field name="active" type="boolean">
152 : parrello 1.11 <Notes>TRUE if this feature is still considered valid, FALSE if it has been logically deleted.</Notes>
153 : parrello 1.8 </Field>
154 : parrello 1.48 <Field name="assignment-maker" type="name-string">
155 :     <Notes>name of the user who made the functional assignment</Notes>
156 :     </Field>
157 :     <Field name="assignment-quality" type="char">
158 :     <Notes>quality of the functional assignment, usually a space, but may be W (indicating weak) or X
159 :     (indicating experimental)</Notes>
160 :     </Field>
161 : parrello 1.41 <Field name="keywords" type="text" searchable="1">
162 :     <Notes>This is a list of search keywords for the feature. It includes the
163 :     functional assignment, subsystem roles, and special properties.</Notes>
164 : parrello 1.36 </Field>
165 : parrello 1.8 <Field name="link" type="text" relation="FeatureLink">
166 :     <Notes>Web hyperlink for this feature. A feature have no hyperlinks or it can have many. The
167 :     links are to other websites that have useful about the gene that the feature represents, and
168 :     are coded as raw HTML, using [b]&lt;a href="[i]link[/i]"&gt;[i]text[/i]&lt;/a&gt;[/b] notation.</Notes>
169 :     </Field>
170 : parrello 1.41 <Field name="conservation" type="float" relation="FeatureConservation">
171 :     <Notes>A number between 0 and 1 that indicates the degree to which this feature's DNA is
172 :     conserved in related genomes. A value of 1 indicates perfect conservation. A value less
173 :     than 1 is a reflect of the degree to which gap characters interfere in the alignment
174 :     between the feature and its close relatives.</Notes>
175 :     </Field>
176 : parrello 1.45 <Field name="essential" type="text" relation="FeatureEssential" special="property_search">
177 :     <Notes>A value indicating the essentiality of the feature, coded as HTML. In most
178 :     cases, this will be a word describing whether the essentiality is confirmed (essential)
179 :     or potential (potential-essential), hyperlinked to the document from which the
180 :     essentiality was curated. If a feature is not essential, this field will have no
181 :     values; otherwise, it may have multiple values.</Notes>
182 :     </Field>
183 :     <Field name="virulent" type="text" relation="FeatureVirulent" special="property_search">
184 :     <Notes>A value indicating the virulence of the feature, coded as HTML. In most
185 :     cases, this will be a phrase or SA number hyperlinked to the document from which
186 :     the virulence information was curated. If the feature is not virulent, this field
187 :     will have no values; otherwise, it may have multiple values.</Notes>
188 :     </Field>
189 :     <Field name="iedb" type="text" relation="FeatureIEDB" special="property_search">
190 :     <Notes>A value indicating whether or not the feature can be found in the
191 :     Immune Epitope Database. If the feature has not been matched to that database,
192 :     this field will have no values. Otherwise, it will have an epitope name and/or
193 :     sequence, hyperlinked to the database.</Notes>
194 :     </Field>
195 : parrello 1.1 </Fields>
196 : parrello 1.8 <Indexes>
197 :     <Index>
198 :     <Notes>This index allows the user to find the feature corresponding to
199 :     the specified alias name.</Notes>
200 :     <IndexFields>
201 :     <IndexField name="alias" order="ascending" />
202 :     </IndexFields>
203 :     </Index>
204 :     </Indexes>
205 : parrello 1.1 </Entity>
206 : parrello 1.27 <Entity name="SynonymGroup" keyType="id-string">
207 :     <Notes>A [i]synonym group[/i] represents a group of features. Substantially identical features
208 :     are mapped to the same synonym group, and this information is used to expand similarities.</Notes>
209 :     </Entity>
210 : parrello 1.1 <Entity name="Role" keyType="string">
211 :     <Notes>A [i]role[/i] describes a biological function that may be fulfilled by a feature.
212 :     One of the main goals of the database is to record the roles of the various features.</Notes>
213 : parrello 1.8 <Fields>
214 : parrello 1.18 <Field name="EC" type="string" relation="RoleEC">
215 :     <Notes>EC code for this role.</Notes>
216 : parrello 1.8 </Field>
217 : parrello 1.15 <Field name="abbr" type="name-string">
218 :     <Notes>Abbreviated name for the role, generally non-unique, but useful
219 :     in column headings for HTML tables.</Notes>
220 :     </Field>
221 : parrello 1.8 </Fields>
222 : parrello 1.18 <Indexes>
223 :     <Index>
224 :     <Notes>This index allows the user to find the role corresponding to
225 :     an EC number.</Notes>
226 :     <IndexFields>
227 :     <IndexField name="EC" order="ascending" />
228 :     </IndexFields>
229 :     </Index>
230 :     </Indexes>
231 : parrello 1.1 </Entity>
232 :     <Entity name="Annotation" keyType="name-string">
233 :     <Notes>An [i]annotation[/i] contains supplementary information about a feature. Annotations
234 : parrello 1.8 are currently the only objects that may be inserted directly into the database. All other
235 : parrello 1.24 information is loaded from data exported by the SEED.</Notes>
236 : parrello 1.8 <Fields>
237 :     <Field name="time" type="date">
238 :     <Notes>Date and time of the annotation.</Notes>
239 :     </Field>
240 :     <Field name="annotation" type="text">
241 :     <Notes>Text of the annotation.</Notes>
242 :     </Field>
243 : parrello 1.1 </Fields>
244 : parrello 1.26 <Indexes>
245 :     <Index>
246 :     <Notes>This index allows the user to find recent annotations.</Notes>
247 :     <IndexFields>
248 :     <IndexField name="time" order="descending" />
249 :     </IndexFields>
250 :     </Index>
251 :     </Indexes>
252 : parrello 1.1 </Entity>
253 : parrello 1.15 <Entity name="Reaction" keyType="key-string">
254 :     <Notes>A [i]reaction[/i] is a chemical process catalyzed by a protein. The reaction ID
255 :     is generally a small number preceded by a letter.</Notes>
256 :     <Fields>
257 :     <Field name="url" type="string" relation="ReactionURL">
258 :     <Notes>HTML string containing a link to a web location that describes the
259 :     reaction. This field is optional.</Notes>
260 :     </Field>
261 :     <Field name="rev" type="boolean">
262 :     <Notes>TRUE if this reaction is reversible, else FALSE</Notes>
263 :     </Field>
264 :     </Fields>
265 :     </Entity>
266 :     <Entity name="Compound" keyType="name-string">
267 :     <Notes>A [i]compound[/i] is a chemical that participates in a reaction.
