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

Annotation of /Sprout/SproutDBD.xml

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.50 - (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 1.1 </Fields>
46 :     <Indexes>
47 : parrello 1.45 <Index>
48 : parrello 1.1 <Notes>This index allows the applications to find all genomes associated with
49 :     a specific access code, so that a complete list of the genomes users can view
50 :     may be generated.</Notes>
51 :     <IndexFields>
52 :     <IndexField name="access-code" order="ascending" />
53 :     <IndexField name="genus" order="ascending" />
54 :     <IndexField name="species" order="ascending" />
55 :     <IndexField name="unique-characterization" order="ascending" />
56 :     </IndexFields>
57 :     </Index>
58 : parrello 1.45 <Index>
59 : parrello 1.37 <Notes>This index allows the applications to find all genomes associated with
60 :     a specific primary (NMPDR) group.</Notes>
61 :     <IndexFields>
62 :     <IndexField name="primary-group" order="ascending" />
63 :     <IndexField name="genus" order="ascending" />
64 :     <IndexField name="species" order="ascending" />
65 :     <IndexField name="unique-characterization" order="ascending" />
66 :     </IndexFields>
67 :     </Index>
68 : parrello 1.45 <Index>
69 : parrello 1.1 <Notes>This index allows the applications to find all genomes for a particular
70 :     species.</Notes>
71 :     <IndexFields>
72 :     <IndexField name="genus" order="ascending" />
73 :     <IndexField name="species" order="ascending" />
74 :     <IndexField name="unique-characterization" order="ascending" />
75 :     </IndexFields>
76 :     </Index>
77 :     </Indexes>
78 :     </Entity>
79 : parrello 1.50 <Entity name="CDD" keyType="key-string">
80 :     <Notes>A CDD is a protein domain designator. It represents the shape of a molecular unit
81 :     on a feature's protein. The ID is six-digit string assigned by the public Conserved Domain
82 :     Database. A CDD can occur on multiple features and a feature generally has multiple CDDs.</Notes>
83 :     </Entity>
84 : parrello 1.1 <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 : parrello 1.50 <Field name="feature-type" type="id-string">
133 : parrello 1.8 <Notes>Code indicating the type of this feature.</Notes>
134 :     </Field>
135 : parrello 1.1 <Field name="translation" type="text" relation="FeatureTranslation">
136 : parrello 1.8 <Notes>[i](optional)[/i] A translation of this feature's residues into character
137 :     codes, formed by concatenating the pieces of the feature together. For a
138 :     protein encoding group, this is the protein characters. For other types
139 :     it is the DNA characters.</Notes>
140 :     </Field>
141 : parrello 1.1 <Field name="upstream-sequence" type="text" relation="FeatureUpstream">
142 : parrello 1.8 <Notes>Upstream sequence the feature. This includes residues preceding the feature as well as some of
143 :     the feature's initial residues.</Notes>
144 :     </Field>
145 : parrello 1.42 <Field name="assignment" type="text">
146 :     <Notes>Default functional assignment for this feature.</Notes>
147 :     </Field>
148 : parrello 1.1 <Field name="active" type="boolean">
149 : parrello 1.11 <Notes>TRUE if this feature is still considered valid, FALSE if it has been logically deleted.</Notes>
150 : parrello 1.8 </Field>
151 : parrello 1.48 <Field name="assignment-maker" type="name-string">
152 :     <Notes>name of the user who made the functional assignment</Notes>
153 :     </Field>
154 :     <Field name="assignment-quality" type="char">
155 :     <Notes>quality of the functional assignment, usually a space, but may be W (indicating weak) or X
156 :     (indicating experimental)</Notes>
157 :     </Field>
158 : parrello 1.41 <Field name="keywords" type="text" searchable="1">
159 :     <Notes>This is a list of search keywords for the feature. It includes the
160 :     functional assignment, subsystem roles, and special properties.</Notes>
161 : parrello 1.36 </Field>
162 : parrello 1.8 <Field name="link" type="text" relation="FeatureLink">
163 :     <Notes>Web hyperlink for this feature. A feature have no hyperlinks or it can have many. The
164 :     links are to other websites that have useful about the gene that the feature represents, and
165 :     are coded as raw HTML, using [b]&lt;a href="[i]link[/i]"&gt;[i]text[/i]&lt;/a&gt;[/b] notation.</Notes>
166 :     </Field>
167 : parrello 1.41 <Field name="conservation" type="float" relation="FeatureConservation">
168 :     <Notes>A number between 0 and 1 that indicates the degree to which this feature's DNA is
169 :     conserved in related genomes. A value of 1 indicates perfect conservation. A value less
170 : parrello 1.50 than 1 is a reflection of the degree to which gap characters interfere in the alignment
171 : parrello 1.41 between the feature and its close relatives.</Notes>
172 :     </Field>
173 : parrello 1.45 <Field name="essential" type="text" relation="FeatureEssential" special="property_search">
174 :     <Notes>A value indicating the essentiality of the feature, coded as HTML. In most
175 :     cases, this will be a word describing whether the essentiality is confirmed (essential)
