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

View of /Sprout/SimBlocksDBD.xml

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.5 - (download) (as text) (annotate)
Tue Feb 7 16:06:55 2006 UTC (14 years, 3 months ago) by parrello
Branch: MAIN
CVS Tags: mgrast_dev_08112011, mgrast_dev_08022011, rast_rel_2014_0912, rast_rel_2008_06_18, rast_rel_2008_06_16, rast_rel_2008_12_18, mgrast_dev_04082011, rast_rel_2008_07_21, rast_rel_2010_0928, rast_2008_0924, mgrast_version_3_2, mgrast_dev_12152011, rast_rel_2008_04_23, mgrast_dev_06072011, rast_rel_2008_09_30, rast_rel_2009_0925, rast_rel_2010_0526, rast_rel_2014_0729, rast_rel_2009_05_18, rast_rel_2010_1206, mgrast_release_3_0, mgrast_dev_03252011, rast_rel_2010_0118, mgrast_rel_2008_0924, mgrast_rel_2008_1110_v2, rast_rel_2009_02_05, rast_rel_2011_0119, mgrast_rel_2008_0625, mgrast_release_3_0_4, mgrast_release_3_0_2, mgrast_release_3_0_3, mgrast_release_3_0_1, mgrast_dev_03312011, mgrast_release_3_1_2, mgrast_release_3_1_1, mgrast_release_3_1_0, mgrast_dev_04132011, rast_rel_2008_10_09, mgrast_dev_04012011, rast_release_2008_09_29, mgrast_rel_2008_0806, mgrast_rel_2008_0923, mgrast_rel_2008_0919, rast_rel_2009_07_09, rast_rel_2010_0827, mgrast_rel_2008_1110, myrast_33, rast_rel_2011_0928, rast_rel_2008_09_29, mgrast_rel_2008_0917, rast_rel_2008_10_29, mgrast_dev_04052011, rast_rel_2009_03_26, mgrast_dev_10262011, rast_rel_2008_11_24, rast_rel_2008_08_07, HEAD
Changes since 1.4: +2 -2 lines
Replaced field "end" with "endpoint" to fix reserved word problem.

<?xml version="1.0" encoding="UTF-8"?>
<Database>
    <Title>Similarity Block Database</Title>
    <Entities>
        <Entity name="Genome" keyType="name-string">
            <Notes>A [i]genome[/i] contains the sequence data for a particular
            individual organism.</Notes>
            <Fields>
                <Field name="description" type="string">
                    <Notes>Brief description of this genome.</Notes>
                </Field>
                <Field name="group-name" type="name-string">
                    <Notes>Name of this genome's close-strain group.</Notes>
                </Field>

