def alifeGuru(listem, folder_expr):
# within replicates alignment parameters
Dw = 2.0 # rt modulation [s]
Gw = 0.30 # gap penalty
# do the alignment
trees = []
expr_list = []
expr_dir = folder_expr
for gru_list in listem:
for item in gru_list:
print('Aligning...' + item)
file_name = os.path.join(expr_dir, item)
expr = load_expr(file_name)
expr_list.append(expr)
F1 = exprl2alignment(expr_list)
print('F1' + '\n')
print(F1)
trees.append(F1)
for t in trees:
T1 = PairwiseAlignment(t, Dw, Gw)
print('T1' + '\n')
print(T1)
A1 = align_with_tree(T1, min_peaks=2)
A1.write_csv(
'/home/cocopalacelove/Desktop/StrawberryExotic/output/Alignments/fullSpec_rt.csv',
'/home/cocopalacelove/Desktop/StrawberryExotic/output/Alignments/fullSpec_area.csv'
)
print(trees)
def aligner(exprs):
mod = 2.5
gp = 0.30
mA = 10.0
bG = []
T2 = []
for i, v in exprs.items():
F1 = exprl2alignment(v)
T1 = PairwiseAlignment(F1, mod, gp)
A1 = align_with_tree(T1, min_peaks=3)
T2.append(A1)
print(len(F1), F1)
print('bG=', bG)
print(T2)
T3 = PairwiseAlignment(T2, mA, gp)
A2 = align_with_tree(T3, min_peaks=4)
# T3 = PairwiseAlignment(T2, mA, gp)
A2.write_csv(
'/home/juicebox/Desktop/Acinis/CDFdata/all_csv/all_p120s30pe10n3_p34_rt.csv',
'/home/juicebox/Desktop/Acinis/CDFdata/all_csv/all_p120s30pe10n3_p34_area.csv'
)
def aligner(exprs, bers, names):
mod = 2.5
gp = 0.30
mA = 10.0
# print exprs
# print names
for dict, n, b in zip(exprs, names, bers):
print dict
print '\n'
print b
print n
print '\n'
#for item, na in zip(dict.items(), n.items()):
for item, v in dict.items():
print item
# print v
F1 = exprl2alignment(v)
T1 = PairwiseAlignment(F1, mod, gp)
A1 = align_with_tree(T1, min_peaks=2)
A1.write_csv(
'/home/juicebox/Desktop/Acinis/CDFdata/CDF/output/' + item +
'rt.csv', '/home/juicebox/Desktop/Acinis/CDFdata/CDF/output/' +
item + 'area.csv')
def multi_align_local(exprlist,
Dw,
Gw,
min_common=1,
tofile=True,
transposed=True):
global exprdir
global outdir
out_prefix = (datetime.datetime.now()).strftime("%Y-%m-%d-%H%M")
print "locally aligning peaks from ", exprdir
F1 = exprl2alignment(exprlist)
T1 = PairwiseAlignment(F1, Dw, Gw)
A1 = align_with_tree(T1, min_peaks=min_common)
if tofile == True:
ci_list = A1.common_ion()
if transposed == True:
A1.write_transposed_output(
os.path.join(exprdir, out_prefix + "_aligned_rt.xlsx"))
else:
A1.write_excel(
os.path.join(exprdir, out_prefix + "_aligned_rt.xlsx"))
A1.write_csv_dk(
