Projects/laydi
Archived
7
0
Fork 0
Code Issues Pull Requests Activity

ups

Browse Source
This commit is contained in:
Arnar Flatberg
2007-07-28 16:05:11 +00:00
parent 9a2e259209
commit 349cab3c51
4 changed files with 297 additions and 131 deletions
Download Patch File Download Diff File Expand all files Collapse all files

104
scripts/lpls/rpy_go.py
View File

@@ -3,32 +3,14 @@ import scipy
import rpy
silent_eval = rpy.with_mode(rpy.NO_CONVERSION, rpy.r)
def get_term_sim(termlist, method = "JiangConrath", verbose=False):
"""Returns the similariy matrix between go-terms.
Arguments:
termlist: character vector of GO terms
method: one of
("JiangConrath","Resnik","Lin","CoutoEnriched","CoutoJiangConrath","CoutoResnik","CoutoLin")
verbose: print out various information or not
"""
_methods = ("JiangConrath","Resnik","Lin","CoutoEnriched","CoutoJiangConrath","CoutoResnik","CoutoLin")
assert(method in _methods)
assert(termlist[0][:2]=='GO')
rpy.r.library("GOSim")
return rpy.r.getTermSim(termlist, method = method, verbose = verbose)
def get_gene_sim(genelist, similarity='OA',
distance="Resnick"):
rpy.r.library("GOSim")
rpy.r.assign("ids", genelist)
silent_eval('a<-getGeneSim(ids)', verbose=FALSE)
def goterms_from_gene(genelist, ontology=['BP'], garbage = ['IEA', 'ISS', 'ND']):
def goterms_from_gene(genelist, ontology='BP', garbage=None):
""" Returns the go-terms from a specified genelist (Entrez id).
Recalculates the information content if needed based on selected evidence codes.
"""
rpy.r.library("GO")
rpy.r.library("GOSim")
_CODES = {"IMP" : "inferred from mutant phenotype",
"IGI" : "inferred from genetic interaction",
"IPI" :"inferred from physical interaction",
@@ -42,25 +24,46 @@ def goterms_from_gene(genelist, ontology=['BP'], garbage = ['IEA', 'ISS', 'ND'])
"IC" : "inferred by curator"
}
_ONTOLOGIES = ['BP', 'CC', 'MF']
assert(scipy.all([(code in _CODES) for code in garbage]))
assert(scipy.all([(ont in _ONTOLOGIES) for ont in ontology]))
have_these = rpy.r('as.list(GOTERM)').keys()
goterms = {}
#assert(scipy.all([(code in _CODES) for code in garbage]) or garbage==None)
assert(ontology in _ONTOLOGIES)
dummy = rpy.r.setOntology(ontology)
ddef = False
if ontology=='BP' and garbage!=None:
# This is for ont=BP and garbage =['IEA', 'ISS', 'ND']
rpy.r.load("ICsBPIMP_IGI_IPI_ISS_IDA_IEP_TAS_NAS_IC.rda")
ic = rpy.r.assign("IC",rpy.r.IC, envir=rpy.r.GOSimEnv)
print len(ic)
else:
ic = rpy.r('get("IC", envir=GOSimEnv)')
print "loading GO definitions environment"
gene2terms = {}
for gene in genelist:
goterms[gene] = []
info = rpy.r('GOENTREZID2GO[["' + str(gene) + '"]]')
