def process_files_singlet(xml_files):
so_many = len(xml_files)
print("****This script is about to make png files for %s xml files. ****" %
so_many)
for file in xml_files:
file_name = os.path.splitext(file)[0]
data = platereader.read_icontrol_xml(file)
print("****The xml file " + file +
" has %s data sections:****" % len(data.keys()))
print(data.keys())
for key in data.keys():
plot_singlet_one_section(data, key)
#fig.tight_layout()
#fig.suptitle("%s_%s" % (file_name,key), fontsize=18)
plt.savefig('%s_%s.png' % (file_name, key))
print('Look at how pretty your data is: %s_%s.png' %
(file_name, key))
return
def process_files_singlet(xml_files):
so_many = len(xml_files)
print("****This script is about to make png files for %s xml files. ****" % so_many)
for file in xml_files:
file_name = os.path.splitext(file)[0]
data = platereader.read_icontrol_xml(file)
print("****The xml file " + file + " has %s data sections:****" % len(data.keys()))
print(data.keys())
for key in data.keys():
plot_singlet_one_section(data,key)
#fig.tight_layout()
#fig.suptitle("%s_%s" % (file_name,key), fontsize=18)
plt.savefig('%s_%s.png' % (file_name,key))
print('Look at how pretty your data is: %s_%s.png' % (file_name,key))
return
container = Container(name="assay-plate", id=id, container_type=container_type)
#
# Assay Parameters
#
Lstated = [ Unit(x, "moles/liter") for x in [20.0e-6,9.15e-6,4.18e-6,1.91e-6,0.875e-6,0.4e-6,0.183e-6,0.0837e-6,0.0383e-6,0.0175e-6,0.008e-6,0] ] # gefitinib concentration
Pstated = Unit(0.5e-6, "moles/liter")
well_volume = Unit(100, "milliliter")
receptor_name = 'Src'
ligand_name = 'gefitinib'
# Load data into well format.
filename = "../ipynbs/data-analysis/binding-assay/data/Gef_WIP_SMH_SrcBos_Extend_013015_mdfx_20150220_18.xml"
from assaytools import platereader
data = platereader.read_icontrol_xml(filename)
# Define wells for fluorescence assay (the verbose way; we'd provide convenience methods to format the plate)
ncolumns = 12
well_group = WellGroup([])
for column in range(ncolumns):
for row in ['A', 'B']:
well_name = row + str(column+1)
well = container.well(well_name)
well.set_volume(well_volume)
well.set_properties({'area' : well_area})
# Set concentrations of well components
if row == 'A':
well.set_properties({'concentrations' : {receptor_name : Pstated, ligand_name : Lstated[column]} })
well.set_properties({'concentration_uncertainties' : {receptor_name : 0.10 * Pstated, ligand_name : 0.08 * Lstated[column]} })
Lstated = [
Unit(x, "moles/liter") for x in [
20.0e-6, 9.15e-6, 4.18e-6, 1.91e-6, 0.875e-6, 0.4e-6, 0.183e-6,
0.0837e-6, 0.0383e-6, 0.0175e-6, 0.008e-6, 0
]
] # gefitinib concentration
Pstated = Unit(0.5e-6, "moles/liter")
well_volume = Unit(100, "milliliter")
receptor_name = 'Src'
ligand_name = 'gefitinib'
# Load data into well format.
filename = "../ipynbs/data-analysis/binding-assay/data/Gef_WIP_SMH_SrcBos_Extend_013015_mdfx_20150220_18.xml"
from assaytools import platereader
data = platereader.read_icontrol_xml(filename)
# Define wells for fluorescence assay (the verbose way; we'd provide convenience methods to format the plate)
ncolumns = 12
well_group = WellGroup([])
for column in range(ncolumns):
for row in ['A', 'B']:
well_name = row + str(column + 1)
well = container.well(well_name)
well.set_volume(well_volume)
well.set_properties({'area': well_area})
# Set concentrations of well components
if row == 'A':
well.set_properties({
'concentrations': {
def read_infinite(container,
xml_filename,
wavelengths_to_analyze=None,
measurements_to_analyze=None):
"""
Read measurements from a Tecan Infinite reader XML file.
