def fastatomodelalignment(libDirectory,motifID,alignmentfile,outputfile):
# read correspondences from the fasta file to the model
InstanceToGroup, InstanceToPDB, InstanceToSequence, GroupToModel, ModelToColumn, SequenceToModel, HasName, HasScore, HasInteriorEdit, HasFullEdit, HasCutoffValue, HasCutoffScore, HasAlignmentScoreDeficit = readcorrespondencesfromfile(alignmentfile)
print "Read alignment to model from " + alignmentfile
FN = libDirectory + "\\" + motifID + "_correspondences.txt"
# read correspondences for the given motif group; there are many such correspondences
InstanceToGroup, InstanceToPDB, InstanceToSequence, GroupToModel, ModelToColumn, SequenceToModelDummy, ModelHasName, ModelHasScore, ModelInteriorEdit, ModelFullEdit, ModelCutoffValue, ModelCutoffScore, ModelDeficit = readcorrespondencesfromfile(FN)
# print HasScore
# print ModelHasName
HasName.update(ModelHasName)
HasScore.update(ModelHasScore)
print "Read model correspondences from " + FN
# Loop through instances from 3D and from the sequence alignment and put in an alignment to display
DisplayColor = {}
aligdata = {} # new dictionary
for a in InstanceToGroup.iterkeys():
m = re.search("(.+Instance_[0-9]+)",a)
aligdata[m.group(1)] = [] # initialize this key with empty list
DisplayColor[m.group(1)] = 'blue' # default display color
for a in SequenceToModel.iterkeys():
m = re.search("(Sequence_[0-9]+)",a)
aligdata[m.group(1)] = [] # initialize this key with empty list
DisplayColor[m.group(1)] = 'black' # default display color
for a in aligdata.iterkeys():
for j in range(0,len(ModelToColumn)):
aligdata[a].append('') # initialize with blank
# sorting by key should keep insertions in order
for a in sorted(InstanceToGroup.iterkeys(), key=columnkeyforsortbynumber):
print a
m = re.search("(.+Instance_[0-9]+)",a)
print m.group(1)
t = int(ModelToColumn[GroupToModel[InstanceToGroup[a]]]) # map position in group to the correct column in the model and in the alignment
aligdata[m.group(1)][t-1] += a[len(a)-1] # last character of the key is the base for this position
for a in sorted(SequenceToModel.iterkeys(), key=positionkeyforsortbynumber):
m = re.search("(Sequence_[0-9]+)",a)
t = int(ModelToColumn[SequenceToModel[a]])
aligdata[m.group(1)][t-1] += a[len(a)-1]
f = open(outputfile,"w")
f.write("<html><title>Alignment to "+motifID+"</title>\n")
f.write("<h1>Alignment of " + alignmentfile +" to "+motifID+"</h1>\n")
f.write("<a href=\"http://rna.bgsu.edu/rna3dhub/motif/view/" + motifID + "\" target=\"_blank\">Motif atlas entry for " + motifID + "</a><br>")
f.write("The correspondence between sequences from 3D structures and the motif group is shown in blue, JAR3D alignments of sequences to the motif group are shown in black, and sequences which are too long or too short to be aligned are indicated by : characters.")
