def score_chaos(self, sum_formula, adduct, img):
if not sum_formula in self.measure_value_score:
self.measure_value_score[sum_formula] = {}
result = 1 - measure_of_chaos(img, self.nlevels, interp=False)[0]
if result == 1:
result = 0
self.measure_value_score[sum_formula][adduct] = result
def run_search(config, IMS_dataset, sum_formulae, adducts, mz_list):
from pyIMS.image_measures import level_sets_measure, isotope_image_correlation, isotope_pattern_match
import time
### Runs the main pipeline
# Get sum formula and predicted m/z peaks for molecules in database
ppm = config['image_generation']['ppm'] # parts per million - a measure of how accuracte the mass spectrometer is
nlevels = config['image_generation']['nlevels'] # parameter for measure of chaos
do_preprocessing = config['image_generation']['do_preprocessing']
interp = config['image_generation']['smooth']
measure_value_score = {}
iso_correlation_score = {}
iso_ratio_score = {}
t0 = time.time()
t_el = 0
for adduct in adducts:
print 'searching -> {}'.format(adduct)
for ii,sum_formula in enumerate(sum_formulae):
if adduct not in mz_list[sum_formula]:#adduct may not be present if it would make an impossible formula, is there a better way to handle this?
# print '{} adduct not found for {}'.format(adduct, mz_list[sum_formula])
continue
if time.time() - t_el > 10.:
t_el = time.time()
print '{:3.2f} done in {:3.0f} seconds'.format(float(ii)/len(sum_formulae),time.time()-t0)
# Allocate dicts if required
if not sum_formula in measure_value_score:
measure_value_score[sum_formula] = {}
if not sum_formula in iso_correlation_score:
iso_correlation_score[sum_formula] = {}
if not sum_formula in iso_ratio_score:
iso_ratio_score[sum_formula] = {}
try:
# 1. Generate ion images
ion_datacube = IMS_dataset.get_ion_image(mz_list[sum_formula][adduct][0],
ppm) # for each spectrum, sum the intensity of all peaks within tol of mz_list
if do_preprocessing:
apply_image_processing(config,ion_datacube) #currently just supports hot-spot removal
# 2. Spatial Chaos
measure_value_score[sum_formula][adduct] = level_sets_measure.measure_of_chaos(
ion_datacube.xic_to_image(0), nlevels, interp=None, clean_im=False)[0]
if measure_value_score[sum_formula][adduct] == 1:
measure_value_score[sum_formula][adduct] = 0
# 3. Score correlation with monoiso
if len(mz_list[sum_formula][adduct][1]) > 1:
iso_correlation_score[sum_formula][adduct] = isotope_image_correlation.isotope_image_correlation(
ion_datacube.xic, weights=mz_list[sum_formula][adduct][1][1:])
else: # only one isotope peak, so correlation doesn't make sense
iso_correlation_score[sum_formula][adduct] = 1
# 4. Score isotope ratio
iso_ratio_score[sum_formula][adduct] = isotope_pattern_match.isotope_pattern_match(ion_datacube.xic,
mz_list[sum_formula][
adduct][1])
except KeyError as e:
print str(e)
print "bad key in: \"{}\" \"{}\" ".format(sum_formula, adduct)
output_results(config, measure_value_score, iso_correlation_score, iso_ratio_score, sum_formulae, [adduct], mz_list)