os.path.join(exprdir, out_prefix + '_aligned_rt.csv'),
os.path.join(exprdir, out_prefix + '_aligned_area.csv'))
#A1.write_common_ion_csv( os.path.join(exprdir, out_prefix + '_area_common_ion.csv'), ci_list)
#A1.write_ion_areas_csv( os.path.join(exprdir, out_prefix + '_aligned_ions.csv') )
return A1
def aligner(exprs):
mod = 2.5
gp = 0.30
mA = 10.0
bG = []
T2 = []
for i in exprs:
F1 = exprl2alignment(i)
print(len(F1), F1)
bG.append(F1)
print('bG=', bG)
#count = 0
# for s in bG:
# #count += 1
# print('s=',s)
# T1 = PairwiseAlignment(s, mod, gp)
# T2.append[T1]
# print(T2)
groups = [[], [], [], [], [], [], [], [], []]
for s, g in zip(bG, groups):
#count += 1
print('s=', s)
g = PairwiseAlignment(s, mod, gp)
print('g=', g)
print(groups)
def singleAlign(exprs, dir, mod, gp, mp, nameTag):
#mod = 2.5
#gp = 0.30
F1 = exprl2alignment(exprs)
T1 = PairwiseAlignment(F1, mod, gp)
A1 = align_with_tree(T1, min_peaks=mp)
#A1.write_csv('/home/cocopalacelove/tmp/sb_out/A1a_rt.csv', '/home/cocopalacelove/tmp/sb_out/A1a_area.csv')
#A1.write_csv(str(dir)+"rasp2018_rt.csv", str(dir)+"rasp2018_area.csv")
#print(str(dir)+"rasp2018_rt.csv", str(dir)+"rasp2018_area.csv")
A1.write_csv(
str(dir) + nameTag + "_rt.csv",
str(dir) + nameTag + "_area.csv")
print(str(dir) + nameTag + "_rt.csv", str(dir) + nameTag + "_area.csv")
def alignAll(exprs, bers, names):
mod = 2.5
gp = 0.30
gp2 = 0.5
mA = 10.0
bG = []
Tall = []
for dict, n, b in zip(exprs, names, bers):
print('dict=', dict)
print '\n'
#print b
print('n=', n)
print '\n'
T2 = []
# for item, na in zip(dict.items(), n.items()):
for item, v in dict.items():
print('itemCount=', len(dict.items()))
print('item=', item)
# print v
F1 = exprl2alignment(v)
T1 = PairwiseAlignment(F1, mod, gp)
A1 = align_with_tree(T1, min_peaks=2)
T2.append(A1)
print('t2=', T2)
T3 = PairwiseAlignment(T2, mA, gp2)
A2 = align_with_tree(T3, min_peaks=3)
Tall.append(A2)
T4 = PairwiseAlignment(Tall, mA, gp2)
A3 = align_with_tree(T4, min_peaks=3)
#
# print'b='+str(b)
# print'n=' + str(n)
A3.write_csv(
'/home/juicebox/Desktop/Acinis/CDFdata/all_csv/all_10020pe2n3p233_rt.csv',
'/home/juicebox/Desktop/Acinis/CDFdata/all_csv/all_10020pe2n3p233_area.csv'
)
def repAlign(exprs, dir, mod1, mod2, gp1, gp2, mp1, mp2, nameTag):
"""
@summary: Converts experiments into alignments then models the pairwise alignments
The alignments are then aligned using the pairwise alignment object.