f.write("<table>")
f.write(alignmentheaderhtml(ModelToColumn, GroupToModel)+'\n')
f.write(alignmentrowshtml(DisplayColor, aligdata, HasName, HasScore, HasInteriorEdit, HasFullEdit, HasCutoffValue, HasCutoffScore, HasAlignmentScoreDeficit))
f.write("</table>")
InteractionsFile = libDirectory + "\\" + motifID + "_interactions.txt"
f.write('<br><b>Conserved interactions between motif group positions in ' + motifID + ':</b>')
f.write('<pre>')
with open(InteractionsFile,"r") as mf:
for line in mf.readlines():
f.write(line)
f.write("</pre>")
ModelFile = libDirectory + "\\" + motifID + "_model.txt"
f.write('<b>JAR3D SCFG/MRF model for ' + motifID + ':</b>')
f.write('<pre>')
with open(ModelFile,"r") as mf:
for line in mf.readlines():
f.write(line)
f.write("</pre>")
f.write("</html>")
f.close()
print "Wrote html file with alignment of 3D instances and sequences for " + motifID
return aligdata
def fastatomodelalignment(libDirectory, motifID, alignmentfile, outputfile):
# read correspondences from the fasta file to the model
InstanceToGroup, InstanceToPDB, InstanceToSequence, GroupToModel, ModelToColumn, SequenceToModel, HasName, HasScore, HasInteriorEdit, HasFullEdit, HasCutoffValue, HasCutoffScore, HasAlignmentScoreDeficit = readcorrespondencesfromfile(
alignmentfile)
print "Read alignment to model from " + alignmentfile
FN = libDirectory + "\\" + motifID + "_correspondences.txt"
# read correspondences for the given motif group; there are many such correspondences
InstanceToGroup, InstanceToPDB, InstanceToSequence, GroupToModel, ModelToColumn, SequenceToModelDummy, ModelHasName, ModelHasScore, ModelInteriorEdit, ModelFullEdit, ModelCutoffValue, ModelCutoffScore, ModelDeficit = readcorrespondencesfromfile(
FN)
# print HasScore
# print ModelHasName
HasName.update(ModelHasName)
HasScore.update(ModelHasScore)
print "Read model correspondences from " + FN
# Loop through instances from 3D and from the sequence alignment and put in an alignment to display
DisplayColor = {}
aligdata = {} # new dictionary
for a in InstanceToGroup.iterkeys():
m = re.search("(.+Instance_[0-9]+)", a)
aligdata[m.group(1)] = [] # initialize this key with empty list
DisplayColor[m.group(1)] = 'blue' # default display color
for a in SequenceToModel.iterkeys():
m = re.search("(Sequence_[0-9]+)", a)
aligdata[m.group(1)] = [] # initialize this key with empty list
DisplayColor[m.group(1)] = 'black' # default display color
for a in aligdata.iterkeys():
for j in range(0, len(ModelToColumn)):
aligdata[a].append('') # initialize with blank
# sorting by key should keep insertions in order
for a in sorted(InstanceToGroup.iterkeys(), key=columnkeyforsortbynumber):
print a
m = re.search("(.+Instance_[0-9]+)", a)
print m.group(1)
t = int(
ModelToColumn[GroupToModel[InstanceToGroup[a]]]
) # map position in group to the correct column in the model and in the alignment
aligdata[m.group(1)][t - 1] += a[
len(a) -
1] # last character of the key is the base for this position
for a in sorted(SequenceToModel.iterkeys(),
key=positionkeyforsortbynumber):
m = re.search("(Sequence_[0-9]+)", a)
t = int(ModelToColumn[SequenceToModel[a]])
aligdata[m.group(1)][t - 1] += a[len(a) - 1]
f = open(outputfile, "w")
f.write("<html><title>Alignment to " + motifID + "</title>\n")
f.write("<h1>Alignment of " + alignmentfile + " to " + motifID + "</h1>\n")
f.write("<a href=\"http://rna.bgsu.edu/rna3dhub/motif/view/" + motifID +
"\" target=\"_blank\">Motif atlas entry for " + motifID +
"</a><br>")
f.write(
"The correspondence between sequences from 3D structures and the motif group is shown in blue, JAR3D alignments of sequences to the motif group are shown in black, and sequences which are too long or too short to be aligned are indicated by : characters."
