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

Annotation of /Sprout/SproutDBD.xml

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.40 - (view) (download) (as text)

1 : parrello 1.1 <?xml version="1.0" encoding="utf-8" ?>
2 :     <Database>
3 :     <Title>Sprout Genome and Subsystem Database</Title>
4 :     <Entities>
5 :     <Entity name="Genome" keyType="name-string">
6 :     <Notes>A [i]genome[/i] contains the sequence data for a particular individual organism.</Notes>
7 :     <Fields>
8 :     <Field name="genus" type="name-string">
9 :     <Notes>Genus of the relevant organism.</Notes>
10 :     <DataGen pass="1">RandParam('streptococcus', 'staphyloccocus', 'felis', 'homo', 'ficticio', 'strangera', 'escherischia', 'carborunda')</DataGen>
11 :     </Field>
12 :     <Field name="species" type="name-string">
13 : parrello 1.8 <Notes>Species of the relevant organism.</Notes>
14 : parrello 1.1 <DataGen pass="1">StringGen('PKVKVKVKVKV')</DataGen>
15 : parrello 1.8 </Field>
16 : parrello 1.1 <Field name="unique-characterization" type="medium-string">
17 : parrello 1.8 <Notes>The unique characterization identifies the particular organism instance from which the
18 :     genome is taken. It is possible to have in the database more than one genome for a
19 : parrello 1.1 particular species, and every individual organism has variations in its DNA.</Notes>
20 : parrello 1.8 <DataGen>StringGen('PKVKVK999')</DataGen>
21 : parrello 1.1 </Field>
22 :     <Field name="access-code" type="key-string">
23 : parrello 1.8 <Notes>The access code determines which users can look at the data relating to this genome.
24 :     Each user is associated with a set of access codes. In order to view a genome, one of
25 :     the user's access codes must match this value.</Notes>
26 :     <DataGen>RandParam('low','medium','high')</DataGen>
27 :     </Field>
28 : parrello 1.15 <Field name="complete" type="boolean">
29 :     <Notes>TRUE if the genome is complete, else FALSE</Notes>
30 :     </Field>
31 : parrello 1.8 <Field name="taxonomy" type="text">
32 :     <Notes>The taxonomy string contains the full taxonomy of the organism, while individual elements
33 :     separated by semi-colons (and optional white space), starting with the domain and ending with
34 :     the disambiguated genus and species (which is the organism's scientific name plus an
35 :     identifying string).</Notes>
36 :     <DataGen pass="2">join('; ', (RandParam('bacteria', 'archaea', 'eukaryote', 'virus', 'environmental'),
37 :     ListGen('PKVKVKVK', 5), $this->{genus}, $this->{species}))</DataGen>
38 :     </Field>
39 : parrello 1.37 <Field name="primary-group" type="name-string">
40 :     <Notes>The primary NMPDR group for this organism. There is always exactly one NMPDR group
41 :     (either based on the organism name or the default value "Supporting"), whereas there can be
42 :     multiple named groups or even none.</Notes>
43 :     </Field>
44 : parrello 1.8 <Field name="group-name" type="name-string" relation="GenomeGroups">
45 :     <Notes>The group identifies a special grouping of organisms that would be displayed on a particular
46 :     page or of particular interest to a research group or web site. A single genome can belong to multiple
47 :     such groups or none at all.</Notes>
48 :     </Field>
49 : parrello 1.1 </Fields>
50 :     <Indexes>
51 : parrello 1.37 <Index Unique="false">
52 : parrello 1.1 <Notes>This index allows the applications to find all genomes associated with
53 :     a specific access code, so that a complete list of the genomes users can view
54 :     may be generated.</Notes>
55 :     <IndexFields>
56 :     <IndexField name="access-code" order="ascending" />
57 :     <IndexField name="genus" order="ascending" />
58 :     <IndexField name="species" order="ascending" />
59 :     <IndexField name="unique-characterization" order="ascending" />
60 :     </IndexFields>
61 :     </Index>
62 :     <Index Unique="false">
63 : parrello 1.37 <Notes>This index allows the applications to find all genomes associated with
64 :     a specific primary (NMPDR) group.</Notes>
65 :     <IndexFields>
66 :     <IndexField name="primary-group" order="ascending" />
67 :     <IndexField name="genus" order="ascending" />
68 :     <IndexField name="species" order="ascending" />
69 :     <IndexField name="unique-characterization" order="ascending" />
70 :     </IndexFields>
71 :     </Index>
72 :     <Index Unique="false">
73 : parrello 1.1 <Notes>This index allows the applications to find all genomes for a particular
74 :     species.</Notes>
75 :     <IndexFields>
76 :     <IndexField name="genus" order="ascending" />
77 :     <IndexField name="species" order="ascending" />
78 :     <IndexField name="unique-characterization" order="ascending" />
79 :     </IndexFields>
80 :     </Index>
81 :     </Indexes>
82 :     </Entity>
83 :     <Entity name="Source" keyType="medium-string">
84 :     <Notes>A [i]source[/i] describes a place from which genome data was taken. This can be an organization
85 :     or a paper citation.</Notes>
86 :     <Fields>
87 :     <Field name="URL" type="string" relation="SourceURL">
88 : parrello 1.8 <Notes>URL the paper cited or of the organization's web site. This field optional.</Notes>
89 :     <DataGen>"http://www.conservativecat.com/Ferdy/TestTarget.php?Source=" . $this->{id}</DataGen>
90 :     </Field>
91 : parrello 1.1 <Field name="description" type="text">
92 : parrello 1.8 <Notes>Description the source. The description can be a street address or a citation.</Notes>
93 :     <DataGen>$this->{id} . ': ' . StringGen(IntGen(50,200))</DataGen>
94 :     </Field>
95 : parrello 1.1 </Fields>
96 :     </Entity>
97 :     <Entity name="Contig" keyType="name-string">
98 :     <Notes>A [i]contig[/i] is a contiguous run of residues. The contig's ID consists of the
99 :     genome ID followed by a name that identifies which contig this is for the parent genome. As
100 :     is the case with all keys in this database, the individual components are separated by a
101 :     period.