return measure_value_score, iso_correlation_score, iso_ratio_score
def run_search(config):
### Runs the main pipeline
# Get sum formula and predicted m/z peaks for molecules in database
sum_formulae,adducts,mz_list = generate_isotope_patterns(config)
# Parse dataset
from pyIMS.hdf5.inMemoryIMS_hdf5 import inMemoryIMS_hdf5
from pyIMS.image_measures import level_sets_measure,isotope_image_correlation,isotope_pattern_match
IMS_dataset=inMemoryIMS_hdf5(config['file_inputs']['data_file'])
ppm = config['image_generation']['ppm'] #parts per million - a measure of how accuracte the mass spectrometer is
nlevels = config['image_generation']['nlevels'] # parameter for measure of chaos
q=config['image_generation']['q']
measure_value_score={}
iso_correlation_score = {}
iso_ratio_score = {}
for sum_formula in sum_formulae:
for adduct in adducts:
# 1. Geneate ion images
ion_datacube = IMS_dataset.get_ion_image(mz_list[sum_formula][adduct][0],ppm) #for each spectrum, sum the intensity of all peaks within tol of mz_list
ion_datacube.xic=hot_spot_removal(ion_datacube.xic,q)
# 2. Spatial Chaos
if not sum_formula in measure_value_score:
measure_value_score[sum_formula] = {}
measure_value_score[sum_formula][adduct] = 1-level_sets_measure.measure_of_chaos(ion_datacube.xic_to_image(0),nlevels,interp=False)[0]
if measure_value_score[sum_formula][adduct] == 1:
measure_value_score[sum_formula][adduct] = 0
# only compare pixels with values in the monoisotopic (otherwise high correlation for large empty areas)
notnull_monoiso = ion_datacube.xic[0] > 0
#for xic in ion_datacube.xic:
# xic = xic[notnull_monoiso]
# 3. Score correlation with monoiso
if not sum_formula in iso_correlation_score:
iso_correlation_score[sum_formula] = {}
if len(mz_list[sum_formula][adduct][1]) > 1:
iso_correlation_score[sum_formula][adduct] = isotope_image_correlation.isotope_image_correlation(ion_datacube.xic,weights=mz_list[sum_formula][adduct][1][1:])
else: # only one isotope peak, so correlation doesn't make sense
iso_correlation_score[sum_formula][adduct] = 1
# 4. Score isotope ratio
if not sum_formula in iso_ratio_score:
iso_ratio_score[sum_formula] = {}
iso_ratio_score[sum_formula][adduct] = isotope_pattern_match.isotope_pattern_match(ion_datacube.xic,mz_list[sum_formula][adduct][1])
return measure_value_score,iso_correlation_score,iso_ratio_score
def mzImages(filename_in,save_dir):
import sys
sys.path.append('C:\\Users\\Luca Rappez\\Desktop\\python_codebase\\')
from pyMS.centroid_detection import gradient
from pyIMS.hdf5.inMemoryIMS_hdf5 import inMemoryIMS_hdf5
from pyIMS.image_measures import level_sets_measure
import matplotlib.pyplot as plt
import numpy as np
#%matplotlib inline
import bokeh as bk
from bokeh.plotting import output_notebook
output_notebook()
print 'step1'
#filename_in = '//psi.embl.de/alexandr/shared/Luca/20150825_CoCulture_Candida_Ecoli/20150821_ADP_LR_colony250K12_DHBsub_260x280_50um.hdf5' #using a temporary hdf5 based format
#save_dir= '//psi.embl.de/alexandr/shared/Luca/20150825_CoCulture_Candida_Ecoli/20150821_ADP_LR_colony250K12_DHBsub_260x280_50um_figures'
