pyobo 0.10.12

标识符和CURIEs的映射

获取ChEBI标识符到名称的映射

import pyobo

chebi_id_to_name = pyobo.get_id_name_mapping('chebi')

name = chebi_id_to_name['132964']
assert name == 'fluazifop-P-butyl'

或者，您没有时间写两行代码

import pyobo

name = pyobo.get_name('chebi', '132964')
assert name == 'fluazifop-P-butyl'

获取ChEBI名称到标识符的反向映射

import pyobo

chebi_name_to_id = pyobo.get_name_id_mapping('chebi')

identifier = chebi_name_to_id['fluazifop-P-butyl']
assert identifier == '132964'

可能你生活在 CURIE 世界中，只是想对像 CHEBI:132964 这样的东西进行标准化

import pyobo

name = pyobo.get_name_by_curie('CHEBI:132964')
assert name == 'fluazifop-P-butyl'

有时你可能会意外地获得一个旧的 CURIE。可以使用底层 OBO 中列出的替代标识符将其映射到更近期的版本

import pyobo

# Look up DNA-binding transcription factor activity (go:0003700)
# based on an old id
primary_curie = pyobo.get_primary_curie('go:0001071')
assert primary_curie == 'go:0003700'

# If it's already the primary, it just gets returned
assert 'go:0003700' == pyobo.get_priority_curie('go:0003700')

映射物种

一些资源为其术语提供了物种信息。将 WikiPathway 标识符映射到物种（作为 NCBI 分类学标识符）

import pyobo

wikipathways_id_to_species = pyobo.get_id_species_mapping('wikipathways')

# Apoptosis (Homo sapiens)
taxonomy_id = wikipathways_id_to_species['WP254']
assert taxonomy_id == '9606'

或者，您没有时间写两行代码

import pyobo

# Apoptosis (Homo sapiens)
taxonomy_id = pyobo.get_species('wikipathways', 'WP254')
assert taxonomy_id == '9606'

基础

也许你有一些想要尝试映射回 ChEBI 同义词的名称/同义词。对于 CHEBI:132964 的品牌名称 Fusilade II，它应该能够查找并找到其首选标签。

import pyobo

prefix, identifier, name = pyobo.ground('chebi', 'Fusilade II')
assert prefix == 'chebi'
assert identifier == '132964'
assert name == 'fluazifop-P-butyl'

# When failure happens...
prefix, identifier, name = pyobo.ground('chebi', 'Definitely not a real name')
assert prefix is None
assert identifier is None
assert name is None

如果你不确定一个名称可能属于哪个命名空间，你可以尝试连续尝试几个（优先考虑覆盖适当实体类型的那些，以避免在冲突时出现假阳性）

import pyobo

# looking for phenotypes/pathways
prefix, identifier, name = pyobo.ground(['efo', 'go'], 'ERAD')
assert prefix == 'go'
assert identifier == '0030433'
assert name == 'ubiquitin-dependent ERAD pathway'

交叉引用

从 ChEBI 到 PubChem 获取交叉引用

import pyobo

chebi_id_to_pubchem_compound_id = pyobo.get_filtered_xrefs('chebi', 'pubchem.compound')

pubchem_compound_id = chebi_id_to_pubchem_compound_id['132964']
assert pubchem_compound_id == '3033674'

如果你没有时间写两行

import pyobo

pubchem_compound_id = pyobo.get_xref('chebi', '132964', 'pubchem.compound')
assert pubchem_compound_id == '3033674'

从 Entrez 到 HGNC 获取交叉引用，但它们只能通过 HGNC 获取，所以你需要翻转它们

import pyobo

hgnc_id_to_ncbigene_id = pyobo.get_filtered_xrefs('hgnc', 'ncbigene')
ncbigene_id_to_hgnc_id = {
    ncbigene_id: hgnc_id
    for hgnc_id, ncbigene_id in hgnc_id_to_ncbigene_id.items()
}
mapt_hgnc = ncbigene_id_to_hgnc_id['4137']
assert mapt_hgnc == '6893'

由于这是一个常见的模式，有一个关键字参数 flip 会为你完成这个操作

import pyobo

ncbigene_id_to_hgnc_id = pyobo.get_filtered_xrefs('hgnc', 'ncbigene', flip=True)
mapt_hgnc_id = ncbigene_id_to_hgnc_id['4137']
assert mapt_hgnc_id == '6893'

如果你没有时间写两行（我承认这一点有点令人困惑）并且需要翻转它

import pyobo

hgnc_id = pyobo.get_xref('hgnc', '4137', 'ncbigene', flip=True)
assert hgnc_id == '6893'

基于预定义的优先级列表和 Inspector Javert 的 Xref 数据库 重新映射 CURIE

import pyobo

# Map to the best source possible
mapt_ncbigene = pyobo.get_priority_curie('hgnc:6893')
assert mapt_ncbigene == 'ncbigene:4137'

