Tralala ...

fluents/lib/blmfuncs.py

@@ -350,14 +350,6 @@ class PLS(Model):
         self.validation()
         self.make_model(self.model['E0'], self.model['F0'],
                         **options.make_model_options())
-        # variance captured
-        var_x, exp_var_x = variances(self.model['E0'], self.model['T'], self.model['P'])
-        self.model['evx'] = var_x
-        self.model['exp_var_x'] = exp_var_x
-
-        var_y, exp_var_y = variances(self.model['F0'], self.model['T'], self.model['Q'])
-        self.model['evy'] = var_y
-        self.model['exp_var_y'] = exp_var_y
                             
         if options['calc_conf']:
             self.confidence(**options.confidence_options())
@@ -435,7 +427,7 @@ class LPLS(Model):
         engine = opt['engine']
         dat = engine(self._data['X'], self._data['Y'], self._data['Z'],
                      opt['amax'], opt['xz_alpha'], opt['center_mth'],
-                     opt['mode'], opt['scale'], False)
+                     opt['scale'], False)
         self.model.update(dat)
         
     def as_dataset(self, name, dtype='Dataset'):
@@ -464,17 +456,21 @@ class LPLS(Model):
         match_ids = {'E' : [ids_0, ids_1],
                      'P' : [ids_1, pc_ids],
                      'T' : [ids_0, pc_ids],
+                     'U' : [ids_0, pc_ids],
                      'W' : [ids_1, pc_ids],
                      'L' : [ids_4, pc_ids],
                      'Q' : [ids_3, pc_ids],
                      'F' : [ids_0, ids_3],
                      'B' : [ids_1, ids_3],
+                     'K' : [ids_1, pc_ids],
                      'tsqx' : [ids_1, zero_dim],
                      'tsqz' : [ids_4, zero_dim],
-                     'K' : [ids_1, pc_ids],
                      'rmsep' : [ids_3, pc_ids],
                      'Rx' : [ids_1, pc_ids],
-                     'Rz' : [ids_4, pc_ids]
+                     'Rz' : [ids_4, pc_ids],
+                     'evx' : [ids_1, zero_dim],
+                     'evy' : [ids_3, zero_dim],
+                     'evz' : [ids_4, zero_dim]
                      }
         
         try:

fluents/lib/cx_stats.py

@@ -1,14 +1,20 @@
+import time
+import cPickle
+
 from scipy import zeros,zeros_like,sqrt,dot,trace,sign,round_,argmax,\
      sort,ravel,newaxis,asarray,diag,sum,outer,argsort,arange,ones_like,\
-     all,apply_along_axis,eye,atleast_2d
+     all,apply_along_axis,eye,atleast_2d,empty
 from scipy.linalg import svd,inv,norm,det,sqrtm
 from scipy.stats import mean,median
+
+#import plots_lpls
+
 from cx_utils import mat_center
 from validation import pls_jkW, lpls_jk
 from select_generators import shuffle_1d
 from engines import pca, pls, bridge
 from engines import nipals_lpls as lpls
-import time
+
 
 
 def hotelling(Pcv, P, p_center='med', cov_center='med',
@@ -292,7 +298,7 @@ def variances(a, t, p):
     
     tot_var = sum(a**2)
     var = 100*(sum(p**2, 0)*sum(t**2, 0))/tot_var
-    var_exp = cumsum(var)
+    var_exp = var.cumsum()
     return var, var_exp
 
 def residual_diagnostics(Y, Yhat, aopt=1):
@@ -365,7 +371,7 @@ def mahalanobis(a, loc=None, acov=None, invcov=None):
 
 def lpls_qvals(a, b, c, aopt=None, alpha=.3, zx_alpha=.5, n_iter=20,
                sim_method='shuffle',p_center='med', cov_center='med',crot=True,
-               strict=False, mean_ctr=[2,0,2]):
+               strict=False, mean_ctr=[2,0,2], nsets=None):
 
     """Returns qvals for l-pls model.
 
