Parent Directory
| 
Revision Log
Revision 1.56 - (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 : | parrello | 1.55 | <Notes>The Sprout database contains the genetic data for all complete organisms in the SeedEnvironment. |
| 5 : | parrello | 1.51 | The data that is not in Sprout-- attributes, similarities, couplings-- is stored on external |
| 6 : | servers available to the Sprout software. The Sprout database is reloaded approximately once | ||
| 7 : | per month. There is significant redundancy in the Sprout database because it has been | ||
| 8 : | optimized for searching. In particular, the Feature table contains an extra copy of the | ||
| 9 : | feature's functional role and a list of possible search terms.</Notes> | ||
| 10 : | parrello | 1.1 | <Entities> |
| 11 : | <Entity name="Genome" keyType="name-string"> | ||
| 12 : | parrello | 1.55 | <DisplayInfo theme="nmpdr" col="3" row="1" /> |
| 13 : | <Notes>A Genome contains the sequence data for a particular individual organism.</Notes> | ||
| 14 : | parrello | 1.1 | <Fields> |
| 15 : | <Field name="genus" type="name-string"> | ||
| 16 : | <Notes>Genus of the relevant organism.</Notes> | ||
| 17 : | </Field> | ||
| 18 : | <Field name="species" type="name-string"> | ||
| 19 : | parrello | 1.8 | <Notes>Species of the relevant organism.</Notes> |
| 20 : | </Field> | ||
| 21 : | parrello | 1.1 | <Field name="unique-characterization" type="medium-string"> |
| 22 : | parrello | 1.8 | <Notes>The unique characterization identifies the particular organism instance from which the |
| 23 : | genome is taken. It is possible to have in the database more than one genome for a | ||
| 24 : | parrello | 1.1 | particular species, and every individual organism has variations in its DNA.</Notes> |
| 25 : | </Field> | ||
| 26 : | parrello | 1.48 | <Field name="version" type="name-string"> |
| 27 : | <Notes>version string for this genome, generally consisting of the genome ID followed | ||
| 28 : | by a period and a string of digits.</Notes> | ||
| 29 : | </Field> | ||
| 30 : | parrello | 1.1 | <Field name="access-code" type="key-string"> |
| 31 : | parrello | 1.52 | <Notes>The access code field is deprecated. Its function has been replaced by |
| 32 : | the account management system developed for the [[RapidAnnotationServer]].</Notes> | ||
| 33 : | parrello | 1.8 | </Field> |
| 34 : | parrello | 1.15 | <Field name="complete" type="boolean"> |
| 35 : | <Notes>TRUE if the genome is complete, else FALSE</Notes> | ||
| 36 : | </Field> | ||
| 37 : | parrello | 1.48 | <Field name="dna-size" type="counter"> |
| 38 : | <Notes>number of base pairs in the genome</Notes> | ||
| 39 : | </Field> | ||
| 40 : | parrello | 1.8 | <Field name="taxonomy" type="text"> |
| 41 : | parrello | 1.52 | <Notes>The taxonomy string contains the full [[Wikipedia:taxonomy]] of the organism, while individual elements |
| 42 : | parrello | 1.8 | separated by semi-colons (and optional white space), starting with the domain and ending with |
| 43 : | the disambiguated genus and species (which is the organism's scientific name plus an | ||
| 44 : | identifying string).</Notes> | ||
| 45 : | </Field> | ||
| 46 : | parrello | 1.37 | <Field name="primary-group" type="name-string"> |
| 47 : | <Notes>The primary NMPDR group for this organism. There is always exactly one NMPDR group | ||
| 48 : | parrello | 1.52 | per organism (either based on the organism name or the default value =Supporting=). In general, |
| 49 : | more data is kept on organisms in NMPDR groups than on supporting organisms.</Notes> | ||
| 50 : | </Field> | ||
| 51 : | <Field name="contigs" type="int"> | ||
| 52 : | <Notes>Number of contigs for this organism.</Notes> | ||
| 53 : | </Field> | ||
| 54 : | <Field name="pegs" type="int"> | ||
| 55 : | <Notes>Number of [[protein encoding genes]] for this organism</Notes> | ||
| 56 : | </Field> | ||
| 57 : | <Field name="rnas" type="int"> | ||
| 58 : | <Notes>Number of RNA features found for this organism.</Notes> | ||
| 59 : | parrello | 1.37 | </Field> |
| 60 : | parrello | 1.1 | </Fields> |
| 61 : | <Indexes> | ||
| 62 : | parrello | 1.45 | <Index> |
| 63 : | parrello | 1.1 | <Notes>This index allows the applications to find all genomes associated with |
| 64 : | a specific access code, so that a complete list of the genomes users can view | ||
| 65 : | may be generated.</Notes> | ||
| 66 : | <IndexFields> | ||
| 67 : | <IndexField name="access-code" order="ascending" /> | ||
| 68 : | <IndexField name="genus" order="ascending" /> | ||
| 69 : | <IndexField name="species" order="ascending" /> | ||
| 70 : | <IndexField name="unique-characterization" order="ascending" /> | ||
| 71 : | </IndexFields> | ||
| 72 : | </Index> | ||
| 73 : | parrello | 1.45 | <Index> |
| 74 : | parrello | 1.37 | <Notes>This index allows the applications to find all genomes associated with |
| 75 : | a specific primary (NMPDR) group.</Notes> | ||
| 76 : | <IndexFields> | ||
| 77 : | <IndexField name="primary-group" order="ascending" /> | ||
| 78 : | <IndexField name="genus" order="ascending" /> | ||
| 79 : | <IndexField name="species" order="ascending" /> | ||
| 80 : | <IndexField name="unique-characterization" order="ascending" /> | ||
| 81 : | </IndexFields> | ||
| 82 : | </Index> | ||
| 83 : | parrello | 1.45 | <Index> |
| 84 : | parrello | 1.1 | <Notes>This index allows the applications to find all genomes for a particular |
| 85 : | species.</Notes> | ||
| 86 : | <IndexFields> | ||
| 87 : | <IndexField name="genus" order="ascending" /> | ||
| 88 : | <IndexField name="species" order="ascending" /> | ||
| 89 : | <IndexField name="unique-characterization" order="ascending" /> | ||
| 90 : | </IndexFields> | ||
| 91 : | </Index> | ||
| 92 : | </Indexes> | ||
| 93 : | </Entity> | ||
| 94 : | parrello | 1.50 | <Entity name="CDD" keyType="key-string"> |
| 95 : | <Notes>A CDD is a protein domain designator. It represents the shape of a molecular unit | ||
| 96 : | parrello | 1.52 | on a feature's protein. The ID is six-digit string assigned by the public |
| 97 : | parrello | 1.55 | Conserved Domain Database. A CDD |
| 98 : | parrello | 1.52 | can occur on multiple features and a feature generally has multiple CDDs.</Notes> |
| 99 : | parrello | 1.50 | </Entity> |
| 100 : | parrello | 1.1 | <Entity name="Source" keyType="medium-string"> |
| 101 : | parrello | 1.55 | <Notes>A source describes a place from which genome data was taken. This can be an organization |
| 102 : | parrello | 1.1 | or a paper citation.</Notes> |
| 103 : | <Fields> | ||
| 104 : | <Field name="URL" type="string" relation="SourceURL"> | ||
| 105 : | parrello | 1.8 | <Notes>URL the paper cited or of the organization's web site. This field optional.</Notes> |
| 106 : | </Field> | ||
| 107 : | parrello | 1.1 | <Field name="description" type="text"> |
| 108 : | parrello | 1.52 | <Notes>Description of the source. The description can be a street address or a citation.</Notes> |
| 109 : | parrello | 1.8 | </Field> |
| 110 : | parrello | 1.1 | </Fields> |
| 111 : | </Entity> | ||
| 112 : | <Entity name="Contig" keyType="name-string"> | ||
| 113 : | parrello | 1.55 | <DisplayInfo theme="nmpdr" col="1" row="1" /> |
| 114 : | <Notes>A contig is a contiguous run of residues. The contig's ID consists of the | ||
| 115 : | parrello | 1.1 | genome ID followed by a name that identifies which contig this is for the parent genome. As |
| 116 : | is the case with all keys in this database, the individual components are separated by a | ||
| 117 : | parrello | 1.52 | period. A contig can contain over a million residues. For performance reasons, therefore, |
| 118 : | parrello | 1.55 | the contig is split into multiple pieces called sequences. The sequences |
| 119 : | parrello | 1.1 | contain the characters that represent the residues as well as data on the quality of |
| 120 : | the residue identification.</Notes> | ||
| 121 : | </Entity> | ||
| 122 : | <Entity name="Sequence" keyType="name-string"> | ||
| 123 : | parrello | 1.55 | <Notes>A sequence is a continuous piece of a contig. Contigs are split into |
| 124 : | parrello | 1.1 | sequences so that we don't have to have the entire contig in memory when we are |
| 125 : | manipulating it. The key of the sequence is the contig ID followed by the index of | ||
| 126 : | the begin point.</Notes> | ||
| 127 : | <Fields> | ||
| 128 : | <Field name="sequence" type="text"> | ||
| 129 : | parrello | 1.52 | <Notes>String consisting of the residues (base pairs). Each residue is described by a single |