# Parse data
IMS_dataset = inMemoryIMS_hdf5(filename_in)
print 'In memory'
ppm = 1.5
# Generate mean spectrum
#hist_axis,mean_spec =IMS_dataset.generate_summary_spectrum(summary_type='mean')
hist_axis,freq_spec = IMS_dataset.generate_summary_spectrum(summary_type='freq',ppm=ppm/2)
#p1 = bk.plotting.figure()
#p1.line(hist_axis,mean_spec/np.max(mean_spec),color='red')
#p1.line(hist_axis,freq_spec/np.max(freq_spec),color='orange')
#bk.plotting.show(p1)
print len(hist_axis)
#plt.figure(figsize=(20,10))
#plt.plot(hist_axis,freq_spec)
#plt.show()
# Centroid detection of frequency spectrum
mz_list,count_list,idx_list = gradient(np.asarray(hist_axis),np.asarray(freq_spec),weighted_bins=2)
c_thresh=0.05
moc_thresh=0.99
print np.sum(count_list>c_thresh)
# Calcualte MoC for images of all peaks
nlevels=30
im_list={}
for ii, c in enumerate(count_list):
#print ii
#print c
if c>c_thresh:
ion_image = IMS_dataset.get_ion_image(np.asarray([mz_list[ii],]),ppm)
im = ion_image.xic_to_image(0)
m,im_moc,levels,nobjs = level_sets_measure.measure_of_chaos(im,nlevels,interp='median') #just output measure value
m=1-m
im_list[mz_list[ii]]={'image':im,'moc':m,'freq':c}
from pySpatialMetabolomics.tools import colourmaps
c_map = colourmaps.get_colormap('grey')#if black images: open->save->rerun
c_pal=[[int(255*cc) for cc in c_map(c)] for c in range(0,254)]
# Export all images
import png as pypng
for mz in im_list:
if im_list[mz]['moc']>moc_thresh:
with open('{}/{}_{}.png'.format(save_dir,mz,im_list[mz]['moc']),'wb') as f_out:
im_out = im_list[mz]['image']
im_out = 254*im_out/np.max(im_out)
w,h = np.shape(im_out)
w = pypng.Writer(h, w, palette=c_pal, bitdepth=8)
w.write(f_out,im_out)
#im_out = im_list[mz]['image']
mz=333.334188269
ion_image = IMS_dataset.get_ion_image(np.asarray([mz,]),ppm)
im_out=ion_image.xic_to_image(0)
m,im_moc,levels,nobjs = level_sets_measure.measure_of_chaos(im,nlevels,interp='') #just output measure value
print 1-m
im_out = 254.*im_out/np.max(im_out)
print mz
#print im_list[mz]['moc']
#plt.figure()
#plt.imshow(im_moc)
#plt.show()
def run_search(config, IMS_dataset, sum_formulae, adducts, mz_list):
from pyIMS.image_measures import level_sets_measure, isotope_image_correlation, isotope_pattern_match
import time
### Runs the main pipeline
# Get sum formula and predicted m/z peaks for molecules in database
ppm = config['image_generation'][
'ppm'] # parts per million - a measure of how accuracte the mass spectrometer is
nlevels = config['image_generation'][
'nlevels'] # parameter for measure of chaos
do_preprocessing = config['image_generation']['do_preprocessing']
interp = config['image_generation']['smooth']
measure_value_score = {}
iso_correlation_score = {}
iso_ratio_score = {}
t0 = time.time()
t_el = 0
for adduct in adducts:
print 'searching -> {}'.format(adduct)
for ii, sum_formula in enumerate(sum_formulae):
if adduct not in mz_list[
sum_formula]: #adduct may not be present if it would make an impossible formula, is there a better way to handle this?
