keep asking for files if they don't exist, filter melting temperature with updated function

3 files changed, 99 insertions, 67 deletions

diff --git a/SelectiveWholeGenomeAmplification b/SelectiveWholeGenomeAmplification
index f6269d5..c92f850 100755
--- a/SelectiveWholeGenomeAmplification
+++ b/SelectiveWholeGenomeAmplification
@@ -121,6 +121,12 @@ done
 : ${max_melting_temp=30}
 : ${min_melting_temp=0}
 
+# Concentrations of solution
+: ${dna_con=5000}
+: ${na_con=10}
+: ${mg_con=20}
+: ${dntps_con=10}
+
 # minimum average binding distance in the foreground
 : ${min_foreground_binding_average=50000}
 
diff --git a/SelectiveWholeGenomeAmplificationUI b/SelectiveWholeGenomeAmplificationUI
index decf5a1..c969d63 100755
--- a/SelectiveWholeGenomeAmplificationUI
+++ b/SelectiveWholeGenomeAmplificationUI
@@ -1,4 +1,6 @@
 #!/usr/bin/env python
+import os.path
+
 foreground = ""
 background = ""
 
@@ -7,57 +9,61 @@ yes_no = {'Y': True, 'y': True,'n': False, 'N': False, 'yes': True, 'no': False,
 variables = {}
 
 questions = [
-	{ 'question' : "Where would you like your output directory to be?", 
-	  'default_str': 'current directory/foreground_background/',
-	  'variable': 'output_directory' },
-
-	{'question': "Where would you like to temporary files to be stored?",
-	 'default_str': '$output_directory/.tmp',
-	 'variable': "temp_directory" },
-
-	{'question': "Where would you like to count files to be stored?",
-	 'default_str': '$output_directory/.tmp',
-	 'variable': "counts_directory" },
-
-	{ 'question': 'maximum mer size you would like to pick?',
-	  'default_str': '12',
-	  'variable': 'max_mer_range' },
-
-	{ 'question': 'minimum mer size you would like to pick?',
-	  'default_str': '6',
-	  'variable': 'min_mer_range' },
-
-	{ 'question': 'eliminate mers that appear less frequently on average than this number ?',
-	  'default_str': '50000',
-	  'variable': 'min_foreground_binding_average' },
-
-	{ 'question': 'maximum size of mer combinations you want to search and select?',
-	  'default_str': '15',
-	  'variable': 'max_select' },
-
-	{ 'question': 'maximum number of mers you want to use as possible primers?',
-	  'default_str': '35',
-	  'variable': 'max_check' },
-
-	{'question': 'enter mers to ignore? (space seperated)',
-	 'default_str': "None",
-	 'variable': 'ignore_mers'},
-
-	{'question': 'enter files to ignore all mers from? (space seperated)',
-	 'default_str': "None",
-	 'variable': 'ignore_all_mers_from_files'},
-
-	{ 'question': 'maximum distance between mers in the final selection?',
-	  'default_str': "5000 bases",
-	  'variable': 'max_mer_distance' },
-
-	{ 'question': 'maximum melting temperature for mers?', 'default_str': '30c', 'variable': 'max_melting_temp' },
-	{ 'question': 'minimum melting temperature for mers?', 'default_str': '0c',  'variable': 'min_melting_temp' },
-	{ 'question': 'maximum number of consecutively binding mers in hetero and homodimers?', 'default_str': '4', 'variable': 'max_consecutive_binding' },
-	{ 'question': 'what extra weight do you want for highgly binding primers? (0-1)', 'default_str': '0', 'variable': 'fg_weight' },
-  { 'question': 'what extra weight do you want for sets with a higher number of primers? (0-1)', 'default_str': '0', 'variable': 'primer_weight'},
-	{ 'question': 'how many scored sets would you like in the top_scored_sets output file?', 'default_str':'10000', 'variable': 'output_top_nb'},
-	{ 'question': 'would you like to use a custom scoring function? see README.md for details', 'default_str':'', 'variable': 'score_func'}
+	{ 'q' : "Where would you like your output directory to be?", 
+	  'def': 'current directory/foreground_background/',
+	  'v': 'output_directory' },
+
+	{'q': "Where would you like to temporary files to be stored?",
+	 'def': '$output_directory/.tmp',
+	 'v': "temp_directory" },
+
+	{'q': "Where would you like to count files to be stored?",
+	 'def': '$output_directory/.tmp',
+	 'v': "counts_directory" },
+
+	{ 'q': 'maximum mer size you would like to pick?',
+	  'def': '12',
+	  'v': 'max_mer_range' },
+
+	{ 'q': 'minimum mer size you would like to pick?',
+	  'def': '6',
+	  'v': 'min_mer_range' },
+
+	{ 'q': 'eliminate mers that appear less frequently on average than this number ?',
+	  'def': '50000',
+	  'v': 'min_foreground_binding_average' },
+
+	{ 'q': 'maximum size of mer combinations you want to search and select?',
+	  'def': '15',
+	  'v': 'max_select' },
+
+	{ 'q': 'maximum number of mers you want to use as possible primers?',
+	  'def': '35',
+	  'v': 'max_check' },
+
+	{'q': 'enter mers to ignore? (space seperated)',
+	 'def': "None",
+	 'v': 'ignore_mers'},
+
+	{'q': 'enter files to ignore all mers from? (space seperated)',
+	 'def': "None",
+	 'v': 'ignore_all_mers_from_files'},
+
+	{ 'q': 'maximum distance between mers in the final selection?',
+	  'def': "5000 bases",
+	  'v': 'max_mer_distance' },
+
+	{ 'q': 'maximum melting temperature for mers?', 'def': '30c', 'v': 'max_melting_temp' },
+	{ 'q': 'minimum melting temperature for mers?', 'def': '0c',  'v': 'min_melting_temp' },
+	{ 'q': 'DNA Concentration (nM)?', 'def': '5000nM',  'v': 'dna_con' },
+	{ 'q': 'Salt Concentration (mM) ?', 'def': '10mM',  'v': 'na_con' },
+	{ 'q': 'Magnesium Concentration (mM)?', 'def': '20mM',  'v': 'mg_con' },
+	{ 'q': 'dNTPs Concentration (mM) ?', 'def': '10mM',  'v': 'dntps_con' },
+	{ 'q': 'maximum number of consecutively binding mers in hetero and homodimers?', 'def': '4', 'v': 'max_consecutive_binding' },
+	{ 'q': 'what extra weight do you want for highgly binding primers? (0-1)', 'def': '0', 'v': 'fg_weight' },
+  { 'q': 'what extra weight do you want for sets with a higher number of primers? (0-1)', 'def': '0', 'v': 'primer_weight'},
+	{ 'q': 'how many scored sets would you like in the top_scored_sets output file?', 'def':'10000', 'v': 'output_top_nb'},
+	{ 'q': 'would you like to use a custom scoring function? see README.md for details', 'def':'', 'v': 'score_func'}
 ]
 