| 130 : | parrello | 1.8 | character in the string.</Notes> |
| 131 : | </Field> | ||
| 132 : | parrello | 1.1 | <Field name="quality-vector" type="text"> |
| 133 : | parrello | 1.9 | <Notes>String describing the quality data for each base pair. Individual values will |
| 134 : | parrello | 1.8 | be separated by periods. The value represents negative exponent of the probability |
| 135 : | of error. Thus, for example, a quality of 30 indicates the probability of error is | ||
| 136 : | parrello | 1.52 | 10^-30. A higher quality number indicates a better chance of a correct match. It is |
| 137 : | possible that the quality data is not known for a sequence. If that is the case, the | ||
| 138 : | quality vector will contain the string =unknown=.</Notes> | ||
| 139 : | parrello | 1.8 | </Field> |
| 140 : | parrello | 1.1 | </Fields> |
| 141 : | </Entity> | ||
| 142 : | parrello | 1.54 | <Entity name="Keyword" keyType="name-string"> |
| 143 : | parrello | 1.55 | <Notes>A keyword is a word that can be used to search the feature table. This entity |
| 144 : | contains the keyword's stem, its phonetic form, and the number of features that | ||
| 145 : | can be found by searching for the word.</Notes> | ||
| 146 : | <Fields> | ||
| 147 : | <Field name="stem" type="name-string"> | ||
| 148 : | <Notes>The stem of a keyword is a normalized form that is independent of parts | ||
| 149 : | of speech. The actual keywords stored in the database search index are stems.</Notes> | ||
| 150 : | </Field> | ||
| 151 : | parrello | 1.54 | <Field name="count" type="counter"> |
| 152 : | <Notes>Number of features that can be found by searching for the specified | ||
| 153 : | keyword.</Notes> | ||
| 154 : | </Field> | ||
| 155 : | parrello | 1.55 | <Field name="phonex" type="name-string"> |
| 156 : | <Notes>A _phonex_ is a string that identifies the phonetic characteristics of the | ||
| 157 : | word stem. This can be used to find alternative spellings if an matching word is not | ||
| 158 : | present.</Notes> | ||
| 159 : | </Field> | ||
| 160 : | parrello | 1.54 | </Fields> |
| 161 : | parrello | 1.55 | <Indexes> |
| 162 : | <Index> | ||
| 163 : | <Notes>This index allows the user to find words by stem.</Notes> | ||
| 164 : | <IndexFields> | ||
| 165 : | <IndexField name="stem" order="ascending" /> | ||
| 166 : | </IndexFields> | ||
| 167 : | </Index> | ||
| 168 : | <Index> | ||
| 169 : | <Notes>This index allows the user to find words by phonex.</Notes> | ||
| 170 : | <IndexFields> | ||
| 171 : | <IndexField name="phonex" order="ascending" /> | ||
| 172 : | <IndexField name="count" order="descending" /> | ||
| 173 : | </IndexFields> | ||
| 174 : | </Index> | ||
| 175 : | </Indexes> | ||
| 176 : | </Entity> | ||
| 177 : | <Entity name="ExternalDatabase" keyType="key-string"> | ||
| 178 : | <Notes>An external database identifies a biological database surveyed by PIR International | ||
| 179 : | as part of an effort to determine which features are essentially identical between bioinformatics | ||
| 180 : | organizations. Each feature in the database will have zero or more corresponding IDs that are | ||
| 181 : | captured from the PIR data. Each corresponding ID is represented in a relationship between an external | ||
| 182 : | database and the feature itself.</Notes> | ||
| 183 : | parrello | 1.54 | </Entity> |
| 184 : | parrello | 1.25 | <Entity name="Feature" keyType="id-string"> |
| 185 : | parrello | 1.55 | <DisplayInfo theme="nmpdr" col="3" row="3" /> |
| 186 : | <Notes>A feature (sometimes also called a "gene" is a part of a genome that is of special interest. Features | ||
| 187 : | parrello | 1.1 | may be spread across multiple contigs of a genome, but never across more than |
| 188 : | one genome. Features can be assigned to roles via spreadsheet cells, | ||
| 189 : | parrello | 1.55 | and are the targets of annotation. Each feature in the database has a unique FigId.</Notes> |
| 190 : | parrello | 1.1 | <Fields> |
| 191 : | parrello | 1.50 | <Field name="feature-type" type="id-string"> |
| 192 : | parrello | 1.52 | <Notes>Code indicating the type of this feature. Among the codes currently |
| 193 : | supported are =peg= for a [[protein encoding gene]], =bs= for a | ||
| 194 : | binding site, =opr= for an operon, and so forth.</Notes> | ||
| 195 : | parrello | 1.8 | </Field> |
| 196 : | parrello | 1.1 | <Field name="translation" type="text" relation="FeatureTranslation"> |
| 197 : | parrello | 1.52 | <Notes>_(optional)_ A translation of this feature's residues into character |
| 198 : | parrello | 1.8 | codes, formed by concatenating the pieces of the feature together. For a |
| 199 : | parrello | 1.52 | [[protein encoding gene]], the translation contains protein characters. For other types |
| 200 : | it contains DNA characters.</Notes> | ||
| 201 : | parrello | 1.8 | </Field> |
| 202 : | parrello | 1.1 | <Field name="upstream-sequence" type="text" relation="FeatureUpstream"> |
| 203 : | parrello | 1.52 | <Notes>Upstream sequence for the feature. This includes residues preceding the feature as |
| 204 : | well as some of the feature's initial residues.</Notes> | ||
| 205 : | parrello | 1.8 | </Field> |
| 206 : | parrello | 1.42 | <Field name="assignment" type="text"> |
| 207 : | <Notes>Default functional assignment for this feature.</Notes> | ||
| 208 : | </Field> | ||
| 209 : | parrello | 1.1 | <Field name="active" type="boolean"> |
| 210 : | parrello | 1.52 | <Notes>(This field is deprecated.) TRUE if this feature is still considered valid, |
| 211 : | FALSE if it has been logically deleted.</Notes> | ||
| 212 : | parrello | 1.8 | </Field> |
| 213 : | parrello | 1.48 | <Field name="assignment-maker" type="name-string"> |
| 214 : | <Notes>name of the user who made the functional assignment</Notes> | ||
| 215 : | </Field> | ||
| 216 : | <Field name="assignment-quality" type="char"> | ||
| 217 : | <Notes>quality of the functional assignment, usually a space, but may be W (indicating weak) or X | ||
| 218 : | (indicating experimental)</Notes> | ||
| 219 : | </Field> | ||
| 220 : | parrello | 1.41 | <Field name="keywords" type="text" searchable="1"> |
| 221 : | <Notes>This is a list of search keywords for the feature. It includes the | ||
| 222 : | functional assignment, subsystem roles, and special properties.</Notes> | ||
| 223 : | parrello | 1.36 | </Field> |
| 224 : | parrello | 1.8 | <Field name="link" type="text" relation="FeatureLink"> |
| 225 : | parrello | 1.52 | <Notes>Web hyperlink for this feature. A feature can have no hyperlinks or it can have many. The |
| 226 : | parrello | 1.8 | links are to other websites that have useful about the gene that the feature represents, and |
| 227 : | parrello | 1.52 | are coded as raw HTML, using <a href="_link_">_text_</a> notation.</Notes> |
| 228 : | parrello | 1.8 | </Field> |
| 229 : | parrello | 1.41 | <Field name="conservation" type="float" relation="FeatureConservation"> |
| 230 : | parrello | 1.52 | <Notes>_(optional)_ A number between 0 and 1 that indicates the degree to which this feature's DNA is |
| 231 : | parrello | 1.41 | conserved in related genomes. A value of 1 indicates perfect conservation. A value less |
| 232 : | parrello | 1.50 | than 1 is a reflection of the degree to which gap characters interfere in the alignment |
| 233 : | parrello | 1.41 | between the feature and its close relatives.</Notes> |
| 234 : | </Field> | ||
| 235 : | parrello | 1.45 | <Field name="essential" type="text" relation="FeatureEssential" special="property_search"> |
| 236 : | <Notes>A value indicating the essentiality of the feature, coded as HTML. In most | ||
| 237 : | cases, this will be a word describing whether the essentiality is confirmed (essential) | ||
| 238 : | or potential (potential-essential), hyperlinked to the document from which the | ||
| 239 : | essentiality was curated. If a feature is not essential, this field will have no | ||
| 240 : | values; otherwise, it may have multiple values.</Notes> | ||
| 241 : | </Field> | ||
| 242 : | <Field name="virulent" type="text" relation="FeatureVirulent" special="property_search"> | ||
| 243 : | <Notes>A value indicating the virulence of the feature, coded as HTML. In most | ||
| 244 : | cases, this will be a phrase or SA number hyperlinked to the document from which | ||
| 245 : | the virulence information was curated. If the feature is not virulent, this field | ||
| 246 : | will have no values; otherwise, it may have multiple values.</Notes> | ||
| 247 : | </Field> | ||
| 248 : | <Field name="iedb" type="text" relation="FeatureIEDB" special="property_search"> | ||