@@ -392,26 +398,25 @@ def lpls_qvals(a, b, c, aopt=None, alpha=.3, zx_alpha=.5, n_iter=20,
     # Full model
     #print "Full model start"
     dat = lpls(a, b, c, aopt, scale='loads', mean_ctr=mean_ctr)
-    Wc,Lc = lpls_jk(a, b, c ,aopt)
+    Wc, Lc = lpls_jk(a, b, c , aopt, nsets=nsets)
     #print "Full hot"
-    cal_tsq_x = hotelling(Wc, dat['W'], alpha=alpha)
+    cal_tsq_x = hotelling(Wc, dat['W'], alpha = alpha)
-    cal_tsq_z = hotelling(Lc, dat['L'], alpha=alpha)
+    cal_tsq_z = hotelling(Lc, dat['L'], alpha = 0)
     
     # Perturbations
     Vs = shuffle_1d(b, n_iter, axis=0)
     for i, b_shuff in enumerate(Vs):
-        #print i
+        print i
-        time.sleep(.01)
         dat = lpls(a, b_shuff,c, aopt, scale='loads', mean_ctr=mean_ctr)
-        Wi, Li = lpls_jk(a, b_shuff, c, aopt)
+        Wi, Li = lpls_jk(a, b_shuff, c, aopt, nsets=nsets)
         pert_tsq_x[:,i] = hotelling(Wi, dat['W'], alpha=alpha)
         pert_tsq_z[:,i] = hotelling(Li, dat['L'], alpha=alpha)
    
-    return fdr(cal_tsq_z, pert_tsq_z, median), fdr(cal_tsq_x, pert_tsq_x, median)
+    return cal_tsq_z, pert_tsq_z, cal_tsq_x, pert_tsq_x
     
 
 
-def fdr(tsq, tsqp, loc_method=median):
+def fdr(tsq, tsqp, loc_method='mean'):
     n, = tsq.shape
     k, m = tsqp.shape
     assert(n==k)
@@ -421,8 +426,13 @@ def fdr(tsq, tsqp, loc_method=median):
     for i in xrange(m):
         for j in xrange(n):
             n_false[j,i] = (tsqp[:,i]>tsq[j]).sum()
-    
+    #cPickle.dump(n_false, open("/tmp/nfalse.dat_"+str(n), "w"))
-    fp = loc_method(n_false,1)
+    if loc_method=='mean':
+        fp = mean(n_false,1)
+    elif loc_method == 'median':
+        fp = median(n_false.T)
+    else:
+        raise ValueError
     n_signif = (arange(n) + 1.0)[r_index]
     fd_rate = fp/n_signif
     return fd_rate

fluents/lib/engines.py

@@ -367,7 +367,6 @@ def w_simpls(aat, b, aopt):
     T = empty((m, aopt))
     H = empty((m, aopt)) # R
     PROJ = empty((m, aopt)) # P?
-
     for i in range(aopt):
         q, s, vh = svd(dot(dot(b.T, aat), b), full_matrices=0)
         u = dot(b, q[:,:1]) #y-factor scores
@@ -722,6 +721,11 @@ def esvd(data, amax=None):
     :notes:
     Numpy supports this by setting full_matrices=0
     """
+    has_arpack = True
+    try:
+        import arpack
+    except:
+        has_arpack = False
     m, n = data.shape
     if m>=n:
         kernel = dot(data.T, data)

fluents/lib/nx_utils.py

@@ -517,7 +517,7 @@ def K_diffusion2(W, normalised=True, alpha=1.0, beta=0.5, ncomp=None):
     return expm(-beta*L)
     
     
-def K_modularity(W,alpha=1.0):
+def K_modularity(W, alpha=1.0):
     """ Returns the matrix square root of Newmans modularity."""
     W = asarray(W)
     t = W.dtype.char
@@ -559,7 +559,7 @@ def modularity_matrix(G, nodelist=None):
     A = NX.adj_matrix(G, nodelist=nodelist)
     d = atleast_2d(G.degree(nbunch=nodelist))
     m = 1.*G.number_of_edges()
-    B = A - A/m
+    B = A - dot(d.T, d)/m
     return B
 