)
f.write("<table>")
f.write(alignmentheaderhtml(ModelToColumn, GroupToModel) + '\n')
f.write(
alignmentrowshtml(DisplayColor, aligdata, HasName, HasScore,
HasInteriorEdit, HasFullEdit, HasCutoffValue,
HasCutoffScore, HasAlignmentScoreDeficit))
f.write("</table>")
InteractionsFile = libDirectory + "\\" + motifID + "_interactions.txt"
f.write('<br><b>Conserved interactions between motif group positions in ' +
motifID + ':</b>')
f.write('<pre>')
with open(InteractionsFile, "r") as mf:
for line in mf.readlines():
f.write(line)
f.write("</pre>")
ModelFile = libDirectory + "\\" + motifID + "_model.txt"
f.write('<b>JAR3D SCFG/MRF model for ' + motifID + ':</b>')
f.write('<pre>')
with open(ModelFile, "r") as mf:
for line in mf.readlines():
f.write(line)
f.write("</pre>")
f.write("</html>")
f.close()
print "Wrote html file with alignment of 3D instances and sequences for " + motifID
return aligdata
def onemodeldiagnostic(motifID,libDirectory,diagDirectory,prevHTML,nextHTML):
n = 1
if n > 0:
FN = diagDirectory + "\\" + motifID + "_diagnostics.txt"
# read correspondences for the given motif group; there are many such correspondences
InstanceToGroup, InstanceToPDB, InstanceToSequence, GroupToModel, ModelToColumn, SequenceToModel, HasName, HasScore, HasInteriorEdit, HasFullEdit, HasCutoffValue, HasCutoffScore, HasAlignmentScoreDeficit = readcorrespondencesfromfile(FN)
print "Read diagnostics from " + FN
# default display color, indexed by instance; each instance will be displayed in one row
DisplayColor = {}
# loop through instances from the motif group and set the color that it will be displayed
for i in InstanceToPDB.iterkeys():
a = re.search("(.+Instance_[0-9]+)",i)
DisplayColor[a.group(1)] = 'blue' # default display color
# loop through sequences from the motif group and set the default display color in a dictionary
for i in SequenceToModel.iterkeys():
a = re.search("(.+Sequence_[0-9]+)",i)
DisplayColor[a.group(1)] = 'black' # default display color
MisAlign = 0
# print GroupToModel
# print SequenceToModel
# print InstanceToPDB
for nt in sorted(InstanceToPDB.iterkeys()):
if GroupToModel[InstanceToGroup[nt]] != SequenceToModel[InstanceToSequence[nt]]:
print nt + ' belongs to ' + GroupToModel[InstanceToGroup[nt]] + ' but was aligned to ' + SequenceToModel[InstanceToSequence[nt]]
MisAlign += 0.5
# a = re.search("(.+Instance_[0-9]+)",nt)
# DisplayColor[a.group(1)] = 'red'
a = re.search("(.+Sequence_[0-9]+)",InstanceToSequence[nt])
DisplayColor[a.group(1)] = 'red'
# Loop through instances from 3D and from the sequence alignment and put in an alignment to display
aligdata = {} # new dictionary
for a in InstanceToGroup.iterkeys():
m = re.search("(.+Instance_[0-9]+)",a)
aligdata[m.group(1)] = [] # initialize this key with empty list
for a in SequenceToModel.iterkeys():
m = re.search("(.+Sequence_[0-9]+)",a)
aligdata[m.group(1)] = [] # initialize this key with empty list
for a in aligdata.iterkeys():
for j in range(0,len(ModelToColumn)):
aligdata[a].append('') # initialize with blank
# sorting by key should keep insertions in order
for a in sorted(InstanceToGroup.iterkeys(), key=columnkeyforsortbynumber):
m = re.search("(.+Instance_[0-9]+)",a)
t = int(ModelToColumn[GroupToModel[InstanceToGroup[a]]]) # map position in group to the correct column in the model and in the alignment
aligdata[m.group(1)][t-1] += a[len(a)-1] # last character of the key is the base for this position
for a in sorted(SequenceToModel.iterkeys(), key=positionkeyforsortbynumber):
m = re.search("(.+Sequence_[0-9]+)",a)
t = int(ModelToColumn[SequenceToModel[a]])
aligdata[m.group(1)][t-1] += a[len(a)-1]
# for a,b in aligdata.iteritems():
# for i in range(0,len(b)-1):
# print '<td>'+aligdata[a][i]+'</td>',
# print
f = open(diagDirectory+"\\"+motifID+"_GroupToModelDiagnostic.html","w")
f.write("<html><title>"+motifID+" alignment</title>\n")
f.write("<h1>Alignment of "+motifID+" sequences from 3D to the JAR3D model</h1>\n")
f.write("<a href=\"" + prevHTML + "\">Previous group</a> | ")
f.write("<a href=\"" + nextHTML + "\">Next group</a> | ")
f.write("<a href=\"GroupToModelDiagnostic.html\">List of all groups</a> | ")
f.write("<a href=\"http://rna.bgsu.edu/rna3dhub/motif/view/" + motifID + "\" target=\"_blank\">Motif atlas entry for " + motifID + "</a> ")
f.write("<br>The correspondence between sequences from 3D structures and the motif group is shown in blue and the JAR3D alignment of the sequences to the motif group is shown in black. Occasionally the two disagree, in which case the JAR3D alignment is shown in red.")