| 249 : | <Notes>A value indicating whether or not the feature can be found in the | ||
| 250 : | Immune Epitope Database. If the feature has not been matched to that database, | ||
| 251 : | this field will have no values. Otherwise, it will have an epitope name and/or | ||
| 252 : | sequence, hyperlinked to the database.</Notes> | ||
| 253 : | </Field> | ||
| 254 : | parrello | 1.50 | <Field name="location-string" type="text"> |
| 255 : | <Notes>Location of the feature, expressed as a comma-delimited list of Sprout location | ||
| 256 : | strings. This gives us a fast mechanism for extracting the feature location. Otherwise, | ||
| 257 : | parrello | 1.52 | we have to painstakingly paste together the [[#IsLocatedIn]] records, which are themselves |
| 258 : | designed to help look for features in a particular region rather than to find the location | ||
| 259 : | of a feature.</Notes> | ||
| 260 : | parrello | 1.50 | </Field> |
| 261 : | parrello | 1.55 | <Field name="signal-peptide" type="name-string"> |
| 262 : | <Notes>The signal peptide location for this feature. This is expressed as start and end | ||
| 263 : | numbers with a hyphen for the relevant amino acids. So, "1-22" would indicate a signal | ||
| 264 : | peptide at the beginning of the feature's protein and extending through 22 amino acid | ||
| 265 : | positions. An empty string means no signal peptide is present.</Notes> | ||
| 266 : | </Field> | ||
| 267 : | <Field name="transmembrane-map" type="text"> | ||
| 268 : | <Notes>A map indicating which sections of a protein will be embedded in a membrane. | ||
| 269 : | This is expressed as a comma-separated list of as start and end numbers with hyphens | ||
| 270 : | for the relevant amino acids. So, "10-12, 40-60" would indicate that there are two | ||
| 271 : | sections of the protein that become embedded in a membrane: the 10th through 12th | ||
| 272 : | amino acids, and the 40th through the 60th. An empty string means no | ||
| 273 : | transmembrane regions are known.</Notes> | ||
| 274 : | </Field> | ||
| 275 : | <Field name="similar-to-human" type="boolean"> | ||
| 276 : | <Notes>TRUE if this feature generates a protein that is similar to one found in humans, | ||
| 277 : | else FALSE</Notes> | ||
| 278 : | </Field> | ||
| 279 : | <Field name="isoelectric-point" type="float"> | ||
| 280 : | <Notes>pH in the surrounding medium at which the charge on a protein is neutral. | ||
| 281 : | If the pH of the medium is lower than this value, the protein will have a net | ||
| 282 : | positive charge. If the pH of the medium is higher, then the protein will have a | ||
| 283 : | net negative charge.</Notes> | ||
| 284 : | </Field> | ||
| 285 : | <Field name="molecular-weight" type="float"> | ||
| 286 : | <Notes>Molecular weight of this feature's protein, in daltons. A weight of 0 | ||
| 287 : | indicates that no protein is created.</Notes> | ||
| 288 : | </Field> | ||
| 289 : | <Field name="sequence-length" type="counter"> | ||
| 290 : | <Notes>Number of base pairs in this feature.</Notes> | ||
| 291 : | </Field> | ||
| 292 : | <Field name="locked" type="boolean"> | ||
| 293 : | <Notes>TRUE if a feature's assignment is locked. A locked feature's functional | ||
| 294 : | role cannot be changed by automated programs.</Notes> | ||
| 295 : | </Field> | ||
| 296 : | <Field name="in-genbank" type="boolean"> | ||
| 297 : | <Notes>TRUE if a feature can be found in GenBank, else FALSE</Notes> | ||
| 298 : | </Field> | ||
| 299 : | parrello | 1.1 | </Fields> |
| 300 : | </Entity> | ||
| 301 : | parrello | 1.50 | <Entity name="FeatureAlias" keyType="medium-string"> |
| 302 : | <Notes>Alternative names for features. A feature can have many aliases. In general, | ||
| 303 : | parrello | 1.52 | each alias corresponds to only one feature, but there are many exceptions to this rule.</Notes> |
| 304 : | </Entity> | ||
| 305 : | <Entity name="SproutUser" keyType="name-string"> | ||
| 306 : | parrello | 1.55 | <Notes>A user is a person who can make annotations and view data in the database. The |
| 307 : | parrello | 1.52 | user object is keyed on the user's login name.</Notes> |
| 308 : | <Fields> | ||
| 309 : | <Field name="description" type="string"> | ||
| 310 : | <Notes>Full name or description of this user.</Notes> | ||
| 311 : | </Field> | ||
| 312 : | <Field name="access-code" type="key-string" relation="UserAccess"> | ||
| 313 : | <Notes>This field is deprecated.</Notes> | ||
| 314 : | </Field> | ||
| 315 : | </Fields> | ||
| 316 : | parrello | 1.50 | </Entity> |
| 317 : | parrello | 1.27 | <Entity name="SynonymGroup" keyType="id-string"> |
| 318 : | parrello | 1.55 | <Notes>A synonym group represents a group of features. Features that represent substantially |
| 319 : | parrello | 1.52 | identical proteins or DNA sequences are mapped to the same synonym group, and this information is |
| 320 : | used to expand similarities.</Notes> | ||
| 321 : | parrello | 1.27 | </Entity> |
| 322 : | parrello | 1.1 | <Entity name="Role" keyType="string"> |
| 323 : | parrello | 1.55 | <DisplayInfo theme="web" col="7" row="3" /> |
| 324 : | <Notes>A role describes a biological function that may be fulfilled by a feature. | ||
| 325 : | parrello | 1.1 | One of the main goals of the database is to record the roles of the various features.</Notes> |
| 326 : | parrello | 1.50 | </Entity> |
| 327 : | <Entity name="RoleEC" keyType="string"> | ||
| 328 : | <Notes>EC code for a role.</Notes> | ||
| 329 : | parrello | 1.1 | </Entity> |
| 330 : | <Entity name="Annotation" keyType="name-string"> | ||
| 331 : | parrello | 1.55 | <DisplayInfo theme="seed" col="1" row="3" /> |
| 332 : | <Notes>An annotation contains supplementary information about a feature. The most | ||
| 333 : | parrello | 1.52 | important type of annotation is the assignment of a [[functional role]]; however, |
| 334 : | other types of annotations are also possible.</Notes> | ||
| 335 : | parrello | 1.8 | <Fields> |
| 336 : | <Field name="time" type="date"> | ||
| 337 : | <Notes>Date and time of the annotation.</Notes> | ||
| 338 : | </Field> | ||
| 339 : | <Field name="annotation" type="text"> | ||
| 340 : | <Notes>Text of the annotation.</Notes> | ||
| 341 : | </Field> | ||
| 342 : | parrello | 1.1 | </Fields> |
| 343 : | parrello | 1.26 | <Indexes> |
| 344 : | <Index> | ||
| 345 : | <Notes>This index allows the user to find recent annotations.</Notes> | ||
| 346 : | <IndexFields> | ||
| 347 : | <IndexField name="time" order="descending" /> | ||
| 348 : | </IndexFields> | ||
| 349 : | </Index> | ||
| 350 : | </Indexes> | ||
| 351 : | parrello | 1.1 | </Entity> |
| 352 : | parrello | 1.15 | <Entity name="Reaction" keyType="key-string"> |
| 353 : | parrello | 1.55 | <DisplayInfo theme="web" col="7" row="5" /> |
| 354 : | <Notes>A reaction is a chemical process catalyzed by a protein. The reaction ID | ||
| 355 : | parrello | 1.15 | is generally a small number preceded by a letter.</Notes> |
| 356 : | <Fields> | ||
| 357 : | <Field name="url" type="string" relation="ReactionURL"> | ||
| 358 : | <Notes>HTML string containing a link to a web location that describes the | ||
| 359 : | reaction. This field is optional.</Notes> | ||
| 360 : | </Field> | ||
| 361 : | <Field name="rev" type="boolean"> | ||
| 362 : | <Notes>TRUE if this reaction is reversible, else FALSE</Notes> | ||
| 363 : | </Field> | ||
| 364 : | </Fields> | ||
| 365 : | </Entity> | ||
| 366 : | <Entity name="Compound" keyType="name-string"> | ||
| 367 : | parrello | 1.55 | <DisplayInfo theme="web" col="7" row="7" /> |
| 368 : | <Notes>A compound is a chemical that participates in a reaction. | ||
| 369 : | parrello | 1.15 | All compounds have a unique ID and may also have one or more names.</Notes> |
| 370 : | <Fields> | ||
| 371 : | parrello | 1.50 | <Field name="label" type="string"> |
| 372 : | parrello | 1.52 | <Notes>Name used in reaction display strings. This is the same as the name |
| 373 : | possessing a priority of 1, but it is placed here to speed up the query | ||
| 374 : | used to create the display strings.</Notes> | ||
| 375 : | parrello | 1.19 | </Field> |
| 376 : | parrello | 1.15 | </Fields> |
| 377 : | parrello | 1.50 | </Entity> |
| 378 : | <Entity name="CompoundName" keyType="string"> | ||
| 379 : | parrello | 1.55 | <Notes>A compound name is a common name for the chemical represented by a |
| 380 : | parrello | 1.50 | compound.</Notes> |
| 381 : | </Entity> | ||
| 382 : | <Entity name="CompoundCAS" keyType="name-string"> | ||