Parameters
----------
wavelengths_to_analyze : list, optional, default=None
If not None, only read measurements involving these wavelengths
measurements_to_analyze : list, optional, default=None
If not None, only read these kinds of measurements (e.g. 'absorbance', 'fluorescence bottom', 'fluorescence top')
Measurements are stored in `well.properties['measurements']` under
* `absorbance` : e.g. { '280:nanometers' : 0.425 }
* `fluorescence` : e.g. { ('280:nanometers', '350:nanometers', 'top') : 15363 }
TODO
----
* Eventually, we can read all components of the Infinite file directly here.
"""
# TODO: Replace read_icontrol_xml with direct processing of XML file
from assaytools import platereader
data = platereader.read_icontrol_xml(xml_filename)
for well in container.all_wells():
well_name = well.humanize()
# Attach plate reader data
# TODO: Only process wells for which measurements are available
if 'measurements' not in well.properties:
well.properties['measurements'] = dict()
measurements = well.properties['measurements']
for key in data:
if key.startswith('Abs_'):
# absorbance
[prefix, wavelength] = key.split('_')
wavelength = wavelength + ':nanometers'
# Skip if requested
if wavelengths_to_analyze and not (wavelength
in wavelengths_to_analyze):
continue
if measurements_to_analyze and not (
'absorbance' in measurements_to_analyze):
continue
# Store
if 'absorbance' not in measurements:
measurements['absorbance'] = dict()
measurements['absorbance'][wavelength] = float(
data[key][well_name])
elif (key.endswith('_TopRead') or key.endswith('_BottomRead')):
# top fluorescence read
[wavelength, suffix] = key.split('_')
excitation_wavelength = wavelength + ':nanometers'
emission_wavelength = '480:nanometers' # This is hard-coded in for now because this information is not available in the platereader.read_icontrol_xml results
if key.endswith('_TopRead'):
geometry = 'top'
else:
geometry = 'bottom'
# Skip if requested
if wavelengths_to_analyze and not (
(excitation_wavelength in wavelengths_to_analyze) and
(emission_wavelength in wavelengths_to_analyze)):
continue
if measurements_to_analyze and not (
('fluorescence %s' % geometry) in measurements_to_analyze):
continue
# Store
if 'fluorescence' not in measurements:
measurements['fluorescence'] = dict()
measurements['fluorescence'][(excitation_wavelength,
emission_wavelength,
geometry)] = float(
data[key][well_name])
def get_data_using_inputs(inputs):
"""
Parses your data according to inputs dictionary. Requires you have a 'file_set' in your inputs.
Parameters
----------
inputs : dict
Dictionary of input information
"""
complex_fluorescence = {}
ligand_fluorescence = {}
for protein in inputs['file_set'].keys():
#concatenate xmls into one dictionary with all ligand data
my_file = []
sw_data = []
# Data just helps define our keys, which will be our data sections.
# We are importing the first two files, because sometimes we have two files per
# data collection, e.g. if we wanted a lot of types of reads
# (there is a limited number of type of read on the infinite per script).
data = platereader.read_icontrol_xml(inputs['file_set']['%s' %
protein][0])
try:
data.update(
platereader.read_icontrol_xml(inputs['file_set']['%s' %
protein][1]))
except:
pass
if 'single_well' in inputs:
for file in inputs['file_set']['%s' % protein]:
my_file.append(file)
data_to_append = {key: None for key in data}
new_dict = platereader.read_icontrol_xml(file)
data_to_append.update(new_dict)
sw_data.append(data_to_append)
#sw_data is a list of dataframes in the order of the list of files
if inputs['protein_wells'][protein][0] not in range(
1, 25): #make sure not a two digit number
if len(str(inputs['protein_wells'][protein]
[0])) == 2 or 3: # is it e.g. 'A1' or 'A11'
if len(inputs['protein_wells'][protein]) == len(
inputs['ligand_order']):
pass
else:
print(
'***To define individual wells, you need to define the same number of wells as ligands.***'
)
break
for i in range(0, len(inputs['ligand_order'])): # i defines ligand
for j, protein_well_ID in enumerate(
inputs['protein_wells'][protein]): # j defines protein
if str(protein_well_ID) in ALPHABET:
#print('Your ligands are in a row (1,2,3,4, etc. are different ligands)!')
