def loadModels(self):
#print self.modelsfile
if self.modelsfile != '':
try:
Fitting.loadModelsFile(self.modelsfile)
except:
pass
#print Fitting.currentmodels.keys()
return
def loadModels(self):
#print self.modelsfile
if self.modelsfile != '':
try:
Fitting.loadModelsFile(self.modelsfile)
except:
pass
#print Fitting.currentmodels.keys()
return
def fitElwellSchellman(self,E=None, d=None, xy=None,transwidth=50,
invert=False,show=True,figname=None):
"""Fit entire raw data simultaneously to the three main thermodynamic
parameters using Elwell/Schellman method"""
if E !=None:
ek = E.getDataset(d)
x,y,a, xerr,yerr = ek.getAll()
elif xy!=None:
x,y = xy
else:
return
if invert == True:
y = [max(y)-i for i in y[:]]
f=plt.figure(figsize=(10,5))
ax=f.add_subplot(121)
p=ax.plot(x,y,'o',alpha=0.5)
ax.set_xlabel('T');ax.set_xlabel('mdeg')
ax.set_title('raw data')
x1,y1,x,y = self.transformCD(x,y,transwidth,ax)
t=[];dg=[]
R=8.3144e-3
for T,fu in zip(x,y):
if fu>=1 or fu<=0:
continue
K = fu/(1-fu)
deltaGt = -R * T * math.log(K)
dg.append(deltaGt)
t.append(T)
ax1=f.add_subplot(122)
p=ax1.plot(t,dg,'x',mew=2,color='black')
ax1.set_xlabel('T'); ax1.set_ylabel('dG(T)')
ax.set_title('stability curve')
A,X=Fitting.doFit(expdata=zip(t,dg),model='schellman',grad=1e-9,conv=1e-9)
fity = X.getFitLine(t)
p=ax1.plot(t,fity,'r',lw=2)
fd=X.getFitDict()
self.drawParams(ax1,fd)
deltaH=fd['deltaH']; deltacp=fd['deltacp']; Tm=fd['Tm']
f.suptitle("Method 2 - deltaH: %2.2f deltaCp: %2.2e Tm: %2.2f" %(deltaH,deltacp,Tm),size=18)
if show == True:
self.showTkFigure(f)
if figname == None: figname = d
figname = figname.replace('.','_')
fname = figname+'m1'+'.png'
f.savefig(fname,dpi=300)
print 'plot saved to %s' %os.path.abspath(fname)
if E!=None:
fdata = Fitting.makeFitData(X.name,vrs=X.variables)
E.insertDataset(xydata=[t,dg], newname=d+'_vanthoff2',replace=True,fit=fdata)
#E.saveProject()
return deltaH, Tm, deltacp
def findBestModel(self):
"""Determine best fit model using SS F-test"""
models = self.modelselector.getcurselection()
if len(models)<2:
print 'select 2 or more models'
return
fitters= []
for m in models:
model = self.modelsdict[m]
X = self.createFitter(model, m)
fitters.append(X)
Fitting.updateModels(self.modelsdict)
self.previewer.findBestModel(models)
return
def testFitter(self):
"""Parse the entry fields and create the fitter"""
self.currentmodel = self.parseValues()
X = self.createFitter(self.currentmodel, self.currentname)
X.guess_start()
if self.previewer.plotfunctionvar.get() == 1:
self.previewer.plotframe.clearData()
self.previewer.plotframe.updateFit(X, showfitvars=True)
else:
X.fit(rounds=60)
self.updateModelsDict()
#update the global fitting models since the plotter uses them
Fitting.updateModels(self.modelsdict)
self.previewer.finishFit(X)
return
def __init__(self, parent=None):
self.parent=parent
if not self.parent:
Frame.__init__(self)
self.main=self.master
else:
self.main=Toplevel()
#self.master=self.main
self.main.title('Model Design')
ws = self.main.winfo_screenwidth()
hs = self.main.winfo_screenheight()
w = 900; h=600
x = (ws/2)-(w/2); y = (hs/2)-(h/2)
self.main.geometry('%dx%d+%d+%d' % (w,h,x,y))
