Python Medline.read方法代码示例

# 需要导入模块: from Bio import Medline [as 别名]
# 或者: from Bio.Medline import read [as 别名]
 def test_medline_from_url(self):
     """Test Entrez into Medline.read from URL"""
     efetch = Entrez.efetch(db="pubmed", id="19304878", rettype="medline", retmode="text")
     record = Medline.read(efetch)
     self.assertTrue(isinstance(record, dict))
     self.assertEqual("19304878", record["PMID"])
     self.assertEqual("10.1093/bioinformatics/btp163 [doi]", record["LID"])

# 需要导入模块: from Bio import Medline [as 别名]
# 或者: from Bio.Medline import read [as 别名]
 def test_read(self):
     with open("Medline/pubmed_result1.txt") as handle:
         record = Medline.read(handle)
     self.assertEqual(record["PMID"], "12230038")
     self.assertEqual(record["OWN"], "NLM")
     self.assertEqual(record["STAT"], "MEDLINE")
     self.assertEqual(record["DA"], "20020916")
     self.assertEqual(record["DCOM"], "20030606")
     self.assertEqual(record["LR"], "20041117")
     self.assertEqual(record["PUBM"], "Print")
     self.assertEqual(record["IS"], "1467-5463 (Print)")
     self.assertEqual(record["VI"], "3")
     self.assertEqual(record["IP"], "3")
     self.assertEqual(record["DP"], "2002 Sep")
     self.assertEqual(record["TI"], "The Bio* toolkits--a brief overview.")
     self.assertEqual(record["PG"], "296-302")
     self.assertEqual(record["AB"], "Bioinformatics research is often difficult to do with commercial software. The Open Source BioPerl, BioPython and Biojava projects provide toolkits with multiple functionality that make it easier to create customised pipelines or analysis. This review briefly compares the quirks of the underlying languages and the functionality, documentation, utility and relative advantages of the Bio counterparts, particularly from the point of view of the beginning biologist programmer.")
     self.assertEqual(record["AD"], "tacg Informatics, Irvine, CA 92612, USA. [email protected]")
     self.assertEqual(record["FAU"], ["Mangalam, Harry"])
     self.assertEqual(record["AU"], ["Mangalam H"])
     self.assertEqual(record["LA"], ["eng"])
     self.assertEqual(record["PT"], ["Journal Article"])
     self.assertEqual(record["PL"], "England")
     self.assertEqual(record["TA"], "Brief Bioinform")
     self.assertEqual(record["JT"], "Briefings in bioinformatics")
     self.assertEqual(record["JID"], "100912837")
     self.assertEqual(record["SB"], "IM")
     self.assertEqual(record["MH"], ["*Computational Biology", "Computer Systems", "Humans", "Internet", "*Programming Languages", "*Software", "User-Computer Interface"])
     self.assertEqual(record["EDAT"], "2002/09/17 10:00")
     self.assertEqual(record["MHDA"], "2003/06/07 05:00")
     self.assertEqual(record["PST"], "ppublish")
     self.assertEqual(record["SO"], "Brief Bioinform. 2002 Sep;3(3):296-302.")

# 需要导入模块: from Bio import Medline [as 别名]
# 或者: from Bio.Medline import read [as 别名]
	def processInput(k):
		print "Querying PMID: "+str(k)+"."
		getall = Medline.read(Entrez.efetch(db="pubmed", id=k, rettype="medline", retmode="text"))
		singlemesh = getall.get("MH")
		singledate = getall.get("EDAT")	
		for j1 in range(len(singlemesh)):
			cur.execute("INSERT INTO MeSH002(PMID, MeSH, Dates) VALUES("+str(k)+",'" + getall.get("MH")[j1][0:24].translate(None, "'*&")+"','" +  str(singledate[0:10]) +"')" )

# 需要导入模块: from Bio import Medline [as 别名]
# 或者: from Bio.Medline import read [as 别名]
 def parse_medline(self, text):
     self.medline = Medline.read(text.split('\n'))
     self.title = self.medline['TI']
     self.journal = self.medline['JT']
     self.citation = self.medline['SO']
     self.date_pub = self.medline['DP']
     try:
         self.authors = self.medline['AU']
     except KeyError:
         self.authors = self.medline['IR']