 

fluents/lib/select_generators.py

@@ -42,8 +42,8 @@ def pls_gen(a, b, n_blocks=None, center=False, index_out=False,axis=0):
      """Random block crossvalidation
     Leave-one-out is a subset, with n_blocks equals a.shape[-1]
     """
-     #index = randperm(a.shape[axis])
+     index = randperm(a.shape[axis])
-     index = arange(a.shape[axis])
+     #index = arange(a.shape[axis])
      if n_blocks==None:
           n_blocks = a.shape[axis]
      n_in_set = ceil(float(a.shape[axis])/n_blocks)

fluents/lib/validation.py

@@ -9,6 +9,7 @@ from select_generators import w_pls_gen,w_pls_gen_jk,pls_gen,pca_gen,diag_pert
 from engines import w_simpls,pls,bridge,pca,nipals_lpls
 from cx_utils import m_shape
 
+
 def w_pls_cv_val(X, Y, amax, n_blocks=None):
     """Returns rmsep and aopt for pls tailored for wide X.
 
@@ -117,6 +118,7 @@ def lpls_val(X, Y, Z, a_max=2, nsets=None,alpha=.5, mean_ctr=[2,0,2]):
     Yhatc = empty((a_max, k, l), 'd')
     sep2 = empty((a_max, k, l), 'd')
     for i, (xcal,xi,ycal,yi,ind) in enumerate(cv_iter):
+        print ind
         dat = nipals_lpls(xcal,ycal,Z,
                           a_max=a_max,
                           alpha=alpha,
@@ -140,7 +142,7 @@ def lpls_val(X, Y, Z, a_max=2, nsets=None,alpha=.5, mean_ctr=[2,0,2]):
             
     # todo: need a better support for class validation
     y_is_class = Y.dtype.char.lower() in ['i','p', 'b', 'h','?']
-    print Y.dtype.char
+    #print Y.dtype.char
     if y_is_class:
         Yhat_class = zeros_like(Yhat)
         for a in range(a_max):
@@ -280,7 +282,7 @@ def lpls_jk(X, Y, Z, a_max, nsets=None, xz_alpha=.5, mean_ctr=[2,0,2]):
     WWx = empty((nsets, n, a_max), 'd')
     WWz = empty((nsets, o, a_max), 'd')
     #WWy = empty((nsets, l, a_max), 'd')
-    for i, (xcal,xi,ycal,yi) in enumerate(cv_iter):
+    for i, (xcal, xi, ycal, yi) in enumerate(cv_iter):
         dat = nipals_lpls(xcal,ycal,Z,a_max=a_max,alpha=xz_alpha,
                           mean_ctr=mean_ctr,scale='loads',verbose=False)
         WWx[i,:,:] = dat['W']

fluents/plots.py

@@ -783,6 +783,7 @@ class NetworkPlot(Plot):
         
         index = scipy.nonzero((xdata>x1) & (xdata<x2) & (ydata>y1) & (ydata<y2))[0]
         ids = self.dataset.get_identifiers(self.current_dim, index)
+        print "ids in rsc: %s" %str(ids)
         ids = self.update_selection(ids, key)
         self.selection_listener(self.current_dim, ids)
 

scripts/lpls/plots_lpls.py

@@ -46,7 +46,7 @@ def dag(terms, ontology):
     __parents = {'bp' : rpy.r.GOBPPARENTS,
                  'mf' : rpy.r.GOMFPARENTS,
                  'cc' : rpy.r.GOCCPARENTS}
-    gograph = rpy.r.GOGraph(terms, __parents.get(ontology))
+    gograph = rpy.r.GOGraph(terms, __parents.get(ontology.lower()))
     dag = rpy.r.edges(gograph)
     #setattr(dag, "_ontology", ontology)
     return dag

scripts/lpls/rpy_go.py

@@ -4,7 +4,7 @@ import rpy
 silent_eval = rpy.with_mode(rpy.NO_CONVERSION, rpy.r)
 import collections
 
-def goterms_from_gene(genelist, ontology='BP', garbage=None):
+def goterms_from_gene(genelist, ontology='BP', garbage=None, ic_cutoff=2.0):
     """ Returns the go-terms from a specified genelist (Entrez id).
 
