@@ -3,5 +3,5 @@ '''first script featured on the website like a hello world''' -myDNA = "ACGTACGTACGTACGTACGTACGT" -print(myDNA) \ No newline at end of file +dna = "ACGTACGTACGTACGTACGTACGT" +print(dna) scripts/original_scripts/3.0/code_01.py @@ -3,10 +3,10 @@ '''second script available, shows a simple way to concatenate two DNA sequences, strings''' -myDNA = "ACGTACGTACGTACGTACGTACGT" -myDNA2 = "TCGATCGATCGATCGATCGA" +dna = "ACGTACGTACGTACGTACGTACGT" +dna2 = "TCGATCGATCGATCGATCGA" print("First and Second sequences") -print(myDNA, myDNA2) -myDNA3 = myDNA + myDNA2 +print(dna, dna2) +dna3 = dna + dna2 print("Concatenated sequence") -print(myDNA3) \ No newline at end of file +print(dna3) scripts/original_scripts/3.0/code_02.py @@ -8,7 +8,7 @@ regex module to transcribe DNA to RNA import re #setting the DNA string -myDNA = 'ACGTTGCAACGTTGCAACGTTGCA' +dna = 'ACGTTGCAACGTTGCAACGTTGCA' #assigning a new regex and compiling it #to find all Ts @@ -16,6 +16,6 @@ regexp = re.compile('T') #create a new string tha will receive #the regex result with Us replacing Ts -myRNA = regexp.sub('U', myDNA) +rna = regexp.sub('U', dna) -print(myRNA) \ No newline at end of file +print(rna) scripts/original_scripts/3.0/code_03.py @@ -10,4 +10,4 @@ file = open(dnafile, 'r') #printing each line of the file for line in file: - print(line, end = '') + print(line, end='') scripts/original_scripts/3.0/code_04.py @@ -3,5 +3,5 @@ '''first script featured on the website like a hello world''' -myDNA = "ACGTACGTACGTACGTACGTACGT" -print myDNA \ No newline at end of file +dna = "ACGTACGTACGTACGTACGTACGT" +print dna scripts/original_scripts/code_01.py @@ -3,10 +3,10 @@ '''second script available, shows a simple way to concatenate two DNA sequences, strings''' -myDNA = "ACGTACGTACGTACGTACGTACGT" -myDNA2 = "TCGATCGATCGATCGATCGA" +dna = "ACGTACGTACGTACGTACGTACGT" +dna2 = "TCGATCGATCGATCGATCGA" print "First and Second sequences" -print myDNA, myDNA2 -myDNA3 = myDNA + myDNA2 +print dna, dna2 +dna3 = dna + dna2 print "Concatenated sequence" -print myDNA3 \ No newline at end of file +print dna3 scripts/original_scripts/code_02.py @@ -8,7 +8,7 @@ regex module to transcribe DNA to RNA import re #setting the DNA string -myDNA = 'ACGTTGCAACGTTGCAACGTTGCA' +dna = 'ACGTTGCAACGTTGCAACGTTGCA' #assigning a new regex and compiling it #to find all Ts @@ -16,6 +16,6 @@ regexp = re.compile('T') #create a new string tha will receive #the regex result with Us replacing Ts -myRNA = regexp.sub('U', myDNA) +rna = regexp.sub('U', dna) -print myRNA \ No newline at end of file +print rna scripts/original_scripts/code_03.py @@ -20,25 +20,25 @@ for line in file: seqlist = list(sequence) #initializing integers to store the counts -totalA = 0 -totalC = 0 -totalG = 0 -totalT = 0 +total_a = 0 +total_c = 0 +total_g = 0 +total_t = 0 #checking each item in the list and updating counts for base in seqlist: if base == 'A': - totalA += 1 + total_a += 1 elif base == 'C': - totalC += 1 + total_c += 1 elif base == 'G': - totalG += 1 + total_g += 1 elif base == 'T': - totalT += 1 + total_t += 1 -print str(totalA) + ' As found' -print str(totalC) + ' Cs found' -print str(totalG) + ' Gs found' -print str(totalT) + ' Ts found' +print str(total_a) + ' As found' +print str(total_c) + ' Cs found' +print str(total_g) + ' Gs found' +print str(total_t) + ' Ts found' scripts/original_scripts/code_07.py @@ -13,14 +13,14 @@ seqlist = open(dnafile, 'r').readlines() temp = ''.join(seqlist) #counting -totalA = temp.count('A') -totalC = temp.count('C') -totalG = temp.count('G') -totalT = temp.count('T') +total_a = temp.count('A') +total_c = temp.count('C') +total_g = temp.count('G') +total_t = temp.count('T') #printing results -print str(totalA) + ' As found' -print str(totalC) + ' Cs found' -print str(totalG) + ' Gs found' -print str(totalT) + ' Ts found' +print str(total_a) + ' As found' +print str(total_c) + ' Cs found' +print str(total_g) + ' Gs found' +print str(total_t) + ' Ts found' scripts/original_scripts/code_08.py @@ -24,10 +24,10 @@ while fileentered == True: #remove carriage returns sequence = sequence.replace('\n', '') #counting - totalA = sequence.count('A') - totalC = sequence.count('C') - totalG = sequence.count('G') - totalT = sequence.count('T') + total_a = sequence.count('A') + total_c = sequence.count('C') + total_g = sequence.count('G') + total_t = sequence.count('T') #create a regex object with non-nucleotide letters to check for "errors" otherletter = re.compile('[BDEFHIJKLMNOPQRSUVXZ]+') #find possible non-nucleotides @@ -36,10 +36,10 @@ while fileentered == True: output = open(filename + '.count', 'w') #writing the output output.write('Count report for file ' + filename + '\n') - output.write('A = ' + str(totalA) + '\n') - output.write('C = ' + str(totalC) + '\n') - output.write('G = ' + str(totalG) + '\n') - output.write('T = ' + str(totalT) + '\n') + output.write('A = ' + str(total_a) + '\n') + output.write('C = ' + str(total_c) + '\n') + output.write('G = ' + str(total_g) + '\n') + output.write('T = ' + str(total_t) + '\n') #if there are non-nucleotides in the sequence, report them if len(extra) > 0: output.write('Also were found ' + str(len(extra)) + ' errors\n') @@ -53,4 +53,4 @@ while fileentered == True: else: #if no filename entered, exit fileentered = False - sys.exit() \ No newline at end of file + sys.exit() scripts/original_scripts/code_09.py @@ -9,15 +9,15 @@ import sys def count_nucleotide_types(seq): '''counting nucleotides and returning a list with counts''' result = [] - totalA = seq.count('A') - totalC = seq.count('C') - totalG = seq.count('G') - totalT = seq.count('T') + total_a = seq.count('A') + total_c = seq.count('C') + total_g = seq.count('G') + total_t = seq.count('T') - result.append(totalA) - result.append(totalC) - result.append(totalG) - result.append(totalT) + result.append(total_a) + result.append(total_c) + result.append(total_g) + result.append(total_t) return result scripts/original_scripts/code_11.py @@ -5,7 +5,7 @@ extremely simple script to DNA transcription ''' -myDNA = 'ACGTTGCAACGTTGCAACGTTGCA' +dna = 'ACGTTGCAACGTTGCAACGTTGCA' #string buil-in replace method -myRNA = myDNA.replace('T', 'U') -print myRNA +rna = dna.replace('T', 'U') +print rna scripts/original_scripts/code_16.py @@ -10,7 +10,7 @@ def read_fasta(file): if line.startswith(">"): if index >= 1: items.append(aninstance) - index+=1 + index += 1 name = line[:-1] seq = '' aninstance = Fasta(name, seq) @@ -19,4 +19,4 @@ def read_fasta(file): aninstance = Fasta(name, seq) items.append(aninstance) - return items \ No newline at end of file + return items scripts/original_scripts/code_26.py @@ -5,14 +5,15 @@ import fasta file = sys.argv[1] temp = file.split('.') -filename = temp[0] +filename_base = temp[0] tag = temp[1] sequences = fasta.read_fasta(open(file, 'r').readlines()) count = 1 for i in sequences: - output = open(filename+'_'+str(count)+'.'+tag, 'w') - output.write(i.name+'\n') + f = filename_base + '_' + str(count) + '.' + tag + output = open(f, 'w') + output.write(i.name + '\n') output.write(i.sequence) - count += 1 \ No newline at end of file + count += 1 scripts/original_scripts/code_27.py @@ -4,4 +4,4 @@ import fasta import sys data = fasta.read_seqs(open(sys.argv[1], 'r').readlines()) -print map(lambda seq:len(seq), data) +print [len(seq) for seq in data] scripts/original_scripts/code_30.py @@ -18,13 +18,13 @@ for line in open(file, 'r'): segment.append(line.strip()) linesize = len(line.strip()) -startline = (start/linesize) + 1 -endline = (end/linesize)+1 +startline = (start / linesize) + 1 +endline = (end / linesize) + 1 if not start % linesize == 0 and not end % linesize == 0: segment[0] = segment[0][startline*linesize-start:] segment[-1] = segment[-1][endline*linesize-end:] -elif not start %linesize == 0: +elif not start % linesize == 0: segment[0] = segment[0][startline*linesize-start:] elif not end % linesize == 0: segment[-1] = segment[-1][endline*linesize-end:] scripts/original_scripts/code_32.py @@ -1,4 +1,5 @@ from collections import defaultdict + def merge_seqs(data1, data2): first, second = defaultdict(list), defaultdict(list) for i in data1: @@ -11,8 +12,8 @@ def merge_seqs(data1, data2): flist = [] for i in shared_ids: - cross = [(a,b) for a in first[i] for b in second[i]] - for j,k in cross: + cross = ((a,b) for a in first[i] for b in second[i]) + for j, k in cross: tempname = j.name + ‘-’ + k.name + ‘->’ + str(len(j.sequence)) tempseq = j.sequence + k.sequence flist.append(tempname + ‘\n’ + tempseq) scripts/original_scripts/code_38.py @@ -1,4 +1,5 @@ from collections import defaultdict + def merge_seqs(data1, data2): first, second = defaultdict(list), defaultdict(list) for i in data1: @@ -11,8 +12,8 @@ def merge_seqs(data1, data2): flist = [] for i in shared_ids: - cross = [(a,b) for a in first[i] for b in second[i]] - for j,k in cross: + cross = ((a,b) for a in first[i] for b in second[i]) + for j, k in cross: tempname = j.name + '-' + k.name + '->'’ + str(len(j.sequence)) tempseq = j.sequence + k.sequence flist.append(tempname + '\n' + tempseq) scripts/original_scripts/code_39.py b7780f146067326205fa47fec7a5389cfa67da37 Paulo Nuin nuin@iMacNuin.gateway.2wire.net http://github.com/nuin/beginning-python-for-bioinformatics/commit/b33813f4ec11a59a5c6381cc5b78044824d25e3f b33813f4ec11a59a5c6381cc5b78044824d25e3f 2009-01-31T09:41:49-08:00 2009-01-31T09:41:49-08:00 patch applied, PEP 8 compliant 43d7d8ec8483baf35959861d1b5850c0c5604b5e Paulo Nuin nuin@iMacNuin.gateway.2wire.net