102 :     [p]A contig can contain over a million residues. For performance reasons, therefore,
103 :     the contig is split into multiple pieces called [i]sequences[/i]. The sequences
104 :     contain the characters that represent the residues as well as data on the quality of
105 :     the residue identification.</Notes>
106 :     </Entity>
107 :     <Entity name="Sequence" keyType="name-string">
108 :     <Notes>A [i]sequence[/i] is a continuous piece of a [i]contig[/i]. Contigs are split into
109 :     sequences so that we don't have to have the entire contig in memory when we are
110 :     manipulating it. The key of the sequence is the contig ID followed by the index of
111 :     the begin point.</Notes>
112 :     <Fields>
113 :     <Field name="sequence" type="text">
114 : parrello 1.8 <Notes>String consisting of the residues. Each residue is described by a single
115 :     character in the string.</Notes>
116 :     <DataGen>RandChars("ACGT", IntGen(100,400))</DataGen>
117 :     </Field>
118 : parrello 1.1 <Field name="quality-vector" type="text">
119 : parrello 1.9 <Notes>String describing the quality data for each base pair. Individual values will
120 : parrello 1.8 be separated by periods. The value represents negative exponent of the probability
121 :     of error. Thus, for example, a quality of 30 indicates the probability of error is
122 :     10^-30. A higher quality number a better chance of a correct match. It is possible
123 : parrello 1.9 that the quality data is not known for a sequence. If that is the case, the quality
124 : parrello 1.8 vector will contain the [b]unknown[/b].</Notes>
125 :     <DataGen>unknown</DataGen>
126 :     </Field>
127 : parrello 1.1 </Fields>
128 :     </Entity>
129 : parrello 1.25 <Entity name="Feature" keyType="id-string">
130 : parrello 1.1 <Notes>A [i]feature[/i] is a part of a genome that is of special interest. Features
131 :     may be spread across multiple contigs of a genome, but never across more than
132 :     one genome. Features can be assigned to roles via spreadsheet cells,
133 :     and are the targets of annotation.</Notes>
134 :     <Fields>
135 :     <Field name="feature-type" type="string">
136 : parrello 1.8 <Notes>Code indicating the type of this feature.</Notes>
137 :     <DataGen>RandParam('peg','rna')</DataGen>
138 :     </Field>
139 : parrello 1.14 <Field name="alias" type="medium-string" relation="FeatureAlias">
140 : parrello 1.9 <Notes>Alternative name for this feature. A feature can have many aliases.</Notes>
141 : parrello 1.8 <DataGen testCount="3">StringGen('Pgi|99999', 'Puni|XXXXXX', 'PAAAAAA999')</DataGen>
142 :     </Field>
143 : parrello 1.1 <Field name="translation" type="text" relation="FeatureTranslation">
144 : parrello 1.8 <Notes>[i](optional)[/i] A translation of this feature's residues into character
145 :     codes, formed by concatenating the pieces of the feature together. For a
146 :     protein encoding group, this is the protein characters. For other types
147 :     it is the DNA characters.</Notes>
148 :     <DataGen testCount="0"></DataGen>
149 :     </Field>
150 : parrello 1.1 <Field name="upstream-sequence" type="text" relation="FeatureUpstream">
151 : parrello 1.8 <Notes>Upstream sequence the feature. This includes residues preceding the feature as well as some of
152 :     the feature's initial residues.</Notes>
153 :     <DataGen testCount="0"></DataGen>
154 :     </Field>
155 : parrello 1.1 <Field name="active" type="boolean">
156 : parrello 1.11 <Notes>TRUE if this feature is still considered valid, FALSE if it has been logically deleted.</Notes>
157 : parrello 1.8 <DataGen>1</DataGen>
158 :     </Field>
159 : parrello 1.36 <Field name="assignment" type="text">
160 :     <Notes>This is the primary functional assignment for the feature.</Notes>
161 :     </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 :     <DataGen testCount="3">'http://www.conservativecat.com/Ferdy/TestTarget.php?Source=' . $this->{id} .
167 :     "&amp;Number=" . IntGen(1,99)</DataGen>
168 :     </Field>
169 : parrello 1.1 </Fields>
170 : parrello 1.8 <Indexes>
171 :     <Index>
172 :     <Notes>This index allows the user to find the feature corresponding to
173 :     the specified alias name.</Notes>
174 :     <IndexFields>
175 :     <IndexField name="alias" order="ascending" />
176 :     </IndexFields>
177 :     </Index>
178 :     </Indexes>
179 : parrello 1.1 </Entity>
180 : parrello 1.27 <Entity name="SynonymGroup" keyType="id-string">
181 :     <Notes>A [i]synonym group[/i] represents a group of features. Substantially identical features
182 :     are mapped to the same synonym group, and this information is used to expand similarities.</Notes>
183 :     </Entity>
184 : parrello 1.1 <Entity name="Role" keyType="string">
185 :     <Notes>A [i]role[/i] describes a biological function that may be fulfilled by a feature.
