def compute_annotations_per_iteration(self, depth=5, saveas=None, bf_thresh=0.0,
num_iterations=10, homologs=False):
'''
Given a file with iterative gene removal data, this function will plot
a bar chart of the GO annotations at a given level (depth) for each iteration.
@param depth: The GO ontology depth to use.
@param saveas: Provide a filename to save the GO annotation results. This will
be a python pickle file. Specify None to avoid saving the results to a file.
@param bf_thresh: The bayes factor threshold. An annotation must have at least this
bayes factor before being counted in the results.
@param num_iterations: The number of iterations to process
@param homologs: Select whether to include gene homologs in the analysis.
'''
iters = self.removed[:num_iterations]
res = []
print "Starting analysis..."
for i,genelist in enumerate(iters):
ifr.print_progress(i, len(iters))
bcdat = self._gen_bar_chart_data(genelist, depth, bf_thresh=bf_thresh, homologs=homologs)
res.append((i,bcdat,genelist))
print ""
if not saveas is None:
cPickle.dump(res, open(saveas,"wb"))
print "Results saved to file: %s"%saveas
self.annotation_dat = res
self.depth = depth #for convenience, remember the depth used to generate the analysis
def get_geneids_from_affy(affy_id_list, affy_file=None):
"""
Returns a dictionary mapping affy probe ids to
the tuple (genebank,unigene,symbol) given an input list
of affy probe ids, and a csv file from affymetrix with
the appropriate information
@param affy_id_list: A list of strings like '1000_at'...
@param affy_file: If none, then the function get_affy_key_file()
will be called to get the full file name and path to the csv file,
else specify the filename/path.
"""
if affy_file is None:
affy_file = get_affy_key_file()
affy_dict = {}
lines = []
with open(affy_file, "r") as f:
for tmpline in f:
if tmpline[0] != "#":
lines.append(tmpline) # omit header/comment lines
for i, ln in enumerate(lines[1:]): # lines[0] is the column headers
ifr.print_progress(i, len(lines))
tmp = ifr.smart_split(ln, sep=",")
key = tmp[0]
genebank = tmp[8]
unigene = tmp[10]
symbol = tmp[14]
affy_dict[key] = (genebank, unigene, symbol)
return affy_dict
def all_IFR_pairs_classification(ifr, numIter=20):
'''
computes the classification accuracy using all
pairs of IFR iterations from the flu_genelist SSVM IFR
'''
acc = {} #the classifier accuracy combining iteration i with j
(D,L,_,_) = ifr.load_flu_mat()
(D2,L2,_,_) = ifr.load_H1N1_mat()
removed = ifr.get_removed_features()
#compute L2 SVM test accuracies for all iterations upto numIter
print "Computing L2 SVM test accuracies for each IFR iteration."
test_acc_list = []
for x in range(numIter):
glx = removed[x]
tmp=pathway_classification(glx, (D,L), (D2,L2))
test_acc_list.append(tmp[0])
print "Computing L2 SVM test accuracies for all pairs of IFR iterations."
cur = 0
total = (numIter/2)*(numIter-1)
for i in range(numIter):
for j in range((i+1),numIter):
ifr.print_progress(cur, total)
cur+=1
gl1 = removed[i]
gl2 = removed[j]
gl = gl1+gl2
a1 = test_acc_list[i]
a2 = test_acc_list[j]
max_acc = max(a1,a2)
#compute combined accuracy
rc=pathway_classification(gl, (D,L), (D2,L2))
#store the results
acc[(i,j)] = (rc[0], "IFR %d + IFR %d"%(i,j), a1, a2, max_acc )
res = sorted( acc.values(), reverse=True)
return res, test_acc_list
def gen_affy_to_geneId_dict(affy_file_subdir="HG_U95A.na33.annot", affy_fn="HG_U95A.na33.annot.csv"):
"""
Converts a list of affymetric probe set ids into a genelist
with names suitable for querying gather or kegg. Generates
a dictionary with entries { affy_id : gene_id_list }. Most times, gene_id_list will
have only a single entry, but several probes have multiple Gene IDs given.
@param affy_file_subdir: The subdirectory of the ifr.DATA_DIR that has
the HG_U95A.na33.annot.csv file.
@param affy_fn: The csv file in the subdirectory with the data. The parameter is
provided in case the file was renamed from the orginal name of "HG_U95A.na33.annot.csv"
@note: Relies on a data file called HG_U95A.na33.annot.csv that must be present
in the HG_U95A.na33.annot subdirectory of the linked Data directory. It would
be most efficient to use this function once and save the resulting dictionary
in a pickle file for later use instead of having to re-parse the data.
"""
affy_dict = {}
affy_file = os.path.join(ifr.DATA_DIR, affy_file_subdir, affy_fn)
lines = []
with open(affy_file, "r") as f:
for tmpline in f:
if tmpline[0] != "#":
lines.append(tmpline) # omit header/comment lines
for i, ln in enumerate(lines[1:]): # lines[0] is the column headers
ifr.print_progress(i, len(lines))
tmp = ifr.smart_split(ln, sep=",")
key = tmp[0]
val = tmp[14]
if val == "---":
# this affy id has no gene symbol
genelist = []
elif "///" in val: # there are more than one GeneIds for this probe
# print "Subfield indicator in Gene Symbol for %s, line: %d."%(key,(i+1))
# print "Val: %s"%tmp[14]
genelist = [x.strip() for x in val.split("///") if x.strip() != ""]
else:
genelist = [val]
affy_dict[key] = list(set(genelist)) # remove duplicates
return affy_dict