| 383 : | parrello | 1.55 | <Notes>This entity represents the Chemical Abstract Service ID for a |
| 384 : | parrello | 1.52 | compound. Each Compound has at most one CAS ID.</Notes> |
| 385 : | parrello | 1.15 | </Entity> |
| 386 : | parrello | 1.5 | <Entity name="Subsystem" keyType="string"> |
| 387 : | parrello | 1.55 | <DisplayInfo theme="seed" col="5" row="1" /> |
| 388 : | <Notes>A subsystem is a collection of roles that work together in a cell. Identification of subsystems | ||
| 389 : | is an important tool for recognizing parallel genetic features in different organisms.</Notes> | ||
| 390 : | <Fields> | ||
| 391 : | <Field name="version" type="int"> | ||
| 392 : | <Notes>Version number for the subsystem. This value is incremented each time the subsystem | ||
| 393 : | is backed up.</Notes> | ||
| 394 : | </Field> | ||
| 395 : | parrello | 1.15 | <Field name="curator" type="string"> |
| 396 : | <Notes>Name of the person currently in charge of the subsystem.</Notes> | ||
| 397 : | </Field> | ||
| 398 : | <Field name="notes" type="text"> | ||
| 399 : | <Notes>Descriptive notes about the subsystem.</Notes> | ||
| 400 : | </Field> | ||
| 401 : | parrello | 1.52 | <Field name="description" type="text"> |
| 402 : | parrello | 1.55 | <Notes>Description of the subsystem's function in the cell.</Notes> |
| 403 : | parrello | 1.52 | </Field> |
| 404 : | parrello | 1.28 | <Field name="classification" type="string" relation="SubsystemClass"> |
| 405 : | parrello | 1.44 | <Notes>Classification string, colon-delimited. This string organizes the |
| 406 : | parrello | 1.42 | subsystems into a hierarchy.</Notes> |
| 407 : | parrello | 1.28 | </Field> |
| 408 : | parrello | 1.55 | <Field name="hope-curation-notes" type="text" relation="SubsystemHopeNotes"> |
| 409 : | <Notes>Text description of how the scenarios were curated.</Notes> | ||
| 410 : | </Field> | ||
| 411 : | parrello | 1.15 | </Fields> |
| 412 : | </Entity> | ||
| 413 : | <Entity name="RoleSubset" keyType="string"> | ||
| 414 : | parrello | 1.55 | <Notes>A role subset is a named collection of roles in a particular subsystem. The |
| 415 : | parrello | 1.15 | subset names are generally very short, non-unique strings. The ID of the parent |
| 416 : | subsystem is prefixed to the subset ID in order to make it unique.</Notes> | ||
| 417 : | </Entity> | ||
| 418 : | <Entity name="GenomeSubset" keyType="string"> | ||
| 419 : | parrello | 1.55 | <Notes>A genome subset is a named collection of genomes that participate |
| 420 : | parrello | 1.15 | in a particular subsystem. The subset names are generally very short, non-unique |
| 421 : | strings. The ID of the parent subsystem is prefixed to the subset ID in order | ||
| 422 : | to make it unique.</Notes> | ||
| 423 : | parrello | 1.1 | </Entity> |
| 424 : | parrello | 1.24 | <Entity name="SSCell" keyType="hash-string"> |
| 425 : | parrello | 1.55 | <DisplayInfo theme="seed" col="5" row="3" /> |
| 426 : | <Notes>Part of the process of subsystem annotation of features | ||
| 427 : | is creating a spreadsheet of genomes and roles to which features are assigned. | ||
| 428 : | A spreadsheet cell represents one of the positions on the spreadsheet.</Notes> | ||
| 429 : | parrello | 1.1 | </Entity> |
| 430 : | parrello | 1.8 | <Entity name="Property" keyType="int"> |
| 431 : | parrello | 1.55 | <Notes>A property is a type of assertion that could be made about the properties of |
| 432 : | parrello | 1.8 | a particular feature. Each property instance is a key/value pair and can be associated |
| 433 : | with many different features. Conversely, a feature can be associated with many key/value | ||
| 434 : | pairs, even some that notionally contradict each other. For example, there can be evidence | ||
| 435 : | that a feature is essential to the organism's survival and evidence that it is superfluous.</Notes> | ||
| 436 : | <Fields> | ||
| 437 : | <Field name="property-name" type="name-string"> | ||
| 438 : | <Notes>Name of this property.</Notes> | ||
| 439 : | </Field> | ||
| 440 : | <Field name="property-value" type="string"> | ||
| 441 : | <Notes>Value associated with this property. For each property | ||
| 442 : | name, there must by a property record for all of its possible | ||
| 443 : | values.</Notes> | ||
| 444 : | </Field> | ||
| 445 : | </Fields> | ||
| 446 : | <Indexes> | ||
| 447 : | <Index> | ||
| 448 : | <Notes>This index enables the application to find all values for a specified property | ||
| 449 : | name, or any given name/value pair.</Notes> | ||
| 450 : | <IndexFields> | ||
| 451 : | <IndexField name="property-name" order="ascending" /> | ||
| 452 : | <IndexField name="property-value" order="ascending" /> | ||
| 453 : | </IndexFields> | ||
| 454 : | </Index> | ||
| 455 : | </Indexes> | ||
| 456 : | </Entity> | ||
| 457 : | <Entity name="Diagram" keyType="name-string"> | ||
| 458 : | parrello | 1.55 | <DisplayInfo theme="web" col="7" row="1" /> |
| 459 : | <Notes>A functional diagram describes a network of chemical reactions, often comprising a single | ||
| 460 : | parrello | 1.8 | subsystem. A diagram is identified by a short name and contains a longer descriptive name. |
| 461 : | The actual diagram shows which functional roles guide the reactions along with the inputs | ||
| 462 : | parrello | 1.52 | and outputs; the database, however, only indicates which roles belong to a particular |
| 463 : | diagram's map.</Notes> | ||
| 464 : | parrello | 1.8 | <Fields> |
| 465 : | <Field name="name" type="text"> | ||
| 466 : | <Notes>Descriptive name of this diagram.</Notes> | ||
| 467 : | </Field> | ||
| 468 : | </Fields> | ||
| 469 : | </Entity> | ||
| 470 : | parrello | 1.31 | <Entity name="Family" keyType="id-string"> |
| 471 : | parrello | 1.55 | <DisplayInfo theme="seed" col="5" row="5" /> |
| 472 : | <Notes>A family (also called a FigFam) is a group of homologous features believed to have | ||
| 473 : | the same function. Families provide a mechanism for verifying the accuracy of functional | ||
| 474 : | assignments and are also used in Rapid Annotation and in determining phylogenetic trees.</Notes> | ||
| 475 : | parrello | 1.31 | <Fields> |
| 476 : | parrello | 1.32 | <Field name="function" type="text"> |
| 477 : | parrello | 1.31 | <Notes>The functional assignment expected for all PEGs in this family.</Notes> |
| 478 : | </Field> | ||
| 479 : | parrello | 1.33 | <Field name="size" type="int"> |
| 480 : | parrello | 1.31 | <Notes>The number of proteins in this family. This may be larger than the |
| 481 : | number of PEGs included in the family, since the family may also contain external | ||
| 482 : | IDs.</Notes> | ||
| 483 : | </Field> | ||
| 484 : | </Fields> | ||
| 485 : | </Entity> | ||
| 486 : | parrello | 1.49 | <Entity name="PDB" keyType="id-string"> |
| 487 : | parrello | 1.55 | <DisplayInfo theme="web" col="3" row="5" /> |
| 488 : | parrello | 1.52 | <Notes>A PDB is a protein data bank entry containing information that can be used |
| 489 : | to determine the shape of the protein and the energies required to dock with it. | ||
| 490 : | parrello | 1.55 | The ID is the four-character name used on the PDB web site.</Notes> |
| 491 : | parrello | 1.49 | <Fields> |
| 492 : | <Field name="docking-count" type="int"> | ||
| 493 : | <Notes>The number of ligands that have been docked against this PDB.</Notes> | ||
| 494 : | </Field> | ||
| 495 : | </Fields> | ||
| 496 : | <Indexes> | ||
| 497 : | <Index> | ||
| 498 : | <IndexFields> | ||
| 499 : | <IndexField name="docking-count" order="descending" /> | ||
| 500 : | <IndexField name="id" order="ascending" /> | ||
| 501 : | </IndexFields> | ||
| 502 : | </Index> | ||
| 503 : | </Indexes> | ||
| 504 : | </Entity> | ||
| 505 : | <Entity name="Ligand" keyType="id-string"> | ||
| 506 : | parrello | 1.55 | <DisplayInfo theme="web" col="3" row="7" /> |
| 507 : | parrello | 1.49 | <Notes>A Ligand is a chemical of interest in computing docking energies against a PDB. |
| 508 : | parrello | 1.52 | The ID of the ligand is an 8-digit ID number in the [[http://zinc.docking.org ZINC database]].</Notes> |
| 509 : | parrello | 1.49 | <Fields> |
| 510 : | <Field name="name" type="long-string"> | ||
| 511 : | <Notes>Chemical name of this ligand.</Notes> | ||
| 512 : | </Field> | ||
| 513 : | </Fields> | ||
| 514 : | </Entity> | ||
| 515 : | parrello | 1.55 | <Entity name="CellLocation" keyType="key-string"> |
| 516 : | <Notes>A section of the cell in which a protein might be found. This includes the cell wall or | ||
| 517 : | membrane, outside the cell, inside the cell, and so forth.</Notes> | ||
