python - 如何从 efetch(Biopython、Entrez)中提取摘要？

Question

我是 python 的新手，想使用 bio 包中的 entrez 系统从 pubmed 中提取摘要。我通过电子搜索获得了我的 UID(存储在 my_list_ges 中)，我还可以使用 efetch 下载条目。然而，现在结果是一个字典列表，条目看起来像字典，但我无法访问它们:

Entrez.email= "my-email@provider.sth"
handle=Entrez.efetch(db="pubmed",id=my_list_ges[0],rettype="null",retmode="xml")
record = Entrez.read(handle)
abstract=record["Abstract"]
handle.close()

结果是类型错误:

TypeError: list indices must be integers, not str 

当我尝试从第一条记录中检索 'Abstract' 时，我得到了一个 KeyError:

>>> record[0]["Abstract"]
KeyError: 'Abstract'

这很奇怪，因为根据电子搜索的结果，我可以通过字典轻松访问我的 UID

记录[0]的结构是:

{u'MedlineCitation': DictElement({
        u'OtherID': [],
        u'OtherAbstract': [],
        u'CitationSubset': ['IM'],
        u'KeywordList': [],
        u'DateCreated': {u'Month': '03', u'Day': '17', u'Year': '2016'},
        u'SpaceFlightMission': [],
        u'GeneralNote': [],
        u'Article':
        DictElement({
            u'ArticleDate': [
                DictElement({u'Month': '03', u'Day': '16', u'Year': '2016'}, attributes={u'DateType': u'Electronic'})],
           u'Pagination': {u'MedlinePgn': 'e0151666'},
           u'AuthorList': ListElement([
            DictElement({
                u'LastName': "O'Neill",
                u'Initials': 'KE',
                u'Identifier': [],
                u'AffiliationInfo': [{
                    u'Affiliation': 'MRC Centre for Regenerative Medicine, Institute for Stem Cell Research, School of Biological Sciences, University of Edinburgh, SCRM Building, 5 Little France Drive, Edinburgh, EH16 4UU, UK.',
                    u'Identifier': []}], 
                u'ForeName': 'Kathy E'
                }, attributes={u'ValidYN': u'Y'}),
            DictElement({
                u'LastName': 'Bredenkamp',
                u'Initials': 'N', u'Identifier': [],
                u'AffiliationInfo': [{
                    u'Affiliation': 'MRC Centre for Regenerative Medicine, Institute for Stem Cell Research, School of Biological Sciences, University of Edinburgh, SCRM Building, 5 Little France Drive, Edinburgh, EH16 4UU, UK.',
                    u'Identifier': []}],
                u'ForeName': 'Nicholas'}, attributes={u'ValidYN': u'Y'}), 
            DictElement({
                u'LastName': 'Tischner',
                u'Initials': 'C',
                u'Identifier': [], 
                u'AffiliationInfo': [{
                    u'Affiliation': 'MRC Centre for Regenerative Medicine, Institute for Stem Cell Research, School of Biological Sciences, University of Edinburgh, SCRM Building, 5 Little France Drive, Edinburgh, EH16 4UU, UK.',
                    u'Identifier': []}],
                u'ForeName': 'Christin'}, attributes={u'ValidYN': u'Y'}),
            DictElement({
                u'LastName': 'Vaidya',
                u'Initials': 'HJ',
                u'Identifier': [],
                u'AffiliationInfo': [{
                    u'Affiliation': 'MRC Centre for Regenerative Medicine, Institute for Stem Cell Research, School of Biological Sciences, University of Edinburgh, SCRM Building, 5 Little France Drive, Edinburgh, EH16 4UU, UK.',
                    u'Identifier': []}],
                u'ForeName': 'Harsh J'}, attributes={u'ValidYN': u'Y'}),
            DictElement({
                u'LastName': 'Stenhouse',
                u'Initials': 'FH',
                u'Identifier': [],
                u'AffiliationInfo': [{
                    u'Affiliation': 'MRC Centre for Regenerative Medicine, Institute for Stem Cell Research, School of Biological Sciences, University of Edinburgh, SCRM Building, 5 Little France Drive, Edinburgh, EH16 4UU, UK.',
                    u'Identifier': []}], u'ForeName': 'Frances H'}, attributes={u'ValidYN': u'Y'}),
            DictElement({
                u'LastName': 'Peddie',
                u'Initials': 'CD',
                u'Identifier': [],
                u'AffiliationInfo': [{
                    u'Affiliation': 'MRC Centre for Regenerative Medicine, Institute for Stem Cell Research, School of Biological Sciences, University of Edinburgh, SCRM Building, 5 Little France Drive, Edinburgh, EH16 4UU, UK.',
                    u'Identifier': []}],
                u'ForeName': 'C Diana'}, attributes={u'ValidYN': u'Y'}),
            DictElement({
                u'LastName': 'Nowell',
                u'Initials': 'CS',
                u'Identifier': [],
                u'AffiliationInfo': [{
                    u'Affiliation': 'MRC Centre for Regenerative Medicine, Institute for Stem Cell Research, School of Biological Sciences, University of Edinburgh, SCRM Building, 5 Little France Drive, Edinburgh, EH16 4UU, UK.',
                    u'Identifier': []}],
                u'ForeName': 'Craig S'}, attributes={u'ValidYN': u'Y'}),
            DictElement({
                u'LastName': 'Gaskell', 
                u'Initials': 'T', 
                u'Identifier': [], 
                u'AffiliationInfo': [{
                    u'Affiliation': 'MRC Centre for Regenerative Medicine, Institute for Stem Cell Research, School of Biological Sciences, University of Edinburgh, SCRM Building, 5 Little France Drive, Edinburgh, EH16 4UU, UK.',
                    u'Identifier': []}],
                u'ForeName': 'Terri'}, attributes={u'ValidYN': u'Y'}),
            DictElement({
                u'LastName': 'Blackburn',
                u'Initials': 'CC',
                u'Identifier': [],
                u'AffiliationInfo': [{
                    u'Affiliation': 'MRC Centre for Regenerative Medicine, Institute for Stem Cell Research, School of Biological Sciences, University of Edinburgh, SCRM Building, 5 Little France Drive, Edinburgh, EH16 4UU, UK.',
                    u'Identifier': []}], u'ForeName': 'C Clare'}, attributes={u'ValidYN': u'Y'})],
            attributes={u'Type': u'authors', u'CompleteYN': u'Y'}),
        u'Language': ['eng'],
        u'PublicationTypeList': [StringElement('Journal Article', attributes={u'UI': u'D016428'})],
        u'Journal': {
            u'ISSN': StringElement('1932-6203', attributes={u'IssnType': u'Electronic'}),
            u'ISOAbbreviation': 'PLoS ONE',
            u'JournalIssue': DictElement({
                u'Volume': '11',
                u'Issue': '3',
                u'PubDate': {u'Year': '2016'}}, attributes={u'CitedMedium': u'Internet'}),
            u'Title': 'PloS one'},
        u'ArticleTitle': 'Foxn1 Is Dynamically Regulated in Thymic Epithelial Cells during Embryogenesis and at the Onset of Thymic Involution.',
        u'ELocationID': [StringElement('10.1371/journal.pone.0151666', attributes={u'ValidYN': u'Y', u'EIdType': u'doi'})],
        u'Abstract': {u'AbstractText': ['--Unnecessarily long abstract removed --']}}, attributes={u'PubModel': u'Electronic-eCollection'}),
        u'PMID': StringElement('26983083', attributes={u'Version': u'1'}),
        u'MedlineJournalInfo': {
            u'MedlineTA': 'PLoS One',
            u'Country': 'United States',
            u'NlmUniqueID': '101285081',
            u'ISSNLinking': '1932-6203'}}, attributes={u'Owner': u'NLM', u'Status': u'In-Data-Review'}),
 u'PubmedData': {
    u'ArticleIdList': [
        StringElement('10.1371/journal.pone.0151666', attributes={u'IdType': u'doi'}),
        StringElement('PONE-D-15-47173', attributes={u'IdType': u'pii'}),
        StringElement('26983083', attributes={u'IdType': u'pubmed'})],
    u'PublicationStatus': 'epublish',
    u'History': [
        DictElement({u'Month': '', u'Day': '', u'Year': '2016'}, attributes={u'PubStatus': u'ecollection'}),
        DictElement({u'Month': '10', u'Day': '28', u'Year': '2015'}, attributes={u'PubStatus': u'received'}),
        DictElement({u'Month': '3', u'Day': '2', u'Year': '2016'}, attributes={u'PubStatus': u'accepted'}),
        DictElement({u'Month': '3', u'Day': '16', u'Year': '2016'}, attributes={u'PubStatus': u'epublish'}),
        DictElement({u'Minute': '0', u'Month': '3', u'Day': '17', u'Hour': '6', u'Year': '2016'}, attributes={u'PubStatus': u'entrez'}),
        DictElement({u'Minute': '0', u'Month': '3', u'Day': '18', u'Hour': '6', u'Year': '2016'}, attributes={u'PubStatus': u'pubmed'}),
        DictElement({u'Minute': '0', u'Month': '3', u'Day': '18', u'Hour': '6', u'Year': '2016'}, attributes={u'PubStatus': u'medline'})]}
}