186 :     One of the main goals of the database is to record the roles of the various features.</Notes>
187 : parrello 1.8 <Fields>
188 : parrello 1.18 <Field name="EC" type="string" relation="RoleEC">
189 :     <Notes>EC code for this role.</Notes>
190 : parrello 1.8 <DataGen testCount="1">StringGen(IntGen(20,40)) . "(" . $this->{id} . ")"</DataGen>
191 :     </Field>
192 : parrello 1.15 <Field name="abbr" type="name-string">
193 :     <Notes>Abbreviated name for the role, generally non-unique, but useful
194 :     in column headings for HTML tables.</Notes>
195 :     </Field>
196 : parrello 1.8 </Fields>
197 : parrello 1.18 <Indexes>
198 :     <Index>
199 :     <Notes>This index allows the user to find the role corresponding to
200 :     an EC number.</Notes>
201 :     <IndexFields>
202 :     <IndexField name="EC" order="ascending" />
203 :     </IndexFields>
204 :     </Index>
205 :     </Indexes>
206 : parrello 1.1 </Entity>
207 :     <Entity name="Annotation" keyType="name-string">
208 :     <Notes>An [i]annotation[/i] contains supplementary information about a feature. Annotations
209 : parrello 1.8 are currently the only objects that may be inserted directly into the database. All other
210 : parrello 1.24 information is loaded from data exported by the SEED.</Notes>
211 : parrello 1.8 <Fields>
212 :     <Field name="time" type="date">
213 :     <Notes>Date and time of the annotation.</Notes>
214 :     </Field>
215 :     <Field name="annotation" type="text">
216 :     <Notes>Text of the annotation.</Notes>
217 :     </Field>
218 : parrello 1.1 </Fields>
219 : parrello 1.26 <Indexes>
220 :     <Index>
221 :     <Notes>This index allows the user to find recent annotations.</Notes>
222 :     <IndexFields>
223 :     <IndexField name="time" order="descending" />
224 :     </IndexFields>
225 :     </Index>
226 :     </Indexes>
227 : parrello 1.1 </Entity>
228 : parrello 1.15 <Entity name="Reaction" keyType="key-string">
229 :     <Notes>A [i]reaction[/i] is a chemical process catalyzed by a protein. The reaction ID
230 :     is generally a small number preceded by a letter.</Notes>
231 :     <Fields>
232 :     <Field name="url" type="string" relation="ReactionURL">
233 :     <Notes>HTML string containing a link to a web location that describes the
234 :     reaction. This field is optional.</Notes>
235 :     </Field>
236 :     <Field name="rev" type="boolean">
237 :     <Notes>TRUE if this reaction is reversible, else FALSE</Notes>
238 :     </Field>
239 :     </Fields>
240 :     </Entity>
241 :     <Entity name="Compound" keyType="name-string">
242 :     <Notes>A [i]compound[/i] is a chemical that participates in a reaction.
243 :     All compounds have a unique ID and may also have one or more names.</Notes>
244 :     <Fields>
245 :     <Field name="name-priority" type="int" relation="CompoundName">
246 :     <Notes>Priority of a compound name. The name with the loweset
247 :     priority is the main name of this compound.</Notes>
248 :     </Field>
249 :     <Field name="name" type="name-string" relation="CompoundName">
250 :     <Notes>Descriptive name for the compound. A compound may
251 :     have several names.</Notes>
252 :     </Field>
253 :     <Field name="cas-id" type="name-string" relation="CompoundCAS">
254 :     <Notes>Chemical Abstract Service ID for this compound (optional).</Notes>
255 :     </Field>
256 : parrello 1.19 <Field name="label" type="name-string">
257 :     <Notes>Name used in reaction display strings.
258 :     It is the same as the name possessing a priority of 1, but it is placed
259 :     here to speed up the query used to create the display strings.</Notes>
260 :     </Field>
261 : parrello 1.15 </Fields>
262 :     <Indexes>
263 :     <Index>
264 :     <Notes>This index allows the user to find the compound corresponding to
265 :     the specified name.</Notes>
266 :     <IndexFields>
267 :     <IndexField name="name" order="ascending" />
268 :     </IndexFields>
269 :     </Index>
270 :     <Index>
271 : parrello 1.17 <Notes>This index allows the user to find the compound corresponding to
272 :     the specified CAS ID.</Notes>
273 :     <IndexFields>
274 :     <IndexField name="cas-id" order="ascending" />
275 :     </IndexFields>
276 :     </Index>
277 :     <Index>
278 : parrello 1.15 <Notes>This index allows the user to access the compound names in
279 :     priority order.</Notes>
280 :     <IndexFields>
281 :     <IndexField name="id" order="ascending" />
282 :     <IndexField name="name-priority" order="ascending" />
283 :     </IndexFields>
284 :     </Index>
285 :     </Indexes>
286 :     </Entity>
287 : parrello 1.5 <Entity name="Subsystem" keyType="string">
288 : parrello 1.1 <Notes>A [i]subsystem[/i] is a collection of roles that work together in a cell. Identification of subsystems
289 :     is an important tool for recognizing parallel genetic features in different organisms.</Notes>
290 : parrello 1.15 <Fields>
291 :     <Field name="curator" type="string">
292 :     <Notes>Name of the person currently in charge of the subsystem.</Notes>
293 :     </Field>
294 :     <Field name="notes" type="text">
295 :     <Notes>Descriptive notes about the subsystem.</Notes>
296 :     </Field>
297 : parrello 1.28 <Field name="classification" type="string" relation="SubsystemClass">
298 :     <Notes>General classification data about the subsystem.</Notes>
299 :     </Field>
300 : parrello 1.15 </Fields>
301 :     </Entity>
302 :     <Entity name="RoleSubset" keyType="string">
303 :     <Notes>A [i]role subset[/i] is a named collection of roles in a particular subsystem. The
304 :     subset names are generally very short, non-unique strings. The ID of the parent
305 :     subsystem is prefixed to the subset ID in order to make it unique.</Notes>
306 :     </Entity>