     Recalculates the information content if needed based on selected evidence codes.
@@ -37,38 +37,30 @@ def goterms_from_gene(genelist, ontology='BP', garbage=None):
         ic = rpy.r('get("IC", envir=GOSimEnv)')
     print "loading GO definitions environment"
     
-    gene2terms = {}
+    gene2terms = collections.defaultdict(list)
     cc = 0
     dd = 0
     ii = 0
-    for gene in genelist:
+    jj = 0
-        info = rpy.r('GOENTREZID2GO[["' + str(gene) + '"]]')
+    all = rpy.r.mget(gene_ids, rpy.r.GOENTREZID2GO,ifnotfound="NA")
-        #print info
+    for gene, terms in all.items():
-        if info:
+        if terms!="NA":
-            skip=False
+            for term,desc in terms.items():
-            for term, desc in info.items():
+                if desc['Ontology'].lower() == ontology and term in ic:
-                if ic.get(term)==scipy.isinf:
+                    if ic[term]>.88:
-                    print "\nIC is Inf on this GO term %s for this gene: %s" %(term,gene)
+                        jj+=1
-                    skip=True
+                        continue
-                if ic.get(term)==None:
+                    cc+=1
-                    #print "\nHave no IC on this GO term %s for this gene: %s" %(term,gene)
+                    gene2terms[gene].append(term)
-                    skip=True
+                else:
-                    ii += 1
+                    dd+=1
-                if desc['Ontology']!=ontology:
-                    #print "\nThis GO term %s belongs to: %s:" %(term,desc['Ontology'])
-                    skip = True
-                    dd += 1
-                if not skip:
-                    if gene2terms.has_key(gene):
-                        gene2terms[gene].append(term)
-                    else:
-                        gene2terms[gene] = [term]
         else:
-            cc += 1
+            ii+=1
                     
-    print "\nNumber of genes without annotation: %d" %cc 
+        
+    print "\nNumber of genes without annotation: %d" %ii 
     print "\nNumber of genes not in %s : %d " %(ontology, dd)
-    print "\nNumber of genes with infs : %d " %ii
+    print "\nNumber of genes with too high IC : %d " %jj
     
     return gene2terms
 
@@ -220,3 +212,15 @@ def data_aff2loc_hgu133a(X, aff_ids, verbose=False):
         print "Ids with unique probeset: %d" %s
     X = scipy.asarray(new_data).T
     return X, new_ids
+
+def R_PLS(x,y,ncomp=3, validation='"LOO"'):
+    rpy.r.library("pls")
+    rpy.r.assign("X", x)
+    rpy.r.assign("Y", y)
+    callstr = "plsr(Y~X, ncomp=" + str(ncomp) + ", validation=" + validation + ")"
+    print callstr
+    result = rpy.r(callstr)
+    return result
+
+
+def gogene()