self.main.protocol('WM_DELETE_WINDOW',self.quit)
self.tableformat = {'cellwidth':50, 'thefont':"Arial 10",
'rowheight':16, 'editable':False,
'rowselectedcolor':'yellow'}
self.filename = None
self.modelsdict = Fitting.createModels()
self.setupGUI()
self.currentname = 'Linear'
self.loadModel(self.currentname)
return
def breslauerMethod(self,E=None, d=None, xy=None,invert=False,
show=True,figname=None):
"""Finds slope of trans region and plugs this in to equation
http://www.springerlink.com/content/r34n0201g30563u7/ """
if E !=None:
ek = E.getDataset(d)
x,y,a, xerr,yerr = ek.getAll()
elif xy!=None:
x,y = xy
else:
return
f=plt.figure(figsize=(10,6))
ax=f.add_subplot(111)
ax.set_xlabel('T')
p=ax.plot(x,y,'o',alpha=0.5)
d50 = self.guessMidpoint(x,y)
A,X=Fitting.doFit(expdata=zip(x,y),model='Unfolding',conv=1e-7,noiter=60,
guess=False,startvalues=[1,1,1,1,1,d50])
fity = X.getFitLine(x)
p=ax.plot(x,fity,'r',lw=2)
fd=X.getFitDict()
self.drawParams(ax,fd)
Tm = fd['d50']; m = fd['m']
R = 8.3144e-3
deltaH = R * math.pow(Tm,2) * m
f.suptitle("Method 4 - deltaH: %2.2f Tm: %2.2f" %(deltaH,Tm),size=18)
if show == True:
self.showTkFigure(f)
if figname != None:
figname = figname.replace('.','_')
f.savefig(figname)
plt.close()
return deltaH, Tm
def createFitter(self, model, name):
"""Create fitter from the current model entry values"""
fitclass = Fitting.createClass(**model)
x,y = self.previewer.getCurrentData()
X = fitclass(exp_data=zip(x,y),variables=None,
callback=self.previewer.updateFit,
name=name)
return X
def findBestModel(self, models, callback=None):
"""Determine best fit model using SS F-test"""
dset = self.datasets[self.dsindex]
ek = self.E.getDataset(dset)
fitdata,p = Fitting.findBestModel(ek, models=models, silent=True)
best = fitdata['model']
text = 'Best model is %s with p value=%2.2e' %(best,p)
tkMessageBox.showinfo('Best fit model result',text)
return
def finishFit(self, X):
"""Call when fitting done"""
d = self.datasets[self.dsindex]
model = X.getResult()['model']
fitdata = Fitting.makeFitData(model, X.variables, X.getError())
self.E.setFitData(d, fitdata)
self.replot()
self.stop = False
return
def findVariableName(self, model, i=0):
"""Find a parameter name for the given model at index i,
used so we don't cause an error when doing processFits when no
variable is given in the conf file"""
X = Fitting.getFitter(model)
if X == None:
print 'no fitter found for this model name'
return 'a'
varname = X.getVarNames()[i]
return varname
def findVariableName(self, model, i=0):
"""Find a parameter name for the given model at index i,
used so we don't cause an error when doing processFits when no
variable is given in the conf file"""
X = Fitting.getFitter(model)
if X==None:
print 'no fitter found for this model name'
return 'a'
varname = X.getVarNames()[i]
return varname
def transformCD(self, x, y, transwidth=None, ax=None):
"""Transform raw data into fraction unfolded per temp value, by fitting to
a general unfolding equation that extracts baseline/slopes"""
#fit baseline slopes and get intercepts
d50 = self.guessMidpoint(x, y)
print 'fitting to get baseline slopes and intercepts..'