protein_well = '%s%s' % (protein_well_ID, i)
buffer_well = '%s%s' % (
inputs['buffer_wells'][protein][j], i)
name = "%s-%s-%s%s" % (protein,
inputs['ligand_order'][i],
protein_well, buffer_well)
elif len(str(protein_well_ID)) == 2 or 3:
if inputs['protein_wells'][protein][0] in range(
1, 25): # make sure not a two digit number
pass
else:
protein_well = protein_well_ID
buffer_well = inputs['buffer_wells'][protein][j]
name = "%s-%s-%s%s" % (protein,
inputs['ligand_order'][j],
protein_well, buffer_well)
else:
#print('Your ligands are in a column (A,B,C,D, etc. are different ligands)!')
protein_well = '%s%s' % (ALPHABET[i], protein_well_ID)
buffer_well = '%s%s' % (
ALPHABET[i], inputs['buffer_wells'][protein][j])
name = "%s-%s-%s%s" % (protein,
inputs['ligand_order'][i],
protein_well, buffer_well)
#print(name)
protein_data = []
buffer_data = []
for k in range(
len(sw_data)
): # k should define ligand concentration if your list of files was ordered correctly
# for spectra assays
if 'wavelength' in inputs:
protein_data.append(
float(
platereader.select_data(
sw_data[k],
inputs['section'], [protein_well],
wavelength='%s' %
inputs['wavelength'])[protein_well]))
buffer_data.append(
float(
platereader.select_data(
sw_data[k],
inputs['section'], [buffer_well],
wavelength='%s' %
inputs['wavelength'])[buffer_well]))
# for single wavelength assays
else:
protein_data.append(
float(
platereader.select_data(
sw_data[k], inputs['section'],
[protein_well])[protein_well]))
buffer_data.append(
float(
platereader.select_data(
sw_data[k], inputs['section'],
[buffer_well])[buffer_well]))
complex_fluorescence[name] = np.asarray(protein_data)
ligand_fluorescence[name] = np.asarray(buffer_data)
else:
for file in inputs['file_set']['%s' % protein]:
my_file.append(file)
new_dict = platereader.read_icontrol_xml(file)
for key in data:
try:
data[key].update(new_dict[key])
except:
pass
# Are there any experiments the user wants to skip analyzing?
skipped_experiments = []
for i, ligand in enumerate(inputs['ligand_order']):
if ligand == None:
skipped_experiments.append(i * 2)
else:
continue
skipped_rows = []
for i in skipped_experiments:
skipped_rows.append(ALPHABET[i])
skipped_rows.append(ALPHABET[i + 1])
if len(skipped_rows) != 0:
print("Skipping analysis of rows: ", skipped_rows)
for i in range(0, len(inputs['ligand_order'] * 2), 2):
if i in skipped_experiments:
continue
else:
protein_row = ALPHABET[i]
buffer_row = ALPHABET[i + 1]
name = "%s-%s-%s%s" % (protein, inputs['ligand_order'][int(
i / 2)], protein_row, buffer_row)
# for spectra assays
if 'wavelength' in inputs:
complex_fluorescence_data = platereader.select_data(
data,
inputs['section'],
protein_row,
wavelength='%s' % inputs['wavelength'])
ligand_fluorescence_data = platereader.select_data(
data,
inputs['section'],
buffer_row,
wavelength='%s' % inputs['wavelength'])
# for single wavelength assays
else:
complex_fluorescence_data = platereader.select_data(
data, inputs['section'], protein_row)
ligand_fluorescence_data = platereader.select_data(
data, inputs['section'], buffer_row)
complex_fluorescence[name] = reorder2list(
complex_fluorescence_data, well)
ligand_fluorescence[name] = reorder2list(
ligand_fluorescence_data, well)
return [complex_fluorescence, ligand_fluorescence]
def read_infinite(container, xml_filename, wavelengths_to_analyze=None, measurements_to_analyze=None):
"""
Read measurements from a Tecan Infinite reader XML file.