f.write("<table>")
f.write(alignmentheaderhtml(ModelToColumn,GroupToModel)+'\n')
f.write(alignmentrowshtml(DisplayColor,aligdata,HasName,HasScore, HasInteriorEdit, HasFullEdit, HasCutoffValue, HasCutoffScore, HasAlignmentScoreDeficit))
f.write("</table>")
InteractionsFile = libDirectory + "\\" + motifID + "_interactions.txt"
f.write('<br><b>Conserved interactions between motif group positions in ' + motifID + ':</b>')
f.write('<pre>')
with open(InteractionsFile,"r") as mf:
for line in mf.readlines():
f.write(line)
f.write("</pre>")
ModelFile = libDirectory + "\\" + motifID + "_model.txt"
f.write('<b>JAR3D SCFG/MRF model for ' + motifID + ':</b>')
f.write('<pre>')
with open(ModelFile,"r") as mf:
for line in mf.readlines():
f.write(line)
f.write("</pre>")
FASTAFile = libDirectory + "\\" + motifID + ".fasta"
f.write('<b>Sequences of instances from ' + motifID + ':<b>')
f.write('<pre>')
with open(FASTAFile,"r") as mf:
for line in mf.readlines():
f.write(line)
f.write("</pre>")
f.write("</html>")
f.close()
print "Wrote html file with alignment of 3D instances and sequences for " + motifID
return aligdata, MisAlign
def onemodeldiagnostic(motifID, libDirectory, diagDirectory, prevHTML,
nextHTML):
n = 1
if n > 0:
FN = diagDirectory + "\\" + motifID + "_diagnostics.txt"
# read correspondences for the given motif group; there are many such correspondences
InstanceToGroup, InstanceToPDB, InstanceToSequence, GroupToModel, ModelToColumn, SequenceToModel, HasName, HasScore, HasInteriorEdit, HasFullEdit, HasCutoffValue, HasCutoffScore, HasAlignmentScoreDeficit = readcorrespondencesfromfile(
FN)
print "Read diagnostics from " + FN
# default display color, indexed by instance; each instance will be displayed in one row
DisplayColor = {}
# loop through instances from the motif group and set the color that it will be displayed
for i in InstanceToPDB.iterkeys():
a = re.search("(.+Instance_[0-9]+)", i)
DisplayColor[a.group(1)] = 'blue' # default display color
# loop through sequences from the motif group and set the default display color in a dictionary
for i in SequenceToModel.iterkeys():
a = re.search("(.+Sequence_[0-9]+)", i)
DisplayColor[a.group(1)] = 'black' # default display color
MisAlign = 0
# print GroupToModel
# print SequenceToModel
# print InstanceToPDB
for nt in sorted(InstanceToPDB.iterkeys()):
if GroupToModel[InstanceToGroup[nt]] != SequenceToModel[
InstanceToSequence[nt]]:
print nt + ' belongs to ' + GroupToModel[InstanceToGroup[
nt]] + ' but was aligned to ' + SequenceToModel[
InstanceToSequence[nt]]
MisAlign += 0.5
# a = re.search("(.+Instance_[0-9]+)",nt)
# DisplayColor[a.group(1)] = 'red'
a = re.search("(.+Sequence_[0-9]+)", InstanceToSequence[nt])
DisplayColor[a.group(1)] = 'red'
# Loop through instances from 3D and from the sequence alignment and put in an alignment to display
aligdata = {} # new dictionary
for a in InstanceToGroup.iterkeys():
m = re.search("(.+Instance_[0-9]+)", a)
aligdata[m.group(1)] = [] # initialize this key with empty list