print 'midpoint is %s' % d50
A, X = Fitting.doFit(expdata=zip(x, y),
model='Unfolding',
noiter=50,
silent=True,
guess=False,
startvalues=[1, 1, 1, 1, 1, d50])
#print X.getResult()
fity = X.getFitLine(x)
fd = X.getFitDict()
if ax != None:
p = ax.plot(x, fity, 'r', lw=2)
self.drawParams(ax, fd)
#we then use slopes and intercepts get frac unfolded at each temp
mn = fd['bn']
mu = fd['bd'] #slopes
#if mu>0.01: mu = 0.01
yn = fd['an']
yu = fd['ad'] #intercepts
d50 = fd['d50']
m = fd['m']
t = []
f = []
#print mu, mn
for T, yo in zip(x, y):
fu = (yo - (yn + mn * T)) / ((yu + mu * T) - (yn + mn * T))
#print fu, (yo-(yn+mn*T)), (m), mu, mn
#if f>0:
f.append(fu)
t.append(T)
#try to take useful transition region of data
at, af = t, f
diff = 1e5
if transwidth != None:
for i in t:
d = abs(i - d50)
if d < diff:
mid = t.index(i)
diff = d
L = int(mid - transwidth)
U = int(mid + transwidth)
t, f = t[L:U], f[L:U]
return at, af, t, f
def simulateCD(self,noise=1.0):
"""Simulate some CD spec data"""
x=list(numpy.arange(290,380,0.2)); y=[]
X=Fitting.getFitter(model='Unfolding',
vrs=[-16, 0.01, -11.6, 0.01, 2.7, 324])
fity = X.getFitLine(x)
for i in fity:
noise=numpy.random.normal(i, 1.0/2)
y.append(i+noise)
cw=csv.writer(open('cd.csv','w'))
for row in zip(x,y):
cw.writerow(row)
return x,y
def simulateCD(self, noise=1.0):
"""Simulate some CD spec data"""
x = list(numpy.arange(290, 380, 0.2))
y = []
X = Fitting.getFitter(model='Unfolding',
vrs=[-16, 0.01, -11.6, 0.01, 2.7, 324])
fity = X.getFitLine(x)
for i in fity:
noise = numpy.random.normal(i, 1.0 / 2)
y.append(i + noise)
cw = csv.writer(open('cd.csv', 'w'))
for row in zip(x, y):
cw.writerow(row)
return x, y
def breslauerMethod(self,
E=None,
d=None,
xy=None,
invert=False,
show=True,
figname=None):
"""Finds slope of trans region and plugs this in to equation
http://www.springerlink.com/content/r34n0201g30563u7/ """
if E != None:
ek = E.getDataset(d)
x, y, a, xerr, yerr = ek.getAll()
elif xy != None:
x, y = xy
else:
return
f = plt.figure(figsize=(10, 6))
ax = f.add_subplot(111)
ax.set_xlabel('T')
p = ax.plot(x, y, 'o', alpha=0.5)
d50 = self.guessMidpoint(x, y)
A, X = Fitting.doFit(expdata=zip(x, y),
model='Unfolding',
conv=1e-7,
noiter=60,
guess=False,
startvalues=[1, 1, 1, 1, 1, d50])
fity = X.getFitLine(x)
p = ax.plot(x, fity, 'r', lw=2)
fd = X.getFitDict()
self.drawParams(ax, fd)
Tm = fd['d50']
m = fd['m']
R = 8.3144e-3
deltaH = R * math.pow(Tm, 2) * m
f.suptitle("Method 4 - deltaH: %2.2f Tm: %2.2f" % (deltaH, Tm),
size=18)
if show == True:
self.showTkFigure(f)
if figname != None:
figname = figname.replace('.', '_')
f.savefig(figname)
plt.close()
return deltaH, Tm
def transformCD(self,x,y,transwidth=None,ax=None):
"""Transform raw data into fraction unfolded per temp value, by fitting to
a general unfolding equation that extracts baseline/slopes"""
#fit baseline slopes and get intercepts
d50 = self.guessMidpoint(x,y)
print 'fitting to get baseline slopes and intercepts..'