307 :     <Entity name="GenomeSubset" keyType="string">
308 :     <Notes>A [i]genome subset[/i] is a named collection of genomes that participate
309 :     in a particular subsystem. The subset names are generally very short, non-unique
310 :     strings. The ID of the parent subsystem is prefixed to the subset ID in order
311 :     to make it unique.</Notes>
312 : parrello 1.1 </Entity>
313 : parrello 1.24 <Entity name="SSCell" keyType="hash-string">
314 : parrello 1.1 <Notes>Part of the process of locating and assigning features is creating a spreadsheet of
315 :     genomes and roles to which features are assigned. A [i]spreadsheet cell[/i] represents one
316 :     of the positions on the spreadsheet.</Notes>
317 :     </Entity>
318 :     <Entity name="SproutUser" keyType="name-string">
319 :     <Notes>A [i]user[/i] is a person who can make annotations and view data in the database. The
320 :     user object is keyed on the user's login name.</Notes>
321 :     <Fields>
322 : parrello 1.8 <Field name="description" type="string">
323 :     <Notes>Full name or description of this user.</Notes>
324 :     </Field>
325 : parrello 1.1 <Field name="access-code" type="key-string" relation="UserAccess">
326 : parrello 1.8 <Notes>Access code possessed by this
327 : parrello 1.1 user. A user can have many access codes; a genome is accessible to the user if its
328 :     access code matches any one of the user's access codes.</Notes>
329 : parrello 1.8 <DataGen testCount="2">RandParam('low', 'medium', 'high')</DataGen>
330 :     </Field>
331 : parrello 1.1 </Fields>
332 :     </Entity>
333 : parrello 1.8 <Entity name="Property" keyType="int">
334 :     <Notes>A [i]property[/i] is a type of assertion that could be made about the properties of
335 :     a particular feature. Each property instance is a key/value pair and can be associated
336 :     with many different features. Conversely, a feature can be associated with many key/value
337 :     pairs, even some that notionally contradict each other. For example, there can be evidence
338 :     that a feature is essential to the organism's survival and evidence that it is superfluous.</Notes>
339 :     <Fields>
340 :     <Field name="property-name" type="name-string">
341 :     <Notes>Name of this property.</Notes>
342 :     </Field>
343 :     <Field name="property-value" type="string">
344 :     <Notes>Value associated with this property. For each property
345 :     name, there must by a property record for all of its possible
346 :     values.</Notes>
347 :     </Field>
348 :     </Fields>
349 :     <Indexes>
350 :     <Index>
351 :     <Notes>This index enables the application to find all values for a specified property
352 :     name, or any given name/value pair.</Notes>
353 :     <IndexFields>
354 :     <IndexField name="property-name" order="ascending" />
355 :     <IndexField name="property-value" order="ascending" />
356 :     </IndexFields>
357 :     </Index>
358 :     </Indexes>
359 :     </Entity>
360 :     <Entity name="Diagram" keyType="name-string">
361 :     <Notes>A functional diagram describes the chemical reactions, often comprising a single
362 :     subsystem. A diagram is identified by a short name and contains a longer descriptive name.
363 :     The actual diagram shows which functional roles guide the reactions along with the inputs
364 :     and outputs; the database, however, only indicate which roles belong to a particular
365 :     map.</Notes>
366 :     <Fields>
367 :     <Field name="name" type="text">
368 :     <Notes>Descriptive name of this diagram.</Notes>
369 :     </Field>
370 :     </Fields>
371 :     </Entity>
372 :     <Entity name="ExternalAliasOrg" keyType="name-string">
373 :     <Notes>An external alias is a feature name for a functional assignment that is not a
374 :     FIG ID. Functional assignments for external aliases are kept in a separate section of
375 :     the database. This table contains a description of the relevant organism for an
376 :     external alias functional assignment.</Notes>
377 :     <Fields>
378 :     <Field name="org" type="text">
379 :     <Notes>Descriptive name of the target organism for this external alias.</Notes>
380 :     </Field>
381 :     </Fields>
382 :     </Entity>
383 :     <Entity name="ExternalAliasFunc" keyType="name-string">
384 :     <Notes>An external alias is a feature name for a functional assignment that is not a
385 :     FIG ID. Functional assignments for external aliases are kept in a separate section of
386 :     the database. This table contains the functional role for the external alias functional
387 :     assignment.</Notes>
388 :     <Fields>
389 :     <Field name="func" type="text">
390 :     <Notes>Functional role for this external alias.</Notes>
391 :     </Field>
392 :     </Fields>
393 :     </Entity>
394 : parrello 1.29 <Entity name="Coupling" keyType="id-string">
395 : parrello 1.6 <Notes>A coupling is a relationship between two features. The features are
396 :     physically close on the contig, and there is evidence that they generally
397 :     belong together. The key of this entity is formed by combining the coupled
398 : parrello 1.8 feature IDs with a space.</Notes>
399 : parrello 1.6 <Fields>
400 :     <Field name="score" type="int">
401 :     <Notes>A number based on the set of PCHs (pairs of close homologs). A PCH
402 :     indicates that two genes near each other on one genome are very similar to
403 :     genes near each other on another genome. The score only counts PCHs for which
404 :     the genomes are very different. (In other words, we have a pairing that persists
405 :     between different organisms.) A higher score implies a stronger meaning to the
406 :     clustering.</Notes>
407 :     </Field>
408 :     </Fields>
409 :     </Entity>