# 需要导入模块: from Bio import Medline [as 别名]
# 或者: from Bio.Medline import read [as 别名]
 def test_pubmed_16381885(self):
     """Bio.TogoWS.entry("pubmed", "16381885")"""
     # Gives Medline plain text
     handle = TogoWS.entry("pubmed", "16381885")
     data = Medline.read(handle)
     handle.close()
     self.assertEqual(data["TI"],
          'From genomics to chemical genomics: new developments in KEGG.')
     self.assertEqual(data["AU"], ['Kanehisa M', 'Goto S', 'Hattori M',
                                   'Aoki-Kinoshita KF', 'Itoh M',
                                   'Kawashima S', 'Katayama T', 'Araki M',
                                   'Hirakawa M'])

# 需要导入模块: from Bio import Medline [as 别名]
# 或者: from Bio.Medline import read [as 别名]
 def test_multiline_mesh(self):
     with open("Medline/pubmed_result3.txt") as handle:
         record = Medline.read(handle)
         self.assertEqual(record["PMID"], "23039619")
     self.assertEqual(record["MH"], ["Blood Circulation",
                                     "High-Intensity Focused Ultrasound Ablation/adverse effects/instrumentation/*methods",
                                     "Humans",
                                     "Models, Biological",
                                     "Sonication",
                                     "Temperature",
                                     "Time Factors",
                                     "Transducers"])

# 需要导入模块: from Bio import Medline [as 别名]
# 或者: from Bio.Medline import read [as 别名]
 def test_medline_from_url(self):
     """Test Entrez into Medline.read from URL"""
     handle = Entrez.efetch(db="pubmed", id="19304878", rettype="medline", retmode="text")
     self.assertTrue(handle.url.startswith(URL_HEAD + "efetch.fcgi?"), handle.url)
     self.assertTrue(URL_TOOL in handle.url)
     self.assertTrue(URL_EMAIL in handle.url)
     self.assertTrue("id=19304878" in handle.url)
     record = Medline.read(handle)
     handle.close()
     self.assertTrue(isinstance(record, dict))
     self.assertEqual("19304878", record["PMID"])
     self.assertEqual("10.1093/bioinformatics/btp163 [doi]", record["LID"])

# 需要导入模块: from Bio import Medline [as 别名]
# 或者: from Bio.Medline import read [as 别名]
 def test_pubmed_16381885(self):
     """Bio.TogoWS.entry("pubmed", "16381885")"""
     # Gives Medline plain text
     handle = TogoWS.entry("pubmed", "16381885")
     data = Medline.read(handle)
     handle.close()
     self.assertEqual(data["TI"], "From genomics to chemical genomics: new developments in KEGG.")
     self.assertEqual(
         data["AU"],
         [
             "Kanehisa M",
             "Goto S",
             "Hattori M",
             "Aoki-Kinoshita KF",
             "Itoh M",
             "Kawashima S",
             "Katayama T",
             "Araki M",
             "Hirakawa M",
         ],
     )

# 需要导入模块: from Bio import Medline [as 别名]
# 或者: from Bio.Medline import read [as 别名]
def fetch_from_entrez(index, cache_dir=False):
    logger = logging.getLogger('build')

    # slugify the index for the cache filename (some indices have symbols not allowed in file names (e.g. /))
    index_slug= slugify(index)
    cache_file_path = '{}/{}'.format('/'.join(cache_dir), index_slug)

    # try fetching from cache
    if cache_dir:
        d = fetch_from_cache(cache_dir, index_slug)
        if d:
            logger.info('Fetched {} from cache'.format(cache_file_path))
            return d
    
    # if nothing is found in the cache, use the web API
    logger.info('Fetching {} from Entrez'.format(index))
    tries = 0
    max_tries = 5
    while tries < max_tries:
        if tries > 0:
            logger.warning('Failed fetching {}, retrying'.format(full_url))
            
        try:
            Entrez.email = '[email protected]'
            handle = Entrez.efetch(
                db="pubmed", 
                id=str(index), 
                rettype="medline", 
                retmode="text"
            )
        except:
            tries += 1
            time.sleep(2)
        else:
            d = Medline.read(handle)

            # save to cache
            save_to_cache(cache_dir, index_slug, d)
            logger.info('Saved entry for {} in cache'.format(cache_file_path))
            return d

# 需要导入模块: from Bio import Medline [as 别名]
# 或者: from Bio.Medline import read [as 别名]
 def fetcher(self):
     handle = Entrez.efetch(db='pubmed', id=self.name, retmode='text', rettype='medline')
     return Medline.read(handle)