| 518 : | </Entity> | ||
| 519 : | <Entity name="Scenario" keyType="string"> | ||
| 520 : | <Notes>A scenario used to verify the validity of subsystem assignments. Each | ||
| 521 : | scenario converrts input compounds to output compounds using reactions. | ||
| 522 : | The scenario may use all of the reactions controlled by a subsystem or only | ||
| 523 : | some, and may also incorporate additional reactions.</Notes> | ||
| 524 : | </Entity> | ||
| 525 : | parrello | 1.1 | </Entities> |
| 526 : | <Relationships> | ||
| 527 : | parrello | 1.55 | <Relationship name="Catalyzes" from="Role" to="Reaction" arity="MM"> |
| 528 : | <DisplayInfo theme="web" /> | ||
| 529 : | <Notes>This relationship connects a role to the reactions it catalyzes. | ||
| 530 : | The purpose of a role is to create proteins that trigger certain | ||
| 531 : | chemical reactions. A single reaction can be triggered by many roles, | ||
| 532 : | and a role can trigger many reactions.</Notes> | ||
| 533 : | </Relationship> | ||
| 534 : | <Relationship name="ExcludesReaction" from="Scenario" to="Reaction" arity="MM"> | ||
| 535 : | <Notes>This relationship connects a scenario to reactions of the parent | ||
| 536 : | subsystem that do not participate in it.</Notes> | ||
| 537 : | </Relationship> | ||
| 538 : | <Relationship name="IncludesReaction" from="Scenario" to="Reaction" arity="MM"> | ||
| 539 : | <Notes>This relationship connects a scenario to reactions that participate | ||
| 540 : | in it but are not part of the parent subsystem.</Notes> | ||
| 541 : | </Relationship> | ||
| 542 : | <Relationship name="HasScenario" from="Subsystem" to="Scenario" arity="MM"> | ||
| 543 : | <Notes>This relationship connects a role to the scenarios used to | ||
| 544 : | validate it.</Notes> | ||
| 545 : | </Relationship> | ||
| 546 : | <Relationship name="IsInputFor" from="Compound" to="Scenario" arity="MM"> | ||
| 547 : | <Notes>This relationship connects a scenario to its input compounds.</Notes> | ||
| 548 : | </Relationship> | ||
| 549 : | <Relationship name="IsOutputOf" from="Compound" to="Scenario" arity="MM"> | ||
| 550 : | <Notes>This relationship connects a scenario to its output compounds</Notes> | ||
| 551 : | <Fields> | ||
| 552 : | <Field name="auxiliary" type="boolean"> | ||
| 553 : | <Notes>TRUE if this is an auxiliary output compound, FALSE if it is a | ||
| 554 : | main output compound.</Notes> | ||
| 555 : | </Field> | ||
| 556 : | </Fields> | ||
| 557 : | </Relationship> | ||
| 558 : | <Relationship name="IsOnDiagram" from="Scenario" to="Diagram" arity="MM"> | ||
| 559 : | <Notes>This relationship connects a scenario to related diagrams.</Notes> | ||
| 560 : | </Relationship> | ||
| 561 : | <Relationship name="IsPossiblePlaceFor" from="CellLocation" to="Feature" arity="MM"> | ||
| 562 : | <Notes>This relationship connects a feature with the various places in a cell that the feature | ||
| 563 : | might be found. The confidence factor is included as intersection data.</Notes> | ||
| 564 : | <Fields> | ||
| 565 : | <Field name="confidence" type="float"> | ||
| 566 : | <Notes>Confidence that the protein will be found in this location, expressed as a | ||
| 567 : | value from 0 to 10.</Notes> | ||
| 568 : | </Field> | ||
| 569 : | </Fields> | ||
| 570 : | </Relationship> | ||
| 571 : | parrello | 1.50 | <Relationship name="IsPresentOnProteinOf" from="CDD" to="Feature" arity="MM"> |
| 572 : | <Notes>This relationship connects a feature to its CDD protein domains. The | ||
| 573 : | match score is included as intersection data.</Notes> | ||
| 574 : | <Fields> | ||
| 575 : | <Field name="score" type="float"> | ||
| 576 : | <Notes>This is the match score between the feature and the CDD. A | ||
| 577 : | lower score is a better match.</Notes> | ||
| 578 : | </Field> | ||
| 579 : | </Fields> | ||
| 580 : | <FromIndex> | ||
| 581 : | <IndexFields> | ||
| 582 : | <IndexField name="score" order="ascending" /> | ||
| 583 : | </IndexFields> | ||
| 584 : | </FromIndex> | ||
| 585 : | </Relationship> | ||
| 586 : | <Relationship name="IsIdentifiedByCAS" from="Compound" to="CompoundCAS" arity="MM"> | ||
| 587 : | <Notes>Relates a compound's CAS ID to the compound itself. Every CAS ID is | ||
| 588 : | associated with a compound, and some are associated with two compounds, but not | ||
| 589 : | all compounds have CAS IDs.</Notes> | ||
| 590 : | </Relationship> | ||
| 591 : | <Relationship name="IsIdentifiedByEC" from="Role" to="RoleEC" arity="MM"> | ||
| 592 : | <Notes>Relates a role to its EC number. Every EC number is associated with a | ||
| 593 : | role, but not all roles have EC numbers.</Notes> | ||
| 594 : | </Relationship> | ||
| 595 : | <Relationship name="IsAliasOf" from="FeatureAlias" to="Feature" arity="MM"> | ||
| 596 : | <Notes>Connects an alias to the feature it represents. Every alias connects | ||
| 597 : | to at least 1 feature, and a feature connects to many aliases.</Notes> | ||
| 598 : | </Relationship> | ||
| 599 : | <Relationship name="HasCompoundName" from="Compound" to="CompoundName" arity="MM"> | ||
| 600 : | <Notes>Connects a compound to its names. A compound generally has several | ||
| 601 : | names</Notes> | ||
| 602 : | <Fields> | ||
| 603 : | <Field name="priority" type="int"> | ||
| 604 : | <Notes>Priority of this name, with 1 being the highest priority, 2 | ||
| 605 : | the next highest, and so forth.</Notes> | ||
| 606 : | </Field> | ||
| 607 : | </Fields> | ||
| 608 : | <FromIndex> | ||
| 609 : | <Notes>This index enables the application to view the names of a compound | ||
| 610 : | in priority order.</Notes> | ||
| 611 : | <IndexFields> | ||
| 612 : | <IndexField name="priority" order="ascending" /> | ||
| 613 : | </IndexFields> | ||
| 614 : | </FromIndex> | ||
| 615 : | </Relationship> | ||
| 616 : | parrello | 1.49 | <Relationship name="IsProteinForFeature" from="PDB" to="Feature" arity="MM"> |
| 617 : | parrello | 1.55 | <DisplayInfo caption="Is Protein\nFor Feature" theme="web" /> |
| 618 : | parrello | 1.49 | <Notes>Relates a PDB to features that produce highly similar proteins.</Notes> |
| 619 : | <Fields> | ||
| 620 : | <Field name="score" type="float"> | ||
| 621 : | <Notes>Similarity score for the comparison between the feature and | ||
| 622 : | the PDB protein. A lower score indicates a better match.</Notes> | ||
| 623 : | </Field> | ||
| 624 : | <Field name="start-location" type="int"> | ||
| 625 : | <Notes>Starting location within the feature of the matching region.</Notes> | ||
| 626 : | </Field> | ||
| 627 : | <Field name="end-location" type="int"> | ||
| 628 : | <Notes>Ending location within the feature of the matching region.</Notes> | ||
| 629 : | </Field> | ||
| 630 : | </Fields> | ||
| 631 : | <ToIndex> | ||
| 632 : | <Notes>This index enables the application to view the PDBs of a | ||
| 633 : | feature in order from the closest match to the furthest.</Notes> | ||
| 634 : | <IndexFields> | ||
| 635 : | <IndexField name="score" order="ascending" /> | ||
| 636 : | </IndexFields> | ||
| 637 : | </ToIndex> | ||
| 638 : | <FromIndex> | ||
| 639 : | <Notes>This index enables the application to view the features of | ||
| 640 : | a PDB in order from the closest match to the furthest.</Notes> | ||
| 641 : | <IndexFields> | ||
| 642 : | <IndexField name="score" order="ascending" /> | ||
| 643 : | </IndexFields> | ||
| 644 : | </FromIndex> | ||
| 645 : | </Relationship> | ||
| 646 : | <Relationship name="DocksWith" from="PDB" to="Ligand" arity="MM"> | ||
| 647 : | parrello | 1.55 | <DisplayInfo caption="Docks With" theme="web" /> |
| 648 : | <Notes>Indicates that a docking result exists between a PDB and a ligand. The | ||
| 649 : | parrello | 1.49 | docking result describes the energy required for the ligand to dock with |
| 650 : | the protein described by the PDB. A lower energy indicates the ligand has a | ||
| 651 : | good chance of disabling the protein. At the current time, only the best | ||
| 652 : | docking results are kept.</Notes> | ||
| 653 : | <Fields> | ||
| 654 : | <Field name="reason" type="id-string"> | ||
| 655 : | <Notes>Indication of the reason for determining the docking result. | ||
| 656 : | parrello | 1.52 | A value of =Random= indicates the docking was attempted as a part |
| 657 : | parrello | 1.49 | of a random survey used to determine the docking characteristics of the |
| 658 : | parrello | 1.52 | PDB. A value of =Rich= indicates the docking was attempted because |
| 659 : | parrello | 1.49 | a low-energy docking result was predicted for the ligand with respect |
