Python Dataset.set_citation方法代码示例

# 需要导入模块: from dipper.models.Dataset import Dataset [as 别名]
# 或者: from dipper.models.Dataset.Dataset import set_citation [as 别名]
class MPD(Source):
    """
    From the [MPD](http://phenome.jax.org/) website:
    This resource is a collaborative standardized collection of measured data
    on laboratory mouse strains and populations. Includes baseline phenotype
    data sets as well as studies of drug, diet, disease and aging effect.
    Also includes protocols, projects and publications, and SNP,
    variation and gene expression studies.

    Here, we pull the data and model the genotypes using GENO and
    the genotype-to-phenotype associations using the OBAN schema.

    MPD provide measurements for particular assays for several strains.
    Each of these measurements is itself mapped to a MP or VT term
    as a phenotype.  Therefore, we can create a strain-to-phenotype association
    based on those strains that lie outside of the "normal" range for the given
    measurements.  We can compute the average of the measurements
    for all strains tested, and then threshold any extreme measurements being
    beyond some threshold beyond the average.

    Our default threshold here, is +/-2 standard deviations beyond the mean.

    Because the measurements are made and recorded at the level of
    a specific sex of each strain, we associate the MP/VT phenotype with
    the sex-qualified genotype/strain.

    """
    MPDDL = 'http://phenomedoc.jax.org/MPD_downloads'
    files = {
        'ontology_mappings': {
            'file': 'ontology_mappings.csv',
            'url': MPDDL + '/ontology_mappings.csv'},
        'straininfo': {
            'file': 'straininfo.csv',
            'url': MPDDL + '/straininfo.csv'},
        'assay_metadata': {
            'file': 'measurements.csv',
            'url': MPDDL + '/measurements.csv'},
        'strainmeans': {
            'file': 'strainmeans.csv.gz',
            'url': MPDDL + '/strainmeans.csv.gz'},
        # 'mpd_datasets_metadata': { #TEC does not seem to be used
        #    'file': 'mpd_datasets_metadata.xml.gz',
        #    'url': MPDDL + '/mpd_datasets_metadata.xml.gz'},
    }

    # the following are strain ids for testing
    # test_ids = [
    #   "MPD:2", "MPD:3", "MPD:5", "MPD:6", "MPD:9", "MPD:11", "MPD:18",
    #   "MPD:20", "MPD:24", "MPD:28", "MPD:30", "MPD:33", "MPD:34", "MPD:36",
    #   "MPD:37", "MPD:39", "MPD:40", "MPD:42", "MPD:47", "MPD:66", "MPD:68",
    #   "MPD:71", "MPD:75", "MPD:78", "MPD:122", "MPD:169", "MPD:438",
    #   "MPD:457","MPD:473", "MPD:481", "MPD:759", "MPD:766", "MPD:770",
    #   "MPD:849",  "MPD:857", "MPD:955", "MPD:964", "MPD:988", "MPD:1005",
    #   "MPD:1017", "MPD:1204", "MPD:1233", "MPD:1235", "MPD:1236", "MPD:1237"]

    test_ids = [
        'MPD:6', 'MPD:849', 'MPD:425', 'MPD:569', "MPD:10", "MPD:1002",
        "MPD:39", "MPD:2319"]

    mgd_agent_id = "MPD:db/q?rtn=people/allinv"
    mgd_agent_label = "Mouse Phenotype Database"
    mgd_agent_type = "foaf:organization"

    def __init__(self, graph_type, are_bnodes_skolemized):
        Source.__init__(self, graph_type, are_bnodes_skolemized, 'mpd')
        # @N, not sure if this step is required
        self.stdevthreshold = 2

        # update the dataset object with details about this resource
        # @N: Note that there is no license as far as I can tell
        self.dataset = Dataset(
            'mpd', 'MPD', 'http://phenome.jax.org', None, None)

        # TODO add a citation for mpd dataset as a whole
        self.dataset.set_citation('PMID:15619963')

        self.assayhash = {}
        self.idlabel_hash = {}
        # to store the mean/zscore of each measure by strain+sex
        self.score_means_by_measure = {}
        # to store the mean value for each measure by strain+sex
        self.strain_scores_by_measure = {}

        return

    def fetch(self, is_dl_forced=False):

        self.get_files(is_dl_forced)
        return

    def parse(self, limit=None):
        """
        MPD data is delivered in four separate csv files and one xml file,
        which we process iteratively and write out as
        one large graph.