The alignment tree is then exported and saved as a .csv file
@param exprs: Dictionary containing .expr files and sample identifiers
@param dir: Directory to save the output alignment .csv files
@param mod1: Retention time tolerance, in seconds (inner-state)
@param mod2: Retention time tolerance, in seconds (between-state)
@param gp1: Gap penalty (inner-state)
@param gp2: Gap penalty (between-state)
@param mp1: Minimum peaks required (inner-state)
@param mp2: Minimum peaks required (between-state)
@param nameTag: Identifier for saving .csv file
@return: Two .csv files which express the similarities of each sample in retention time & peak area
"""
bG = []
T2 = []
for i, v in exprs.items():
F1 = exprl2alignment(v)
T1 = PairwiseAlignment(F1, mod1, gp1)
A1 = align_with_tree(T1, min_peaks=mp1)
T2.append(A1)
#print('v=', v)
#print("i=", i)
print(len(F1), F1)
print(T2)
T3 = PairwiseAlignment(T2, mod2, gp2)
A2 = align_with_tree(T3, min_peaks=mp2)
# T3 = PairwiseAlignment(T2, mA, gp)
A2.write_csv(
str(dir) + nameTag + '_rep_rt.csv',
str(dir) + nameTag + '_rep_area.csv')
print(
str(dir) + nameTag + '_rep_rt.csv',
str(dir) + nameTag + '_rep_area.csv')
def multi_align_local(exprlist, Dw, Gw, min_common=1, tofile=True, transposed=True):
global exprdir
global outdir
out_prefix = (datetime.datetime.now()).strftime("%Y-%m-%d-%H%M")
print "locally aligning peaks from ", exprdir
F1 = exprl2alignment(exprlist)
T1 = PairwiseAlignment(F1, Dw, Gw)
A1 = align_with_tree(T1, min_peaks=min_common)
if tofile == True:
ci_list = A1.common_ion()
if transposed == True:
A1.write_transposed_output(os.path.join(exprdir, out_prefix + "_aligned_rt.xlsx"))
else:
A1.write_excel(os.path.join(exprdir, out_prefix + "_aligned_rt.xlsx"))
A1.write_csv_dk( os.path.join(exprdir, out_prefix + '_aligned_rt.csv'), os.path.join(exprdir, out_prefix + '_aligned_area.csv') )
#A1.write_common_ion_csv( os.path.join(exprdir, out_prefix + '_area_common_ion.csv'), ci_list)
#A1.write_ion_areas_csv( os.path.join(exprdir, out_prefix + '_aligned_ions.csv') )
return A1
def align2(exprs, names, bers):
min = 1.5
mod = 2.5
gp = 0.30
#mA = 10.0
print()
for dict, n, b in zip(exprs, names, bers):
#print ('dict='+dict)
#print '\n'
#print ('b='+str(b))
print('b=' + str(b))
print '\n'
T2 = []
#for item, na in zip(dict.items(), n.items()):
for item, v in dict.items():
print('item=' + str(item))
# print v
F1 = exprl2alignment(v)
T1 = PairwiseAlignment(F1, min, gp)
A1 = align_with_tree(T1, min_peaks=2)
T2.append(A1)
T3 = PairwiseAlignment(T2, mod, gp)
A2 = align_with_tree(T3, min_peaks=2)
# print'b='+str(b)
# print'n=' + str(n)
A2.write_csv(
'/home/juicebox/Desktop/Acinis/CDFdata/CDF/output2/' + str(b) +
'_7035rt.csv',
'/home/juicebox/Desktop/Acinis/CDFdata/CDF/output2/' + str(b) +
'_7035area.csv')
def alife(exprZ, folder_expr):
# within replicates alignment parameters
Dw = 10.0 # rt modulation [s]
Gw = 0.30 # gap penalty
# do the alignment
expr_list = []
expr_dir = folder_expr
for expr_code in exprZ:
print('Aligning...' + expr_code)
file_name = os.path.join(expr_dir, expr_code)
expr = load_expr(file_name)
expr_list.append(expr)
F1 = exprl2alignment(expr_list)
print('F1' + '\n')
print(F1)
T1 = PairwiseAlignment(F1, Dw, Gw)
print('T1' + '\n')
print(T1)
A1 = align_with_tree(T1, min_peaks=2)
A1.write_csv(
'/home/cocopalacelove/Desktop/StrawberryExotic/output/Alignments/Allstar10_rt.csv',
'/home/cocopalacelove/Desktop/StrawberryExotic/output/Alignments/Allstar10_area.csv'
)
def singleAlign(exprs, dir, mod, gp, mp, nameTag):
"""
@summary: Converts experiments into alignments then models the pairwise alignments.
The alignments are then aligned using the pairwise alignment object.
