def fix_affy_dict(affy_dict):
"""
Given an affy dict in form { probe_id:(genebank,unigene,symbol)},
such as generated by get_geneids_from_affy() by reading a CSV file,
this attempts to fix those entries where the symbol was missing or
multiple-valued by doing a live query against the latest symbol
information from ncbi web sources.
"""
# N = len(affy_dict)
new_dict = {}
for ix, k in enumerate(affy_dict.keys()):
lookup = False
# svo_util.print_progress(ix, N)
(genebank, unigene, symbol) = affy_dict[k]
if symbol == "---":
print "(%d) %s unknown" % ((ix + 1), k),
lookup = True
elif "///" in symbol:
print "(%d) %s ambiguous" % ((ix + 1), k),
lookup = True
if lookup:
if (unigene == "---") or ("///" in unigene):
symbol = ifr.get_official_name(genebank)
else:
# if we have a unigene name, try it first,
# but if it doesn't work, then try the genebank
symbol = ifr.get_official_name(unigene)
if symbol == unigene:
symbol = ifr.get_official_name(genebank)
print " = %s" % symbol
new_dict[k] = (genebank, unigene, symbol)
return new_dict
def _pathway_classification(self,genelist,common_scale=False):
'''
Given a genelist from the data set, such as a collection of genes belonging to a specific
pathway, this function computes the accuracy of a standard (L2) SVM classifier
'''
(D,L) = self.traindat
(D2,L2) = self.testdat
G = self.feature_names
idxs = []
for x in genelist:
while x in self.known_aliases: x = self.known_aliases[x]
#alias could be key to another alias...so go down until we stop finding substitutions
if x in self.known_bad: continue #skip the ones we know are not resolvable
try:
idx = G.index(x)
except(ValueError):
print "Gene %s is not a known feature name. Querying for official name..."%x
xn = ifr.get_official_name(x, entrezgene=True)
if (xn is None) or (xn==x):
xn = None
self.known_bad.append(x)
print "No other official name found, gene will be skipped."
else:
print "Substituting %s for %s."%(xn,x)
self.known_aliases[x] = xn
try:
idx = G.index(xn) if (not xn is None) else None
except(ValueError):
idx = None #happens when official name is found, but still not in list
if not idx is None: idxs.append(idx)
rc = ifr.svm_engine((D,L), (D2,L2), perm=idxs, common_scale=common_scale, verbose=False,
no_normalization=False, loss="L2", penalty="L2", C=1.0)
return rc
def pathway_classification(genelist, feature_names=None, traindat=None, testdat=None, return_err_idxs=False,
common_scale=False, verbose=True ):
'''
Given a genelist from the flu data set, such as a collection of genes belonging to a specific
pathway, this function computes the accuracy of a standard (L2) SVM classifier
@param genelist: The list of genes forming the pathway
@param feature_names: The list of feature (gene) names associated with the columns of test/train data.
The feature_names must contain the genes in genelist, or a lookup will be performed to find the matching alias.
If None, then feature names will be the genes from the Duke Influenza data.
@param traindat: If None, then H3N2 data will be used. Else, specify the tuple (D,L) where D is the
data matrix (samples in rows) and L is the label vector
@param testdat: If None, then H1N1 data will be used. Else, specify (D2,L2) tuple for test data.
@param return_err_idxs: If true, then the indexes in the test set where the classifier is wrong will
be returned.
@param common_scale: If true, then the test data will be scaled using the training data mean/std, else
it will be scaled using its own mean/std.
@param verbose: If true, more output will be displayed.
@return: Either returns rc or rc, err_set, where rc is the return from the svm engine, which is the tuple
(test_accuracy, factors, clf, train_accuracy). See L{ifr.svm_engine}.
'''
global PC_KNOWN_BAD
global PC_KNOWN_ALIASES
if traindat is None:
(D,L,_,_) = ifr.load_flu_mat()
else:
(D,L) = traindat
if testdat is None:
(D2,L2,_,_) = ifr.load_H1N1_mat()
else:
(D2,L2) = testdat
G = feature_names if (not feature_names is None) else ( ifr.load_gene_ids(short_name_only=True) )
idxs = []
for x in genelist:
while x in PC_KNOWN_ALIASES:
if verbose: print "%s is known alias to %s."%(x, PC_KNOWN_ALIASES[x])
x = PC_KNOWN_ALIASES[x]
#alias could be key to another alias...so go down until we stop finding substitutions
if x in PC_KNOWN_BAD:
if verbose: print "%s is known bad, skipping gene."%x
continue
try:
idx = G.index(x)
except(ValueError):
#x is probably an alias to a gene name in G
if verbose:
print "Gene %s is not a known feature name. Querying for official name..."%x
xn = ifr.get_official_name(x, entrezgene=True)
if (xn is None) or (xn==x):
if verbose: print "No other official name found, gene will be skipped."
xn = None
PC_KNOWN_BAD.append(x)
else:
print "Substituting %s for %s."%(xn,x)
PC_KNOWN_ALIASES[x] = xn
try:
idx = G.index(xn) if (not xn is None) else None
except(ValueError):
idx = None #happens when official name is found, but still not in list
if not idx is None: idxs.append(idx)
rc = ifr.svm_engine((D,L), (D2,L2), perm=idxs, common_scale=common_scale, verbose=False,
no_normalization=False, loss="L2", penalty="L2", C=1.0)
if return_err_idxs:
IX = sp.array( range(len(L2)))
errs = IX[ rc[4] != L2] #indexes where prediction is not correct
err_set = set(errs)
return rc, err_set
else:
return rc