        :param limit:
        :return:
        """
#.........这里部分代码省略.........

# 需要导入模块: from dipper.models.Dataset import Dataset [as 别名]
# 或者: from dipper.models.Dataset.Dataset import set_citation [as 别名]
class GeneReviews(Source):
    """
    Here we process the GeneReviews mappings to OMIM,
    plus inspect the GeneReviews (html) books to pull the clinical descriptions
    in order to populate the definitions of the terms in the ontology.
    We define the GeneReviews items as classes that are either grouping classes
    over OMIM disease ids (gene ids are filtered out),
    or are made as subclasses of DOID:4 (generic disease).

    Note that GeneReviews
    [copyright policy](http://www.ncbi.nlm.nih.gov/books/NBK138602/)
    (as of 2015.11.20) says:

    GeneReviews® chapters are owned by the University of Washington, Seattle,
    © 1993-2015. Permission is hereby granted to reproduce, distribute,
    and translate copies of content materials provided that
    (i) credit for source (www.ncbi.nlm.nih.gov/books/NBK1116/)
        and copyright (University of Washington, Seattle)
        are included with each copy;
    (ii) a link to the original material is provided whenever the material is
        published elsewhere on the Web; and
    (iii) reproducers, distributors, and/or translators comply with this
        copyright notice and the GeneReviews Usage Disclaimer.

    This script doesn't pull the GeneReviews books from the NCBI Bookshelf
    directly; scripting this task is expressly prohibited by
    [NCBIBookshelf policy](http://www.ncbi.nlm.nih.gov/books/NBK45311/).
    However, assuming you have acquired the books (in html format) via
    permissible means, a parser for those books is provided here to extract
    the clinical descriptions to define the NBK identified classes.

    """

    files = {
        'idmap': {'file': 'NBKid_shortname_OMIM.txt',
                  'url': GRDL + '/NBKid_shortname_OMIM.txt'},
        'titles': {'file': 'GRtitle_shortname_NBKid.txt',
                   'url': GRDL + '/GRtitle_shortname_NBKid.txt'}
        }

    def __init__(self):
        Source.__init__(self, 'genereviews')

        self.load_bindings()

        self.dataset = Dataset(
            'genereviews', 'Gene Reviews', 'http://genereviews.org/',
            None, 'http://www.ncbi.nlm.nih.gov/books/NBK138602/')
        self.dataset.set_citation('GeneReviews:NBK1116')

        self.gu = GraphUtils(curie_map.get())

        self.book_ids = set()
        self.all_books = {}

        if 'test_ids' not in config.get_config() or\
                'disease' not in config.get_config()['test_ids']:
            logger.warning("not configured with disease test ids.")
            self.test_ids = list()
        else:
            # select ony those test ids that are omim's.
            self.test_ids = config.get_config()['test_ids']['disease']

        return

    def fetch(self, is_dl_forced=False):
        """
        We fetch GeneReviews id-label map and id-omim mapping files from NCBI.
        :return: None
        """

        self.get_files(is_dl_forced)

        return

    def parse(self, limit=None):
        """
        :return: None
        """

        if self.testOnly:
            self.testMode = True

        self._get_titles(limit)
        self._get_equivids(limit)

        self.create_books()
        self.process_nbk_html(limit)

        self.load_bindings()

        # no test subset for now; test == full graph
        self.testgraph = self.graph

        logger.info("Found %d nodes", len(self.graph))

        return

    def _get_equivids(self, limit):
        """
#.........这里部分代码省略.........