print 'midpoint is %s' %d50
A,X=Fitting.doFit(expdata=zip(x,y),model='Unfolding',noiter=50,silent=True,
guess=False,startvalues=[1,1,1,1,1,d50])
#print X.getResult()
fity = X.getFitLine(x)
fd=X.getFitDict()
if ax!=None:
p=ax.plot(x,fity,'r',lw=2)
self.drawParams(ax,fd)
#we then use slopes and intercepts get frac unfolded at each temp
mn = fd['bn']; mu = fd['bd'] #slopes
#if mu>0.01: mu = 0.01
yn = fd['an']; yu = fd['ad'] #intercepts
d50 = fd['d50']; m = fd['m']
t=[]; f=[]
#print mu, mn
for T,yo in zip(x,y):
fu = (yo-(yn+mn*T)) / ((yu+mu*T)-(yn+mn*T))
#print fu, (yo-(yn+mn*T)), (m), mu, mn
#if f>0:
f.append(fu)
t.append(T)
#try to take useful transition region of data
at,af=t,f
diff=1e5
if transwidth != None:
for i in t:
d=abs(i-d50)
if d<diff:
mid = t.index(i)
diff=d
L=int(mid-transwidth); U=int(mid+transwidth)
t,f = t[L:U], f[L:U]
return at,af,t,f
def fitElwellSchellman(self,
E=None,
d=None,
xy=None,
transwidth=50,
invert=False,
show=True,
figname=None):
"""Fit entire raw data simultaneously to the three main thermodynamic
parameters using Elwell/Schellman method"""
if E != None:
ek = E.getDataset(d)
x, y, a, xerr, yerr = ek.getAll()
elif xy != None:
x, y = xy
else:
return
if invert == True:
y = [max(y) - i for i in y[:]]
f = plt.figure(figsize=(10, 5))
ax = f.add_subplot(121)
p = ax.plot(x, y, 'o', alpha=0.5)
ax.set_xlabel('T')
ax.set_xlabel('mdeg')
ax.set_title('raw data')
x1, y1, x, y = self.transformCD(x, y, transwidth, ax)
t = []
dg = []
R = 8.3144e-3
for T, fu in zip(x, y):
if fu >= 1 or fu <= 0:
continue
K = fu / (1 - fu)
deltaGt = -R * T * math.log(K)
dg.append(deltaGt)
t.append(T)
ax1 = f.add_subplot(122)
p = ax1.plot(t, dg, 'x', mew=2, color='black')
ax1.set_xlabel('T')
ax1.set_ylabel('dG(T)')
ax.set_title('stability curve')
A, X = Fitting.doFit(expdata=zip(t, dg),
model='schellman',
grad=1e-9,
conv=1e-9)
fity = X.getFitLine(t)
p = ax1.plot(t, fity, 'r', lw=2)
fd = X.getFitDict()
self.drawParams(ax1, fd)
deltaH = fd['deltaH']
deltacp = fd['deltacp']
Tm = fd['Tm']
f.suptitle("Method 2 - deltaH: %2.2f deltaCp: %2.2e Tm: %2.2f" %
(deltaH, deltacp, Tm),
size=18)
if show == True:
self.showTkFigure(f)
if figname == None: figname = d
figname = figname.replace('.', '_')
fname = figname + 'm1' + '.png'
f.savefig(fname, dpi=300)
print 'plot saved to %s' % os.path.abspath(fname)
if E != None:
fdata = Fitting.makeFitData(X.name, vrs=X.variables)
E.insertDataset(xydata=[t, dg],
newname=d + '_vanthoff2',
replace=True,
fit=fdata)
#E.saveProject()
return deltaH, Tm, deltacp
def fitDifferentialCurve(self,
E=None,
d=None,
xy=None,
smooth=0,
invert=False,
show=True,
figname=None):
"""Derive differential denaturation curve and fit to get deltaH
We smooth the unfolding curve and then differentiate and finally
fit to a 3 parameter equation.
See http://www.ncbi.nlm.nih.gov/pubmed/10933511"""
if E != None:
ek = E.getDataset(d)
x, y, a, xerr, yerr = ek.getAll()
elif xy != None:
x, y = xy
else:
return
if invert == True:
y = [max(y) - i for i in y[:]]
leg = []
lines = []
f = plt.figure(figsize=(10, 5))
ax = f.add_subplot(121)
p = ax.plot(x, y, 'x', color='black', mew=3, alpha=0.5)
leg.append(p)
lines.append('original')
#smooth
if smooth == 0:
smooth = int(len(x) / 15.0)
s = self.smoothListGaussian(y, smooth)
p = ax.plot(x[:len(s) - 1], s[:-1], lw=3)
leg.append(p)
lines.append('smoothed')
ax.set_title("original data")
ax.set_xlabel('T')
ax1 = f.add_subplot(122)
#differentiate
dx, ds = self.differentiate(x[:len(s)], s)
