names_number = 0
for line in f:
if line[0] == ">":
#write new name to name file and phylip document
h.write(new_name + "\n")
g.write("\n" + new_name + " ")
#write this line to name file (minus >)
h.write(line.strip('>'))
#set up next name
names_number = names_number + 1
new_name = new_name[:-len(str(int(names_number)))] + str(names_number)
else:
g.write(''.join(line.split()))
dante.log ("Program ran: FASTAtoPHYLIPandNAMES.py")
dante.log ("Input file: " + file_name)
dante.log ("Output file 1: " + file_name_phylip)
dante.log ("Output file 2: " + file_name_names)
except:
traceback.print_exc(file=sys.stdout)
exit(0)
#TEST COMMAND
# python link/dante/FASTAtoPHYLIPandNAMES.py link/dante/testfiles/TestAlign.fasta
#REQUIRES BIOPYTHON TO BE INSTALLED
#REQUIRES DANTE MODULE
import sys #for helping with command line interface
import dante #main dante functions
import traceback #for helping with errors
try:
dante.log("Running BLAST_Summary.py")
#allows multiple inputs at command line or will ask for an input file
#gets a list of fasta files
for filename in dante.makeFileList(sys.argv):
file_name_new = dante.makeNewFileName ("Desktop/Output", filename,".summary.tsv")
dante.log(str("Original File Name: " + filename))
dante.log(str("New File Name: " + file_name_new))
dante.BLASTSummary(filename, file_name_new)
print "_____Summary_____"
print "For filename: ", filename
print "Output file: ", file_name_new
except:
traceback.print_exc(file=sys.stdout)
dante.log(traceback.format_exc())
exit(0)
#REQUIRES BIOPYTHON TO BE INSTALLED
#REQUIRES NCBI+ TO BE INSTALLED
#REQUIRES DANTE MODULE
from Bio.Blast import NCBIXML
from Bio.Blast.Applications import NcbiblastnCommandline
import sys #for helping with command line interface
import dante #main dante functions
import traceback #for helping with errors
try:
dante.log("Running BLAST.GetCloseReps.py")
#Get search information from user
rep_number = dante.getNumber("How many representatives do you want?")
dante.log("How many representatives do you want?")
dante.log(rep_number)
database = str(raw_input("Which database do you want to search?"))
dante.log("Which database do you want to search?")
blast_db_format = 5 #exports hits as XML
dante.log("Database format")
dante.log(blast_db_format)
#allows multiple inputs at command line or will ask for an input file
#gets a list of fasta files
for filename in dante.makeFileList(sys.argv):
dante.log("Input Filename")
dante.log(filename)
file_name_xml = dante.makeNewFileName("Desktop/Output", filename, str(".BLAST." + database + ".top" + str(rep_number) + "hits.xml"))
result_handle = open(filename,'r') #open the xml file for reading
blast_records = NCBIXML.parse(result_handle) #parses the file to a blast_records object
total = 0
for record in blast_records: #go through every record generated
for alignment in record.alignments:
name_set.add(alignment.title.split('|')[1]) #adds id number to set (removes duplicates)
new_file = dante.makeNewFileName ('Desktop/Output', filename, "seqs.fasta")
with open(new_file,'w') as f:
for value in name_set: #walks through every id number
#Biopython for retreving fasta files
handle = Entrez.efetch(db="nucleotide", id=value, rettype="fasta", retmode="text")
f.write(handle.read())
dante.log("Program Ran: BlastXMLtoFasta.py")
dante.log("Input file: " + filename)
dante.log("Output file:" + new_file)
except:
traceback.print_exc(file=sys.stdout)
exit(0)
#Test File
# python link/dante/BlastXMLtoFasta.py link/dante/testfiles/TestBLAST.xml