Answer 1

我发现返回 Medline 记录并对其进行解析要容易得多。我为相关查询插入了完整的工作代码:query = "Tischner[AU] Cortex-specific down-regulation"。 下面代码的关键点是fetch_rec()函数使用rettype='Medline', retmode='text'然后使用BioPython的解析结果记录Medline 模块。

from StringIO import StringIO
from Bio import Entrez, Medline

def search_medline(query, email):
    Entrez.email = email
    search = Entrez.esearch(db='pubmed', term=query, usehistory='y')
    handle = Entrez.read(search)
    try:
        return handle
    except Exception as e:
        raise IOError(str(e))
    finally:
        search.close()

def fetch_rec(rec_id, entrez_handle):
    fetch_handle = Entrez.efetch(db='pubmed', id=rec_id,
                                 rettype='Medline', retmode='text',
                                 webenv=entrez_handle['WebEnv'],
                                 query_key=entrez_handle['QueryKey'])
    rec = fetch_handle.read()
    return rec

def main(query, email):
    rec_handler = search_medline(query, email)

    for rec_id in rec_handler['IdList']:
        rec = fetch_rec(rec_id, rec_handler)
        rec_file = StringIO(rec)
        medline_rec = Medline.read(rec_file)
        if 'AB' in medline_rec:
            print(medline_rec['AB'])

if __name__ == '__main__':
    email = "my-email@provider.sth"
    query = "Tischner[AU] Cortex-specific down-regulation"
    main(query, email)

它会打印出您要查找的摘要，但是通过更改 query 参数，该脚本可以适用于任何搜索。有更有效的方法来提取大量记录，但对于小型搜索来说，这就足够了。