scripts/lpls/run_smoker.py

@@ -1,17 +1,56 @@
 import sys
 import rpy
-from pylab import gca, figure, subplot
+from pylab import gca, figure, subplot,plot
 from scipy import *
-from lpls import *
+from scipy.linalg import norm
+from lpls import correlation_loadings
+
 import rpy_go
 sys.path.append("../../fluents") # home of dataset
 sys.path.append("../../fluents/lib") # home of cx_stats
+sys.path.append("/home/flatberg/fluents/scripts/lpls")
 import dataset
 import cx_stats
-from plots_lpls import plot_corrloads
+from engines import nipals_lpls
+from validation import lpls_val, lpls_jk
+from plots_lpls import plot_corrloads, plot_dag
+import plots_lpls
+
+# Possible outliers
+# http://www.pubmedcentral.nih.gov/articlerender.fcgi?tool=pubmed&pubmedid=16817967
+sample_outliers = ['OV:NCI_ADR_RES', 'CNS:SF_295', 'CNS:SF_539', 'RE:SN12C', 'LC:NCI_H226', 'LC:NCI_H522', 'PR:PC_3', 'PR:DU_145']
+
+
+####### OPTIONS ###########
+# data
+chip = "hgu133a"
+use_data = 'uma'
+subset = 'plsr'
+small_test = False
+use_sbg_subset = True # the sandberg nci-Ygroups subset
+std_y = True
+std_z = False
+# go
+ontology = "bp"
+min_genes = 5
+similarities = ("JiangConrath","Resnik","Lin","CoutoEnriched","CoutoJiangConrath","CoutoResnik","CoutoLin")
+meth = similarities[2]
+go_term_sim = "OA"
+# lpls
+a_max = 5
+aopt = 2
+xz_alpha = .4
+w_alpha = .3
+mean_ctr = [2, 0, 2]
+nsets = None
+qval_cutoff = 0.01
+n_iter = 200
+
+alpha_check = False
+calc_rmsep = False
+
 
 ######## DATA ##########
-use_data='uma'
 if use_data=='smoker':
     # full smoker data
     DX = dataset.read_ftsv(open("../../data/smokers-full/Smokers.ftsv"))
@@ -21,7 +60,7 @@ if use_data=='smoker':
 elif use_data=='scherf':
     DX = dataset.read_ftsv(open("../../data/scherf/scherfX.ftsv"))
     DY = dataset.read_ftsv(open("../../data/scherf/scherfY.ftsv"))
-    Y = DY.asarray().astype('d')
+    Yg = DY.asarray().astype('d')
     gene_ids = DX.get_identifiers('gene_ids', sorted=True)
 elif use_data=='staunton':
     pass
@@ -30,10 +69,16 @@ elif use_data=='uma':
     DYg = dataset.read_ftsv(open("../../data/uma/Yg133.ftsv"))
     DY = dataset.read_ftsv(open("../../data/uma/Yd.ftsv"))
     Y = DY.asarray().astype('d')
+    Yg = DYg.asarray().astype('d')
     gene_ids = DX.get_identifiers('gene_ids', sorted=True)
 
 # use subset with defined GO-terms
-gene2goterms = rpy_go.goterms_from_gene(gene_ids)
+ic_all = 2026006.0 # sum of all ic in BP
+max_ic = -log(1/ic_all)
+ic_cutoff = -log(min_genes/ic_all)/max_ic
+print "Information cutoff for min %d genes: %.2f" %(min_genes, ic_cutoff)
+
+gene2goterms = rpy_go.goterms_from_gene(gene_ids, ic_cutoff=ic_cutoff)
 all_terms = set()
 for t in gene2goterms.values():
     all_terms.update(t)
@@ -48,20 +93,18 @@ X = DX.asarray()
 index = DX.get_indices('gene_ids', gene_ids)
 X = X[:,index]
 
-1/0
-
 # Use only subset defined on GO
 ontology = 'BP'
 print "\n\nFiltering genes by Go terms "
 
-# use subset based on SAM or IQR
+# use subset based on SAM,PLSR or (IQR)
-subset = 'not'
+
 if subset=='sam':
     # select subset genes by SAM
     rpy.r.library("siggenes")
     rpy.r.library("qvalue")
     rpy.r.assign("data", X.T)
-    cl = dot(DY.asarray(), diag(arange(Y.shape[1])+1)).sum(1)
+    cl = dot(DYg.asarray(), diag(arange(Yg.shape[1])+1)).sum(1)
     rpy.r.assign("cl", cl)
     rpy.r.assign("B", 20)
     # Perform a SAM analysis.
@@ -72,21 +115,30 @@ if subset=='sam':
     qq = rpy.r('qobj<-qvalue(sam.out@p.value)')
     qvals = asarray(qq['qvalues'])
     # cut off
-    cutoff = 0.01
+    cutoff = 0.001
     index = where(qvals<cutoff)[0]
+    if small_test:
+        index = index[:20]
+    
     # Subset data
     X = X[:,index]
     
     gene_ids = [gid for i, gid in enumerate(gene_ids) if i in index]
+    print "\nNumber of genes: %s" %len(gene_ids)
     print "\nWorking on subset with %s genes " %len(gene_ids)
 