176 :     or potential (potential-essential), hyperlinked to the document from which the
177 :     essentiality was curated. If a feature is not essential, this field will have no
178 :     values; otherwise, it may have multiple values.</Notes>
179 :     </Field>
180 :     <Field name="virulent" type="text" relation="FeatureVirulent" special="property_search">
181 :     <Notes>A value indicating the virulence of the feature, coded as HTML. In most
182 :     cases, this will be a phrase or SA number hyperlinked to the document from which
183 :     the virulence information was curated. If the feature is not virulent, this field
184 :     will have no values; otherwise, it may have multiple values.</Notes>
185 :     </Field>
186 : parrello 1.50 <Field name="cello" type="name-string">
187 :     <Notes>The cello value specifies the expected location of the protein: cytoplasm,
188 :     cell wall, inner membrane, and so forth.</Notes>
189 :     </Field>
190 : parrello 1.45 <Field name="iedb" type="text" relation="FeatureIEDB" special="property_search">
191 :     <Notes>A value indicating whether or not the feature can be found in the
192 :     Immune Epitope Database. If the feature has not been matched to that database,
193 :     this field will have no values. Otherwise, it will have an epitope name and/or
194 :     sequence, hyperlinked to the database.</Notes>
195 :     </Field>
196 : parrello 1.50 <Field name="location-string" type="text">
197 :     <Notes>Location of the feature, expressed as a comma-delimited list of Sprout location
198 :     strings. This gives us a fast mechanism for extracting the feature location. Otherwise,
199 :     we have to painstakingly paste together the IsLocatedIn records, which are themselves
200 :     designed to help look for genes in a particular region rather than to find the location
201 :     of a gene.</Notes>
202 :     </Field>
203 : parrello 1.1 </Fields>
204 : parrello 1.8 <Indexes>
205 :     <Index>
206 : parrello 1.50 <Notes>This index allows us to locate a feature by its CELLO value.</Notes>
207 : parrello 1.8 <IndexFields>
208 : parrello 1.50 <IndexField name="cello" order="ascending" />
209 : parrello 1.8 </IndexFields>
210 :     </Index>
211 :     </Indexes>
212 : parrello 1.1 </Entity>
213 : parrello 1.50 <Entity name="FeatureAlias" keyType="medium-string">
214 :     <Notes>Alternative names for features. A feature can have many aliases. In general,
215 :     each alias corresponds to only one feature, but there are exceptionsis is not strictly enforced.</Notes>
216 :     </Entity>
217 : parrello 1.27 <Entity name="SynonymGroup" keyType="id-string">
218 :     <Notes>A [i]synonym group[/i] represents a group of features. Substantially identical features
219 :     are mapped to the same synonym group, and this information is used to expand similarities.</Notes>
220 :     </Entity>
221 : parrello 1.1 <Entity name="Role" keyType="string">
222 :     <Notes>A [i]role[/i] describes a biological function that may be fulfilled by a feature.
223 :     One of the main goals of the database is to record the roles of the various features.</Notes>
224 : parrello 1.50 </Entity>
225 :     <Entity name="RoleEC" keyType="string">
226 :     <Notes>EC code for a role.</Notes>
227 : parrello 1.1 </Entity>
228 :     <Entity name="Annotation" keyType="name-string">
229 :     <Notes>An [i]annotation[/i] contains supplementary information about a feature. Annotations
230 : parrello 1.8 are currently the only objects that may be inserted directly into the database. All other
231 : parrello 1.24 information is loaded from data exported by the SEED.</Notes>
232 : parrello 1.8 <Fields>
233 :     <Field name="time" type="date">
234 :     <Notes>Date and time of the annotation.</Notes>
235 :     </Field>
236 :     <Field name="annotation" type="text">
237 :     <Notes>Text of the annotation.</Notes>
238 :     </Field>
239 : parrello 1.1 </Fields>
240 : parrello 1.26 <Indexes>
241 :     <Index>
242 :     <Notes>This index allows the user to find recent annotations.</Notes>
243 :     <IndexFields>
244 :     <IndexField name="time" order="descending" />
245 :     </IndexFields>
246 :     </Index>
247 :     </Indexes>
248 : parrello 1.1 </Entity>
249 : parrello 1.15 <Entity name="Reaction" keyType="key-string">
250 :     <Notes>A [i]reaction[/i] is a chemical process catalyzed by a protein. The reaction ID
251 :     is generally a small number preceded by a letter.</Notes>
252 :     <Fields>
253 :     <Field name="url" type="string" relation="ReactionURL">
254 :     <Notes>HTML string containing a link to a web location that describes the
255 :     reaction. This field is optional.</Notes>
256 :     </Field>
257 :     <Field name="rev" type="boolean">
258 :     <Notes>TRUE if this reaction is reversible, else FALSE</Notes>
259 :     </Field>
260 :     </Fields>
261 :     </Entity>
262 :     <Entity name="Compound" keyType="name-string">
263 :     <Notes>A [i]compound[/i] is a chemical that participates in a reaction.
264 :     All compounds have a unique ID and may also have one or more names.</Notes>
265 :     <Fields>
266 : parrello 1.50 <Field name="label" type="string">
267 : parrello 1.19 <Notes>Name used in reaction display strings.