268 :     All compounds have a unique ID and may also have one or more names.</Notes>
269 :     <Fields>
270 :     <Field name="name-priority" type="int" relation="CompoundName">
271 :     <Notes>Priority of a compound name. The name with the loweset
272 :     priority is the main name of this compound.</Notes>
273 :     </Field>
274 :     <Field name="name" type="name-string" relation="CompoundName">
275 :     <Notes>Descriptive name for the compound. A compound may
276 :     have several names.</Notes>
277 :     </Field>
278 :     <Field name="cas-id" type="name-string" relation="CompoundCAS">
279 :     <Notes>Chemical Abstract Service ID for this compound (optional).</Notes>
280 :     </Field>
281 : parrello 1.19 <Field name="label" type="name-string">
282 :     <Notes>Name used in reaction display strings.
283 :     It is the same as the name possessing a priority of 1, but it is placed
284 :     here to speed up the query used to create the display strings.</Notes>
285 :     </Field>
286 : parrello 1.15 </Fields>
287 :     <Indexes>
288 :     <Index>
289 :     <Notes>This index allows the user to find the compound corresponding to
290 :     the specified name.</Notes>
291 :     <IndexFields>
292 :     <IndexField name="name" order="ascending" />
293 :     </IndexFields>
294 :     </Index>
295 :     <Index>
296 : parrello 1.17 <Notes>This index allows the user to find the compound corresponding to
297 :     the specified CAS ID.</Notes>
298 :     <IndexFields>
299 :     <IndexField name="cas-id" order="ascending" />
300 :     </IndexFields>
301 :     </Index>
302 :     <Index>
303 : parrello 1.15 <Notes>This index allows the user to access the compound names in
304 :     priority order.</Notes>
305 :     <IndexFields>
306 :     <IndexField name="id" order="ascending" />
307 :     <IndexField name="name-priority" order="ascending" />
308 :     </IndexFields>
309 :     </Index>
310 :     </Indexes>
311 :     </Entity>
312 : parrello 1.5 <Entity name="Subsystem" keyType="string">
313 : parrello 1.1 <Notes>A [i]subsystem[/i] is a collection of roles that work together in a cell. Identification of subsystems
314 :     is an important tool for recognizing parallel genetic features in different organisms.</Notes>
315 : parrello 1.15 <Fields>
316 :     <Field name="curator" type="string">
317 :     <Notes>Name of the person currently in charge of the subsystem.</Notes>
318 :     </Field>
319 :     <Field name="notes" type="text">
320 :     <Notes>Descriptive notes about the subsystem.</Notes>
321 :     </Field>
322 : parrello 1.28 <Field name="classification" type="string" relation="SubsystemClass">
323 : parrello 1.44 <Notes>Classification string, colon-delimited. This string organizes the
324 : parrello 1.42 subsystems into a hierarchy.</Notes>
325 : parrello 1.28 </Field>
326 : parrello 1.15 </Fields>
327 :     </Entity>
328 :     <Entity name="RoleSubset" keyType="string">
329 :     <Notes>A [i]role subset[/i] is a named collection of roles in a particular subsystem. The
330 :     subset names are generally very short, non-unique strings. The ID of the parent
331 :     subsystem is prefixed to the subset ID in order to make it unique.</Notes>
332 :     </Entity>
333 :     <Entity name="GenomeSubset" keyType="string">
334 :     <Notes>A [i]genome subset[/i] is a named collection of genomes that participate
335 :     in a particular subsystem. The subset names are generally very short, non-unique
336 :     strings. The ID of the parent subsystem is prefixed to the subset ID in order
337 :     to make it unique.</Notes>
338 : parrello 1.1 </Entity>
339 : parrello 1.24 <Entity name="SSCell" keyType="hash-string">
340 : parrello 1.1 <Notes>Part of the process of locating and assigning features is creating a spreadsheet of
341 :     genomes and roles to which features are assigned. A [i]spreadsheet cell[/i] represents one
342 :     of the positions on the spreadsheet.</Notes>
343 :     </Entity>
344 :     <Entity name="SproutUser" keyType="name-string">
345 :     <Notes>A [i]user[/i] is a person who can make annotations and view data in the database. The
346 :     user object is keyed on the user's login name.</Notes>
347 :     <Fields>
348 : parrello 1.8 <Field name="description" type="string">
349 :     <Notes>Full name or description of this user.</Notes>
350 :     </Field>
351 : parrello 1.1 <Field name="access-code" type="key-string" relation="UserAccess">
352 : parrello 1.8 <Notes>Access code possessed by this
353 : parrello 1.1 user. A user can have many access codes; a genome is accessible to the user if its
354 :     access code matches any one of the user's access codes.</Notes>
355 : parrello 1.8 </Field>
356 : parrello 1.1 </Fields>
357 :     </Entity>