| 660 : | to the PDB.</Notes> | ||
| 661 : | </Field> | ||
| 662 : | <Field name="tool" type="id-string"> | ||
| 663 : | <Notes>Name of the tool used to produce the docking result.</Notes> | ||
| 664 : | </Field> | ||
| 665 : | <Field name="total-energy" type="float"> | ||
| 666 : | <Notes>Total energy required for the ligand to dock with the PDB | ||
| 667 : | protein, in kcal/mol. A negative value means energy is released.</Notes> | ||
| 668 : | </Field> | ||
| 669 : | <Field name="vanderwalls-energy" type="float"> | ||
| 670 : | <Notes>Docking energy in kcal/mol that results from the geometric fit | ||
| 671 : | (Van der Waals force) between the PDB and the ligand.</Notes> | ||
| 672 : | </Field> | ||
| 673 : | <Field name="electrostatic-energy" type="float"> | ||
| 674 : | <Notes>Docking energy in kcal/mol that results from the movement of | ||
| 675 : | parrello | 1.52 | electrons (electrostatic force) between the PDB and the ligand.</Notes> |
| 676 : | parrello | 1.49 | </Field> |
| 677 : | </Fields> | ||
| 678 : | <FromIndex> | ||
| 679 : | <Notes>This index enables the application to view a PDB's docking results from | ||
| 680 : | the lowest energy (best docking) to highest energy (worst docking).</Notes> | ||
| 681 : | <IndexFields> | ||
| 682 : | <IndexField name="total-energy" order="ascending" /> | ||
| 683 : | </IndexFields> | ||
| 684 : | </FromIndex> | ||
| 685 : | <ToIndex> | ||
| 686 : | <Notes>This index enables the application to view a ligand's docking results from | ||
| 687 : | parrello | 1.52 | the lowest energy (best docking) to highest energy (worst docking).</Notes> |
| 688 : | parrello | 1.49 | </ToIndex> |
| 689 : | </Relationship> | ||
| 690 : | parrello | 1.55 | <Relationship name="IsAlsoFoundIn" from="Feature" to="ExternalDatabase" arity="MM"> |
| 691 : | <Notes>This relationship connects a feature to external databases that contain | ||
| 692 : | essentially identical features. The name used in the external database is stored | ||
| 693 : | in the relationship as intersection data.</Notes> | ||
| 694 : | <Fields> | ||
| 695 : | <Field name="alias" type="name-string"> | ||
| 696 : | <Notes>ID of the feature in the specified external database.</Notes> | ||
| 697 : | </Field> | ||
| 698 : | </Fields> | ||
| 699 : | <Indexes> | ||
| 700 : | <Index> | ||
| 701 : | <Notes>This index allows direct access to features by external ID.</Notes> | ||
| 702 : | <IndexFields> | ||
| 703 : | <IndexField name="alias" order="ascending" /> | ||
| 704 : | </IndexFields> | ||
| 705 : | </Index> | ||
| 706 : | </Indexes> | ||
| 707 : | </Relationship> | ||
| 708 : | parrello | 1.34 | <Relationship name="IsFamilyForFeature" from="Family" to="Feature" arity="MM"> |
| 709 : | parrello | 1.55 | <DisplayInfo caption="Belongs To" theme="seed" /> |
| 710 : | parrello | 1.31 | <Notes>This relationship connects a protein family to all of its PEGs and connects |
| 711 : | each PEG to all of its protein families.</Notes> | ||
| 712 : | </Relationship> | ||
| 713 : | parrello | 1.50 | <Relationship name="IsSynonymGroupFor" from="SynonymGroup" to="Feature" arity="MM"> |
| 714 : | parrello | 1.27 | <Notes>This relation connects a synonym group to the features that make it |
| 715 : | up.</Notes> | ||
| 716 : | </Relationship> | ||
| 717 : | parrello | 1.24 | <Relationship name="HasFeature" from="Genome" to="Feature" arity="1M"> |
| 718 : | parrello | 1.55 | <DisplayInfo theme="nmpdr" caption="Has\nFeature" /> |
| 719 : | parrello | 1.24 | <Notes>This relationship connects a genome to all of its features. This |
| 720 : | relationship is redundant in a sense, because the genome ID is part | ||
| 721 : | of the feature ID; however, it makes the creation of certain queries more | ||
| 722 : | convenient because you can drag in filtering information for a feature's | ||
| 723 : | genome.</Notes> | ||
| 724 : | <Fields> | ||
| 725 : | <Field name="type" type="key-string"> | ||
| 726 : | <Notes>Feature type (eg. peg, rna)</Notes> | ||
| 727 : | </Field> | ||
| 728 : | </Fields> | ||
| 729 : | parrello | 1.38 | <FromIndex> |
| 730 : | parrello | 1.24 | <Notes>This index enables the application to view the features of a |
| 731 : | Genome sorted by type.</Notes> | ||
| 732 : | <IndexFields> | ||
| 733 : | <IndexField name="type" order="ascending" /> | ||
| 734 : | </IndexFields> | ||
| 735 : | parrello | 1.38 | </FromIndex> |
| 736 : | parrello | 1.24 | </Relationship> |
| 737 : | parrello | 1.1 | <Relationship name="HasContig" from="Genome" to="Contig" arity="1M"> |
| 738 : | parrello | 1.55 | <DisplayInfo caption="Is Part Of" theme="nmpdr" /> |
| 739 : | parrello | 1.1 | <Notes>This relationship connects a genome to the contigs that contain the actual genetic |
| 740 : | information.</Notes> | ||
| 741 : | </Relationship> | ||
| 742 : | <Relationship name="ComesFrom" from="Genome" to="Source" arity="MM"> | ||
| 743 : | <Notes>This relationship connects a genome to the sources that mapped it. A genome can | ||
| 744 : | come from a single source or from a cooperation among multiple sources.</Notes> | ||
| 745 : | </Relationship> | ||
| 746 : | <Relationship name="IsMadeUpOf" from="Contig" to="Sequence" arity="1M"> | ||
| 747 : | <Notes>A contig is stored in the database as an ordered set of sequences. By splitting the | ||
| 748 : | contig into sequences, we get a performance boost from only needing to keep small portions | ||
| 749 : | of a contig in memory at any one time. This relationship connects the contig to its | ||
| 750 : | constituent sequences.</Notes> | ||
| 751 : | <Fields> | ||
| 752 : | <Field name="len" type="int"> | ||
| 753 : | parrello | 1.15 | <Notes>Length of the sequence.</Notes> |
| 754 : | </Field> | ||
| 755 : | parrello | 1.1 | <Field name="start-position" type="int"> |
| 756 : | parrello | 1.15 | <Notes>Index (1-based) of the point in the contig where this |
| 757 : | sequence starts.</Notes> | ||
| 758 : | </Field> | ||
| 759 : | parrello | 1.1 | </Fields> |
| 760 : | <FromIndex> | ||
| 761 : | <Notes>This index enables the application to find all of the sequences in | ||
| 762 : | parrello | 1.8 | a contig in order, and makes it easier to find a particular residue section.</Notes> |
| 763 : | parrello | 1.1 | <IndexFields> |
| 764 : | <IndexField name="start-position" order="ascending" /> | ||
| 765 : | <IndexField name="len" order="ascending" /> | ||
| 766 : | </IndexFields> | ||
| 767 : | </FromIndex> | ||
| 768 : | </Relationship> | ||
| 769 : | <Relationship name="IsTargetOfAnnotation" from="Feature" to="Annotation" arity="1M"> | ||
| 770 : | parrello | 1.55 | <DisplayInfo caption="Targets" theme="seed" /> |
| 771 : | parrello | 1.1 | <Notes>This relationship connects a feature to its annotations.</Notes> |
| 772 : | </Relationship> | ||
| 773 : | <Relationship name="MadeAnnotation" from="SproutUser" to="Annotation" arity="1M"> | ||
| 774 : | <Notes>This relationship connects an annotation to the user who made it.</Notes> | ||
| 775 : | </Relationship> | ||
| 776 : | <Relationship name="ParticipatesIn" from="Genome" to="Subsystem" arity="MM"> | ||
| 777 : | parrello | 1.55 | <DisplayInfo caption="\nParticipates\nIn" theme="seed" /> |
| 778 : | parrello | 1.1 | <Notes>This relationship connects subsystems to the genomes that use |
| 779 : | it. If the subsystem has been curated for the genome, then the subsystem's roles will also be | ||
| 780 : | parrello | 1.52 | connected to the genome features through the *SSCell* object.</Notes> |
| 781 : | parrello | 1.15 | <Fields> |
| 782 : | <Field name="variant-code" type="key-string"> | ||
| 783 : | parrello | 1.20 | <Notes>Code indicating the subsystem variant to which this |
| 784 : | parrello | 1.15 | genome belongs. Each subsystem can have multiple variants. A variant |
| 785 : | parrello | 1.52 | code of =-1= indicates that the genome does not have a functional |
| 786 : | variant of the subsystem. A variant code of =0= indicates that | ||
| 787 : | parrello | 1.20 | the genome's participation is considered iffy.</Notes> |
| 788 : | parrello | 1.15 | </Field> |
| 789 : | </Fields> | ||
| 790 : | <ToIndex> | ||
| 791 : | <Notes>This index enables the application to find all of the genomes using | ||
| 792 : | a subsystem in order by variant code, which is how we wish to display them | ||
| 793 : | in the spreadsheets.</Notes> | ||
| 794 : | <IndexFields> | ||
| 795 : | <IndexField name="variant-code" order="ascending" /> | ||
| 796 : | </IndexFields> | ||
| 797 : | </ToIndex> | ||
| 798 : | parrello | 1.1 | </Relationship> |