# Sometimes you know you're the best. Own it.
assert 'ncbigene:4137' == pyobo.get_priority_curie('ncbigene:4137')

使用 Inspector Javert 的 Xref 数据库找到映射到给定 CURIE 的所有 CURIE

import pyobo

# Get a set of all CURIEs mapped to MAPT
mapt_curies = pyobo.get_equivalent('hgnc:6893')
assert 'ncbigene:4137' in mapt_curies
assert 'ensembl:ENSG00000186868' in mapt_curies

如果你不想等待在本地构建数据库以用于 pyobo.get_priority_curie 和 pyobo.get_equivalent，你可以使用以下代码从 Zenodo 下载一个版本

import pyobo.resource_utils

pyobo.resource_utils.ensure_inspector_javert()

属性

获取属性，如 SMILES。这些的语义是在 OBO-OBO 基础上定义的。

import pyobo

# I don't make the rules. I wouldn't have chosen this as the key for this property. It could be any string
chebi_smiles_property = 'http://purl.obolibrary.org/obo/chebi/smiles'
chebi_id_to_smiles = pyobo.get_filtered_properties_mapping('chebi', chebi_smiles_property)

smiles = chebi_id_to_smiles['132964']
assert smiles == 'C1(=CC=C(N=C1)OC2=CC=C(C=C2)O[C@@H](C(OCCCC)=O)C)C(F)(F)F'

如果你没有时间写两行

import pyobo

smiles = pyobo.get_property('chebi', '132964', 'http://purl.obolibrary.org/obo/chebi/smiles')
assert smiles == 'C1(=CC=C(N=C1)OC2=CC=C(C=C2)O[C@@H](C(OCCCC)=O)C)C(F)(F)F'

层次结构

检查一个实体是否在层次结构中

import networkx as nx
import pyobo

# check that go:0008219 ! cell death is an ancestor of go:0006915 ! apoptotic process
assert 'go:0008219' in pyobo.get_ancestors('go', '0006915')

# check that go:0070246 ! natural killer cell apoptotic process is a
# descendant of go:0006915 ! apoptotic process
apopototic_process_descendants = pyobo.get_descendants('go', '0006915')
assert 'go:0070246' in apopototic_process_descendants

获取给定节点下的子层次结构

# get the descendant graph of go:0006915 ! apoptotic process
apopototic_process_subhierarchy = pyobo.get_subhierarchy('go', '0006915')

# check that go:0070246 ! natural killer cell apoptotic process is a
# descendant of go:0006915 ! apoptotic process through the subhierarchy
assert 'go:0070246' in apopototic_process_subhierarchy

获取在节点数据字典中预加载属性的自定义层次结构

import pyobo

prop = 'http://purl.obolibrary.org/obo/chebi/smiles'
chebi_hierarchy = pyobo.get_hierarchy('chebi', properties=[prop])

assert 'chebi:132964' in chebi_hierarchy
assert prop in chebi_hierarchy.nodes['chebi:132964']
assert chebi_hierarchy.nodes['chebi:132964'][prop] == 'C1(=CC=C(N=C1)OC2=CC=C(C=C2)O[C@@H](C(OCCCC)=O)C)C(F)(F)F'

关系

获取 HGNC 和 MGI 之间的所有同源关系（注意：这是单向的）

>>> import pyobo
>>> human_mapt_hgnc_id = '6893'
>>> mouse_mapt_mgi_id = '97180'
>>> hgnc_mgi_orthology_mapping = pyobo.get_relation_mapping('hgnc', 'ro:HOM0000017', 'mgi')
>>> assert mouse_mapt_mgi_id == hgnc_mgi_orthology_mapping[human_mapt_hgnc_id]

如果你想一行完成

>>> import pyobo
>>> human_mapt_hgnc_id = '6893'
>>> mouse_mapt_mgi_id = '97180'
>>> assert mouse_mapt_mgi_id == pyobo.get_relation('hgnc', 'ro:HOM0000017', 'mgi', human_mapt_hgnc_id)

使用 PyOBO 编写的测试

如果你正在编写自己的代码，它依赖于 PyOBO，并且在持续集成环境中对其进行了单元测试（你应该这样做），你可能已经意识到在每次构建时加载所有资源并不是那么快。在这些情况下，你可以使用一些预先构建的补丁，如下所示

import unittest
import pyobo
from pyobo.mocks import get_mock_id_name_mapping

mock_id_name_mapping = get_mock_id_name_mapping({
    'chebi': {
        '132964': 'fluazifop-P-butyl',
    },
})

class MyTestCase(unittest.TestCase):
    def my_test(self):
        with mock_id_name_mapping:
            # use functions directly, or use your functions that wrap them
            pyobo.get_name('chebi', '1234')