#ds = [i/max(ds) for i in ds]
ds = [i * 10 for i in ds]
cw = csv.writer(open('diffcd.csv', 'w'))
for row in zip(dx, ds):
cw.writerow(row)
p = ax1.plot(dx, ds, '-', lw=1.5, alpha=0.7, color='black')
leg.append(p)
lines.append('differential')
ax1.set_title("differential denaturation")
ax1.set_xlabel('T')
ax1.set_ylabel('dsignal/dT')
A, X = Fitting.doFit(expdata=zip(dx, ds),
model='diffDenaturation',
grad=1e-9,
conv=1e-10)
fity = X.getFitLine(dx)
p = ax1.plot(dx, fity, 'r', lw=2)
leg.append(p)
lines.append('fit')
t = X.getFitDict()
self.drawParams(ax1, t)
dHkcal = t['deltaH'] / 4.184
f.suptitle('Method 3 - deltaH: %2.2f kJ/mol (%2.2f kcal) Tm: %2.2f' %
(t['deltaH'], dHkcal, t['Tm']),
size=18)
ax.legend(leg, lines, loc='best', prop=FontProperties(size="smaller"))
#f.subplots_adjust(hspace=0.8)
if show == True:
self.showTkFigure(f)
if figname != None:
figname = figname.replace('.', '_')
f.savefig(figname + 'm3', dpi=300)
plt.close()
if E != None:
fdata = Fitting.makeFitData(X.name, vrs=X.variables)
E.insertDataset(xydata=[dx, ds],
newname=d + '_diff',
replace=True,
fit=fdata)
#E.saveProject()
return t['deltaH'], t['Tm']
def fitDifferentialCurve(self, E=None, d=None, xy=None,smooth=0,
invert=False,show=True,figname=None):
"""Derive differential denaturation curve and fit to get deltaH
We smooth the unfolding curve and then differentiate and finally
fit to a 3 parameter equation.
See http://www.ncbi.nlm.nih.gov/pubmed/10933511"""
if E !=None:
ek = E.getDataset(d)
x,y,a, xerr,yerr = ek.getAll()
elif xy!=None:
x,y = xy
else:
return
if invert == True:
y = [max(y)-i for i in y[:]]
leg=[]; lines=[]
f=plt.figure(figsize=(10,5))
ax=f.add_subplot(121)
p=ax.plot(x,y,'x',color='black',mew=3,alpha=0.5)
leg.append(p); lines.append('original')
#smooth
if smooth == 0:
smooth=int(len(x)/15.0)
s=self.smoothListGaussian(y,smooth)
p=ax.plot(x[:len(s)-1],s[:-1],lw=3)
leg.append(p); lines.append('smoothed')
ax.set_title("original data")
ax.set_xlabel('T')
ax1=f.add_subplot(122)
#differentiate
dx,ds = self.differentiate(x[:len(s)],s)
#ds = [i/max(ds) for i in ds]
ds = [i*10 for i in ds]
cw=csv.writer(open('diffcd.csv','w'))
for row in zip(dx,ds):
cw.writerow(row)
p=ax1.plot(dx,ds,'-',lw=1.5,alpha=0.7,color='black')
leg.append(p); lines.append('differential')
ax1.set_title("differential denaturation")
ax1.set_xlabel('T'); ax1.set_ylabel('dsignal/dT')
A,X=Fitting.doFit(expdata=zip(dx,ds),model='diffDenaturation',grad=1e-9,conv=1e-10)
fity = X.getFitLine(dx)
p=ax1.plot(dx,fity,'r',lw=2)
leg.append(p); lines.append('fit')
t=X.getFitDict()
self.drawParams(ax1,t)
dHkcal=t['deltaH']/4.184
f.suptitle('Method 3 - deltaH: %2.2f kJ/mol (%2.2f kcal) Tm: %2.2f' %(t['deltaH'],dHkcal,t['Tm']),size=18)
ax.legend(leg,lines,loc='best',prop=FontProperties(size="smaller"))
#f.subplots_adjust(hspace=0.8)
if show == True:
self.showTkFigure(f)
if figname != None:
figname = figname.replace('.','_')
f.savefig(figname+'m3',dpi=300)
plt.close()
if E!=None:
fdata = Fitting.makeFitData(X.name,vrs=X.variables)
E.insertDataset(xydata=[dx,ds], newname=d+'_diff',replace=True,fit=fdata)
#E.saveProject()
return t['deltaH'],t['Tm']
def do_search(self, globalop, proteinop, proteins, residues, nucleus, pka):
"""Do searches for the various parameters, name, pka etc"""
import re, urllib
from PEATDB.PEATTables import PEATTableModel
import PEATDB.Ekin.Fitting as Fitting
from PEATDB.Ekin.Web import EkinWeb
DB = self.DB
EW = EkinWeb()
ekincols = DB.ekintypes
found=[]
protlist = proteins.split(' ')