     # update valid go-terms
-    gene2goterms = rpy_go.goterms_from_gene(gene_ids)
+    gene2goterms = rpy_go.goterms_from_gene(gene_ids, ic_cutoff=ic_cutoff)
     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)
+elif subset=='plsr':
+    cx_stats.pls_qvals(X, Y)
 else:
     # noimp (smoker data is prefiltered)
     pass
@@ -94,16 +146,18 @@ else:
 
 rpy.r.library("GOSim")
 # Go-term similarity matrix
-methods = ("JiangConrath","Resnik","Lin","CoutoEnriched","CoutoJiangConrath","CoutoResnik","CoutoLin")
-meth = methods[2]
-print "Term-term similarity matrix (method = %s)" %meth
 
+print "Term-term similarity matrix (method = %s)" %meth
 print "\nCalculating term-term similarity matrix"
 
+if meth=="CoutoEnriched":
+    aa = 0
+    ba = 0
+    rpy.r.setEnrichmentFactors(alpha = aa, beta =ba) 
 rpytmat = rpy.with_mode(rpy.NO_CONVERSION, rpy.r.getTermSim)(terms, method=meth,verbose=False)
 tmat = rpy.r.assign("haha", rpytmat)
 print "\n Calculating Z matrix"
-Z = rpy_go.genego_sim(gene2goterms,gene_ids,terms,rpytmat,go_term_sim="OA",term_sim=meth)
+Z = rpy_go.genego_sim(gene2goterms,gene_ids,terms,rpytmat,go_term_sim=go_term_sim,term_sim=meth)
 
 # update data (X) matrix
 newind = DX.get_indices('gene_ids', gene_ids)
@@ -112,72 +166,131 @@ Xr = DX.asarray()[:,newind]
 
 ######## LPLSR ######## 
 print "LPLSR ..."
-a_max = 10
+Y = Yg
-aopt = 3
+
-xz_alpha = .6
+if use_sbg_subset:
-w_alpha = .1
+    Y_old = Y.copy()
-mean_ctr = [2, 0, 2]
+    Xr_old = Xr.copy() 
+    keep_samples = ['CN', 'ME', 'LE', 'CO', 'RE']
+    sample_ids = DY.get_identifiers('cline', sorted=True)
+    keep_ind = [i for i,name in enumerate(sample_ids) if name[:2] in keep_samples]
+    Xr = Xr[keep_ind,:]
+    Y = Y[keep_ind,:]
+    Y = Y[:, where(Y.sum(0)>1)[0]]
+    
 
 # standardize Z?
 sdtz = False
 if sdtz:
     Z = Z/Z.std(0)
 
-T, W, P, Q, U, L, K, B, b0, evx, evy, evz,mnx,mny,mnz = nipals_lpls(Xr,Y,Z, a_max,
+sdty = True
-                                                                    alpha=xz_alpha,
+if sdty:
-                                                                    mean_ctr=mean_ctr)
+    Y = Y/Y.std(0)
+lpls_result = nipals_lpls(Xr,Y,Z, a_max,alpha=xz_alpha,mean_ctr=mean_ctr)
+globals().update(lpls_result)
 
 # Correlation loadings
 dx,Rx,rssx = correlation_loadings(Xr, T, P)
 dx,Ry,rssy = correlation_loadings(Y, T, Q)
 cadz,Rz,rssz = correlation_loadings(Z.T, W, L)
-# Prediction error
-rmsep , yhat, class_error = cv_lpls(Xr, Y, Z, a_max, alpha=xz_alpha,mean_ctr=mean_ctr)
-alpha_check=True
-if alpha_check:
 