Parameters
----------
wavelengths_to_analyze : list, optional, default=None
If not None, only read measurements involving these wavelengths
measurements_to_analyze : list, optional, default=None
If not None, only read these kinds of measurements (e.g. 'absorbance', 'fluorescence bottom', 'fluorescence top')
Measurements are stored in `well.properties['measurements']` under
* `absorbance` : e.g. { '280:nanometers' : 0.425 }
* `fluorescence` : e.g. { ('280:nanometers', '350:nanometers', 'top') : 15363 }
TODO
----
* Eventually, we can read all components of the Infinite file directly here.
"""
# TODO: Replace read_icontrol_xml with direct processing of XML file
from assaytools import platereader
data = platereader.read_icontrol_xml(xml_filename)
for well in container.all_wells():
well_name = well.humanize()
# Attach plate reader data
# TODO: Only process wells for which measurements are available
if 'measurements' not in well.properties:
well.properties['measurements'] = dict()
measurements = well.properties['measurements']
for key in data:
if key.startswith('Abs_'):
# absorbance
[prefix, wavelength] = key.split('_')
wavelength = wavelength + ':nanometers'
# Skip if requested
if wavelengths_to_analyze and not (wavelength in wavelengths_to_analyze):
continue
if measurements_to_analyze and not ('absorbance' in measurements_to_analyze):
continue
# Store
if 'absorbance' not in measurements:
measurements['absorbance'] = dict()
measurements['absorbance'][wavelength] = float(data[key][well_name])
elif (key.endswith('_TopRead') or key.endswith('_BottomRead')):
# top fluorescence read
[wavelength, suffix] = key.split('_')
excitation_wavelength = wavelength + ':nanometers'
emission_wavelength = '480:nanometers' # This is hard-coded in for now because this information is not available in the platereader.read_icontrol_xml results
if key.endswith('_TopRead'):
geometry = 'top'
else:
geometry = 'bottom'
# Skip if requested
if wavelengths_to_analyze and not ((excitation_wavelength in wavelengths_to_analyze) and (emission_wavelength in wavelengths_to_analyze)):
continue
if measurements_to_analyze and not (('fluorescence %s' % geometry) in measurements_to_analyze):
continue
# Store
if 'fluorescence' not in measurements:
measurements['fluorescence'] = dict()
measurements['fluorescence'][(excitation_wavelength, emission_wavelength, geometry)] = float(data[key] [well_name])
def quick_model(inputs):
xml_files = glob("%s/*.xml" % inputs['xml_file_path'])
print(xml_files)
for my_file in xml_files:
file_name = os.path.splitext(my_file)[0]
print(file_name)
data = platereader.read_icontrol_xml(my_file)
for i in range(0,15,2):
protein_row = ALPHABET[i]
buffer_row = ALPHABET[i+1]
name = "%s-%s%s"%(inputs['ligand_order'][i/2],protein_row,buffer_row)
print(name)
metadata = {}
metadata = dict(inputs)
try:
part1_data_protein = platereader.select_data(data, inputs['section'], protein_row)
part1_data_buffer = platereader.select_data(data, inputs['section'], buffer_row)
except:
continue
reorder_protein = reorder2list(part1_data_protein,well)
reorder_buffer = reorder2list(part1_data_buffer,well)
#these need to be changed so they are TAKEN FROM INPUTS!!!
# Uncertainties in protein and ligand concentrations.
dPstated = 0.35 * inputs['Pstated'] # protein concentration uncertainty
dLstated = 0.08 * inputs['Lstated'] # ligand concentraiton uncertainty (due to gravimetric preparation and HP D300 dispensing)
from assaytools import pymcmodels
pymc_model = pymcmodels.make_model(inputs['Pstated'], dPstated, inputs['Lstated'], dLstated,
top_complex_fluorescence=reorder_protein,
top_ligand_fluorescence=reorder_buffer,
use_primary_inner_filter_correction=True,
use_secondary_inner_filter_correction=True,
assay_volume=inputs['assay_volume'], DG_prior='uniform')
import datetime
my_datetime = datetime.datetime.now().strftime("%Y-%m-%d %H:%M")
my_datetime_filename = datetime.datetime.now().strftime("%Y-%m-%d %H%M")
mcmc = pymcmodels.run_mcmc(pymc_model, db = 'pickle', dbname = '%s_mcmc-%s.pickle'%(name,my_datetime))
map = pymcmodels.map_fit(pymc_model)
pymcmodels.show_summary(pymc_model, map, mcmc)
DeltaG_map = map.DeltaG.value
DeltaG = mcmc.DeltaG.trace().mean()
dDeltaG = mcmc.DeltaG.trace().std()
## PLOT MODEL
#from assaytools import plots
#figure = plots.plot_measurements(Lstated, Pstated, pymc_model, mcmc=mcmc)
#Code below inspired by import above, but didn't quite work to import it...