residuelist = residues.split(' ')
def createPhrase(items, op):
if op == 'or':
logicsymbol = '|'
else:
logicsymbol = '+'
itemlist = items.split(' ')
phrase =''
c=1
for i in itemlist:
if c == len(itemlist):
phrase = phrase + i
else:
phrase = phrase + i + logicsymbol
c=c+1
return re.compile(phrase, re.IGNORECASE)
#if there is a protein name entered, get the list of proteins/records to use
#otherwise use all records to search for the other keys
names = []
keywords = {}
for p in DB.getRecs():
name = DB[p].name
names.append((name,p))
if hasattr(DB[p], 'keywords'):
keywords[name] = DB[p].keywords
else:
keywords[name] = ''
names.sort()
#create search expressions
s_protein = createPhrase(proteins, proteinop)
s_residue = createPhrase(residues, 'or')
pkarange = pka.split('-')
#do search
for name in names:
proteinname = name[0]
protein = name[1]
if s_protein.search(proteinname) or s_protein.search(keywords[proteinname]):
found.append(protein)
if len(found)==0:
print '<h2>Sorry, no proteins found that match this name. <h2>'
return
elif residues == '' and pka == '':
self.show_DB(selected=found)
return found
#now search for the other keys inside selected proteins if needed
ekinfound={}; foundfits={}
ignore =['__fit_matches__', '__Exp_Meta_Dat__', '__datatabs_fits__']
kys = list(DB.getRecs())
kys.sort()
if len(found) == 0 or globalop == 'or':
found = DB.getRecs()
print '<table id="mytable" cellspacing=0 align=center>'
'''search recs for residue and pkarange
and add dataset names to new ekinfound dict'''
for protein in found:
for col in DB[protein].keys():
if nucleus != 'any':
if nucleus not in col:
continue
E = DB[protein][col]
if DB['userfields'].has_key(col):
fieldtype=DB['userfields'][col]['field_type']
else:
fieldtype=None
if fieldtype in ekincols:
dk = E.datasets
fits = E.__datatabs_fits__
for k in dk:
meta = E.getMetaData(k)
try:
thisres = meta['residue']
except:
thisres = k
if thisres == None:
thisres = k
if residues != '':
if s_residue.search(thisres) and not k in ignore:
if not ekinfound.has_key(protein+'$'+col):
ekinfound[protein+'$'+col]=[]
ekinfound[protein+'$'+col].append(k)
if pka != '':
foundpka = 0
if k in fits.keys():
if fits[k] == None:
continue
if fits[k].has_key('model'):
model = fits[k]['model']
else:
continue
if not foundfits.has_key(protein+'$'+col):
foundfits[protein+'$'+col]={}
X = Fitting.getFitter(model)
pnames = X.varnames
i=0
#check if first num is larger, then swap
try:
pk1=float(pkarange[0])
pk2=float(pkarange[1])
except:
print '<h2> Error: pka values are not valid </h2>'
return
if pk1 > pk2:
tmp = pk1
pk1 = pk2
pk2 = tmp
#iterate thru parameter names and match any pK fields
#this code is not that efficient!
for p in pnames:
if 'pK' in p:
pka = fits[k][i]
if pka >= pk1 and pka <= pk2:
foundpka=1
i=i+1
#if match is 'ANY', just append dataset if not there already
#also for case if no residue value entered
if globalop == 'or' or residues == '':
if foundpka == 1:
if not ekinfound.has_key(protein+'$'+col):
ekinfound[protein+'$'+col]=[]
if not k in ekinfound[protein+'$'+col]:
ekinfound[protein+'$'+col].append(k)
#if match is 'ALL', need to check dataset already found
#and if no pka found, remove it. if both are true keep it
elif globalop == 'and':
if foundpka == 0:
if ekinfound.has_key(protein+'$'+col) and k in ekinfound[protein+'$'+col]:
#print 'removing', protein, col
ekinfound[protein+'$'+col].remove(k)
foundfits[protein+'$'+col][k]=fits[k]
#check for empty fields in ekinfound dict and delete them..