410 : parrello 1.30 <Entity name="PCH" keyType="counter">
411 : parrello 1.6 <Notes>A PCH (physically close homolog) connects a clustering (which is a
412 :     pair of physically close features on a contig) to a second pair of physically
413 :     close features that are similar to the first. Essentially, the PCH is a
414 :     relationship between two clusterings in which the first clustering's features
415 :     are similar to the second clustering's features. The simplest model for
416 :     this would be to simply relate clusterings to each other; however, not all
417 :     physically close pairs qualify as clusterings, so we relate a clustering to
418 : parrello 1.30 a pair of features. The key a unique ID number.</Notes>
419 : parrello 1.6 <Fields>
420 :     <Field name="used" type="boolean">
421 :     <Notes>TRUE if this PCH is used in scoring the attached clustering,
422 :     else FALSE. If a clustering has a PCH for a particular genome and many
423 :     similar genomes are present, then a PCH will probably exist for the
424 :     similar genomes as well. When this happens, only one of the PCHs will
425 :     be scored: the others are considered duplicates of the same evidence.</Notes>
426 :     </Field>
427 :     </Fields>
428 :     </Entity>
429 : parrello 1.31 <Entity name="Family" keyType="id-string">
430 :     <Notes>A family is a group of homologous PEGs believed to have the same function. Protein
431 :     families provide a mechanism for verifying the accuracy of functional assignments
432 :     and are also used in determining phylogenetic trees.</Notes>
433 :     <Fields>
434 : parrello 1.32 <Field name="function" type="text">
435 : parrello 1.31 <Notes>The functional assignment expected for all PEGs in this family.</Notes>
436 :     </Field>
437 : parrello 1.33 <Field name="size" type="int">
438 : parrello 1.31 <Notes>The number of proteins in this family. This may be larger than the
439 :     number of PEGs included in the family, since the family may also contain external
440 :     IDs.</Notes>
441 :     </Field>
442 :     </Fields>
443 :     </Entity>
444 : parrello 1.1 </Entities>
445 :     <Relationships>
446 : parrello 1.34 <Relationship name="IsFamilyForFeature" from="Family" to="Feature" arity="MM">
447 : parrello 1.31 <Notes>This relationship connects a protein family to all of its PEGs and connects
448 :     each PEG to all of its protein families.</Notes>
449 :     </Relationship>
450 : parrello 1.6 <Relationship name="ParticipatesInCoupling" from="Feature" to="Coupling" arity="MM">
451 :     <Notes>This relationship connects a feature to all the functional couplings
452 :     in which it participates. A functional coupling is a recognition of the fact
453 :     that the features are close to each other on a chromosome, and similar
454 :     features in other genomes also tend to be close.</Notes>
455 :     <Fields>
456 :     <Field name="pos" type="int">
457 :     <Notes>Ordinal position of the feature in the coupling. Currently,
458 :     this is either "1" or "2".</Notes>
459 :     </Field>
460 :     </Fields>
461 :     <ToIndex>
462 :     <Notes>This index enables the application to view the features of
463 :     a coupling in the proper order. The order influences the way the
464 :     PCHs are examined.</Notes>
465 :     <IndexFields>
466 :     <IndexField name="pos" order="ascending" />
467 :     </IndexFields>
468 :     </ToIndex>
469 :     </Relationship>
470 : parrello 1.27 <Relationship name="IsSynonymGroupFor" from="SynonymGroup" to="Feature" arity="1M">
471 :     <Notes>This relation connects a synonym group to the features that make it
472 :     up.</Notes>
473 :     </Relationship>
474 : parrello 1.24 <Relationship name="HasFeature" from="Genome" to="Feature" arity="1M">
475 :     <Notes>This relationship connects a genome to all of its features. This
476 :     relationship is redundant in a sense, because the genome ID is part
477 :     of the feature ID; however, it makes the creation of certain queries more
478 :     convenient because you can drag in filtering information for a feature's
479 :     genome.</Notes>
480 :     <Fields>
481 :     <Field name="type" type="key-string">
482 :     <Notes>Feature type (eg. peg, rna)</Notes>
483 :     </Field>
484 :     </Fields>
485 : parrello 1.38 <FromIndex>
486 : parrello 1.24 <Notes>This index enables the application to view the features of a
487 :     Genome sorted by type.</Notes>
488 :     <IndexFields>
489 :     <IndexField name="type" order="ascending" />
490 :     </IndexFields>
491 : parrello 1.38 </FromIndex>
492 : parrello 1.24 </Relationship>
493 : parrello 1.6 <Relationship name="IsEvidencedBy" from="Coupling" to="PCH" arity="1M">
494 :     <Notes>This relationship connects a functional coupling to the physically
495 :     close homologs (PCHs) which affirm that the coupling is meaningful.</Notes>
496 :     </Relationship>
497 :     <Relationship name="UsesAsEvidence" from="PCH" to="Feature" arity="MM">
498 :     <Notes>This relationship connects a PCH to the features that represent its
499 :     evidence. Each PCH is connected to a parent coupling that relates two features
500 :     on a specific genome. The PCH's evidence that the parent coupling is functional
501 :     is the existence of two physically close features on a different genome that
502 :     correspond to the features in the coupling. Those features are found on the
503 :     far side of this relationship.</Notes>
504 :     <Fields>
505 :     <Field name="pos" type="int">
506 :     <Notes>Ordinal position of the feature in the coupling that corresponds
507 :     to our target feature. There is a one-to-one correspondence between the
508 :     features connected to the PCH by this relationship and the features
509 :     connected to the PCH's parent coupling. The ordinal position is used