358 : parrello 1.8 <Entity name="Property" keyType="int">
359 :     <Notes>A [i]property[/i] is a type of assertion that could be made about the properties of
360 :     a particular feature. Each property instance is a key/value pair and can be associated
361 :     with many different features. Conversely, a feature can be associated with many key/value
362 :     pairs, even some that notionally contradict each other. For example, there can be evidence
363 :     that a feature is essential to the organism's survival and evidence that it is superfluous.</Notes>
364 :     <Fields>
365 :     <Field name="property-name" type="name-string">
366 :     <Notes>Name of this property.</Notes>
367 :     </Field>
368 :     <Field name="property-value" type="string">
369 :     <Notes>Value associated with this property. For each property
370 :     name, there must by a property record for all of its possible
371 :     values.</Notes>
372 :     </Field>
373 :     </Fields>
374 :     <Indexes>
375 :     <Index>
376 :     <Notes>This index enables the application to find all values for a specified property
377 :     name, or any given name/value pair.</Notes>
378 :     <IndexFields>
379 :     <IndexField name="property-name" order="ascending" />
380 :     <IndexField name="property-value" order="ascending" />
381 :     </IndexFields>
382 :     </Index>
383 :     </Indexes>
384 :     </Entity>
385 :     <Entity name="Diagram" keyType="name-string">
386 :     <Notes>A functional diagram describes the chemical reactions, often comprising a single
387 :     subsystem. A diagram is identified by a short name and contains a longer descriptive name.
388 :     The actual diagram shows which functional roles guide the reactions along with the inputs
389 :     and outputs; the database, however, only indicate which roles belong to a particular
390 :     map.</Notes>
391 :     <Fields>
392 :     <Field name="name" type="text">
393 :     <Notes>Descriptive name of this diagram.</Notes>
394 :     </Field>
395 :     </Fields>
396 :     </Entity>
397 :     <Entity name="ExternalAliasOrg" keyType="name-string">
398 :     <Notes>An external alias is a feature name for a functional assignment that is not a
399 :     FIG ID. Functional assignments for external aliases are kept in a separate section of
400 :     the database. This table contains a description of the relevant organism for an
401 :     external alias functional assignment.</Notes>
402 :     <Fields>
403 :     <Field name="org" type="text">
404 :     <Notes>Descriptive name of the target organism for this external alias.</Notes>
405 :     </Field>
406 :     </Fields>
407 :     </Entity>
408 :     <Entity name="ExternalAliasFunc" keyType="name-string">
409 :     <Notes>An external alias is a feature name for a functional assignment that is not a
410 :     FIG ID. Functional assignments for external aliases are kept in a separate section of
411 :     the database. This table contains the functional role for the external alias functional
412 :     assignment.</Notes>
413 :     <Fields>
414 :     <Field name="func" type="text">
415 :     <Notes>Functional role for this external alias.</Notes>
416 :     </Field>
417 :     </Fields>
418 :     </Entity>
419 : parrello 1.29 <Entity name="Coupling" keyType="id-string">
420 : parrello 1.6 <Notes>A coupling is a relationship between two features. The features are
421 :     physically close on the contig, and there is evidence that they generally
422 :     belong together. The key of this entity is formed by combining the coupled
423 : parrello 1.8 feature IDs with a space.</Notes>
424 : parrello 1.6 <Fields>
425 :     <Field name="score" type="int">
426 :     <Notes>A number based on the set of PCHs (pairs of close homologs). A PCH
427 :     indicates that two genes near each other on one genome are very similar to
428 :     genes near each other on another genome. The score only counts PCHs for which
429 :     the genomes are very different. (In other words, we have a pairing that persists
430 :     between different organisms.) A higher score implies a stronger meaning to the
431 :     clustering.</Notes>
432 :     </Field>
433 :     </Fields>
434 :     </Entity>
435 : parrello 1.30 <Entity name="PCH" keyType="counter">
436 : parrello 1.6 <Notes>A PCH (physically close homolog) connects a clustering (which is a
437 :     pair of physically close features on a contig) to a second pair of physically
438 :     close features that are similar to the first. Essentially, the PCH is a
439 :     relationship between two clusterings in which the first clustering's features
440 :     are similar to the second clustering's features. The simplest model for
441 :     this would be to simply relate clusterings to each other; however, not all