for d in ekinfound.keys():
if len(ekinfound[d])==0:
del(ekinfound[d])
#if no results, just say that and return
if len(ekinfound)==0:
print '<h2> Sorry, no records found that match these parameters. </h2>'
return
#top display button and options
print '<form name="resultsform" action="%s/main.cgi" METHOD="POST" ENCTYPE="multipart/form-data">' %self.bindir
self.write_sessionkey('show_datasets')
print '<td valign=top align=right colspan=3> <input type=submit value="display selected" name=submit>'
print '<label><input type=checkbox name="plotoption" value=3>single graph</label>'
print '<label><input type=checkbox name="normalise" value=1>normalise</label>'
print '<label><input type=checkbox name="logx" value=1>log-x</label>'
print '<label><input type=checkbox name="logy" value=1>log-y</label>'
print '<label><input type=checkbox name="legend" value=1>legend</label>'
print '<input type=button value="Check All" onClick="checkAll(document.resultsform.residue)">'
print '<input type=button value="Uncheck All" onClick="uncheckAll(document.resultsform.residue)"></td>'
print '</tr>'
#header
cols=['protein','column','residues']
for c in cols:
print '<th>'+c+'</th>'
print '</tr>'
ekys = ekinfound.keys()
ekys.sort()
r=1
for k in ekys:
if r % 2 == 0:
cls = "spec"
else:
cls = ""
fields = k.split('$')
protein = fields[0]
column = fields[1]
proteinname = DB[protein]['name']
print '<tr>'
print '<th class="spec">%s</th> <td> %s </td>' %(proteinname, column)
print '<td>'
for residue in ekinfound[k]:
residuefield = k+"$"+residue
fithtml = ''
try:
print '<input type=checkbox id="residue" name="residue" value=%s>' %("'"+residuefield+"'")
except:
print 'UnicodeEncodeError'
continue
urlfields = urllib.urlencode({'login':self.user,'project':self.project,
'residue': residuefield,'action': 'show_datasets'})
print '<a href="/cgi-bin/titration_db/main.cgi?%s" target="_blank">%s</a>'\
% (urlfields, residue)
print '</tr>'
r=r+1
print '</form>'
print '</table>'
self.footer()
return
def fitVantHoff(self,
E=None,
d=None,
xy=None,
transwidth=80,
invert=False,
show=True,
figname=None):
"""Derive fraction unfolded, get K and fit to Van't Hoff.
see http://www.jbc.org/content/277/43/40717.full
or http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2144003/
"""
if E != None:
if not d in E.datasets:
print 'no such dataset, %s' % d
print 'available datasets:', E.datasets
return
ek = E.getDataset(d)
x, y = ek.getxySorted()
elif xy != None:
x, y = xy
if 'Convert Celsius-Kelvin' in self.conversions.getcurselection():
x = [i + 273 for i in x]
if invert == True:
y = [max(y) - i for i in y[:]]
f = plt.figure(figsize=(18, 6))
ax = f.add_subplot(131)
p = ax.plot(x, y, 'o', alpha=0.6)
ax.set_xlabel('T(K)')
ax.set_ylabel('mdeg')
ax.set_title('raw data')
x1, y1, x, y = self.transformCD(x, y, transwidth, ax)
cw = csv.writer(open('frac_unfolded_' + d + '.csv', 'w'))
cw.writerow(['temp', 'frac'])
for i in zip(x1, y1):
cw.writerow(i)
#derive lnK vs 1/T
t = []
k = []
for T, fu in zip(x, y):
if fu >= 1 or fu <= 0:
continue
K = fu / (1 - fu)
klog = math.log(K)
k.append(klog)
t.append(1 / T)
if len(t) < 2: return None, None, None
ax = f.add_subplot(132)
p = ax.plot(x1, y1, 'o', color='g', alpha=0.6)
ax.set_xlabel('T(K)')
ax.set_ylabel('fu')
ax.set_title('fraction unfolded')
ax = f.add_subplot(133)
p = ax.plot(t, k, 'x', mew=2, color='black')
ax.set_xlabel('1/T') #(r'$1/T ($K^-1)$')
ax.set_ylabel('ln K')
formatter = matplotlib.ticker.ScalarFormatter()
formatter.set_scientific(True)
formatter.set_powerlimits((0, 0))
ax.xaxis.set_major_formatter(formatter)
for l in ax.get_xticklabels():
l.set_rotation(30)
#fit this van't hoff plot
A, X = Fitting.doFit(expdata=zip(t, k), model='Linear')
fitk = X.getFitLine(t)
p = ax.plot(t, fitk, 'r', lw=2)
fd = X.getFitDict()
#self.drawParams(ax,fd)
#slope is deltaH/R/1000 in kJ
deltaH = -fd['a'] * self.R / 1000
deltaS = fd['b'] * self.R / 1000
f.suptitle("Method 1 - deltaH: %2.2f deltaS: %2.2f" % (deltaH, deltaS),
size=18)
f.subplots_adjust(bottom=0.15, top=0.85)
if show == True:
self.showTkFigure(f)
if figname == None: figname = d
figname = figname.replace('.', '_')
fname = figname + 'm1' + '.png'
f.savefig(fname, dpi=300)
print 'plot saved to %s' % os.path.abspath(fname)
#plt.close()
if E != None:
fdata = Fitting.makeFitData(X.name, vrs=X.variables)
E.insertDataset(xydata=[t, k],
newname=d + '_vanthoff',
replace=True,
fit=fdata)
#E.saveProject()
return deltaH, deltaS, ax
def fitVantHoff(self, E=None, d=None, xy=None, transwidth=80, invert=False,
show=True, figname=None):
"""Derive fraction unfolded, get K and fit to Van't Hoff.
