example remote config

docs/examples/data_scrape.py

@@ -12,7 +12,7 @@
 )
 import dendropy
 
-configfi = "tests/data/ncbiblast.config"
+configfi = "docs/examples/example.config"
 study_id = "ot_350"
 tree_id = "Tr53297"
 workdir ="scrape_ot_350"

docs/examples/example.config

@@ -0,0 +1,73 @@
+### never have in-line comments in this file
+
+
+#######
+## BLAST SETTINGS
+
+[blast]
+#Use your email address, please, this is just for NCBI records
+Entrez.email = ejmctavish@gmail.com
+
+#The statistcal cutoff for matches
+e_value_thresh = 0.001
+
+# the max number of matches for each blast search
+hitlist_size = 25
+
+# define location for blast database, should be local for the moment.
+location = remote
+#Options [local, remote]
+
+# if location = local, localblastdb path must be absolute path '/'
+localblastdb = /shared/localblastdb_meta/
+
+
+# if location = remote:
+#default url_base is ncbi, to run on AWS set url here
+#url_base =
+
+# number of cores to use
+num_threads = 8
+
+
+# when to reblast the included sequences
+delay = 90
+
+#######
+## PHYSCRAPER SETTINGS
+
+[physcraper]
+# what to do whith tips from OToL that are not known: unmapped remove: remove tips, keep = set to id of mrca
+unmapped = keep
+
+#This is how much shorter new sequences are allowed to be compared to your original sequence lengths when added to aln. Is used in during the process of adding new seqs as well as removing seq that are too short
+seq_len_perc = 0.8
+
+# value that determines how many seq need to be present before the beginning and end of alignment will be trimmed
+trim_perc = 0.75
+
+# max length for values to add to aln
+max_len = 2.5
+
+
+#######
+## INTERNAL PHYSCRAPER SETTINGS
+#---------------------------------------------------------------------------------
+#Things below here you should not need to change!
+
+#Only required if blast location is local
+[ncbi_parser]
+nodes_fn = ./taxonomy/nodes.dmp
+names_fn = ./taxonomy/names.dmp
+
+[phylesystem]
+location = api
+#local or api, leave set to api unless you have installed phylesystem locally
+
+[taxonomy]
+#You should not need to change any of these!
+ott_ncbi = taxonomy/ott_ncbi
+get_ncbi_taxonomy = taxonomy/get_ncbi_taxonomy.sh
+ncbi_dmp = taxonomy/gi_taxid_nucl.dmp
+id_pickle = taxonomy/id_dmp.p
+