| 799 : | <Relationship name="OccursInSubsystem" from="Role" to="Subsystem" arity="MM"> | ||
| 800 : | parrello | 1.55 | <DisplayInfo caption="Uses" theme="seed" /> |
| 801 : | <Notes>This relationship connects roles to the subsystems that implement them.</Notes> | ||
| 802 : | parrello | 1.15 | <Fields> |
| 803 : | parrello | 1.50 | <Field name="abbr" type="name-string"> |
| 804 : | <Notes>Abbreviated name for the role, generally non-unique, but useful | ||
| 805 : | in column headings for HTML tables.</Notes> | ||
| 806 : | </Field> | ||
| 807 : | parrello | 1.15 | <Field name="column-number" type="int"> |
| 808 : | <Notes>Column number for this role in the specified subsystem's | ||
| 809 : | spreadsheet.</Notes> | ||
| 810 : | </Field> | ||
| 811 : | parrello | 1.55 | <Field name="auxiliary" type="boolean"> |
| 812 : | <Notes>If TRUE, then this role is ancillary to the purpose of the subsystem. | ||
| 813 : | If FALSE, it is essential to its metabolic pathway.</Notes> | ||
| 814 : | </Field> | ||
| 815 : | <Field name="hope_reaction_note" type="text"> | ||
| 816 : | <Notes>A description of the status of a role in relation to the | ||
| 817 : | reactions it produces as determined by the scenarios. If present, | ||
| 818 : | will indicate if the role has been determined to be auxiliary, | ||
| 819 : | if it has been examined to verify an automatic assignment, and so | ||
| 820 : | forth.</Notes> | ||
| 821 : | </Field> | ||
| 822 : | <Field name="hope_reaction_link" type="text"> | ||
| 823 : | <Notes>A description of the mapping between the reactions of | ||
| 824 : | this role and the scenarios used to validate it.</Notes> | ||
| 825 : | </Field> | ||
| 826 : | parrello | 1.15 | </Fields> |
| 827 : | <ToIndex> | ||
| 828 : | <Notes>This index enables the application to see the subsystem roles | ||
| 829 : | in column order. The ordering of the roles is usually significant, | ||
| 830 : | so it is important to preserve it.</Notes> | ||
| 831 : | <IndexFields> | ||
| 832 : | <IndexField name="column-number" order="ascending" /> | ||
| 833 : | </IndexFields> | ||
| 834 : | </ToIndex> | ||
| 835 : | parrello | 1.1 | </Relationship> |
| 836 : | <Relationship name="IsGenomeOf" from="Genome" to="SSCell" arity="1M"> | ||
| 837 : | parrello | 1.55 | <DisplayInfo caption="Is Row Of" theme="seed" /> |
| 838 : | parrello | 1.1 | <Notes>This relationship connects a subsystem's spreadsheet cell to the |
| 839 : | genome for the spreadsheet column.</Notes> | ||
| 840 : | </Relationship> | ||
| 841 : | <Relationship name="IsRoleOf" from="Role" to="SSCell" arity="1M"> | ||
| 842 : | parrello | 1.55 | <DisplayInfo caption="Is In\nColumn\nFor" theme="seed" /> |
| 843 : | parrello | 1.1 | <Notes>This relationship connects a subsystem's spreadsheet cell to the |
| 844 : | role for the spreadsheet row.</Notes> | ||
| 845 : | </Relationship> | ||
| 846 : | <Relationship name="ContainsFeature" from="SSCell" to="Feature" arity="MM"> | ||
| 847 : | parrello | 1.55 | <DisplayInfo caption="Is\nContained\nIn" theme="seed" /> |
| 848 : | parrello | 1.1 | <Notes>This relationship connects a subsystem's spreadsheet cell to the |
| 849 : | features assigned to it.</Notes> | ||
| 850 : | parrello | 1.15 | <Fields> |
| 851 : | <Field name="cluster-number" type="int"> | ||
| 852 : | <Notes>ID of this feature's cluster. Clusters represent families of | ||
| 853 : | related proteins participating in a subsystem.</Notes> | ||
| 854 : | </Field> | ||
| 855 : | </Fields> | ||
| 856 : | </Relationship> | ||
| 857 : | <Relationship name="IsAComponentOf" from="Compound" to="Reaction" arity="MM"> | ||
| 858 : | parrello | 1.55 | <DisplayInfo caption="Involves" theme="web" /> |
| 859 : | parrello | 1.15 | <Notes>This relationship connects a reaction to the compounds that participate |
| 860 : | in it.</Notes> | ||
| 861 : | <Fields> | ||
| 862 : | <Field name="product" type="boolean"> | ||
| 863 : | <Notes>TRUE if the compound is a product of the reaction, FALSE if | ||
| 864 : | it is a substrate. When a reaction is written on paper in | ||
| 865 : | chemical notation, the substrates are left of the arrow and the | ||
| 866 : | products are to the right. Sorting on this field will cause | ||
| 867 : | the substrates to appear first, followed by the products. If the | ||
| 868 : | reaction is reversible, then the notion of substrates and products | ||
| 869 : | is not at intuitive; however, a value here of FALSE still puts the | ||
| 870 : | compound left of the arrow and a value of TRUE still puts it to the | ||
| 871 : | right.</Notes> | ||
| 872 : | </Field> | ||
| 873 : | parrello | 1.19 | <Field name="stoichiometry" type="key-string"> |
| 874 : | parrello | 1.15 | <Notes>Number of molecules of the compound that participate in a |
| 875 : | single instance of the reaction. For example, if a reaction | ||
| 876 : | parrello | 1.19 | produces two water molecules, the stoichiometry of water for the |
| 877 : | parrello | 1.15 | reaction would be two. When a reaction is written on paper in |
| 878 : | parrello | 1.19 | chemical notation, the stoichiometry is the number next to the |
| 879 : | parrello | 1.15 | chemical formula of the compound.</Notes> |
| 880 : | </Field> | ||
| 881 : | <Field name="main" type="boolean"> | ||
| 882 : | <Notes>TRUE if this compound is one of the main participants in | ||
| 883 : | the reaction, else FALSE. It is permissible for none of the | ||
| 884 : | compounds in the reaction to be considered main, in which | ||
| 885 : | case this value would be FALSE for all of the relevant | ||
| 886 : | compounds.</Notes> | ||
| 887 : | </Field> | ||
| 888 : | <Field name="loc" type="key-string"> | ||
| 889 : | <Notes>An optional character string that indicates the relative | ||
| 890 : | position of this compound in the reaction's chemical formula. The | ||
| 891 : | location affects the way the compounds present as we cross the | ||
| 892 : | relationship from the reaction side. The product/substrate flag | ||
| 893 : | comes first, then the value of this field, then the main flag. | ||
| 894 : | The default value is an empty string; however, the empty string | ||
| 895 : | sorts first, so if this field is used, it should probably be | ||
| 896 : | used for every compound in the reaction.</Notes> | ||
| 897 : | </Field> | ||
| 898 : | parrello | 1.19 | <Field name="discriminator" type="int"> |
| 899 : | <Notes>A unique ID for this record. The discriminator does not | ||
| 900 : | provide any useful data, but it prevents identical records from | ||
| 901 : | being collapsed by the SELECT DISTINCT command used by ERDB to | ||
| 902 : | retrieve data.</Notes> | ||
| 903 : | </Field> | ||
| 904 : | parrello | 1.15 | </Fields> |
| 905 : | <ToIndex> | ||
| 906 : | <Notes>This index presents the compounds in the reaction in the | ||
| 907 : | order they should be displayed when writing it in chemical notation. | ||
| 908 : | All the substrates appear before all the products, and within that | ||
| 909 : | ordering, the main compounds appear first.</Notes> | ||
| 910 : | parrello | 1.19 | <IndexFields> |
| 911 : | <IndexField name="product" order="ascending" /> | ||
| 912 : | <IndexField name="loc" order="ascending" /> | ||
| 913 : | <IndexField name="main" order="descending" /> | ||
| 914 : | </IndexFields> | ||
| 915 : | parrello | 1.15 | </ToIndex> |
| 916 : | parrello | 1.1 | </Relationship> |
| 917 : | <Relationship name="IsLocatedIn" from="Feature" to="Contig" arity="MM"> | ||
| 918 : | parrello | 1.55 | <DisplayInfo caption="Is\nLocation\nOf" theme="nmpdr" /> |
| 919 : | parrello | 1.1 | <Notes>This relationship connects a feature to the contig segments that work together |
| 920 : | to effect it. The segments are numbered sequentially starting from 1. The database is | ||
| 921 : | required to place an upper limit on the length of each segment. If a segment is longer | ||
| 922 : | parrello | 1.52 | than the maximum, it can be broken into smaller bits. The upper limit enables applications |
| 923 : | to locate all features that contain a specific residue. For example, if the upper limit | ||
| 924 : | is 100 and we are looking for a feature that contains residue 234 of contig *ABC*, we | ||
| 925 : | can look for features with a begin point between 135 and 333. The results can then be | ||
| 926 : | filtered by direction and length of the segment.</Notes> | ||
| 927 : | parrello | 1.1 | <Fields> |
| 928 : | <Field name="locN" type="int"> | ||
| 929 : | parrello | 1.8 | <Notes>Sequence number of this segment.</Notes> |
| 930 : | </Field> | ||