 def bool_ask(ask_string, default):
@@ -74,10 +80,10 @@ def bool_ask(ask_string, default):
 	return yes_no[ans]
 
 def ask(question_dict):
-	question = question_dict['question']
-	default_str = question_dict['default_str']
+	question = question_dict['q']
+	default = question_dict['def']
 
-	ask_string = question + " (Default=" + str(default_str) + ")" + ": "
+	ask_string = question + " (Default=" + str(default) + ")" + ": "
 
 	ans = raw_input(ask_string)
 	return ans 
@@ -100,6 +106,16 @@ def run(variables_as_a_string):
 	except:
 		pass
 
+def file_ask(query):
+	response = None
+	while response is None:
+		response = raw_input(query)
+		if os.path.isfile(response) is not True:
+			print "That file doesn't exist."
+			response = None
+
+	return response
+
 
 if(bool_ask("would you like to input all your variables at once?", "n")):
 	variables = raw_input("Please paste in your variables (space delimited) and Run:")
@@ -110,14 +126,14 @@ if(bool_ask("would you like to input all your variables at once?", "n")):
 else:
 	for q in questions:
 		if 'bool' in q:
-			res = ask_bool(q['question'], q['default'])
+			res = ask_bool(q['q'], q['def'])
 		else:
 			res = ask(q)
 