442 :     physically close pairs qualify as clusterings, so we relate a clustering to
443 : parrello 1.30 a pair of features. The key a unique ID number.</Notes>
444 : parrello 1.6 <Fields>
445 :     <Field name="used" type="boolean">
446 :     <Notes>TRUE if this PCH is used in scoring the attached clustering,
447 :     else FALSE. If a clustering has a PCH for a particular genome and many
448 :     similar genomes are present, then a PCH will probably exist for the
449 :     similar genomes as well. When this happens, only one of the PCHs will
450 :     be scored: the others are considered duplicates of the same evidence.</Notes>
451 :     </Field>
452 :     </Fields>
453 :     </Entity>
454 : parrello 1.31 <Entity name="Family" keyType="id-string">
455 :     <Notes>A family is a group of homologous PEGs believed to have the same function. Protein
456 :     families provide a mechanism for verifying the accuracy of functional assignments
457 :     and are also used in determining phylogenetic trees.</Notes>
458 :     <Fields>
459 : parrello 1.32 <Field name="function" type="text">
460 : parrello 1.31 <Notes>The functional assignment expected for all PEGs in this family.</Notes>
461 :     </Field>
462 : parrello 1.33 <Field name="size" type="int">
463 : parrello 1.31 <Notes>The number of proteins in this family. This may be larger than the
464 :     number of PEGs included in the family, since the family may also contain external
465 :     IDs.</Notes>
466 :     </Field>
467 :     </Fields>
468 :     </Entity>
469 : parrello 1.49 <Entity name="PDB" keyType="id-string">
470 :     <Notes>A PDB is a protein database containing information that can be used to determine
471 :     the shape of the protein and the energies required to dock with it. The ID is the
472 :     four-character name used on the PDB web site.</Notes>
473 :     <Fields>
474 :     <Field name="docking-count" type="int">
475 :     <Notes>The number of ligands that have been docked against this PDB.</Notes>
476 :     </Field>
477 :     </Fields>
478 :     <Indexes>
479 :     <Index>
480 :     <IndexFields>
481 :     <IndexField name="docking-count" order="descending" />
482 :     <IndexField name="id" order="ascending" />
483 :     </IndexFields>
484 :     </Index>
485 :     </Indexes>
486 :     </Entity>
487 :     <Entity name="Ligand" keyType="id-string">
488 :     <Notes>A Ligand is a chemical of interest in computing docking energies against a PDB.
489 :     The ID of the ligand is an 8-digit ZINC ID number.</Notes>
490 :     <Fields>
491 :     <Field name="name" type="long-string">
492 :     <Notes>Chemical name of this ligand.</Notes>
493 :     </Field>
494 :     </Fields>
495 :     </Entity>
496 : parrello 1.1 </Entities>
497 :     <Relationships>
498 : parrello 1.49 <Relationship name="IsProteinForFeature" from="PDB" to="Feature" arity="MM">
499 :     <Notes>Relates a PDB to features that produce highly similar proteins.</Notes>
500 :     <Fields>
501 :     <Field name="score" type="float">
502 :     <Notes>Similarity score for the comparison between the feature and
503 :     the PDB protein. A lower score indicates a better match.</Notes>
504 :     </Field>
505 :     <Field name="start-location" type="int">
506 :     <Notes>Starting location within the feature of the matching region.</Notes>
507 :     </Field>
508 :     <Field name="end-location" type="int">
509 :     <Notes>Ending location within the feature of the matching region.</Notes>
510 :     </Field>
511 :     </Fields>
512 :     <ToIndex>
513 :     <Notes>This index enables the application to view the PDBs of a
514 :     feature in order from the closest match to the furthest.</Notes>
515 :     <IndexFields>
516 :     <IndexField name="score" order="ascending" />
517 :     </IndexFields>
518 :     </ToIndex>
519 :     <FromIndex>
520 :     <Notes>This index enables the application to view the features of
521 :     a PDB in order from the closest match to the furthest.</Notes>
522 :     <IndexFields>
523 :     <IndexField name="score" order="ascending" />
524 :     </IndexFields>
525 :     </FromIndex>
526 :     </Relationship>
527 :     <Relationship name="DocksWith" from="PDB" to="Ligand" arity="MM">
528 :     <Notes>Indicates that a docking result exists between a PDB and a ligand. The
529 :     docking result describes the energy required for the ligand to dock with
530 :     the protein described by the PDB. A lower energy indicates the ligand has a
531 :     good chance of disabling the protein. At the current time, only the best
532 :     docking results are kept.</Notes>
533 :     <Fields>
534 :     <Field name="reason" type="id-string">
535 :     <Notes>Indication of the reason for determining the docking result.