#print info
if info:
skip=False
for term, desc in info.items():
if term not in have_these:
print "GO miss:"
print term
if desc['Ontology'] in ontology and desc['Evidence'] not in garbage:
goterms[gene].append(term)
if ic.get(term)==scipy.isinf:
print "\nIC is Inf on this GO term %s for this gene: %s" %(term,gene)
skip=True
if ic.get(term)==None:
#print "\nHave no IC on this GO term %s for this gene: %s" %(term,gene)
skip=True
if desc['Ontology']!=ontology:
#print "\nThis GO term %s belongs to: %s:" %(term,desc['Ontology'])
skip = True
if not skip:
if gene2terms.has_key(gene):
gene2terms[gene].append(term)
else:
gene2terms[gene] = [term]
else:
print "\nHave no Annotation on this gene: %s" %gene
return goterms
return gene2terms
def genego_matrix(goterms, tmat, gene_ids, term_ids, func=min):
def genego_matrix(goterms, tmat, gene_ids, term_ids, func=max):
ngenes = len(gene_ids)
nterms = len(term_ids)
gene2indx = {}
@@ -71,23 +74,46 @@ def genego_matrix(goterms, tmat, gene_ids, term_ids, func=min):
term2indx[id]=i
#G = scipy.empty((nterms, ngenes),'d')
G = []
newindex = []
new_gene_index = []
for gene, terms in goterms.items():
g_ind = gene2indx[gene]
if len(terms)>0:
t_ind = []
newindex.append(g_ind)
new_gene_index.append(g_ind)
for term in terms:
if term2indx.has_key(term): t_ind.append(term2indx[term])
print t_ind
subsim = tmat[t_ind, :]
gene_vec = scipy.apply_along_axis(func, 0, subsim)
G.append(gene_vec)
return scipy.asarray(G), newindex
return scipy.asarray(G), new_gene_index
def genego_sim(gene2go, gene_ids, all_go_terms, STerm, go_term_sim="OA", term_sim="Lin", verbose=False):
"""Returns go-terms x genes similarity matrix.
:input:
- gene2go: dict: keys: gene_id, values: go_terms
- gene_ids: list of gene ids (entrez ids)
- STerm: (go_terms x go_terms) similarity matrix
- go_terms_sim: similarity measure between a gene and multiple go terms (max, mean, OA)
- term_sim: similarity measure between two go-terms
- verbose
"""
rpy.r.library("GOSim")
#gene_ids = gene2go.keys()
GG = scipy.empty((len(all_go_terms), len(gene_ids)), 'd')
for j,gene in enumerate(gene_ids):
for i,go_term in enumerate(all_go_terms):
if verbose:
print "\nAssigning similarity from %s to terms(gene): %s" %(go_term,gene)
GG_ij = rpy.r.getGSim(go_term, gene2go[gene], similarity=go_term_sim,
similarityTerm=term_sim, STerm=STerm, verbose=verbose)
GG[i,j] = GG_ij
return GG
def goterm2desc(gotermlist):
"""Returns the go-terms description keyed by go-term
"""Returns the go-terms description keyed by go-term.
"""
rpy.r.library("GO")
term2desc = {}