-		variables[q['variable']] = res 
+		variables[q['v']] = res 
 
-	foreground = raw_input("Input the path to your foreground file:")
-	background = raw_input("Input the path to your background file:")
+	foreground = file_ask("Input the path to your foreground file:")
+	foreground = file_ask("Input the path to your background file:")
 
 	if(bool_ask("Would you like to output your inserted variables to a string you can later paste?", "y")):
 		print variables_to_string(variables)
diff --git a/src/filter_melting_temperature.py b/src/filter_melting_temperature.py
index 26f6b54..b452b92 100644
--- a/src/filter_melting_temperature.py
+++ b/src/filter_melting_temperature.py
@@ -1,10 +1,11 @@
 #!/usr/bin/env python
+import argparse
 import sys
+import math
 
 """Calculate the thermodynamic melting temperatures of nucleotide sequences."""
 
-import math
-def Tm_staluc(s, dnac=5000, na=10, mg=20, dNTPs=10):
+def Tm_staluc(s, dna=5000, na=10, mg=20, dntps=10):
 		"""Returns DNA/DNA tm using nearest neighbor thermodynamics.
 
 		dnac is DNA concentration [nM]
@@ -73,7 +74,7 @@ def Tm_staluc(s, dnac=5000, na=10, mg=20, dNTPs=10):
 		vsTC,vh = tercorr(sup)
 		vs = vsTC
 		
-		k = (dnac/4.0)*1e-9
+		k = (dna/4.0)*1e-9
 		#With complementary check on, the 4.0 should be changed to a variable.
 		
 		#DNA/DNA
@@ -102,10 +103,10 @@ def Tm_staluc(s, dnac=5000, na=10, mg=20, dNTPs=10):
 		tm = ((1000* (-dh))/(-ds+(R * (math.log(k)))))-273.15
 		Mmg = mg * 1E-3
 		Mna = na * 1E-3
-		Mdntp = dNTPs * 1E-3
+		Mdntp = dntps * 1E-3
 
-		Fmg = ((3E4 * Mdntp - 3E4 * Mmg + 1) + ((3E4 * Mdntp - 3E4 * Mmg + 1)**2 + 4 * 3E4 * Mmg)**0.5 )/ (2 * 3E4)
-		cationratio = - Fmg**0.5 / Mna
+		Fmg = (-(3E4 * Mdntp - 3E4 * Mmg + 1) + ((3E4 * Mdntp - 3E4 * Mmg + 1)**2 + 4 * 3E4 * Mmg )**0.5 )/ (2 * 3E4)
+		cationratio = Fmg**0.5 / Mna
 		
 		if cationratio < 0.22:
 			SaltCorrectedTm = 1 / ( (1 / tm) + ((4.29 * fgc(s) - 3.95) * math.log(Mna) + 0.940 * (math.log(Mna))**2) * 1E-5 )
@@ -141,11 +142,20 @@ def in_temp_range(kmer):
 
 	return min_melting_temp < melt_temp < max_melting_temp
 
-min_melting_temp = float(sys.argv[1])
-max_melting_temp = float(sys.argv[2])
 
 
 if __name__ == "__main__":
+
+	parser = argparse.ArgumentParser(description="Filter mers, input is stdin, output is stdout") 
+	parser.add_argument("-m", "--min", help="min melting temp [c]", required=True, type=float)
+	parser.add_argument("-x", "--max", help="max melting temp [c]", required=True, type=float)
+	parser.add_argument("-d", "--dna", help="DNA concentation [nM]", required=False, type=int, default=5000)
+	parser.add_argument("-n", "--na", help="sodium concentation [mM]", required=False, type=int, default=10)
+	parser.add_argument("-g", "--mg", help="magnesium concentation [mM]", required=False, type=int, default=20)
+	parser.add_argument("-p", "--dntp", help="dNTPs concentation [mM]", required=False, type=int, default=10)
+
+	ar = parser.parse_args()
+
 	for line in sys.stdin:
-		if min_melting_temp < Tm_staluc(line.split("\t")[0]) < max_melting_temp:
+		if ar.min < Tm_staluc(line.split("\t")[0], dna=ar.dna, na=ar.na, mg=ar.mg, dntps=ar.dntp) < ar.max:
 			sys.stdout.write(line)