+# Prediction error
+if calc_rmsep:
+    rmsep , yhat, class_error = lpls_val(Xr, Y, Z, a_max, alpha=xz_alpha,mean_ctr=mean_ctr)
+
+
+if alpha_check:  
     Alpha = arange(0.01, 1, .1)
     Rmsep,Yhat, CE = [],[],[]
     for a in Alpha:
         print "alpha %f" %a
-        rmsep , yhat, ce = cv_lpls(Xr, Y, Z, a_max, alpha=xz_alpha,mean_ctr=mean_ctr)
+        rmsep , yhat, ce = lpls_val(Xr, Y, Z, a_max, alpha=a,mean_ctr=mean_ctr,nsets=nsets)
-        Rmsep.append(rmsep)
+        Rmsep.append(rmsep.copy())
-        Yhat.append(yhat)
+        #Yhat.append(yhat.copy())
-        CE.append(ce)
+        #CE.append(ce.copy())
     Rmsep = asarray(Rmsep)
-    Yhat = asarray(Yhat)
+    #Yhat = asarray(Yhat)
-    CE = asarray(CE)
+    #CE = asarray(CE)
 
 
 # Significance Hotellings T
-Wx, Wz, Wy, = jk_lpls(Xr, Y, Z, aopt, mean_ctr=mean_ctr,alpha=xz_alpha)
+#Wx, Wz = lpls_jk(Xr, Y, Z, aopt, mean_ctr=mean_ctr, xz_alpha=xz_alpha, nsets=nsets)
-Ws = W*apply_along_axis(norm, 0, T)
+#Ws = W*apply_along_axis(norm, 0, T)
-tsqx = cx_stats.hotelling(Wx, Ws[:,:aopt], alpha=w_alpha)
+#tsqx = cx_stats.hotelling(Wx, Ws[:,:aopt], alpha=w_alpha)
-tsqz = cx_stats.hotelling(Wz, L[:,:aopt], alpha=0)
+#tsqz = cx_stats.hotelling(Wz, L[:,:aopt], alpha=0)
+
+# qvals
+cal_tsq_z, pert_tsq_z, cal_tsq_x, pert_tsq_x = cx_stats.lpls_qvals(Xr, Y, Z, aopt=aopt, zx_alpha=xz_alpha, n_iter=n_iter)
+
+qvalz = cx_stats.fdr(cal_tsq_z, pert_tsq_z, 'median')
+qvalx = cx_stats.fdr(cal_tsq_x, pert_tsq_x, 'median')
 
 
-## plots ##
+# p-values, set-enrichment analysis
-figure(1) #rmsep
+active_genes_ids = where(qvalx < qval_cutoff)[0]
-bar_w = .2
+active_genes = [name for i,name in enumerate(gene_ids) if i in active_genes_ids]
-bar_col = 'rgb'*5
+active_universe = gene_ids
-m = Y.shape[1]
+gsea_result, gsea_params= rpy_go.gene_GO_hypergeo_test(genelist=active_genes,universe=active_universe,chip=chip,pval_cutoff=1.0,cond=False,test_direction="over")
-for a in range(m):
+active_goterms_ids = where(qvalz < qval_cutoff)[0]
-    bar(arange(a_max)+a*bar_w+.1, rmsep[:,a], width=bar_w, color=bar_col[a])
+active_goterms = [name for i,name in enumerate(terms) if i in active_goterms_ids]
-ylim([rmsep.min()-.05, rmsep.max()+.05]) 
-title('RMSEP')
 