108
scripts/lpls/run_smoker.py
View File

@@ -23,7 +23,7 @@ data = DX.asarray().T
rpy.r.assign("data", data)
cl = dot(DY.asarray(), diag([1,2,3])).sum(1)
rpy.r.assign("cl", cl)
rpy.r.assign("B", 100)
rpy.r.assign("B", 20)
# Perform a SAM analysis.
print "Starting SAM"
sam = rpy.r('sam.out<-sam(data=data,cl=cl,B=B,rand=123)')
@@ -32,63 +32,74 @@ print "SAM done"
qq = rpy.r('qobj<-qvalue(sam.out@p.value)')
qvals = asarray(qq['qvalues'])
# cut off
co = 0.001
index = where(qvals<0.01)[0]
cutoff = 2
index = where(qvals<cutoff)[0]
# Subset data
X = DX.asarray()
Xr = X[:,index]
gene_ids = DX.get_identifiers('gene_ids', index)
print "\nWorkiing on subset with %s genes " %len(gene_ids)
### Build GO data ####
print "\nWorking on subset with %s genes " %len(gene_ids)
#gene2ind = {}
#for i, gene in enumerate(gene_ids):
# gene2ind[gene] = i
print "Go terms ..."
goterms = rpy_go.goterms_from_gene(gene_ids)
terms = set()
for t in goterms.values():
terms.update(t)
terms = list(terms)
print "Number of go-terms: %s" %len(terms)
### Build GO data ####
print "\n\nFiltering genes by Go terms "
gene2goterms = rpy_go.goterms_from_gene(gene_ids)
all_terms = set()
for t in gene2goterms.values():
all_terms.update(t)
terms = list(all_terms)
print "\nNumber of go-terms: %s" %len(terms)
# update genelist
gene_ids = gene2goterms.keys()
print "\nNumber of genes: %s" %len(gene_ids)
rpy.r.library("GOSim")
# Go-term similarity matrix
methods = ("JiangConrath","Resnik","Lin","CoutoEnriched","CoutoJiangConrath","CoutoResnik","CoutoLin")
meth = methods[0]
meth = methods[3]
print "Term-term similarity matrix (method = %s)" %meth
if meth=="CoutoEnriched":
rpy.r('setEnrichmentFactors(alpha=0.1,beta=0.5)')
print "Calculating term-term similarity matrix"
tmat = rpy.r.getTermSim(terms, verbose=False, method=meth)
print "\nCalculating term-term similarity matrix"
rpytmat1 = rpy.with_mode(rpy.NO_CONVERSION, rpy.r.getTermSim)(terms, method=meth,verbose=False)
tmat1 = rpy.r.assign("haha", rpytmat1)
# check if all terms where found
nanindex = where(isnan(tmat1[:,0]))[0]
if len(nanindex)>0:
raise valueError("NANs in tmat")
# Z-matrix
#Z, newind = rpy_go.genego_matrix(terms, tmat, gene_ids, terms,func=mean)
#Z = Z.T
Z1 = rpy_go.genego_sim(gene2goterms,gene_ids,terms,rpytmat1,go_term_sim="OA",term_sim=meth)
#### do another
meth = methods[4]
rpytmat = rpy.with_mode(rpy.NO_CONVERSION, rpy.r.getTermSim)(terms, method=meth,verbose=False)
tmat = rpy.r.assign("haha", rpytmat)
# check if all terms where found
nanindex = where(isnan(tmat[:,0]))[0]
keep=[]
has_miss = False
if len(nanindex)>0:
has_miss = True
print "Some terms missing in similarity matrix"
keep = where(isnan(tmat[:,0])!=True)[0]
print "Number of nans: %d" %len(nanindex)
tmat_new = tmat[:,keep][keep,:]
new_terms = [i for ind,i in enumerate(terms) if ind in keep]
bad_terms = [i for ind,i in enumerate(terms) if ind not in keep]
# update go-term dict
for gene,trm in goterms.items():
for t in trm:
if t in bad_terms:
trm.remove(t)
if len(trm)==0:
print "Removing gene: %s" %gene
goterms[gene]=trm
terms = new_terms
tmat = tmat_new
raise valueError("NANs in tmat")
# Z-matrix
# func (min, max, median, mean, etc),
# func decides on the representation of gene-> goterm when multiple
# goterms exist for one gene
Z, newind = rpy_go.genego_matrix(goterms, tmat, gene_ids, terms,func=mean)
Z = Z.T
# update X matrix (no go-terms available)
Xr = Xr[:,newind]
new_gene_ids = asarray(gene_ids)[newind]
#Z, newind = rpy_go.genego_matrix(terms, tmat, gene_ids, terms,func=mean)
#Z = Z.T
Z = rpy_go.genego_sim(gene2goterms,gene_ids,terms,rpytmat,go_term_sim="OA",term_sim=meth)
# update data (X) matrix
#newind = [gene2ind[gene] for gene in gene_ids]
newind = DX.get_indices('gene_ids', gene_ids)
Xr = X[:,newind]
#new_gene_ids = asarray(gene_ids)[newind]
######## LPLSR ########
@@ -112,11 +123,14 @@ if alpha_check:
rmsep , yhat, ce = cv_lpls(Xr, Y, Z, a_max, alpha=alpha)
Rmsep.append(rmsep)
Yhat.append(yhat)
CE.append(yhat)
CE.append(ce)
Rmsep = asarray(Rmsep)
Yhat = asarray(Yhat)
CE = asarray(CE)
figure(200)
# Significance Hotellings T
Wx, Wz, Wy, = jk_lpls(Xr, Y, Z, aopt)
@@ -135,7 +149,13 @@ for a in range(m):
ylim([rmsep.min()-.05, rmsep.max()+.05])
title('RMSEP')
figure(2) # Hypoid correlations
figure(2)
for a in range(m):
bar(arange(a_max)+a*bar_w+.1, class_error[:,a], width=bar_w, color=bar_col[a])
ylim([class_error.min()-.05, class_error.max()+.05])
title('Classification accuracy')
figure(3) # Hypoid correlations
plot_corrloads(Rz, pc1=0, pc2=1, s=tsqz/10.0, c='b', zorder=5, expvar=evz, ax=None)
ax = gca()
ylabels = DY.get_identifiers('_cat', sorted=True)