510 :     to decode that relationship. Currently, this field is either "1" or
511 :     "2".</Notes>
512 :     </Field>
513 :     </Fields>
514 :     <FromIndex>
515 :     <Notes>This index enables the application to view the features of
516 :     a PCH in the proper order.</Notes>
517 :     <IndexFields>
518 :     <IndexField name="pos" order="ascending" />
519 :     </IndexFields>
520 :     </FromIndex>
521 :     </Relationship>
522 : parrello 1.1 <Relationship name="HasContig" from="Genome" to="Contig" arity="1M">
523 :     <Notes>This relationship connects a genome to the contigs that contain the actual genetic
524 :     information.</Notes>
525 :     </Relationship>
526 :     <Relationship name="ComesFrom" from="Genome" to="Source" arity="MM">
527 :     <Notes>This relationship connects a genome to the sources that mapped it. A genome can
528 :     come from a single source or from a cooperation among multiple sources.</Notes>
529 :     </Relationship>
530 :     <Relationship name="IsMadeUpOf" from="Contig" to="Sequence" arity="1M">
531 :     <Notes>A contig is stored in the database as an ordered set of sequences. By splitting the
532 :     contig into sequences, we get a performance boost from only needing to keep small portions
533 :     of a contig in memory at any one time. This relationship connects the contig to its
534 :     constituent sequences.</Notes>
535 :     <Fields>
536 :     <Field name="len" type="int">
537 : parrello 1.15 <Notes>Length of the sequence.</Notes>
538 :     </Field>
539 : parrello 1.1 <Field name="start-position" type="int">
540 : parrello 1.15 <Notes>Index (1-based) of the point in the contig where this
541 :     sequence starts.</Notes>
542 :     </Field>
543 : parrello 1.1 </Fields>
544 :     <FromIndex>
545 :     <Notes>This index enables the application to find all of the sequences in
546 : parrello 1.8 a contig in order, and makes it easier to find a particular residue section.</Notes>
547 : parrello 1.1 <IndexFields>
548 :     <IndexField name="start-position" order="ascending" />
549 :     <IndexField name="len" order="ascending" />
550 :     </IndexFields>
551 :     </FromIndex>
552 :     </Relationship>
553 :     <Relationship name="IsTargetOfAnnotation" from="Feature" to="Annotation" arity="1M">
554 :     <Notes>This relationship connects a feature to its annotations.</Notes>
555 :     </Relationship>
556 :     <Relationship name="MadeAnnotation" from="SproutUser" to="Annotation" arity="1M">
557 :     <Notes>This relationship connects an annotation to the user who made it.</Notes>
558 :     </Relationship>
559 :     <Relationship name="ParticipatesIn" from="Genome" to="Subsystem" arity="MM">
560 :     <Notes>This relationship connects subsystems to the genomes that use
561 :     it. If the subsystem has been curated for the genome, then the subsystem's roles will also be
562 :     connected to the genome features through the [b]SSCell[/b] object.</Notes>
563 : parrello 1.15 <Fields>
564 :     <Field name="variant-code" type="key-string">
565 : parrello 1.20 <Notes>Code indicating the subsystem variant to which this
566 : parrello 1.15 genome belongs. Each subsystem can have multiple variants. A variant
567 : parrello 1.20 code of [b]-1[/b] indicates that the genome does not have a functional
568 :     variant of the subsystem. A variant code of [b]0[/b] indicates that
569 :     the genome's participation is considered iffy.</Notes>
570 : parrello 1.15 </Field>
571 :     </Fields>
572 :     <ToIndex>
573 :     <Notes>This index enables the application to find all of the genomes using
574 :     a subsystem in order by variant code, which is how we wish to display them
575 :     in the spreadsheets.</Notes>
576 :     <IndexFields>
577 :     <IndexField name="variant-code" order="ascending" />
578 :     </IndexFields>
579 :     </ToIndex>
580 : parrello 1.1 </Relationship>
581 :     <Relationship name="OccursInSubsystem" from="Role" to="Subsystem" arity="MM">
582 :     <Notes>This relationship connects roles to the subsystems that implement them. </Notes>
583 : parrello 1.15 <Fields>
584 :     <Field name="column-number" type="int">
585 :     <Notes>Column number for this role in the specified subsystem's
586 :     spreadsheet.</Notes>
587 :     </Field>
588 :     </Fields>
589 :     <ToIndex>
590 :     <Notes>This index enables the application to see the subsystem roles
591 :     in column order. The ordering of the roles is usually significant,
592 :     so it is important to preserve it.</Notes>
593 :     <IndexFields>
594 :     <IndexField name="column-number" order="ascending" />
595 :     </IndexFields>
596 :     </ToIndex>
597 : parrello 1.1 </Relationship>
598 :     <Relationship name="IsGenomeOf" from="Genome" to="SSCell" arity="1M">
599 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
600 :     genome for the spreadsheet column.</Notes>
601 :     </Relationship>
602 :     <Relationship name="IsRoleOf" from="Role" to="SSCell" arity="1M">
603 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
604 :     role for the spreadsheet row.</Notes>
605 :     </Relationship>
606 :     <Relationship name="ContainsFeature" from="SSCell" to="Feature" arity="MM">
607 :     <Notes>This relationship connects a subsystem's spreadsheet cell to the
608 :     features assigned to it.</Notes>
609 : parrello 1.15 <Fields>
610 :     <Field name="cluster-number" type="int">
611 :     <Notes>ID of this feature's cluster. Clusters represent families of
612 :     related proteins participating in a subsystem.</Notes>
613 :     </Field>
614 :     </Fields>
615 :     </Relationship>
616 :     <Relationship name="IsAComponentOf" from="Compound" to="Reaction" arity="MM">
617 :     <Notes>This relationship connects a reaction to the compounds that participate