268 :     It is the same as the name possessing a priority of 1, but it is placed
269 :     here to speed up the query used to create the display strings.</Notes>
270 :     </Field>
271 : parrello 1.15 </Fields>
272 : parrello 1.50 </Entity>
273 :     <Entity name="CompoundName" keyType="string">
274 :     <Notes>A [i]compound name[/i] is a common name for the chemical represented by a
275 :     compound.</Notes>
276 :     </Entity>
277 :     <Entity name="CompoundCAS" keyType="name-string">
278 :     <Notes>This entity represents the Chemical Abstract Service ID for a compound. Each
279 :     Compound has at most one CAS ID.</Notes>
280 : parrello 1.15 </Entity>
281 : parrello 1.5 <Entity name="Subsystem" keyType="string">
282 : parrello 1.1 <Notes>A [i]subsystem[/i] is a collection of roles that work together in a cell. Identification of subsystems
283 :     is an important tool for recognizing parallel genetic features in different organisms.</Notes>
284 : parrello 1.15 <Fields>
285 :     <Field name="curator" type="string">
286 :     <Notes>Name of the person currently in charge of the subsystem.</Notes>
287 :     </Field>
288 :     <Field name="notes" type="text">
289 :     <Notes>Descriptive notes about the subsystem.</Notes>
290 :     </Field>
291 : parrello 1.28 <Field name="classification" type="string" relation="SubsystemClass">
292 : parrello 1.44 <Notes>Classification string, colon-delimited. This string organizes the
293 : parrello 1.42 subsystems into a hierarchy.</Notes>
294 : parrello 1.28 </Field>
295 : parrello 1.15 </Fields>
296 :     </Entity>
297 :     <Entity name="RoleSubset" keyType="string">
298 :     <Notes>A [i]role subset[/i] is a named collection of roles in a particular subsystem. The
299 :     subset names are generally very short, non-unique strings. The ID of the parent
300 :     subsystem is prefixed to the subset ID in order to make it unique.</Notes>
301 :     </Entity>
302 :     <Entity name="GenomeSubset" keyType="string">
303 :     <Notes>A [i]genome subset[/i] is a named collection of genomes that participate
304 :     in a particular subsystem. The subset names are generally very short, non-unique
305 :     strings. The ID of the parent subsystem is prefixed to the subset ID in order
306 :     to make it unique.</Notes>
307 : parrello 1.1 </Entity>
308 : parrello 1.24 <Entity name="SSCell" keyType="hash-string">
309 : parrello 1.1 <Notes>Part of the process of locating and assigning features is creating a spreadsheet of
310 :     genomes and roles to which features are assigned. A [i]spreadsheet cell[/i] represents one
311 :     of the positions on the spreadsheet.</Notes>
312 :     </Entity>
313 :     <Entity name="SproutUser" keyType="name-string">
314 :     <Notes>A [i]user[/i] is a person who can make annotations and view data in the database. The
315 :     user object is keyed on the user's login name.</Notes>
316 :     <Fields>
317 : parrello 1.8 <Field name="description" type="string">
318 :     <Notes>Full name or description of this user.</Notes>
319 :     </Field>
320 : parrello 1.1 <Field name="access-code" type="key-string" relation="UserAccess">
321 : parrello 1.8 <Notes>Access code possessed by this
322 : parrello 1.1 user. A user can have many access codes; a genome is accessible to the user if its
323 :     access code matches any one of the user's access codes.</Notes>
324 : parrello 1.8 </Field>
325 : parrello 1.1 </Fields>
326 :     </Entity>
327 : parrello 1.8 <Entity name="Property" keyType="int">
328 :     <Notes>A [i]property[/i] is a type of assertion that could be made about the properties of
329 :     a particular feature. Each property instance is a key/value pair and can be associated
330 :     with many different features. Conversely, a feature can be associated with many key/value
331 :     pairs, even some that notionally contradict each other. For example, there can be evidence
332 :     that a feature is essential to the organism's survival and evidence that it is superfluous.</Notes>
333 :     <Fields>
334 :     <Field name="property-name" type="name-string">
335 :     <Notes>Name of this property.</Notes>
336 :     </Field>
337 :     <Field name="property-value" type="string">
338 :     <Notes>Value associated with this property. For each property
339 :     name, there must by a property record for all of its possible
340 :     values.</Notes>
341 :     </Field>
342 :     </Fields>
343 :     <Indexes>
344 :     <Index>
345 :     <Notes>This index enables the application to find all values for a specified property
346 :     name, or any given name/value pair.</Notes>
347 :     <IndexFields>
348 :     <IndexField name="property-name" order="ascending" />
349 :     <IndexField name="property-value" order="ascending" />
350 :     </IndexFields>
351 :     </Index>
352 :     </Indexes>
353 :     </Entity>
354 :     <Entity name="Diagram" keyType="name-string">
355 :     <Notes>A functional diagram describes the chemical reactions, often comprising a single
356 :     subsystem. A diagram is identified by a short name and contains a longer descriptive name.