536 :     A value of [b]Random[/b] indicates the docking was attempted as a part
537 :     of a random survey used to determine the docking characteristics of the
538 :     PDB. A value of [b]Rich[/b] indicates the docking was attempted because
539 :     a low-energy docking result was predicted for the ligand with respect
540 :     to the PDB.</Notes>
541 :     </Field>
542 :     <Field name="tool" type="id-string">
543 :     <Notes>Name of the tool used to produce the docking result.</Notes>
544 :     </Field>
545 :     <Field name="total-energy" type="float">
546 :     <Notes>Total energy required for the ligand to dock with the PDB
547 :     protein, in kcal/mol. A negative value means energy is released.</Notes>
548 :     </Field>
549 :     <Field name="vanderwalls-energy" type="float">
550 :     <Notes>Docking energy in kcal/mol that results from the geometric fit
551 :     (Van der Waals force) between the PDB and the ligand.</Notes>
552 :     </Field>
553 :     <Field name="electrostatic-energy" type="float">
554 :     <Notes>Docking energy in kcal/mol that results from the movement of
555 :     electrons (electrostatic force) between the PDB and the ligan.</Notes>
556 :     </Field>
557 :     </Fields>
558 :     <FromIndex>
559 :     <Notes>This index enables the application to view a PDB's docking results from
560 :     the lowest energy (best docking) to highest energy (worst docking).</Notes>
561 :     <IndexFields>
562 :     <IndexField name="total-energy" order="ascending" />
563 :     </IndexFields>
564 :     </FromIndex>
565 :     <ToIndex>
566 :     <Notes>This index enables the application to view a ligand's docking results from
567 :     the lowest energy (best docking) to highest energy (worst docking). Note that
568 :     since we only keep the best docking results for a PDB, this index is not likely
569 :     to provide useful results.</Notes>
570 :     </ToIndex>
571 :     </Relationship>
572 : parrello 1.34 <Relationship name="IsFamilyForFeature" from="Family" to="Feature" arity="MM">
573 : parrello 1.31 <Notes>This relationship connects a protein family to all of its PEGs and connects
574 :     each PEG to all of its protein families.</Notes>
575 :     </Relationship>
576 : parrello 1.6 <Relationship name="ParticipatesInCoupling" from="Feature" to="Coupling" arity="MM">
577 :     <Notes>This relationship connects a feature to all the functional couplings
578 :     in which it participates. A functional coupling is a recognition of the fact
579 :     that the features are close to each other on a chromosome, and similar
580 :     features in other genomes also tend to be close.</Notes>
581 :     <Fields>
582 :     <Field name="pos" type="int">
583 :     <Notes>Ordinal position of the feature in the coupling. Currently,
584 :     this is either "1" or "2".</Notes>
585 :     </Field>
586 :     </Fields>
587 :     <ToIndex>
588 :     <Notes>This index enables the application to view the features of
589 :     a coupling in the proper order. The order influences the way the
590 :     PCHs are examined.</Notes>
591 :     <IndexFields>
592 :     <IndexField name="pos" order="ascending" />
593 :     </IndexFields>
594 :     </ToIndex>
595 :     </Relationship>
596 : parrello 1.27 <Relationship name="IsSynonymGroupFor" from="SynonymGroup" to="Feature" arity="1M">
597 :     <Notes>This relation connects a synonym group to the features that make it
598 :     up.</Notes>
599 :     </Relationship>
600 : parrello 1.24 <Relationship name="HasFeature" from="Genome" to="Feature" arity="1M">
601 :     <Notes>This relationship connects a genome to all of its features. This
602 :     relationship is redundant in a sense, because the genome ID is part
603 :     of the feature ID; however, it makes the creation of certain queries more
604 :     convenient because you can drag in filtering information for a feature's
605 :     genome.</Notes>
606 :     <Fields>
607 :     <Field name="type" type="key-string">
608 :     <Notes>Feature type (eg. peg, rna)</Notes>
609 :     </Field>
610 :     </Fields>
611 : parrello 1.38 <FromIndex>
612 : parrello 1.24 <Notes>This index enables the application to view the features of a
613 :     Genome sorted by type.</Notes>
614 :     <IndexFields>
615 :     <IndexField name="type" order="ascending" />
616 :     </IndexFields>
617 : parrello 1.38 </FromIndex>
618 : parrello 1.24 </Relationship>
619 : parrello 1.6 <Relationship name="IsEvidencedBy" from="Coupling" to="PCH" arity="1M">
620 :     <Notes>This relationship connects a functional coupling to the physically
621 :     close homologs (PCHs) which affirm that the coupling is meaningful.</Notes>
622 :     </Relationship>
623 :     <Relationship name="UsesAsEvidence" from="PCH" to="Feature" arity="MM">
624 :     <Notes>This relationship connects a PCH to the features that represent its
625 :     evidence. Each PCH is connected to a parent coupling that relates two features
626 :     on a specific genome. The PCH's evidence that the parent coupling is functional
627 :     is the existence of two physically close features on a different genome that
628 :     correspond to the features in the coupling. Those features are found on the
629 :     far side of this relationship.</Notes>
630 :     <Fields>
631 :     <Field name="pos" type="int">
632 :     <Notes>Ordinal position of the feature in the coupling that corresponds
633 :     to our target feature. There is a one-to-one correspondence between the
634 :     features connected to the PCH by this relationship and the features
635 :     connected to the PCH's parent coupling. The ordinal position is used
636 :     to decode that relationship. Currently, this field is either "1" or
637 :     "2".</Notes>
