当前位置: 首页>>代码示例>>Python>>正文


Python Genotype.addGeneProduct方法代码示例

本文整理汇总了Python中dipper.models.Genotype.Genotype.addGeneProduct方法的典型用法代码示例。如果您正苦于以下问题:Python Genotype.addGeneProduct方法的具体用法?Python Genotype.addGeneProduct怎么用?Python Genotype.addGeneProduct使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在dipper.models.Genotype.Genotype的用法示例。


在下文中一共展示了Genotype.addGeneProduct方法的2个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: _process_genes

# 需要导入模块: from dipper.models.Genotype import Genotype [as 别名]
# 或者: from dipper.models.Genotype.Genotype import addGeneProduct [as 别名]
    def _process_genes(self, taxid, limit=None):
        if self.test_mode:
            graph = self.testgraph
        else:
            graph = self.graph

        model = Model(graph)
        geno = Genotype(graph)

        raw = '/'.join((self.rawdir, self.files[taxid]['file']))
        line_counter = 0
        LOG.info("Processing Ensembl genes for tax %s", taxid)
        with open(raw, 'r', encoding="utf8") as csvfile:
            filereader = csv.reader(csvfile, delimiter='\t')
            for row in filereader:
                if len(row) < 4:
                    LOG.warning("Too few columns in: " + row)
                    raise ValueError("Data error for file %s", raw)
                (ensembl_gene_id, external_gene_name, description, gene_biotype,
                 entrezgene, ensembl_peptide_id, uniprotswissprot) = row[0:7]

                # in the case of human genes, we also get the hgnc id,
                # and is the last col
                if taxid == '9606':
                    hgnc_id = row[7]
                else:
                    hgnc_id = None

                if self.test_mode and entrezgene != '' and \
                        int(entrezgene) not in self.gene_ids:
                    continue

                line_counter += 1
                gene_id = 'ENSEMBL:' + ensembl_gene_id
                peptide_curie = 'ENSEMBL:{}'.format(ensembl_peptide_id)
                uniprot_curie = 'UniProtKB:{}'.format(uniprotswissprot)
                entrez_curie = 'NCBIGene:{}'.format(entrezgene)

                if description == '':
                    description = None
                gene_biotype = gene_biotype.strip()
                gene_type_id = self.resolve(gene_biotype, False)
                if gene_type_id == gene_biotype.strip():   # did not resolve
                    gene_type_id = self.globaltt['polypeptide']

                model.addClassToGraph(
                    gene_id, external_gene_name, gene_type_id, description)
                model.addIndividualToGraph(peptide_curie, None, gene_type_id)
                model.addIndividualToGraph(uniprot_curie, None, gene_type_id)

                if entrezgene != '':
                    if taxid == '9606':
                        # Use HGNC for eq in human data
                        model.addXref(gene_id, entrez_curie)
                    else:
                        model.addEquivalentClass(gene_id, entrez_curie)
                if hgnc_id is not None and hgnc_id != '':
                    model.addEquivalentClass(gene_id, hgnc_id)
                geno.addTaxon('NCBITaxon:'+taxid, gene_id)
                if ensembl_peptide_id != '':
                    geno.addGeneProduct(gene_id, peptide_curie)
                    if uniprotswissprot != '':
                        geno.addGeneProduct(gene_id, uniprot_curie)
                        model.addXref(peptide_curie, uniprot_curie)

                if not self.test_mode and limit is not None and line_counter > limit:
                    break

        return
开发者ID:TomConlin,项目名称:dipper,代码行数:71,代码来源:Ensembl.py

示例2: _process_genes

# 需要导入模块: from dipper.models.Genotype import Genotype [as 别名]
# 或者: from dipper.models.Genotype.Genotype import addGeneProduct [as 别名]
    def _process_genes(self, taxid, limit=None):
        if self.testMode:
            g = self.testgraph
        else:
            g = self.graph

        model = Model(g)
        geno = Genotype(g)

        raw = '/'.join((self.rawdir, self.files[taxid]['file']))
        line_counter = 0
        logger.info("Processing Ensembl genes for tax %s", taxid)
        with open(raw, 'r', encoding="utf8") as csvfile:
            filereader = csv.reader(csvfile, delimiter='\t')
            for row in filereader:
                if len(row) < 4:
                    raise ValueError("Data error for file %s", raw)
                (ensembl_gene_id, external_gene_name,
                 description, gene_biotype, entrezgene,
                 peptide_id, uniprot_swissprot) = row[0:7]

                # in the case of human genes, we also get the hgnc id,
                # and is the last col
                if taxid == '9606':
                    hgnc_id = row[7]
                else:
                    hgnc_id = None

                if self.testMode and entrezgene != '' \
                        and int(entrezgene) not in self.gene_ids:
                    continue

                line_counter += 1
                gene_id = 'ENSEMBL:' + ensembl_gene_id
                peptide_curie = 'ENSEMBL:{}'.format(peptide_id)
                uniprot_curie = 'UniProtKB:{}'.format(uniprot_swissprot)
                entrez_curie = 'NCBIGene:{}'.format(entrezgene)

                if description == '':
                    description = None
                # gene_type_id = self._get_gene_type(gene_biotype)
                gene_type_id = None
                model.addClassToGraph(
                    gene_id, external_gene_name, gene_type_id, description)
                model.addIndividualToGraph(peptide_curie, None, self._get_gene_type("polypeptide"))
                model.addIndividualToGraph(uniprot_curie, None, self._get_gene_type("polypeptide"))

                if entrezgene != '':
                    model.addEquivalentClass(gene_id, entrez_curie)
                if hgnc_id is not None and hgnc_id != '':
                    model.addEquivalentClass(gene_id, hgnc_id)
                geno.addTaxon('NCBITaxon:'+taxid, gene_id)
                if peptide_id != '':
                    geno.addGeneProduct(gene_id, peptide_curie)
                    if uniprot_swissprot != '':
                        geno.addGeneProduct(gene_id, uniprot_curie)
                        model.addXref(peptide_curie, uniprot_curie)

                if not self.testMode \
                        and limit is not None and line_counter > limit:
                    break

        return
开发者ID:kshefchek,项目名称:dipper,代码行数:65,代码来源:Ensembl.py


注:本文中的dipper.models.Genotype.Genotype.addGeneProduct方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。