# print '{} adduct not found for {}'.format(adduct, mz_list[sum_formula])
continue
if time.time() - t_el > 10.:
t_el = time.time()
print '{:3.2f} done in {:3.0f} seconds'.format(
float(ii) / len(sum_formulae),
time.time() - t0)
# Allocate dicts if required
if not sum_formula in measure_value_score:
measure_value_score[sum_formula] = {}
if not sum_formula in iso_correlation_score:
iso_correlation_score[sum_formula] = {}
if not sum_formula in iso_ratio_score:
iso_ratio_score[sum_formula] = {}
try:
# 1. Generate ion images
ion_datacube = IMS_dataset.get_ion_image(
mz_list[sum_formula][adduct][0], ppm
) # for each spectrum, sum the intensity of all peaks within tol of mz_list
if do_preprocessing:
apply_image_processing(
config, ion_datacube
) #currently just supports hot-spot removal
# 2. Spatial Chaos
measure_value_score[sum_formula][
adduct] = level_sets_measure.measure_of_chaos(
ion_datacube.xic_to_image(0),
nlevels,
interp=None,
clean_im=False)[0]
if measure_value_score[sum_formula][adduct] == 1:
measure_value_score[sum_formula][adduct] = 0
# 3. Score correlation with monoiso
if len(mz_list[sum_formula][adduct][1]) > 1:
iso_correlation_score[sum_formula][
adduct] = isotope_image_correlation.isotope_image_correlation(
ion_datacube.xic,
weights=mz_list[sum_formula][adduct][1][1:])
else: # only one isotope peak, so correlation doesn't make sense
iso_correlation_score[sum_formula][adduct] = 1
# 4. Score isotope ratio
iso_ratio_score[sum_formula][
adduct] = isotope_pattern_match.isotope_pattern_match(
ion_datacube.xic, mz_list[sum_formula][adduct][1])
except KeyError as e:
print str(e)
print "bad key in: \"{}\" \"{}\" ".format(sum_formula, adduct)
output_results(config, measure_value_score, iso_correlation_score,
iso_ratio_score, sum_formulae, [adduct], mz_list)
return measure_value_score, iso_correlation_score, iso_ratio_score
def plot_images(ion_datacube, iso_spect, iso_max, q_val=99, c_map="hot"):
import numpy as np
import matplotlib.pyplot as plt
from pyIMS.image_measures import level_sets_measure, isotope_image_correlation, isotope_pattern_match
measure_value_score = 1 - level_sets_measure.measure_of_chaos(ion_datacube.xic_to_image(0), 30, interp="median")[0]
# 3. Score correlation with monoiso
if len(iso_spect[1]) > 1:
iso_correlation_score = isotope_image_correlation.isotope_image_correlation(
ion_datacube.xic, weights=iso_spect[1][1:]
)
else: # only one isotope peak, so correlation doesn't make sense
iso_correlation_score = 1
iso_ratio_score = isotope_pattern_match.isotope_pattern_match(ion_datacube.xic, iso_spect[1])
msm_score = measure_value_score * iso_correlation_score * iso_ratio_score
ax = [
plt.subplot2grid((2, 4), (0, 0)),
plt.subplot2grid((2, 4), (0, 1)),
plt.subplot2grid((2, 4), (0, 2)),
plt.subplot2grid((2, 4), (0, 3)),
plt.subplot2grid((2, 4), (1, 0), colspan=4, rowspan=1),
]
for a in ax:
a.cla()
# plot images
for ii in range(0, iso_max):
im = ion_datacube.xic_to_image(ii)
# hot-spot removal
notnull = im > 0
if np.sum(notnull == False) == np.shape(im)[0] * np.shape(im)[1]:
im = im
else:
im_q = np.percentile(im[notnull], q_val)
im_rep = im > im_q
im[im_rep] = im_q
ax[ii].imshow(im, cmap=c_map, interpolation="nearest")
ax[ii].set_title("m/z: {:3.4f}".format(iso_spect[0][ii]))
# plot spectrum
notnull = ion_datacube.xic_to_image(0) > 0
data_spect = [np.sum(ion_datacube.xic_to_image(ii)) for ii in range(0, iso_max)]
data_spect = data_spect / np.linalg.norm(data_spect)