357 :     The actual diagram shows which functional roles guide the reactions along with the inputs
358 :     and outputs; the database, however, only indicate which roles belong to a particular
359 :     map.</Notes>
360 :     <Fields>
361 :     <Field name="name" type="text">
362 :     <Notes>Descriptive name of this diagram.</Notes>
363 :     </Field>
364 :     </Fields>
365 :     </Entity>
366 :     <Entity name="ExternalAliasOrg" keyType="name-string">
367 :     <Notes>An external alias is a feature name for a functional assignment that is not a
368 :     FIG ID. Functional assignments for external aliases are kept in a separate section of
369 :     the database. This table contains a description of the relevant organism for an
370 :     external alias functional assignment.</Notes>
371 :     <Fields>
372 :     <Field name="org" type="text">
373 :     <Notes>Descriptive name of the target organism for this external alias.</Notes>
374 :     </Field>
375 :     </Fields>
376 :     </Entity>
377 :     <Entity name="ExternalAliasFunc" keyType="name-string">
378 :     <Notes>An external alias is a feature name for a functional assignment that is not a
379 :     FIG ID. Functional assignments for external aliases are kept in a separate section of
380 :     the database. This table contains the functional role for the external alias functional
381 :     assignment.</Notes>
382 :     <Fields>
383 :     <Field name="func" type="text">
384 :     <Notes>Functional role for this external alias.</Notes>
385 :     </Field>
386 :     </Fields>
387 :     </Entity>
388 : parrello 1.31 <Entity name="Family" keyType="id-string">
389 :     <Notes>A family is a group of homologous PEGs believed to have the same function. Protein
390 :     families provide a mechanism for verifying the accuracy of functional assignments
391 :     and are also used in determining phylogenetic trees.</Notes>
392 :     <Fields>
393 : parrello 1.32 <Field name="function" type="text">
394 : parrello 1.31 <Notes>The functional assignment expected for all PEGs in this family.</Notes>
395 :     </Field>
396 : parrello 1.33 <Field name="size" type="int">
397 : parrello 1.31 <Notes>The number of proteins in this family. This may be larger than the
398 :     number of PEGs included in the family, since the family may also contain external
399 :     IDs.</Notes>
400 :     </Field>
401 :     </Fields>
402 :     </Entity>
403 : parrello 1.49 <Entity name="PDB" keyType="id-string">
404 :     <Notes>A PDB is a protein database containing information that can be used to determine
405 :     the shape of the protein and the energies required to dock with it. The ID is the
406 :     four-character name used on the PDB web site.</Notes>
407 :     <Fields>
408 :     <Field name="docking-count" type="int">
409 :     <Notes>The number of ligands that have been docked against this PDB.</Notes>
410 :     </Field>
411 :     </Fields>
412 :     <Indexes>
413 :     <Index>
414 :     <IndexFields>
415 :     <IndexField name="docking-count" order="descending" />
416 :     <IndexField name="id" order="ascending" />
417 :     </IndexFields>
418 :     </Index>
419 :     </Indexes>
420 :     </Entity>
421 :     <Entity name="Ligand" keyType="id-string">
422 :     <Notes>A Ligand is a chemical of interest in computing docking energies against a PDB.
423 :     The ID of the ligand is an 8-digit ZINC ID number.</Notes>
424 :     <Fields>
425 :     <Field name="name" type="long-string">
426 :     <Notes>Chemical name of this ligand.</Notes>
427 :     </Field>
428 :     </Fields>
429 :     </Entity>
430 : parrello 1.1 </Entities>
431 :     <Relationships>
432 : parrello 1.50 <Relationship name="IsPresentOnProteinOf" from="CDD" to="Feature" arity="MM">
433 :     <Notes>This relationship connects a feature to its CDD protein domains. The
434 :     match score is included as intersection data.</Notes>
435 :     <Fields>
436 :     <Field name="score" type="float">
437 :     <Notes>This is the match score between the feature and the CDD. A
438 :     lower score is a better match.</Notes>
439 :     </Field>
440 :     </Fields>
441 :     <FromIndex>
442 :     <IndexFields>
443 :     <IndexField name="score" order="ascending" />
444 :     </IndexFields>
445 :     </FromIndex>
446 :     </Relationship>
447 :     <Relationship name="IsIdentifiedByCAS" from="Compound" to="CompoundCAS" arity="MM">
448 :     <Notes>Relates a compound's CAS ID to the compound itself. Every CAS ID is
449 :     associated with a compound, and some are associated with two compounds, but not
450 :     all compounds have CAS IDs.</Notes>
451 :     </Relationship>
452 :     <Relationship name="IsIdentifiedByEC" from="Role" to="RoleEC" arity="MM">
453 :     <Notes>Relates a role to its EC number. Every EC number is associated with a
454 :     role, but not all roles have EC numbers.</Notes>
455 :     </Relationship>
456 :     <Relationship name="IsAliasOf" from="FeatureAlias" to="Feature" arity="MM">
457 :     <Notes>Connects an alias to the feature it represents. Every alias connects
458 :     to at least 1 feature, and a feature connects to many aliases.</Notes>
459 :     </Relationship>
460 :     <Relationship name="HasCompoundName" from="Compound" to="CompoundName" arity="MM">
461 :     <Notes>Connects a compound to its names. A compound generally has several
462 :     names</Notes>
463 :     <Fields>
464 :     <Field name="priority" type="int">
465 :     <Notes>Priority of this name, with 1 being the highest priority, 2
466 :     the next highest, and so forth.</Notes>
467 :     </Field>
468 :     </Fields>
469 :     <FromIndex>