618 :     in it.</Notes>
619 :     <Fields>
620 :     <Field name="product" type="boolean">
621 :     <Notes>TRUE if the compound is a product of the reaction, FALSE if
622 :     it is a substrate. When a reaction is written on paper in
623 :     chemical notation, the substrates are left of the arrow and the
624 :     products are to the right. Sorting on this field will cause
625 :     the substrates to appear first, followed by the products. If the
626 :     reaction is reversible, then the notion of substrates and products
627 :     is not at intuitive; however, a value here of FALSE still puts the
628 :     compound left of the arrow and a value of TRUE still puts it to the
629 :     right.</Notes>
630 :     </Field>
631 : parrello 1.19 <Field name="stoichiometry" type="key-string">
632 : parrello 1.15 <Notes>Number of molecules of the compound that participate in a
633 :     single instance of the reaction. For example, if a reaction
634 : parrello 1.19 produces two water molecules, the stoichiometry of water for the
635 : parrello 1.15 reaction would be two. When a reaction is written on paper in
636 : parrello 1.19 chemical notation, the stoichiometry is the number next to the
637 : parrello 1.15 chemical formula of the compound.</Notes>
638 :     </Field>
639 :     <Field name="main" type="boolean">
640 :     <Notes>TRUE if this compound is one of the main participants in
641 :     the reaction, else FALSE. It is permissible for none of the
642 :     compounds in the reaction to be considered main, in which
643 :     case this value would be FALSE for all of the relevant
644 :     compounds.</Notes>
645 :     </Field>
646 :     <Field name="loc" type="key-string">
647 :     <Notes>An optional character string that indicates the relative
648 :     position of this compound in the reaction's chemical formula. The
649 :     location affects the way the compounds present as we cross the
650 :     relationship from the reaction side. The product/substrate flag
651 :     comes first, then the value of this field, then the main flag.
652 :     The default value is an empty string; however, the empty string
653 :     sorts first, so if this field is used, it should probably be
654 :     used for every compound in the reaction.</Notes>
655 :     </Field>
656 : parrello 1.19 <Field name="discriminator" type="int">
657 :     <Notes>A unique ID for this record. The discriminator does not
658 :     provide any useful data, but it prevents identical records from
659 :     being collapsed by the SELECT DISTINCT command used by ERDB to
660 :     retrieve data.</Notes>
661 :     </Field>
662 : parrello 1.15 </Fields>
663 :     <ToIndex>
664 :     <Notes>This index presents the compounds in the reaction in the
665 :     order they should be displayed when writing it in chemical notation.
666 :     All the substrates appear before all the products, and within that
667 :     ordering, the main compounds appear first.</Notes>
668 : parrello 1.19 <IndexFields>
669 :     <IndexField name="product" order="ascending" />
670 :     <IndexField name="loc" order="ascending" />
671 :     <IndexField name="main" order="descending" />
672 :     </IndexFields>
673 : parrello 1.15 </ToIndex>
674 : parrello 1.1 </Relationship>
675 :     <Relationship name="IsLocatedIn" from="Feature" to="Contig" arity="MM">
676 :     <Notes>This relationship connects a feature to the contig segments that work together
677 :     to effect it. The segments are numbered sequentially starting from 1. The database is
678 :     required to place an upper limit on the length of each segment. If a segment is longer
679 :     than the maximum, it can be broken into smaller bits.
680 :     [p]The upper limit enables applications to locate all features that contain a specific
681 :     residue. For example, if the upper limit is 100 and we are looking for a feature that
682 :     contains residue 234 of contig [b]ABC[/b], we can look for features with a begin point
683 :     between 135 and 333. The results can then be filtered by direction and length of the
684 :     segment.</Notes>
685 :     <Fields>
686 :     <Field name="locN" type="int">
687 : parrello 1.8 <Notes>Sequence number of this segment.</Notes>
688 :     </Field>
689 : parrello 1.1 <Field name="beg" type="int">
690 : parrello 1.8 <Notes>Index (1-based) of the first residue in the contig that
691 :     belongs to the segment.</Notes>
692 :     </Field>
693 : parrello 1.1 <Field name="len" type="int">
694 : parrello 1.8 <Notes>Number of residues in the segment. A length of 0 identifies
695 :     a specific point between residues. This is the point before the residue if the direction
696 :     is forward and the point after the residue if the direction is backward.</Notes>
697 :     </Field>
698 : parrello 1.1 <Field name="dir" type="char">
699 : parrello 1.8 <Notes>Direction of the segment: [b]+[/b] if it is forward and
700 :     [b]-[/b] if it is backward.</Notes>
701 :     </Field>
702 : parrello 1.1 </Fields>
703 :     <FromIndex Unique="false">
704 :     <Notes>This index allows the application to find all the segments of a feature in
705 : parrello 1.8 the proper order.</Notes>
706 : parrello 1.1 <IndexFields>
707 :     <IndexField name="locN" order="ascending" />
708 :     </IndexFields>
709 :     </FromIndex>
710 :     <ToIndex>
711 :     <Notes>This index is the one used by applications to find all the feature
712 :     segments that contain a specific residue.</Notes>
713 :     <IndexFields>
714 :     <IndexField name="beg" order="ascending" />
715 :     </IndexFields>
716 :     </ToIndex>
717 :     </Relationship>
718 : parrello 1.8 <Relationship name="HasProperty" from="Feature" to="Property" arity="MM">
719 :     <Notes>This relationship connects a feature to its known property values.