| 931 : | parrello | 1.1 | <Field name="beg" type="int"> |
| 932 : | parrello | 1.8 | <Notes>Index (1-based) of the first residue in the contig that |
| 933 : | belongs to the segment.</Notes> | ||
| 934 : | </Field> | ||
| 935 : | parrello | 1.1 | <Field name="len" type="int"> |
| 936 : | parrello | 1.8 | <Notes>Number of residues in the segment. A length of 0 identifies |
| 937 : | a specific point between residues. This is the point before the residue if the direction | ||
| 938 : | is forward and the point after the residue if the direction is backward.</Notes> | ||
| 939 : | </Field> | ||
| 940 : | parrello | 1.1 | <Field name="dir" type="char"> |
| 941 : | parrello | 1.52 | <Notes>Direction of the segment: =+= if it is forward and |
| 942 : | =-= if it is backward.</Notes> | ||
| 943 : | parrello | 1.8 | </Field> |
| 944 : | parrello | 1.1 | </Fields> |
| 945 : | parrello | 1.45 | <FromIndex> |
| 946 : | parrello | 1.1 | <Notes>This index allows the application to find all the segments of a feature in |
| 947 : | parrello | 1.8 | the proper order.</Notes> |
| 948 : | parrello | 1.1 | <IndexFields> |
| 949 : | <IndexField name="locN" order="ascending" /> | ||
| 950 : | </IndexFields> | ||
| 951 : | </FromIndex> | ||
| 952 : | <ToIndex> | ||
| 953 : | <Notes>This index is the one used by applications to find all the feature | ||
| 954 : | segments that contain a specific residue.</Notes> | ||
| 955 : | <IndexFields> | ||
| 956 : | <IndexField name="beg" order="ascending" /> | ||
| 957 : | </IndexFields> | ||
| 958 : | </ToIndex> | ||
| 959 : | </Relationship> | ||
| 960 : | parrello | 1.8 | <Relationship name="HasProperty" from="Feature" to="Property" arity="MM"> |
| 961 : | <Notes>This relationship connects a feature to its known property values. | ||
| 962 : | The relationship contains text data that indicates the paper or organization | ||
| 963 : | that discovered evidence that the feature possesses the property. So, for | ||
| 964 : | example, if two papers presented evidence that a feature is essential, | ||
| 965 : | there would be an instance of this relationship for both.</Notes> | ||
| 966 : | <Fields> | ||
| 967 : | <Field name="evidence" type="text"> | ||
| 968 : | <Notes>URL or citation of the paper or | ||
| 969 : | institution that reported evidence of the relevant feature possessing | ||
| 970 : | the specified property value.</Notes> | ||
| 971 : | </Field> | ||
| 972 : | </Fields> | ||
| 973 : | </Relationship> | ||
| 974 : | <Relationship name="RoleOccursIn" from="Role" to="Diagram" arity="MM"> | ||
| 975 : | parrello | 1.55 | <DisplayInfo caption="Shows" theme="web" /> |
| 976 : | parrello | 1.8 | <Notes>This relationship connects a role to the diagrams on which it |
| 977 : | appears. A role frequently identifies an enzyme, and can appear in many | ||
| 978 : | diagrams. A diagram generally contains many different roles.</Notes> | ||
| 979 : | </Relationship> | ||
| 980 : | <Relationship name="HasSSCell" from="Subsystem" to="SSCell" arity="1M"> | ||
| 981 : | parrello | 1.55 | <DisplayInfo caption="Is Container Of" theme="seed" /> |
| 982 : | parrello | 1.8 | <Notes>This relationship connects a subsystem to the spreadsheet cells |
| 983 : | used to analyze and display it. The cells themselves can be thought of | ||
| 984 : | as a grid with Roles on one axis and Genomes on the other. The | ||
| 985 : | various features of the subsystem are then assigned to the cells.</Notes> | ||
| 986 : | </Relationship> | ||
| 987 : | <Relationship name="IsTrustedBy" from="SproutUser" to="SproutUser" arity="MM"> | ||
| 988 : | <Notes>This relationship identifies the users trusted by each | ||
| 989 : | particular user. When viewing functional assignments, the | ||
| 990 : | assignment displayed is the most recent one by a user trusted | ||
| 991 : | by the current user. The current user implicitly trusts himself. | ||
| 992 : | If no trusted users are specified in the database, the user | ||
| 993 : | parrello | 1.52 | also implicitly trusts the user =FIG=.</Notes> |
| 994 : | parrello | 1.8 | </Relationship> |
| 995 : | parrello | 1.15 | <Relationship name="ConsistsOfRoles" from="RoleSubset" to="Role" arity="MM"> |
| 996 : | <Notes>This relationship connects a role subset to the roles that it covers. | ||
| 997 : | A subset is, essentially, a named group of roles belonging to a specific | ||
| 998 : | subsystem, and this relationship effects that. Note that will a role | ||
| 999 : | may belong to many subsystems, a subset belongs to only one subsystem, | ||
| 1000 : | and all roles in the subset must have that subsystem in common.</Notes> | ||
| 1001 : | </Relationship> | ||
| 1002 : | <Relationship name="ConsistsOfGenomes" from="GenomeSubset" to="Genome" arity="MM"> | ||
| 1003 : | <Notes>This relationship connects a subset to the genomes that it covers. | ||
| 1004 : | A subset is, essentially, a named group of genomes participating in a specific | ||
| 1005 : | subsystem, and this relationship effects that. Note that while a genome | ||
| 1006 : | may belong to many subsystems, a subset belongs to only one subsystem, | ||
| 1007 : | and all genomes in the subset must have that subsystem in common.</Notes> | ||
| 1008 : | </Relationship> | ||
| 1009 : | <Relationship name="HasRoleSubset" from="Subsystem" to="RoleSubset" arity="1M"> | ||
| 1010 : | <Notes>This relationship connects a subsystem to its constituent | ||
| 1011 : | role subsets. Note that some roles in a subsystem may not belong to a | ||
| 1012 : | subset, so the relationship between roles and subsystems cannot be | ||
| 1013 : | derived from the relationships going through the subset.</Notes> | ||
| 1014 : | </Relationship> | ||
| 1015 : | <Relationship name="HasGenomeSubset" from="Subsystem" to="GenomeSubset" arity="1M"> | ||
| 1016 : | <Notes>This relationship connects a subsystem to its constituent | ||
| 1017 : | genome subsets. Note that some genomes in a subsystem may not belong to a | ||
| 1018 : | subset, so the relationship between genomes and subsystems cannot be | ||
| 1019 : | derived from the relationships going through the subset.</Notes> | ||
| 1020 : | </Relationship> | ||
| 1021 : | parrello | 1.39 | <Relationship name="HasRoleInSubsystem" from="Feature" to="Subsystem" arity="MM"> |
| 1022 : | <Notes>This relationship connects a feature to the subsystems in which it | ||
| 1023 : | participates. This is technically redundant information, but it is used | ||
| 1024 : | parrello | 1.52 | so often that it gets its own table for performance reasons.</Notes> |
| 1025 : | parrello | 1.40 | <Fields> |
| 1026 : | <Field name="genome" type="name-string"> | ||
| 1027 : | <Notes>ID of the genome containing the feature</Notes> | ||
| 1028 : | </Field> | ||
| 1029 : | <Field name="type" type="key-string"> | ||
| 1030 : | <Notes>Feature type (eg. peg, rna)</Notes> | ||
| 1031 : | </Field> | ||
| 1032 : | </Fields> | ||
| 1033 : | <ToIndex> | ||
| 1034 : | <Notes>This index enables the application to view the features of a | ||
| 1035 : | subsystem sorted by genome and feature type.</Notes> | ||
| 1036 : | <IndexFields> | ||
| 1037 : | <IndexField name="genome" order="ascending" /> | ||
| 1038 : | <IndexField name="type" order="ascending" /> | ||
| 1039 : | </IndexFields> | ||
| 1040 : | </ToIndex> | ||
| 1041 : | parrello | 1.39 | </Relationship> |
| 1042 : | parrello | 1.1 | </Relationships> |
| 1043 : | parrello | 1.56 | <Shapes> |
| 1044 : | <Shape type="oval" name="Pins"> | ||
| 1045 : | <DisplayInfo theme="nmpdr" col="1" row="4.5" fixed="1" /> | ||
| 1046 : | <Notes>The Pin Server provides information about functional couplings between features.</Notes> | ||
| 1047 : | </Shape> | ||
| 1048 : | <Shape type="oval" name="Sims"> | ||
| 1049 : | <DisplayInfo theme="nmpdr" col="1.5" row="5" fixed="1" /> | ||
| 1050 : | <Notes>The Similarity Server contains a high-performance custom database of similarities between features.</Notes> | ||
| 1051 : | </Shape> | ||
| 1052 : | <Shape type="oval" name="BBHs"> | ||
| 1053 : | <DisplayInfo theme="nmpdr" col="2" row="5.5" fixed="1" /> | ||
| 1054 : | <Notes>For each feature, the BBH Server has that feature's bidirectional best hits in other genomes.</Notes> | ||
| 1055 : | </Shape> | ||
| 1056 : | <Shape type="arrow" name="WebServices" from="Sims" to="Feature"> | ||
| 1057 : | <DisplayInfo caption=" " theme="nmpdr" col="2.5" row="4" /> | ||
| 1058 : | </Shape> | ||
| 1059 : | </Shapes> | ||
| 1060 : | parrello | 1.1 | </Database> |
| MCS Webmaster | ViewVC Help |
| Powered by ViewVC 1.0.3 |