638 :     </Field>
639 :     </Fields>
640 :     <FromIndex>
641 :     <Notes>This index enables the application to view the features of
642 :     a PCH in the proper order.</Notes>
643 :     <IndexFields>
644 :     <IndexField name="pos" order="ascending" />
645 :     </IndexFields>
646 :     </FromIndex>
647 :     </Relationship>
648 : parrello 1.1 <Relationship name="HasContig" from="Genome" to="Contig" arity="1M">
649 :     <Notes>This relationship connects a genome to the contigs that contain the actual genetic
650 :     information.</Notes>
651 :     </Relationship>
652 :     <Relationship name="ComesFrom" from="Genome" to="Source" arity="MM">
653 :     <Notes>This relationship connects a genome to the sources that mapped it. A genome can
654 :     come from a single source or from a cooperation among multiple sources.</Notes>
655 :     </Relationship>
656 :     <Relationship name="IsMadeUpOf" from="Contig" to="Sequence" arity="1M">
657 :     <Notes>A contig is stored in the database as an ordered set of sequences. By splitting the
658 :     contig into sequences, we get a performance boost from only needing to keep small portions
659 :     of a contig in memory at any one time. This relationship connects the contig to its
660 :     constituent sequences.</Notes>
661 :     <Fields>
662 :     <Field name="len" type="int">
663 : parrello 1.15 <Notes>Length of the sequence.</Notes>
664 :     </Field>
665 : parrello 1.1 <Field name="start-position" type="int">
666 : parrello 1.15 <Notes>Index (1-based) of the point in the contig where this
667 :     sequence starts.</Notes>
668 :     </Field>
669 : parrello 1.1 </Fields>
670 :     <FromIndex>
671 :     <Notes>This index enables the application to find all of the sequences in
672 : parrello 1.8 a contig in order, and makes it easier to find a particular residue section.</Notes>
673 : parrello 1.1 <IndexFields>
674 :     <IndexField name="start-position" order="ascending" />
675 :     <IndexField name="len" order="ascending" />
676 :     </IndexFields>
677 :     </FromIndex>
678 :     </Relationship>
679 :     <Relationship name="IsTargetOfAnnotation" from="Feature" to="Annotation" arity="1M">
680 :     <Notes>This relationship connects a feature to its annotations.</Notes>
681 :     </Relationship>
682 :     <Relationship name="MadeAnnotation" from="SproutUser" to="Annotation" arity="1M">
683 :     <Notes>This relationship connects an annotation to the user who made it.</Notes>
684 :     </Relationship>
685 :     <Relationship name="ParticipatesIn" from="Genome" to="Subsystem" arity="MM">
686 :     <Notes>This relationship connects subsystems to the genomes that use
687 :     it. If the subsystem has been curated for the genome, then the subsystem's roles will also be
688 :     connected to the genome features through the [b]SSCell[/b] object.</Notes>
689 : parrello 1.15 <Fields>
690 :     <Field name="variant-code" type="key-string">
691 : parrello 1.20 <Notes>Code indicating the subsystem variant to which this
692 : parrello 1.15 genome belongs. Each subsystem can have multiple variants. A variant
693 : parrello 1.20 code of [b]-1[/b] indicates that the genome does not have a functional
694 :     variant of the subsystem. A variant code of [b]0[/b] indicates that
695 :     the genome's participation is considered iffy.</Notes>
696 : parrello 1.15 </Field>
697 :     </Fields>
698 :     <ToIndex>
699 :     <Notes>This index enables the application to find all of the genomes using
700 :     a subsystem in order by variant code, which is how we wish to display them
701 :     in the spreadsheets.</Notes>
702 :     <IndexFields>
703 :     <IndexField name="variant-code" order="ascending" />
704 :     </IndexFields>
705 :     </ToIndex>
706 : parrello 1.1 </Relationship>
707 :     <Relationship name="OccursInSubsystem" from="Role" to="Subsystem" arity="MM">
708 :     <Notes>This relationship connects roles to the subsystems that implement them. </Notes>
709 : parrello 1.15 <Fields>
710 :     <Field name="column-number" type="int">
711 :     <Notes>Column number for this role in the specified subsystem's
712 :     spreadsheet.</Notes>
713 :     </Field>
714 :     </Fields>
715 :     <ToIndex>
716 :     <Notes>This index enables the application to see the subsystem roles
717 :     in column order. The ordering of the roles is usually significant,
718 :     so it is important to preserve it.</Notes>
719 :     <IndexFields>
720 :     <IndexField name="column-number" order="ascending" />
721 :     </IndexFields>
722 :     </ToIndex>
723 : parrello 1.1 </Relationship>
724 :     <Relationship name="IsGenomeOf" from="Genome" to="SSCell" arity="1M">
725 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
726 :     genome for the spreadsheet column.</Notes>
727 :     </Relationship>
728 :     <Relationship name="IsRoleOf" from="Role" to="SSCell" arity="1M">
729 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
730 :     role for the spreadsheet row.</Notes>
731 :     </Relationship>
732 :     <Relationship name="ContainsFeature" from="SSCell" to="Feature" arity="MM">
733 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
734 :     features assigned to it.</Notes>
735 : parrello 1.15 <Fields>
736 :     <Field name="cluster-number" type="int">
737 :     <Notes>ID of this feature's cluster. Clusters represent families of
738 :     related proteins participating in a subsystem.</Notes>
739 :     </Field>
740 :     </Fields>
741 :     </Relationship>
742 :     <Relationship name="IsAComponentOf" from="Compound" to="Reaction" arity="MM">
743 :     <Notes>This relationship connects a reaction to the compounds that participate
744 :     in it.</Notes>
745 :     <Fields>
746 :     <Field name="product" type="boolean">