720 :     The relationship contains text data that indicates the paper or organization
721 :     that discovered evidence that the feature possesses the property. So, for
722 :     example, if two papers presented evidence that a feature is essential,
723 :     there would be an instance of this relationship for both.</Notes>
724 :     <Fields>
725 :     <Field name="evidence" type="text">
726 :     <Notes>URL or citation of the paper or
727 :     institution that reported evidence of the relevant feature possessing
728 :     the specified property value.</Notes>
729 :     </Field>
730 :     </Fields>
731 :     </Relationship>
732 :     <Relationship name="RoleOccursIn" from="Role" to="Diagram" arity="MM">
733 :     <Notes>This relationship connects a role to the diagrams on which it
734 :     appears. A role frequently identifies an enzyme, and can appear in many
735 :     diagrams. A diagram generally contains many different roles.</Notes>
736 :     </Relationship>
737 :     <Relationship name="HasSSCell" from="Subsystem" to="SSCell" arity="1M">
738 :     <Notes>This relationship connects a subsystem to the spreadsheet cells
739 :     used to analyze and display it. The cells themselves can be thought of
740 :     as a grid with Roles on one axis and Genomes on the other. The
741 :     various features of the subsystem are then assigned to the cells.</Notes>
742 :     </Relationship>
743 :     <Relationship name="IsTrustedBy" from="SproutUser" to="SproutUser" arity="MM">
744 :     <Notes>This relationship identifies the users trusted by each
745 :     particular user. When viewing functional assignments, the
746 :     assignment displayed is the most recent one by a user trusted
747 :     by the current user. The current user implicitly trusts himself.
748 :     If no trusted users are specified in the database, the user
749 :     also implicitly trusts the user [b]FIG[/b].</Notes>
750 :     </Relationship>
751 : parrello 1.15 <Relationship name="ConsistsOfRoles" from="RoleSubset" to="Role" arity="MM">
752 :     <Notes>This relationship connects a role subset to the roles that it covers.
753 :     A subset is, essentially, a named group of roles belonging to a specific
754 :     subsystem, and this relationship effects that. Note that will a role
755 :     may belong to many subsystems, a subset belongs to only one subsystem,
756 :     and all roles in the subset must have that subsystem in common.</Notes>
757 :     </Relationship>
758 :     <Relationship name="ConsistsOfGenomes" from="GenomeSubset" to="Genome" arity="MM">
759 :     <Notes>This relationship connects a subset to the genomes that it covers.
760 :     A subset is, essentially, a named group of genomes participating in a specific
761 :     subsystem, and this relationship effects that. Note that while a genome
762 :     may belong to many subsystems, a subset belongs to only one subsystem,
763 :     and all genomes in the subset must have that subsystem in common.</Notes>
764 :     </Relationship>
765 :     <Relationship name="HasRoleSubset" from="Subsystem" to="RoleSubset" arity="1M">
766 :     <Notes>This relationship connects a subsystem to its constituent
767 :     role subsets. Note that some roles in a subsystem may not belong to a
768 :     subset, so the relationship between roles and subsystems cannot be
769 :     derived from the relationships going through the subset.</Notes>
770 :     </Relationship>
771 :     <Relationship name="HasGenomeSubset" from="Subsystem" to="GenomeSubset" arity="1M">
772 :     <Notes>This relationship connects a subsystem to its constituent
773 :     genome subsets. Note that some genomes in a subsystem may not belong to a
774 :     subset, so the relationship between genomes and subsystems cannot be
775 :     derived from the relationships going through the subset.</Notes>
776 :     </Relationship>
777 :     <Relationship name="Catalyzes" from="Role" to="Reaction" arity="MM">
778 :     <Notes>This relationship connects a role to the reactions it catalyzes.
779 :     The purpose of a role is to create proteins that trigger certain
780 :     chemical reactions. A single reaction can be triggered by many roles,
781 :     and a role can trigger many reactions.</Notes>
782 :     </Relationship>
783 : parrello 1.39 <Relationship name="HasRoleInSubsystem" from="Feature" to="Subsystem" arity="MM">
784 :     <Notes>This relationship connects a feature to the subsystems in which it
785 :     participates. This is technically redundant information, but it is used
786 :     so often that it deserves its own table.</Notes>
787 : parrello 1.40 <Fields>
788 :     <Field name="genome" type="name-string">
789 :     <Notes>ID of the genome containing the feature</Notes>
790 :     </Field>
791 :     <Field name="type" type="key-string">
792 :     <Notes>Feature type (eg. peg, rna)</Notes>
793 :     </Field>
794 :     </Fields>
795 :     <ToIndex>
796 :     <Notes>This index enables the application to view the features of a
797 :     subsystem sorted by genome and feature type.</Notes>
798 :     <IndexFields>
799 :     <IndexField name="genome" order="ascending" />
800 :     <IndexField name="type" order="ascending" />
801 :     </IndexFields>
802 :     </ToIndex>
803 : parrello 1.39 </Relationship>
804 : parrello 1.1 </Relationships>
805 :     </Database>

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3