470 :     <Notes>This index enables the application to view the names of a compound
471 :     in priority order.</Notes>
472 :     <IndexFields>
473 :     <IndexField name="priority" order="ascending" />
474 :     </IndexFields>
475 :     </FromIndex>
476 :     </Relationship>
477 : parrello 1.49 <Relationship name="IsProteinForFeature" from="PDB" to="Feature" arity="MM">
478 :     <Notes>Relates a PDB to features that produce highly similar proteins.</Notes>
479 :     <Fields>
480 :     <Field name="score" type="float">
481 :     <Notes>Similarity score for the comparison between the feature and
482 :     the PDB protein. A lower score indicates a better match.</Notes>
483 :     </Field>
484 :     <Field name="start-location" type="int">
485 :     <Notes>Starting location within the feature of the matching region.</Notes>
486 :     </Field>
487 :     <Field name="end-location" type="int">
488 :     <Notes>Ending location within the feature of the matching region.</Notes>
489 :     </Field>
490 :     </Fields>
491 :     <ToIndex>
492 :     <Notes>This index enables the application to view the PDBs of a
493 :     feature in order from the closest match to the furthest.</Notes>
494 :     <IndexFields>
495 :     <IndexField name="score" order="ascending" />
496 :     </IndexFields>
497 :     </ToIndex>
498 :     <FromIndex>
499 :     <Notes>This index enables the application to view the features of
500 :     a PDB in order from the closest match to the furthest.</Notes>
501 :     <IndexFields>
502 :     <IndexField name="score" order="ascending" />
503 :     </IndexFields>
504 :     </FromIndex>
505 :     </Relationship>
506 :     <Relationship name="DocksWith" from="PDB" to="Ligand" arity="MM">
507 :     <Notes>Indicates that a docking result exists between a PDB and a ligand. The
508 :     docking result describes the energy required for the ligand to dock with
509 :     the protein described by the PDB. A lower energy indicates the ligand has a
510 :     good chance of disabling the protein. At the current time, only the best
511 :     docking results are kept.</Notes>
512 :     <Fields>
513 :     <Field name="reason" type="id-string">
514 :     <Notes>Indication of the reason for determining the docking result.
515 :     A value of [b]Random[/b] indicates the docking was attempted as a part
516 :     of a random survey used to determine the docking characteristics of the
517 :     PDB. A value of [b]Rich[/b] indicates the docking was attempted because
518 :     a low-energy docking result was predicted for the ligand with respect
519 :     to the PDB.</Notes>
520 :     </Field>
521 :     <Field name="tool" type="id-string">
522 :     <Notes>Name of the tool used to produce the docking result.</Notes>
523 :     </Field>
524 :     <Field name="total-energy" type="float">
525 :     <Notes>Total energy required for the ligand to dock with the PDB
526 :     protein, in kcal/mol. A negative value means energy is released.</Notes>
527 :     </Field>
528 :     <Field name="vanderwalls-energy" type="float">
529 :     <Notes>Docking energy in kcal/mol that results from the geometric fit
530 :     (Van der Waals force) between the PDB and the ligand.</Notes>
531 :     </Field>
532 :     <Field name="electrostatic-energy" type="float">
533 :     <Notes>Docking energy in kcal/mol that results from the movement of
534 :     electrons (electrostatic force) between the PDB and the ligan.</Notes>
535 :     </Field>
536 :     </Fields>
537 :     <FromIndex>
538 :     <Notes>This index enables the application to view a PDB's docking results from
539 :     the lowest energy (best docking) to highest energy (worst docking).</Notes>
540 :     <IndexFields>
541 :     <IndexField name="total-energy" order="ascending" />
542 :     </IndexFields>
543 :     </FromIndex>
544 :     <ToIndex>
545 :     <Notes>This index enables the application to view a ligand's docking results from
546 :     the lowest energy (best docking) to highest energy (worst docking). Note that
547 :     since we only keep the best docking results for a PDB, this index is not likely
548 :     to provide useful results.</Notes>
549 :     </ToIndex>
550 :     </Relationship>
551 : parrello 1.34 <Relationship name="IsFamilyForFeature" from="Family" to="Feature" arity="MM">
552 : parrello 1.31 <Notes>This relationship connects a protein family to all of its PEGs and connects
553 :     each PEG to all of its protein families.</Notes>
554 :     </Relationship>
555 : parrello 1.50 <Relationship name="IsSynonymGroupFor" from="SynonymGroup" to="Feature" arity="MM">
556 : parrello 1.27 <Notes>This relation connects a synonym group to the features that make it
557 :     up.</Notes>
558 :     </Relationship>
559 : parrello 1.24 <Relationship name="HasFeature" from="Genome" to="Feature" arity="1M">
560 :     <Notes>This relationship connects a genome to all of its features. This
561 :     relationship is redundant in a sense, because the genome ID is part
562 :     of the feature ID; however, it makes the creation of certain queries more
563 :     convenient because you can drag in filtering information for a feature's
564 :     genome.</Notes>
565 :     <Fields>
566 :     <Field name="type" type="key-string">
567 :     <Notes>Feature type (eg. peg, rna)</Notes>
568 :     </Field>
569 :     </Fields>
570 : parrello 1.38 <FromIndex>
571 : parrello 1.24 <Notes>This index enables the application to view the features of a
572 :     Genome sorted by type.</Notes>
573 :     <IndexFields>
574 :     <IndexField name="type" order="ascending" />
575 :     </IndexFields>
576 : parrello 1.38 </FromIndex>
577 : parrello 1.24 </Relationship>