747 :     <Notes>TRUE if the compound is a product of the reaction, FALSE if
748 :     it is a substrate. When a reaction is written on paper in
749 :     chemical notation, the substrates are left of the arrow and the
750 :     products are to the right. Sorting on this field will cause
751 :     the substrates to appear first, followed by the products. If the
752 :     reaction is reversible, then the notion of substrates and products
753 :     is not at intuitive; however, a value here of FALSE still puts the
754 :     compound left of the arrow and a value of TRUE still puts it to the
755 :     right.</Notes>
756 :     </Field>
757 : parrello 1.19 <Field name="stoichiometry" type="key-string">
758 : parrello 1.15 <Notes>Number of molecules of the compound that participate in a
759 :     single instance of the reaction. For example, if a reaction
760 : parrello 1.19 produces two water molecules, the stoichiometry of water for the
761 : parrello 1.15 reaction would be two. When a reaction is written on paper in
762 : parrello 1.19 chemical notation, the stoichiometry is the number next to the
763 : parrello 1.15 chemical formula of the compound.</Notes>
764 :     </Field>
765 :     <Field name="main" type="boolean">
766 :     <Notes>TRUE if this compound is one of the main participants in
767 :     the reaction, else FALSE. It is permissible for none of the
768 :     compounds in the reaction to be considered main, in which
769 :     case this value would be FALSE for all of the relevant
770 :     compounds.</Notes>
771 :     </Field>
772 :     <Field name="loc" type="key-string">
773 :     <Notes>An optional character string that indicates the relative
774 :     position of this compound in the reaction's chemical formula. The
775 :     location affects the way the compounds present as we cross the
776 :     relationship from the reaction side. The product/substrate flag
777 :     comes first, then the value of this field, then the main flag.
778 :     The default value is an empty string; however, the empty string
779 :     sorts first, so if this field is used, it should probably be
780 :     used for every compound in the reaction.</Notes>
781 :     </Field>
782 : parrello 1.19 <Field name="discriminator" type="int">
783 :     <Notes>A unique ID for this record. The discriminator does not
784 :     provide any useful data, but it prevents identical records from
785 :     being collapsed by the SELECT DISTINCT command used by ERDB to
786 :     retrieve data.</Notes>
787 :     </Field>
788 : parrello 1.15 </Fields>
789 :     <ToIndex>
790 :     <Notes>This index presents the compounds in the reaction in the
791 :     order they should be displayed when writing it in chemical notation.
792 :     All the substrates appear before all the products, and within that
793 :     ordering, the main compounds appear first.</Notes>
794 : parrello 1.19 <IndexFields>
795 :     <IndexField name="product" order="ascending" />
796 :     <IndexField name="loc" order="ascending" />
797 :     <IndexField name="main" order="descending" />
798 :     </IndexFields>
799 : parrello 1.15 </ToIndex>
800 : parrello 1.1 </Relationship>
801 :     <Relationship name="IsLocatedIn" from="Feature" to="Contig" arity="MM">
802 :     <Notes>This relationship connects a feature to the contig segments that work together
803 :     to effect it. The segments are numbered sequentially starting from 1. The database is
804 :     required to place an upper limit on the length of each segment. If a segment is longer
805 :     than the maximum, it can be broken into smaller bits.
806 :     [p]The upper limit enables applications to locate all features that contain a specific
807 :     residue. For example, if the upper limit is 100 and we are looking for a feature that
808 :     contains residue 234 of contig [b]ABC[/b], we can look for features with a begin point
809 :     between 135 and 333. The results can then be filtered by direction and length of the
810 :     segment.</Notes>
811 :     <Fields>
812 :     <Field name="locN" type="int">
813 : parrello 1.8 <Notes>Sequence number of this segment.</Notes>
814 :     </Field>
815 : parrello 1.1 <Field name="beg" type="int">
816 : parrello 1.8 <Notes>Index (1-based) of the first residue in the contig that
817 :     belongs to the segment.</Notes>
818 :     </Field>
819 : parrello 1.1 <Field name="len" type="int">
820 : parrello 1.8 <Notes>Number of residues in the segment. A length of 0 identifies
821 :     a specific point between residues. This is the point before the residue if the direction
822 :     is forward and the point after the residue if the direction is backward.</Notes>
823 :     </Field>
824 : parrello 1.1 <Field name="dir" type="char">
825 : parrello 1.8 <Notes>Direction of the segment: [b]+[/b] if it is forward and
826 :     [b]-[/b] if it is backward.</Notes>
827 :     </Field>
828 : parrello 1.1 </Fields>
829 : parrello 1.45 <FromIndex>
830 : parrello 1.1 <Notes>This index allows the application to find all the segments of a feature in
831 : parrello 1.8 the proper order.</Notes>
832 : parrello 1.1 <IndexFields>
833 :     <IndexField name="locN" order="ascending" />
834 :     </IndexFields>
835 :     </FromIndex>
836 :     <ToIndex>
837 :     <Notes>This index is the one used by applications to find all the feature
838 :     segments that contain a specific residue.</Notes>
839 :     <IndexFields>
840 :     <IndexField name="beg" order="ascending" />
841 :     </IndexFields>
842 :     </ToIndex>
843 :     </Relationship>
844 : parrello 1.8 <Relationship name="HasProperty" from="Feature" to="Property" arity="MM">
845 :     <Notes>This relationship connects a feature to its known property values.