            </Fields>
            <Indexes>
                <Index>
                    <Notes>This index sorts the genomes by group so that
                    close strains are placed next to each other.</Notes>
                    <IndexFields>
                        <IndexField name="group-name" order="ascending" />
                        <IndexField name="id" order="ascending" />
                    </IndexFields>
                </Index>
            </Indexes>
        </Entity>
        <Entity name="Contig" keyType="key-string">
            <Notes>A [i]contig[/i] is a contiguous run of nucleotides. The contig's
            ID consists of the genome ID followed by a name that identifies
            which contig this is for the parent genome. The individual components
            are separated by a colon.</Notes>
        </Entity>
        <Entity name="GroupBlock" keyType="name-string">
            <Notes>A [i]group block[/i] is a set of similar genome regions.
            A group block can represent a gene or an inter-genic region.
            The result is that every position in a contig belongs to exactly
            one block, though some will belong to several.</Notes>
            <Fields>
                <Field name="len" type="int">
                    <Notes>Number of nucleotides in the regions belonging to
                    this block. This may include insertion markers ([b]-[/b]).</Notes>
                </Field>
                <Field name="pattern" type="text">
                    <Notes>A representation of the nucleotides in the group,
                    with question marks substituted for positions that are
                    not identical for all group members.</Notes>
                </Field>
                <Field name="variance" type="float">
                    <Notes>The proportion of nucleotides that vary between
                    regions in this group. For example, a value of 0 means all
                    regions are identical at every position. A value of
                    0.5 means all regions are identical at exactly half of
                    the positions. For a block length of 100, a value
                    of 0.03 means all regions are identical at every position
                    but 3. The variance does not indicate the degree
                    of dissimilarity, just how much of each region needs to be
                    examined for SNPs.</Notes>
                </Field>
                <Field name="snip-count" type="int">
                    <Notes>The number of positions at which the nucleotides
                    vary between regions in this group. The variance value
                    is this number divided by the block length.</Notes>
                </Field>
                <Field name="description" type="string">
                    <Notes>Descriptive name of this block. This will be
                    the gene name for gene blocks, and a generated
                    string for inter-genic blocks.</Notes>
                </Field>
            </Fields>
        </Entity>
        <Entity name="Region" keyType="name-string">
            <Notes>A [i]region[/i] describes a location in a contig, and
            essentially bridges the gap between blocks and contigs. Each
            instance of this object corresponds to a single segment on
            a contig. The key is the region's sprout-style location
            string.</Notes>
            <Fields>
                <Field name="contigID" type="key-string">
                    <Notes>Name of the contig containing this region.</Notes>
                </Field>
                <Field name="position" type="int">
                    <Notes>Index (1-based) of the region's leftmost nucleotide
                    in the contig.</Notes>
                </Field>
                <Field name="direction" type="char">
                    <Notes>[b]+[/b] for a forward region, [b]-[/b] for a reverse
                    region.</Notes>
                </Field>
                <Field name="content" type="text">
                    <Notes>Nucleotide sequence of variance in this region
                    (upper case). For a forward region, this is the exact
                    content of each position of variance in the region.
                    For a reverse region, it is the complement in
                    reverse order.</Notes>
                </Field>
                <Field name="len" type="int">
                    <Notes>Length of this region. This may be slightly smaller
                    than the block length.</Notes>
                </Field>
                <Field name="endpoint" type="int">
                    <Notes>Index (1-based) of the region's rightmost nucleotide
                    in the contig.</Notes>
                </Field>
                <Field name="peg" type="name-string">
                    <Notes>PEG identifier for this block if it is a gene block,
                    or a string generated from the nearby PEGs if it is an
                    inter-genic block</Notes>
                </Field>
            </Fields>
            <Indexes>
                <Index>
                    <Notes>This index enables the application to find regions
                    that overlap a specific section of the contig.  The index
                    can be used to find the first region whose end point is at
                    or follows the start of the section in question. Because
                    every nucleotide is in at most one region, this guarantees
                    that if any region overlaps the section, the region found
                    by the index will.</Notes>
                    <IndexFields>
                        <IndexField name="endpoint" order="ascending" />
                    </IndexFields>
                </Index>
            </Indexes>
        </Entity>
    </Entities>
    <Relationships>
        <Relationship name="ContainsRegion" from="Contig" to="Region" arity="1M">
            <Notes>This relationship connects contigs to the regions on
            them.</Notes>
            <Fields>
                <Field name="position" type="int">
                    <Notes>Index (1-based) of the region's leftmost nucleotide
                    in the contig.</Notes>
                </Field>
                <Field name="len" type="int">
                    <Notes>Length of this region. This may be slightly smaller
                    than the block length.</Notes>
                </Field>
            </Fields>
            <ToIndex>
                <Notes>This index enables the application to find all of the
                regions in a contig in the order they are present in the
                contig.</Notes>
                <IndexFields>
                    <IndexField name="position" order="ascending" />
                    <IndexField name="len" order="descending" />
                </IndexFields>
            </ToIndex>
        </Relationship>
        <Relationship name="IncludesRegion" from="GroupBlock" to="Region" arity="1M">
            <Notes>This relationship connects a block to the regions it covers. Note
            that since the ID of the region is its Sprout-style location string,
            often it is not necessary to cross to the [b]Region[/b] table when
            accessing this relationship.</Notes>
        </Relationship>
        <Relationship name="HasInstanceOf" from="Genome" to="GroupBlock" arity="MM">
            <Notes>This relationship connects a genome to the groups represented
            in its contigs. It provides a fast was to get an ordered list of
            groups for a genome. The group lists for genomes can then be
            merged to determine the common groups of a set of genomes.</Notes>
        </Relationship>
        <Relationship name="ConsistsOf" from="Genome" to="Contig" arity="1M">
            <Notes>This relationship connects a genome to its contigs.</Notes>
        </Relationship>
    </Relationships>
</Database>

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3