Merge pull request #125 from McTavishLab/api-key

Api key

bin/physcraper_run.py

@@ -34,6 +34,8 @@
 parser.add_argument("-db", "--blast_db", help="local download of blast database")
 parser.add_argument("-u", "--blast_url", help="a URL for your own mirrored blast database")
 parser.add_argument("-e","--email", help="email address for ncbi blast searches")
+parser.add_argument("-ak","--api_key", help="ncbi api key")
+
 parser.add_argument("-ev","--eval", help="blast evalue cutoff")
 parser.add_argument("-hl","--hitlist_len", help="number of blast searches to save per taxon")
 
@@ -46,7 +48,7 @@
 
 parser.add_argument("-tx","--taxonomy", help="path to taxonomy")
 
-parser.add_argument("-v","--verbose", help="OpenTree study id")
+parser.add_argument("-v","--verbose", action="store_true", help="OpenTree study id")
 
 
 
@@ -130,6 +132,9 @@
 if args.email:
     conf.email = args.email
 
+if args.api_key:
+    conf.api_key = args.api_key
+
 sys.stdout.write("Configuration Settings\n")
 sys.stdout.write(conf.config_str()+"\n")
 

docs/LocalDB.md

@@ -2,6 +2,15 @@ Blast Utilities
 
 ## Create an NCBI API key
 
+Generating an NCBI API key will speed up downloading full sequences following blast searches.
+See (NCBI API keys for details)[https://ncbiinsights.ncbi.nlm.nih.gov/2017/11/02/new-api-keys-for-the-e-utilities/]
+
+You can add your api key to your config using
+
+    Entrez.api_key = <apikey>
+
+or as a flag in your physcraper_run script --api_key 
+
 
 
 ### To Update or download blast DB:

docs/examples/example.config

@@ -6,7 +6,10 @@
 
 [blast]
 #Use your email address, please, this is just for NCBI records
-Entrez.email = ejmctavish@gmail.com
+Entrez.email = None
+
+#You can speed up the NCBI calls by generating a personal API key
+Entrez.api_key = None
 
 #The statistcal cutoff for matches
 e_value_thresh = 0.001

physcraper/configobj.py

@@ -87,6 +87,7 @@ def set_defaults(self):
         self.delay = 90
         self.spp_threshold = 5
         self.minlen = 0.8
+        self.api_key = None
         self.maxlen = 1.2
         self.taxonomy_dir = "{}/taxonomy".format(physcraper_dir)
         self.ott_ncbi = "{}/ott_ncbi".format(self.taxonomy_dir)
@@ -127,10 +128,15 @@ def read_config(self, configfi, interactive):
         config.read_file(open(configfi))
 
         # read in blast settings
-        self.email = config["blast"]["Entrez.email"]
+        self.email = config["blast"].get("Entrez.email")
         if not "@" in self.email:
             sys.stderr.write("your email `%s` does not have an @ sign. NCBI blast requests an email address.\n" % self.email)
-
+        if config["blast"].get("Entrez.api_key"):
+            self.api_key = config["blast"]["Entrez.api_key"]
+            if self.api_key == 'None':
+                self.api_key = None
+        else:
+            self.api_key = None
         self.e_value_thresh = config["blast"]["e_value_thresh"]
         assert is_number(self.e_value_thresh), (
                 "value `%s` does not exists" % self.e_value_thresh

physcraper/ids.py

@@ -203,6 +203,8 @@ def entrez_efetch(self, gb_id):
         """
         tries = 10
         Entrez.email = self.config.email
+        if self.config.api_key:
+            Entrez.api_key = self.config.apikey
         handle = None
 
         # method needs delay because of ncbi settings