diff options
| -rwxr-xr-x | SelectiveWholeGenomeAmplificationGUI | 223 |
1 files changed, 223 insertions, 0 deletions
diff --git a/SelectiveWholeGenomeAmplificationGUI b/SelectiveWholeGenomeAmplificationGUI new file mode 100755 index 0000000..40d3ffc --- /dev/null +++ b/SelectiveWholeGenomeAmplificationGUI @@ -0,0 +1,223 @@ +#!/usr/bin/env python2.7 +import os.path + +def run_generic(cmd): + ''' + get the length of a fasta file by piping it through several unix + programs. + + 1) remove headers by grepping for any ">" at the start of a line + 2) delete all occurances of a new line, to join sequences together + 3) sum the number of characters. + ''' + from subprocess import Popen + from subprocess import PIPE + + fh = Popen(cmd, stdout=PIPE, shell=True, executable='/bin/bash') + + return fh.stdout.readlines() + +foreground = "" +background = "" + +yes_no = {'Y': True, 'y': True,'n': False, 'N': False, 'yes': True, 'no': False, '': '' } + +variables = {} + +questions = [ + { 'q' : "what is your foreground fasta file?", + 'def': '', + 'tab': 'file', + 'v': 'foreground', + 't': 'file'}, + + { 'q' : "what is your background fasta file?", + 'def': '', + 'v': 'background', + 'tab': 'file', + 't': 'file'}, + + { 'q' : "Where would you like your output directory to be?", + 'def': 'current directory/foreground_background/', + 'v': 'output_directory', + 'tab': 'file', + 't': 'dir'}, + + {'q': "Where would you like to temporary files to be stored?", + 'def': '$output_directory/.tmp', + 'v': "temp_directory", + 'tab': 'file', + 't': 'dir'}, + + {'q': "Where would you like to count files to be stored?", + 'def': '$output_directory/.tmp', + 'v': "counts_directory", + 'tab': 'file', + 't': 'dir' }, + + { 'q': 'maximum mer size you would like to pick?', + 'def': '12', + 'v': 'max_mer_range', + 'tab': 'filter', + 't': 'int'}, + + { 'q': 'minimum mer size you would like to pick?', + 'def': '6', + 'v': 'min_mer_range', + 'tab': 'filter', + 't': 'int'}, + + { 'q': 'eliminate mers that appear on average less than this ?', + 'def': '50000', + 'v': 'min_foreground_binding_average', + 'tab': 'filter', + 't': 'int'}, + + { 'q': 'maximum size of mer combinations you want to search and select?', + 'def': '15', + 'v': 'max_select', + 'tab': 'filter', + 't': 'int'}, + + { 'q': 'maximum number of mers you want to use as possible primers?', + 'def': '35', + 'v': 'max_check', + 'tab': 'filter', + 't': 'int'}, + + {'q': 'enter mers to ignore? (space seperated)', + 'def': "None", + 'v': 'ignore_mers', + 'tab': 'filter', + 't': 'str'}, + + {'q': 'enter files to ignore all mers from? (space seperated)', + 'def': "None", + 'v': 'ignore_all_mers_from_files', + 'tab': 'filter', + 't': 'file', + 'opt': 'multiple'}, + + { 'q': 'maximum distance between mers in the final selection?', + 'def': "5000", + 'v': 'max_mer_distance', + 'tab': 'filter', + 't': 'int'}, + + { 'q': 'minimum background ratio?', + 'def': "None", + 'v': 'min_bg_ratio', + 'tab': 'filter', + 't': 'int'}, + + { 'q': 'maximum melting temperature for mers?', 'def': '30c', 'v': 'max_melting_temp', 't': 'float', 'tab':'melting'}, + { 'q': 'minimum melting temperature for mers?', 'def': '0c', 'v': 'min_melting_temp', 't': 'float' , 'tab':'melting'}, + { 'q': 'DNA Concentration (nM)?', 'def': '5000nM', 'v': 'dna_con', 't':'float', 'tab':'melting' }, + { 'q': 'Salt Concentration (mM) ?', 'def': '10mM', 'v': 'na_con', 't':'float', 'tab':'melting' }, + { 'q': 'Magnesium Concentration (mM)?', 'def': '20mM', 'v': 'mg_con', 't':'float', 