846 :     The relationship contains text data that indicates the paper or organization
847 :     that discovered evidence that the feature possesses the property. So, for
848 :     example, if two papers presented evidence that a feature is essential,
849 :     there would be an instance of this relationship for both.</Notes>
850 :     <Fields>
851 :     <Field name="evidence" type="text">
852 :     <Notes>URL or citation of the paper or
853 :     institution that reported evidence of the relevant feature possessing
854 :     the specified property value.</Notes>
855 :     </Field>
856 :     </Fields>
857 :     </Relationship>
858 :     <Relationship name="RoleOccursIn" from="Role" to="Diagram" arity="MM">
859 :     <Notes>This relationship connects a role to the diagrams on which it
860 :     appears. A role frequently identifies an enzyme, and can appear in many
861 :     diagrams. A diagram generally contains many different roles.</Notes>
862 :     </Relationship>
863 :     <Relationship name="HasSSCell" from="Subsystem" to="SSCell" arity="1M">
864 :     <Notes>This relationship connects a subsystem to the spreadsheet cells
865 :     used to analyze and display it. The cells themselves can be thought of
866 :     as a grid with Roles on one axis and Genomes on the other. The
867 :     various features of the subsystem are then assigned to the cells.</Notes>
868 :     </Relationship>
869 :     <Relationship name="IsTrustedBy" from="SproutUser" to="SproutUser" arity="MM">
870 :     <Notes>This relationship identifies the users trusted by each
871 :     particular user. When viewing functional assignments, the
872 :     assignment displayed is the most recent one by a user trusted
873 :     by the current user. The current user implicitly trusts himself.
874 :     If no trusted users are specified in the database, the user
875 :     also implicitly trusts the user [b]FIG[/b].</Notes>
876 :     </Relationship>
877 : parrello 1.15 <Relationship name="ConsistsOfRoles" from="RoleSubset" to="Role" arity="MM">
878 :     <Notes>This relationship connects a role subset to the roles that it covers.
879 :     A subset is, essentially, a named group of roles belonging to a specific
880 :     subsystem, and this relationship effects that. Note that will a role
881 :     may belong to many subsystems, a subset belongs to only one subsystem,
882 :     and all roles in the subset must have that subsystem in common.</Notes>
883 :     </Relationship>
884 :     <Relationship name="ConsistsOfGenomes" from="GenomeSubset" to="Genome" arity="MM">
885 :     <Notes>This relationship connects a subset to the genomes that it covers.
886 :     A subset is, essentially, a named group of genomes participating in a specific
887 :     subsystem, and this relationship effects that. Note that while a genome
888 :     may belong to many subsystems, a subset belongs to only one subsystem,
889 :     and all genomes in the subset must have that subsystem in common.</Notes>
890 :     </Relationship>
891 :     <Relationship name="HasRoleSubset" from="Subsystem" to="RoleSubset" arity="1M">
892 :     <Notes>This relationship connects a subsystem to its constituent
893 :     role subsets. Note that some roles in a subsystem may not belong to a
894 :     subset, so the relationship between roles and subsystems cannot be
895 :     derived from the relationships going through the subset.</Notes>
896 :     </Relationship>
897 :     <Relationship name="HasGenomeSubset" from="Subsystem" to="GenomeSubset" arity="1M">
898 :     <Notes>This relationship connects a subsystem to its constituent
899 :     genome subsets. Note that some genomes in a subsystem may not belong to a
900 :     subset, so the relationship between genomes and subsystems cannot be
901 :     derived from the relationships going through the subset.</Notes>
902 :     </Relationship>
903 :     <Relationship name="Catalyzes" from="Role" to="Reaction" arity="MM">
904 :     <Notes>This relationship connects a role to the reactions it catalyzes.
905 :     The purpose of a role is to create proteins that trigger certain
906 :     chemical reactions. A single reaction can be triggered by many roles,
907 :     and a role can trigger many reactions.</Notes>
908 :     </Relationship>
909 : parrello 1.39 <Relationship name="HasRoleInSubsystem" from="Feature" to="Subsystem" arity="MM">
910 :     <Notes>This relationship connects a feature to the subsystems in which it
911 :     participates. This is technically redundant information, but it is used
912 :     so often that it deserves its own table.</Notes>
913 : parrello 1.40 <Fields>
914 :     <Field name="genome" type="name-string">
915 :     <Notes>ID of the genome containing the feature</Notes>
916 :     </Field>
917 :     <Field name="type" type="key-string">
918 :     <Notes>Feature type (eg. peg, rna)</Notes>
919 :     </Field>
920 :     </Fields>
921 :     <ToIndex>
922 :     <Notes>This index enables the application to view the features of a
923 :     subsystem sorted by genome and feature type.</Notes>
924 :     <IndexFields>
925 :     <IndexField name="genome" order="ascending" />
926 :     <IndexField name="type" order="ascending" />
927 :     </IndexFields>
928 :     </ToIndex>
929 : parrello 1.39 </Relationship>
930 : parrello 1.1 </Relationships>
931 :     </Database>

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3