The alignment tree is then exported and saved as a .csv file
@param exprs: List containing .expr files to be aligned
@param dir: Directory to save the output alignment .csv files
@param mod: Retention time tolerance, in seconds
@param gp: Gap penalty
@param mp: Minimum peaks required
@param nameTag: Identifier for saving .csv file
@return: Two .csv files which express the similarities of each sample in retention time & peak area
"""
F1 = exprl2alignment(exprs)
T1 = PairwiseAlignment(F1, mod, gp)
A1 = align_with_tree(T1, min_peaks=mp)
A1.write_csv(
str(dir) + nameTag + "_s_rt.csv",
str(dir) + nameTag + "_s_area.csv")
print(str(dir) + nameTag + "_s_rt.csv", str(dir) + nameTag + "_s_area.csv")
exprA_codes = ["a0806_077", "a0806_078", "a0806_079"]
exprB_codes = ["a0806_140", "a0806_141", "a0806_142"]
# within replicates alignment parameters
Dw = 2.5 # rt modulation [s]
Gw = 0.30 # gap penalty
# do the alignment
print 'Aligning expt A'
expr_list = []
expr_dir = "../61a/output/"
for expr_code in exprA_codes:
file_name = os.path.join(expr_dir, expr_code + ".expr")
expr = load_expr(file_name)
expr_list.append(expr)
F1 = exprl2alignment(expr_list)
T1 = PairwiseAlignment(F1, Dw, Gw)
A1 = align_with_tree(T1, min_peaks=2)
top_ion_list = A1.common_ion()
A1.write_common_ion_csv('output/area2.csv', top_ion_list)
print 'Aligning expt B'
expr_list = []
expr_dir = "../61b/output/"
for expr_code in exprB_codes:
file_name = os.path.join(expr_dir, expr_code + ".expr")
expr = load_expr(file_name)
expr_list.append(expr)
F2 = exprl2alignment(expr_list)
T2 = PairwiseAlignment(F2, Dw, Gw)
exprA_codes = [ "a0806_077", "a0806_078", "a0806_079" ]
exprB_codes = [ "a0806_140", "a0806_141", "a0806_142" ]
# within replicates alignment parameters
Dw = 2.5 # rt modulation [s]
Gw = 0.30 # gap penalty
# do the alignment
print 'Aligning expt A'
expr_list = []
expr_dir = "../61a/output/"
for expr_code in exprA_codes:
file_name = os.path.join(expr_dir, expr_code + ".expr")
expr = load_expr(file_name)
expr_list.append(expr)
F1 = exprl2alignment(expr_list)
T1 = PairwiseAlignment(F1, Dw, Gw)
A1 = align_with_tree(T1, min_peaks=2)
top_ion_list = A1.common_ion()
A1.write_common_ion_csv('output/area2.csv', top_ion_list)
print 'Aligning expt B'
expr_list = []
expr_dir = "../61b/output/"
for expr_code in exprB_codes:
file_name = os.path.join(expr_dir, expr_code + ".expr")
expr = load_expr(file_name)
expr_list.append(expr)
F2 = exprl2alignment(expr_list)
T2 = PairwiseAlignment(F2, Dw, Gw)
##################
# peak alignment #
##################
# within-state alignments
alignments = []
for group, expr_files in group_list:
print " Aligning expt:", group
expr_list = []
for file_name in expr_files:
expr = load_expr(file_name)
expr_list.append(expr)
# require common peaks in at least half the number of files
n = (len(expr_list)+1)/2
F = exprl2alignment(expr_list)
T = PairwiseAlignment(F, Dw, Gw)
A = align_with_tree(T, min_peaks=n)
alignments.append(A)
# between-state alignment
print "\n Aligning between-state"
Tb = PairwiseAlignment(alignments, Db, Gb)
Ab = align_with_tree(Tb)
Ab.write_csv(os.path.join(base_path, 'rt.csv'), os.path.join(base_path, 'area.csv'))