578 : parrello 1.1 <Relationship name="HasContig" from="Genome" to="Contig" arity="1M">
579 :     <Notes>This relationship connects a genome to the contigs that contain the actual genetic
580 :     information.</Notes>
581 :     </Relationship>
582 :     <Relationship name="ComesFrom" from="Genome" to="Source" arity="MM">
583 :     <Notes>This relationship connects a genome to the sources that mapped it. A genome can
584 :     come from a single source or from a cooperation among multiple sources.</Notes>
585 :     </Relationship>
586 :     <Relationship name="IsMadeUpOf" from="Contig" to="Sequence" arity="1M">
587 :     <Notes>A contig is stored in the database as an ordered set of sequences. By splitting the
588 :     contig into sequences, we get a performance boost from only needing to keep small portions
589 :     of a contig in memory at any one time. This relationship connects the contig to its
590 :     constituent sequences.</Notes>
591 :     <Fields>
592 :     <Field name="len" type="int">
593 : parrello 1.15 <Notes>Length of the sequence.</Notes>
594 :     </Field>
595 : parrello 1.1 <Field name="start-position" type="int">
596 : parrello 1.15 <Notes>Index (1-based) of the point in the contig where this
597 :     sequence starts.</Notes>
598 :     </Field>
599 : parrello 1.1 </Fields>
600 :     <FromIndex>
601 :     <Notes>This index enables the application to find all of the sequences in
602 : parrello 1.8 a contig in order, and makes it easier to find a particular residue section.</Notes>
603 : parrello 1.1 <IndexFields>
604 :     <IndexField name="start-position" order="ascending" />
605 :     <IndexField name="len" order="ascending" />
606 :     </IndexFields>
607 :     </FromIndex>
608 :     </Relationship>
609 :     <Relationship name="IsTargetOfAnnotation" from="Feature" to="Annotation" arity="1M">
610 :     <Notes>This relationship connects a feature to its annotations.</Notes>
611 :     </Relationship>
612 :     <Relationship name="MadeAnnotation" from="SproutUser" to="Annotation" arity="1M">
613 :     <Notes>This relationship connects an annotation to the user who made it.</Notes>
614 :     </Relationship>
615 :     <Relationship name="ParticipatesIn" from="Genome" to="Subsystem" arity="MM">
616 :     <Notes>This relationship connects subsystems to the genomes that use
617 :     it. If the subsystem has been curated for the genome, then the subsystem's roles will also be
618 :     connected to the genome features through the [b]SSCell[/b] object.</Notes>
619 : parrello 1.15 <Fields>
620 :     <Field name="variant-code" type="key-string">
621 : parrello 1.20 <Notes>Code indicating the subsystem variant to which this
622 : parrello 1.15 genome belongs. Each subsystem can have multiple variants. A variant
623 : parrello 1.20 code of [b]-1[/b] indicates that the genome does not have a functional
624 :     variant of the subsystem. A variant code of [b]0[/b] indicates that
625 :     the genome's participation is considered iffy.</Notes>
626 : parrello 1.15 </Field>
627 :     </Fields>
628 :     <ToIndex>
629 :     <Notes>This index enables the application to find all of the genomes using
630 :     a subsystem in order by variant code, which is how we wish to display them
631 :     in the spreadsheets.</Notes>
632 :     <IndexFields>
633 :     <IndexField name="variant-code" order="ascending" />
634 :     </IndexFields>
635 :     </ToIndex>
636 : parrello 1.1 </Relationship>
637 :     <Relationship name="OccursInSubsystem" from="Role" to="Subsystem" arity="MM">
638 :     <Notes>This relationship connects roles to the subsystems that implement them. </Notes>
639 : parrello 1.15 <Fields>
640 : parrello 1.50 <Field name="abbr" type="name-string">
641 :     <Notes>Abbreviated name for the role, generally non-unique, but useful
642 :     in column headings for HTML tables.</Notes>
643 :     </Field>
644 : parrello 1.15 <Field name="column-number" type="int">
645 :     <Notes>Column number for this role in the specified subsystem's
646 :     spreadsheet.</Notes>
647 :     </Field>
648 :     </Fields>
649 :     <ToIndex>
650 :     <Notes>This index enables the application to see the subsystem roles
651 :     in column order. The ordering of the roles is usually significant,
652 :     so it is important to preserve it.</Notes>
653 :     <IndexFields>
654 :     <IndexField name="column-number" order="ascending" />
655 :     </IndexFields>
656 :     </ToIndex>
657 : parrello 1.1 </Relationship>
658 :     <Relationship name="IsGenomeOf" from="Genome" to="SSCell" arity="1M">
659 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
660 :     genome for the spreadsheet column.</Notes>
661 :     </Relationship>
662 :     <Relationship name="IsRoleOf" from="Role" to="SSCell" arity="1M">
663 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
664 :     role for the spreadsheet row.</Notes>
665 :     </Relationship>
666 :     <Relationship name="ContainsFeature" from="SSCell" to="Feature" arity="MM">
667 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
668 :     features assigned to it.</Notes>
669 : parrello 1.15 <Fields>
670 :     <Field name="cluster-number" type="int">
671 :     <Notes>ID of this feature's cluster. Clusters represent families of
672 :     related proteins participating in a subsystem.</Notes>
673 :     </Field>
674 :     </Fields>
675 :     </Relationship>
676 :     <Relationship name="IsAComponentOf" from="Compound" to="Reaction" arity="MM">
677 :     <Notes>This relationship connects a reaction to the compounds that participate
678 :     in it.</Notes>
679 :     <Fields>
680 :     <Field name="product" type="boolean">
681 :     <Notes>TRUE if the compound is a product of the reaction, FALSE if