plt.clf()
plt.subplot(211)
property_name = 'top_complex_fluorescence'
complex = getattr(pymc_model, property_name)
plt.semilogx(inputs['Lstated'], complex.value, 'ko',label='complex')
property_name = 'top_ligand_fluorescence'
ligand = getattr(pymc_model, property_name)
plt.semilogx(inputs['Lstated'], ligand.value, 'ro',label='ligand')
for top_complex_fluorescence_model in mcmc.top_complex_fluorescence_model.trace()[::10]:
plt.semilogx(inputs['Lstated'], top_complex_fluorescence_model, 'k:')
for top_ligand_fluorescence_model in mcmc.top_ligand_fluorescence_model.trace()[::10]:
plt.semilogx(inputs['Lstated'], top_ligand_fluorescence_model, 'r:')
plt.xlabel('$[L]_T$ (M)');
plt.ylabel('fluorescence units');
plt.legend(loc=0);
## PLOT TRACE
plt.subplot(212)
plt.hist(mcmc.DeltaG.trace(), 40, alpha=0.75, label="DeltaG = %.1f +- %.1f kT"%(DeltaG, dDeltaG))
plt.axvline(x=DeltaG,color='blue')
plt.axvline(x=DeltaG_map,color='black',linestyle='dashed',label="MAP = %.1f"%DeltaG_map)
plt.legend(loc=0)
plt.xlabel('$\Delta G$ ($k_B T$)');
plt.ylabel('$P(\Delta G)$');
plt.xlim(-35,-10)
plt.suptitle("%s: %s" % (name, my_datetime))
plt.tight_layout()
fig1 = plt.gcf()
fig1.savefig('delG_%s-%s.png'%(name, my_datetime_filename))
np.save('DeltaG_%s-%s.npy'%(name, my_datetime_filename),DeltaG)
np.save('DeltaG_trace_%s-%s.npy'%(name, my_datetime_filename),mcmc.DeltaG.trace())
Kd = np.exp(mcmc.DeltaG.trace().mean())
dKd = np.exp(mcmc.DeltaG.trace()).std()
if (Kd < 1e-12):
Kd_summary = "%.1f nM +- %.1f fM" % (Kd/1e-15, dKd/1e-15)
elif (Kd < 1e-9):
Kd_summary = "%.1f pM +- %.1f pM" % (Kd/1e-12, dKd/1e-12)
elif (Kd < 1e-6):
Kd_summary = "%.1f nM +- %.1f nM" % (Kd/1e-9, dKd/1e-9)
elif (Kd < 1e-3):
Kd_summary = "%.1f uM +- %.1f uM" % (Kd/1e-6, dKd/1e-6)
elif (Kd < 1):
Kd_summary = "%.1f mM +- %.1f mM" % (Kd/1e-3, dKd/1e-3)
else:
Kd_summary = "%.3e M +- %.3e M" % (Kd, dKd)
outputs = {
'raw_data_file' : my_file,
'name' : name,
'analysis' : 'pymcmodels', #right now this is hardcoded, BOOO
'outfiles' : '%s_mcmc-%s.pickle, delG_%s-%s.png,DeltaG_%s-%s.npy,DeltaG_trace_%s-%s.npy'%(name,my_datetime,name,my_datetime,name,my_datetime,name,my_datetime),
'DeltaG' : "DeltaG = %.1f +- %.1f kT, MAP estimate = %.1f" % (DeltaG, dDeltaG, DeltaG_map),
'Kd' : Kd_summary,
'datetime' : my_datetime
}
metadata.update(outputs)
metadata['Pstated'] = metadata['Pstated'].tolist()
metadata['Lstated'] = metadata['Lstated'].tolist()
with open('%s-%s.json'%(name,my_datetime), 'w') as outfile:
json.dump(metadata, outfile, sort_keys = True, indent = 4, ensure_ascii=False)
# This is a script version of DMSO-backfill.ipynb
from assaytools import platereader
import matplotlib.pyplot as plt
import string
import numpy as np
part1 = "p38_singlet1_20160420_153238.xml"
part2 = "p38_singlet2_20160420_154750.xml"
part1_data = platereader.read_icontrol_xml(part1)
part2_data = platereader.read_icontrol_xml(part2)
part1_data_C = platereader.select_data(part1_data, '280_480_TOP_120', 'C')
part1_data_D = platereader.select_data(part1_data, '280_480_TOP_120', 'D')