iso_spect[1] = iso_spect[1] / np.linalg.norm(iso_spect[1])
markerline, stemlines, baseline = ax[4].stem(iso_spect[0][0:iso_max], iso_spect[1][0:iso_max], "g")
plt.title(
"moc: {:3.4f} spat: {:3.2f} spec: {:3.2f} msm: {:3.3f}".format(
measure_value_score, iso_correlation_score, iso_ratio_score, msm_score
)
)
plt.setp(stemlines, linewidth=2, color="g") # set stems colors
plt.setp(markerline, "markerfacecolor", "g", "markeredgecolor", "g") # make points
markerline, stemlines, baseline = ax[4].stem(iso_spect[0][0:iso_max], data_spect, "r")
plt.setp(stemlines, linewidth=2, color="r") # set stems colors
plt.setp(markerline, "markerfacecolor", "r", "markeredgecolor", "r") # make points
# plot proxy artist
proxies = []
h, = plt.plot(iso_spect[0][0], [0], "-g")
proxies.append(h)
h, = plt.plot(iso_spect[0][0], [0], "-r")
proxies.append(h)
ax[4].legend(proxies, ("predicted pattern", "data pattern"), numpoints=1)
return ax
def plot_images(ion_datacube, iso_spect, iso_max, q_val=99, c_map='hot'):
import numpy as np
import matplotlib.pyplot as plt
from pyIMS.image_measures import level_sets_measure, isotope_image_correlation, isotope_pattern_match
measure_value_score = 1 - level_sets_measure.measure_of_chaos(
ion_datacube.xic_to_image(0), 30, interp="median")[0]
# 3. Score correlation with monoiso
if len(iso_spect[1]) > 1:
iso_correlation_score = isotope_image_correlation.isotope_image_correlation(
ion_datacube.xic, weights=iso_spect[1][1:])
else: # only one isotope peak, so correlation doesn't make sense
iso_correlation_score = 1
iso_ratio_score = isotope_pattern_match.isotope_pattern_match(
ion_datacube.xic, iso_spect[1])
msm_score = measure_value_score * iso_correlation_score * iso_ratio_score
ax = [
plt.subplot2grid((2, 4), (0, 0)),
plt.subplot2grid((2, 4), (0, 1)),
plt.subplot2grid((2, 4), (0, 2)),
plt.subplot2grid((2, 4), (0, 3)),
plt.subplot2grid((2, 4), (1, 0), colspan=4, rowspan=1)
]
for a in ax:
a.cla()
# plot images
for ii in range(0, iso_max):
im = ion_datacube.xic_to_image(ii)
# hot-spot removal
notnull = im > 0
if np.sum(notnull == False) == np.shape(im)[0] * np.shape(im)[1]:
im = im
else:
im_q = np.percentile(im[notnull], q_val)
im_rep = im > im_q
im[im_rep] = im_q
ax[ii].imshow(im, cmap=c_map, interpolation='nearest')
ax[ii].set_title('m/z: {:3.4f}'.format(iso_spect[0][ii]))
# plot spectrum
notnull = ion_datacube.xic_to_image(0) > 0
data_spect = [
np.sum(ion_datacube.xic_to_image(ii)) for ii in range(0, iso_max)
]
data_spect = data_spect / np.linalg.norm(data_spect)
iso_spect[1] = iso_spect[1] / np.linalg.norm(iso_spect[1])
markerline, stemlines, baseline = ax[4].stem(iso_spect[0][0:iso_max],
iso_spect[1][0:iso_max], 'g')
plt.title("moc: {:3.4f} spat: {:3.2f} spec: {:3.2f} msm: {:3.3f}".format(
measure_value_score, iso_correlation_score, iso_ratio_score,
msm_score))
plt.setp(stemlines, linewidth=2, color='g') # set stems colors
plt.setp(markerline, 'markerfacecolor', 'g', 'markeredgecolor',
'g') # make points
markerline, stemlines, baseline = ax[4].stem(iso_spect[0][0:iso_max],
data_spect, 'r')
plt.setp(stemlines, linewidth=2, color='r') # set stems colors
plt.setp(markerline, 'markerfacecolor', 'r', 'markeredgecolor',
'r') # make points
#plot proxy artist
proxies = []
h, = plt.plot(iso_spect[0][0], [0], '-g')
proxies.append(h)
h, = plt.plot(iso_spect[0][0], [0], '-r')
proxies.append(h)
ax[4].legend(proxies, ('predicted pattern', 'data pattern'), numpoints=1)
return ax