for a in SequenceToModel.iterkeys():
m = re.search("(.+Sequence_[0-9]+)", a)
aligdata[m.group(1)] = [] # initialize this key with empty list
for a in aligdata.iterkeys():
for j in range(0, len(ModelToColumn)):
aligdata[a].append('') # initialize with blank
# sorting by key should keep insertions in order
for a in sorted(InstanceToGroup.iterkeys(),
key=columnkeyforsortbynumber):
m = re.search("(.+Instance_[0-9]+)", a)
t = int(
ModelToColumn[GroupToModel[InstanceToGroup[a]]]
) # map position in group to the correct column in the model and in the alignment
aligdata[m.group(1)][t - 1] += a[
len(a) -
1] # last character of the key is the base for this position
for a in sorted(SequenceToModel.iterkeys(),
key=positionkeyforsortbynumber):
m = re.search("(.+Sequence_[0-9]+)", a)
t = int(ModelToColumn[SequenceToModel[a]])
aligdata[m.group(1)][t - 1] += a[len(a) - 1]
# for a,b in aligdata.iteritems():
# for i in range(0,len(b)-1):
# print '<td>'+aligdata[a][i]+'</td>',
# print
f = open(
diagDirectory + "\\" + motifID + "_GroupToModelDiagnostic.html",
"w")
f.write("<html><title>" + motifID + " alignment</title>\n")
f.write("<h1>Alignment of " + motifID +
" sequences from 3D to the JAR3D model</h1>\n")
f.write("<a href=\"" + prevHTML + "\">Previous group</a> | ")
f.write("<a href=\"" + nextHTML + "\">Next group</a> | ")
f.write(
"<a href=\"GroupToModelDiagnostic.html\">List of all groups</a> | "
)
f.write("<a href=\"http://rna.bgsu.edu/rna3dhub/motif/view/" +
motifID + "\" target=\"_blank\">Motif atlas entry for " +
motifID + "</a> ")
f.write(
"<br>The correspondence between sequences from 3D structures and the motif group is shown in blue and the JAR3D alignment of the sequences to the motif group is shown in black. Occasionally the two disagree, in which case the JAR3D alignment is shown in red."
)
f.write("<table>")
f.write(alignmentheaderhtml(ModelToColumn, GroupToModel) + '\n')
f.write(
alignmentrowshtml(DisplayColor, aligdata, HasName, HasScore,
HasInteriorEdit, HasFullEdit, HasCutoffValue,
HasCutoffScore, HasAlignmentScoreDeficit))
f.write("</table>")
InteractionsFile = libDirectory + "\\" + motifID + "_interactions.txt"
f.write(
'<br><b>Conserved interactions between motif group positions in ' +
motifID + ':</b>')
f.write('<pre>')
with open(InteractionsFile, "r") as mf:
for line in mf.readlines():
f.write(line)
f.write("</pre>")
ModelFile = libDirectory + "\\" + motifID + "_model.txt"
f.write('<b>JAR3D SCFG/MRF model for ' + motifID + ':</b>')
f.write('<pre>')
with open(ModelFile, "r") as mf:
for line in mf.readlines():
f.write(line)
f.write("</pre>")
FASTAFile = libDirectory + "\\" + motifID + ".fasta"
f.write('<b>Sequences of instances from ' + motifID + ':<b>')
f.write('<pre>')
with open(FASTAFile, "r") as mf:
for line in mf.readlines():
f.write(line)
f.write("</pre>")
f.write("</html>")
f.close()
print "Wrote html file with alignment of 3D instances and sequences for " + motifID
return aligdata, MisAlign