682 :     it is a substrate. When a reaction is written on paper in
683 :     chemical notation, the substrates are left of the arrow and the
684 :     products are to the right. Sorting on this field will cause
685 :     the substrates to appear first, followed by the products. If the
686 :     reaction is reversible, then the notion of substrates and products
687 :     is not at intuitive; however, a value here of FALSE still puts the
688 :     compound left of the arrow and a value of TRUE still puts it to the
689 :     right.</Notes>
690 :     </Field>
691 : parrello 1.19 <Field name="stoichiometry" type="key-string">
692 : parrello 1.15 <Notes>Number of molecules of the compound that participate in a
693 :     single instance of the reaction. For example, if a reaction
694 : parrello 1.19 produces two water molecules, the stoichiometry of water for the
695 : parrello 1.15 reaction would be two. When a reaction is written on paper in
696 : parrello 1.19 chemical notation, the stoichiometry is the number next to the
697 : parrello 1.15 chemical formula of the compound.</Notes>
698 :     </Field>
699 :     <Field name="main" type="boolean">
700 :     <Notes>TRUE if this compound is one of the main participants in
701 :     the reaction, else FALSE. It is permissible for none of the
702 :     compounds in the reaction to be considered main, in which
703 :     case this value would be FALSE for all of the relevant
704 :     compounds.</Notes>
705 :     </Field>
706 :     <Field name="loc" type="key-string">
707 :     <Notes>An optional character string that indicates the relative
708 :     position of this compound in the reaction's chemical formula. The
709 :     location affects the way the compounds present as we cross the
710 :     relationship from the reaction side. The product/substrate flag
711 :     comes first, then the value of this field, then the main flag.
712 :     The default value is an empty string; however, the empty string
713 :     sorts first, so if this field is used, it should probably be
714 :     used for every compound in the reaction.</Notes>
715 :     </Field>
716 : parrello 1.19 <Field name="discriminator" type="int">
717 :     <Notes>A unique ID for this record. The discriminator does not
718 :     provide any useful data, but it prevents identical records from
719 :     being collapsed by the SELECT DISTINCT command used by ERDB to
720 :     retrieve data.</Notes>
721 :     </Field>
722 : parrello 1.15 </Fields>
723 :     <ToIndex>
724 :     <Notes>This index presents the compounds in the reaction in the
725 :     order they should be displayed when writing it in chemical notation.
726 :     All the substrates appear before all the products, and within that
727 :     ordering, the main compounds appear first.</Notes>
728 : parrello 1.19 <IndexFields>
729 :     <IndexField name="product" order="ascending" />
730 :     <IndexField name="loc" order="ascending" />
731 :     <IndexField name="main" order="descending" />
732 :     </IndexFields>
733 : parrello 1.15 </ToIndex>
734 : parrello 1.1 </Relationship>
735 :     <Relationship name="IsLocatedIn" from="Feature" to="Contig" arity="MM">
736 :     <Notes>This relationship connects a feature to the contig segments that work together
737 :     to effect it. The segments are numbered sequentially starting from 1. The database is
738 :     required to place an upper limit on the length of each segment. If a segment is longer
739 :     than the maximum, it can be broken into smaller bits.
740 :     [p]The upper limit enables applications to locate all features that contain a specific
741 :     residue. For example, if the upper limit is 100 and we are looking for a feature that
742 :     contains residue 234 of contig [b]ABC[/b], we can look for features with a begin point
743 :     between 135 and 333. The results can then be filtered by direction and length of the
744 :     segment.</Notes>
745 :     <Fields>
746 :     <Field name="locN" type="int">
747 : parrello 1.8 <Notes>Sequence number of this segment.</Notes>
748 :     </Field>
749 : parrello 1.1 <Field name="beg" type="int">
750 : parrello 1.8 <Notes>Index (1-based) of the first residue in the contig that
751 :     belongs to the segment.</Notes>
752 :     </Field>
753 : parrello 1.1 <Field name="len" type="int">
754 : parrello 1.8 <Notes>Number of residues in the segment. A length of 0 identifies
755 :     a specific point between residues. This is the point before the residue if the direction
756 :     is forward and the point after the residue if the direction is backward.</Notes>
757 :     </Field>
758 : parrello 1.1 <Field name="dir" type="char">
759 : parrello 1.8 <Notes>Direction of the segment: [b]+[/b] if it is forward and
760 :     [b]-[/b] if it is backward.</Notes>
761 :     </Field>
762 : parrello 1.1 </Fields>
763 : parrello 1.45 <FromIndex>
764 : parrello 1.1 <Notes>This index allows the application to find all the segments of a feature in
765 : parrello 1.8 the proper order.</Notes>
766 : parrello 1.1 <IndexFields>
767 :     <IndexField name="locN" order="ascending" />
768 :     </IndexFields>
769 :     </FromIndex>
770 :     <ToIndex>
771 :     <Notes>This index is the one used by applications to find all the feature
772 :     segments that contain a specific residue.</Notes>
773 :     <IndexFields>
774 :     <IndexField name="beg" order="ascending" />
775 :     </IndexFields>
776 :     </ToIndex>
777 :     </Relationship>
778 : parrello 1.8 <Relationship name="HasProperty" from="Feature" to="Property" arity="MM">
779 :     <Notes>This relationship connects a feature to its known property values.