see http://www.jbc.org/content/277/43/40717.full
or http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2144003/
"""
if E != None:
if not d in E.datasets:
print 'no such dataset, %s' %d
print 'available datasets:', E.datasets
return
ek = E.getDataset(d)
x,y = ek.getxySorted()
elif xy!=None:
x,y = xy
if 'Convert Celsius-Kelvin' in self.conversions.getcurselection():
x = [i+273 for i in x]
if invert == True:
y = [max(y)-i for i in y[:]]
f=plt.figure(figsize=(18,6))
ax=f.add_subplot(131)
p=ax.plot(x,y,'o',alpha=0.6)
ax.set_xlabel('T(K)'); ax.set_ylabel('mdeg')
ax.set_title('raw data')
x1,y1,x,y = self.transformCD(x,y,transwidth,ax)
cw=csv.writer(open('frac_unfolded_'+d+'.csv','w'))
cw.writerow(['temp','frac'])
for i in zip(x1,y1):
cw.writerow(i)
#derive lnK vs 1/T
t=[]; k=[]
for T,fu in zip(x,y):
if fu>=1 or fu<=0:
continue
K = fu/(1-fu)
klog = math.log(K)
k.append(klog)
t.append(1/T)
if len(t)<2: return None, None, None
ax=f.add_subplot(132)
p=ax.plot(x1,y1,'o',color='g',alpha=0.6)
ax.set_xlabel('T(K)'); ax.set_ylabel('fu')
ax.set_title('fraction unfolded')
ax=f.add_subplot(133)
p=ax.plot(t,k,'x',mew=2,color='black')
ax.set_xlabel('1/T')#(r'$1/T ($K^-1)$')
ax.set_ylabel('ln K')
formatter = matplotlib.ticker.ScalarFormatter()
formatter.set_scientific(True)
formatter.set_powerlimits((0,0))
ax.xaxis.set_major_formatter(formatter)
for l in ax.get_xticklabels():
l.set_rotation(30)
#fit this van't hoff plot
A,X=Fitting.doFit(expdata=zip(t,k),model='Linear')
fitk = X.getFitLine(t)
p=ax.plot(t,fitk,'r',lw=2)
fd=X.getFitDict()
#self.drawParams(ax,fd)
#slope is deltaH/R/1000 in kJ
deltaH = -fd['a']*self.R/1000
deltaS = fd['b']*self.R/1000
f.suptitle("Method 1 - deltaH: %2.2f deltaS: %2.2f" %(deltaH,deltaS),size=18)
f.subplots_adjust(bottom=0.15,top=0.85)
if show==True:
self.showTkFigure(f)
if figname == None: figname = d
figname = figname.replace('.','_')
fname = figname+'m1'+'.png'
f.savefig(fname,dpi=300)
print 'plot saved to %s' %os.path.abspath(fname)
#plt.close()
if E!=None:
fdata = Fitting.makeFitData(X.name,vrs=X.variables)
E.insertDataset(xydata=[t,k], newname=d+'_vanthoff',replace=True,fit=fdata)
#E.saveProject()
return deltaH, deltaS, ax