'tab':'melting'}, + { 'q': 'dNTPs Concentration (mM) ?', 'def': '10mM', 'v': 'dntps_con', 't':'float', 'tab':'melting'}, + { 'q': 'maximum number of consecutively binding mers in hetero and homodimers?', 'def': '4', 'v': 'max_consecutive_binding', 't':'int', 'tab':'filter' }, + { 'q': 'what extra weight do you want for highgly binding primers? (0-1)', 'def': '0', 'v': 'fg_weight', 't':'float', 'tab':'scoring'}, + { 'q': 'what extra weight do you want for sets with a higher number of primers? (0-1)', 'def': '0', 'v': 'primer_weight', 't':'float', 'tab':'scoring'}, + { 'q': 'how many scored sets would you like in the top_scored_sets output file?', 'def':'10000', 'v': 'output_top_nb', 't':'int', 'tab':'scoring'}, + { 'q': 'custom scoring function (see README.md for details) ', 'def':'', 'v': 'score_func', 't':'str', 'tab':'scoring'} +] + +def bool_ask(ask_string, default): + ans = "" + + ask_string = ask_string + " (Y/N/Default=" + str(default) + ")" + ": " + + ans = raw_input(ask_string) + while ans not in yes_no.keys(): + ans = raw_input(ask_string) + if ans is '': + ans = default + + return yes_no[ans] + +def ask(question_dict): + question = question_dict['q'] + default = question_dict['def'] + + ask_string = question + " (Default=" + str(default) + ")" + ": " + + ans = raw_input(ask_string) + return ans + +def variables_to_string(variables): + ret = "" + for variable in variables: + if variables[variable] is not '': + ret = ret + variable + "=\"" + variables[variable] + "\" " + + ret = ret + "foreground=\"" + foreground + "\" " + ret = ret + "background=\"" + background + "\" " + return ret + +def run(variables_as_a_string): + + import subprocess + try: + subprocess.check_call(variables_as_a_string + " " + "SelectiveWholeGenomeAmplification " + foreground + " " + background, shell=True) + except: + pass + +def yad_ask_all_questions(questions): + import random + + key = random.randint(0,100000) + + cmd_d = { + 'file': "yad --form --plug=" + str(key) + " --tabnum=1 ", + 'filter': "yad --form --plug=" + str(key) + " --tabnum=2 ", + 'melting': "yad --form --plug=" + str(key) + " --tabnum=3 ", + 'scoring': "yad --form --plug=" + str(key) + " --tabnum=4 " + } + container = 'yad --notebook --key=' + str(key) + ' --tab="Files" --tab="filter" --tab="Melting Temperature" --tab="Scoring" --title="Selective Genome Amplification Options" ' + shmcleanup = "ipcrm -M `printf 0x%0.8x "+ str(key) + "` 2> /dev/null" + + for q in questions: + qstr = '--field="' + q['q'] + " (" + q['v'] + ')":LBL ' + + # if it's a directory + if q['t'] is 'dir': + qstr += "--field=" + q['v'] + ":DIR" + + # if it's a file + elif q['t'] is 'file': + if 'opt' in q: + if q['opt'] is 'multiple': + qstr += "--field" + q['v'] + ":TXT" + else: + qstr += "--field=" + q['v'] + ":FL" + + elif q['t'] is 'bool': + qstr += "--field" + q['v'] + ":CHK" + + elif q['t'] is 'int': + qstr += "--field=" + q['v'] + ":NUM" + + elif q['t'] is 'float': + qstr += "--field=" + q['v'] + ":NUM" + elif q['t'] is 'txt': + qstr += "--field=" + q['v'] + ":TXT" + + elif q['t'] is 'str': + qstr += "--field=" + q['v'] + "" + + cmd_d[q['tab']] += qstr + " " + + cmd = "cat <( %s ) <( %s ) <( %s ) <( %s ) & %s; %s" % (cmd_d['file'], cmd_d['filter'], cmd_d['melting'], cmd_d['scoring'], container, shmcleanup) + + print cmd + res = run_generic(cmd) + return res + + +variable = yad_ask_all_questions(questions) +print variable + +print variables_to_string(variables) +run(variables_to_string(variables)) +raw_input("Press Enter to exit...") |