780 :     The relationship contains text data that indicates the paper or organization
781 :     that discovered evidence that the feature possesses the property. So, for
782 :     example, if two papers presented evidence that a feature is essential,
783 :     there would be an instance of this relationship for both.</Notes>
784 :     <Fields>
785 :     <Field name="evidence" type="text">
786 :     <Notes>URL or citation of the paper or
787 :     institution that reported evidence of the relevant feature possessing
788 :     the specified property value.</Notes>
789 :     </Field>
790 :     </Fields>
791 :     </Relationship>
792 :     <Relationship name="RoleOccursIn" from="Role" to="Diagram" arity="MM">
793 :     <Notes>This relationship connects a role to the diagrams on which it
794 :     appears. A role frequently identifies an enzyme, and can appear in many
795 :     diagrams. A diagram generally contains many different roles.</Notes>
796 :     </Relationship>
797 :     <Relationship name="HasSSCell" from="Subsystem" to="SSCell" arity="1M">
798 :     <Notes>This relationship connects a subsystem to the spreadsheet cells
799 :     used to analyze and display it. The cells themselves can be thought of
800 :     as a grid with Roles on one axis and Genomes on the other. The
801 :     various features of the subsystem are then assigned to the cells.</Notes>
802 :     </Relationship>
803 :     <Relationship name="IsTrustedBy" from="SproutUser" to="SproutUser" arity="MM">
804 :     <Notes>This relationship identifies the users trusted by each
805 :     particular user. When viewing functional assignments, the
806 :     assignment displayed is the most recent one by a user trusted
807 :     by the current user. The current user implicitly trusts himself.
808 :     If no trusted users are specified in the database, the user
809 :     also implicitly trusts the user [b]FIG[/b].</Notes>
810 :     </Relationship>
811 : parrello 1.15 <Relationship name="ConsistsOfRoles" from="RoleSubset" to="Role" arity="MM">
812 :     <Notes>This relationship connects a role subset to the roles that it covers.
813 :     A subset is, essentially, a named group of roles belonging to a specific
814 :     subsystem, and this relationship effects that. Note that will a role
815 :     may belong to many subsystems, a subset belongs to only one subsystem,
816 :     and all roles in the subset must have that subsystem in common.</Notes>
817 :     </Relationship>
818 :     <Relationship name="ConsistsOfGenomes" from="GenomeSubset" to="Genome" arity="MM">
819 :     <Notes>This relationship connects a subset to the genomes that it covers.
820 :     A subset is, essentially, a named group of genomes participating in a specific
821 :     subsystem, and this relationship effects that. Note that while a genome
822 :     may belong to many subsystems, a subset belongs to only one subsystem,
823 :     and all genomes in the subset must have that subsystem in common.</Notes>
824 :     </Relationship>
825 :     <Relationship name="HasRoleSubset" from="Subsystem" to="RoleSubset" arity="1M">
826 :     <Notes>This relationship connects a subsystem to its constituent
827 :     role subsets. Note that some roles in a subsystem may not belong to a
828 :     subset, so the relationship between roles and subsystems cannot be
829 :     derived from the relationships going through the subset.</Notes>
830 :     </Relationship>
831 :     <Relationship name="HasGenomeSubset" from="Subsystem" to="GenomeSubset" arity="1M">
832 :     <Notes>This relationship connects a subsystem to its constituent
833 :     genome subsets. Note that some genomes in a subsystem may not belong to a
834 :     subset, so the relationship between genomes and subsystems cannot be
835 :     derived from the relationships going through the subset.</Notes>
836 :     </Relationship>
837 :     <Relationship name="Catalyzes" from="Role" to="Reaction" arity="MM">
838 :     <Notes>This relationship connects a role to the reactions it catalyzes.
839 :     The purpose of a role is to create proteins that trigger certain
840 :     chemical reactions. A single reaction can be triggered by many roles,
841 :     and a role can trigger many reactions.</Notes>
842 :     </Relationship>
843 : parrello 1.39 <Relationship name="HasRoleInSubsystem" from="Feature" to="Subsystem" arity="MM">
844 :     <Notes>This relationship connects a feature to the subsystems in which it
845 :     participates. This is technically redundant information, but it is used
846 :     so often that it deserves its own table.</Notes>
847 : parrello 1.40 <Fields>
848 :     <Field name="genome" type="name-string">
849 :     <Notes>ID of the genome containing the feature</Notes>
850 :     </Field>
851 :     <Field name="type" type="key-string">
852 :     <Notes>Feature type (eg. peg, rna)</Notes>
853 :     </Field>
854 :     </Fields>
855 :     <ToIndex>
856 :     <Notes>This index enables the application to view the features of a
857 :     subsystem sorted by genome and feature type.</Notes>
858 :     <IndexFields>
859 :     <IndexField name="genome" order="ascending" />
860 :     <IndexField name="type" order="ascending" />
861 :     </IndexFields>
862 :     </ToIndex>
863 : parrello 1.39 </Relationship>
864 : parrello 1.1 </Relationships>
865 :     </Database>

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3