part1_data_K = platereader.select_data(part1_data, '280_480_TOP_120', 'K')
part1_data_L = platereader.select_data(part1_data, '280_480_TOP_120', 'L')
well = dict()
for j in string.ascii_uppercase:
for i in range(1,25):
well['%s' %j + '%s' %i] = i
Lstated = np.array([20.0e-6,14.0e-6,9.82e-6,6.88e-6,4.82e-6,3.38e-6,2.37e-6,1.66e-6,1.16e-6,0.815e-6,0.571e-6,0.4e-6,0.28e-6,0.196e-6,0.138e-6,0.0964e-6,0.0676e-6,0.0474e-6,0.0320e-6,0.0240e-6,0.0160e-6,0.0120e-6,0.008e-6,0.00001e-6], np.float64) # ligand concentration, M
# Stated concentrations of protein and ligand.
Pstated = 0.5e-6 * np.ones([24],np.float64) # protein concentration, M
# Assay configuration details
import math
assay_volume = 50e-6 # assay volume, L
def get_data_using_inputs(inputs):
"""
Parses your data according to inputs dictionary. Requires you have a 'file_set' in your inputs.
Parameters
----------
inputs : dict
Dictionary of input information
"""
complex_fluorescence = {}
ligand_fluorescence = {}
for protein in inputs['file_set'].keys():
#concatenate xmls into one dictionary with all ligand data
my_file = []
# Data just helps define our keys, which will be our data sections.
# We are importing the first two files, because sometimes we have two files per
# data collection, e.g. if we wanted a lot of types of reads
# (there is a limited number of type of read on the infinite per script).
data = platereader.read_icontrol_xml(inputs['file_set']['%s' %
protein][0])
try:
data.update(
platereader.read_icontrol_xml(inputs['file_set']['%s' %
protein][1]))
except:
pass
for file in inputs['file_set']['%s' % protein]:
my_file.append(file)
new_dict = platereader.read_icontrol_xml(file)
for key in data:
try:
data[key].update(new_dict[key])
except:
pass
# Are there any experiments the user wants to skip analyzing?
skipped_experiments = []
for i, ligand in enumerate(inputs['ligand_order']):
if ligand == None:
skipped_experiments.append(i * 2)
else:
continue
skipped_rows = []
for i in skipped_experiments:
skipped_rows.append(ALPHABET[i])
skipped_rows.append(ALPHABET[i + 1])
print("Skipping analysis of rows: ", skipped_rows)
for i in range(0, len(inputs['ligand_order'] * 2), 2):
if i in skipped_experiments:
continue
else:
protein_row = ALPHABET[i]
buffer_row = ALPHABET[i + 1]
name = "%s-%s-%s%s" % (protein, inputs['ligand_order'][int(
i / 2)], protein_row, buffer_row)
# for spectra assays
if 'wavelength' in inputs:
complex_fluorescence_data = platereader.select_data(
data,
inputs['section'],
protein_row,
wavelength='%s' % inputs['wavelength'])
ligand_fluorescence_data = platereader.select_data(
data,
inputs['section'],
buffer_row,
wavelength='%s' % inputs['wavelength'])
# for single wavelength assays
else:
complex_fluorescence_data = platereader.select_data(
data, inputs['section'], protein_row)
ligand_fluorescence_data = platereader.select_data(
data, inputs['section'], buffer_row)
complex_fluorescence[name] = reorder2list(
complex_fluorescence_data, well)
ligand_fluorescence[name] = reorder2list(
ligand_fluorescence_data, well)
return [complex_fluorescence, ligand_fluorescence]