-figure(2)
+gsea_t2p = dict(zip(gsea_result['GOBPID'], gsea_result['Pvalue']))
-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
+
+
+
+#### PLOTS ####
+
+from pylab import *
+from scipy import where
+dg = plots_lpls.dag(terms, "bp")
+pos = None
+
+figure(300)
+subplot(2,1,1)
+pos = plots_lpls.plot_dag(dg, node_color=cal_tsq_z, pos=pos, nodelist=terms)
+subplot(2,1,2)
+pos = plot_dag(dg, node_color=qvalz, pos=pos, nodelist=terms)
+
+
+if calc_rmsep:
+    figure(1) #rmsep
+    bar_w = .2
+    bar_col = 'rgb'*5
+    m = Y.shape[1]
+    for a in range(m):
+        bar(arange(a_max)+a*bar_w+.1, rmsep[:,a], width=bar_w, color=bar_col[a])
+    ylim([rmsep.min()-.05, rmsep.max()+.05]) 
+    title('RMSEP: Y(%s)' %Y.get_name())
+
+#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) # Hyploid correlations
+tsqz = cal_tsq_z
+tsqx = cal_tsq_x
 tsqz_s = 250*tsqz/tsqz.max()
-plot_corrloads(Rz, pc1=0, pc2=1, s=tsqz_s, c=tsqz, zorder=5, expvar=evz, ax=None,alpha=.5)
+td = rpy_go.goterm2desc(terms)
+tlabels = [td[i] for i in terms]
+keep = where(qvalz<0.01)[0]
+k_Rz = Rz[keep,:]
+k_tsqz_s = tsqz_s[keep]
+k_tsq = tsqz[keep]
+k_tlabels = [name for i,name in enumerate(tlabels) if i in keep]
+plot_corrloads(Rz, pc1=0, pc2=1, s=tsqz_s, c=tsqz, zorder=5, expvar=evz, ax=None,alpha=.5,labels=None)
+#plot_corrloads(k_Rz, pc1=0, pc2=1, s=k_tsqz_s, c=k_tsqz, zorder=5, expvar=evz, ax=None,alpha=.5,labels=None)
 ax = gca()
+yglabels = DYg.get_identifiers(DYg.get_dim_name()[1], sorted=True)
 ylabels = DY.get_identifiers(DY.get_dim_name()[1], sorted=True)
-plot_corrloads(Ry, pc1=0, pc2=1, s=150, c='g', zorder=5, expvar=evy, ax=ax,labels=ylabels,alpha=.5)
+blabels = yglabels[:]
+blabels.append(ylabels[0])
+plot_corrloads(Ry, pc1=0, pc2=1, s=150, c='g', marker='s', zorder=5, expvar=evy, ax=ax,labels=None,alpha=.9)
+plot_corrloads(Rx, pc1=0, pc2=1, s=5, c='k', zorder=1, expvar=evx, ax=ax)
+
 
 figure(4)
 subplot(221)

workflows/smokers.py

@@ -1,5 +1,6 @@
 import sys,os
 import webbrowser
+import cPickle
 
 from fluents import logger, plots,workflow,dataset,main
 from fluents.lib import blmfuncs,nx_utils,validation,engines,cx_stats,cx_utils
@@ -57,6 +58,8 @@ class SmallTestWorkflow(workflow.Workflow):
         go.add_function(gobrowser.PlotDagFunction())
         go.add_function(GoEnrichment())
         go.add_function(GoEnrichmentCond())
+        go.add_function(MapGO2Gene())
+        go.add_function(MapGene2GO())
         self.add_stage(go)
 
         # EXTRA PLOTS
@@ -354,7 +357,7 @@ class GoEnrichment(workflow.Function):
         # Get universe
         # Here, we are using a defined dataset to represent the universe
         if not 'gene_ids' in data:
-            logger.log('notice', 'No dimension called [gene_ids] in dataset: %s', data.get_name())
+            logger.log('notice', 'No dimension called [gene_ids] in dataset: %s' %data.get_name())
             return
         universe = list(data.get_identifiers('gene_ids'))
         logger.log('notice', 'Universe consists of %s gene ids from %s' %(len(universe), data.get_name()))
@@ -417,7 +420,7 @@ class GoEnrichmentCond(workflow.Function):
             return
         
         # Hypergeometric parameter object
-        pval_cutoff = 0.9999
+        pval_cutoff = 1
         cond = True
         test_direction = 'over'
         params = rpy.r.new("GOHyperGParams",
@@ -443,3 +446,65 @@ class GoEnrichmentCond(workflow.Function):
                                name='P values (enrichment)')
         return [xout]
 
+
+class MapGene2GO(workflow.Function):
+    def __init__(self, ont='bp', gene_id_name='gene_ids'):
+        self._ont = ont
+        self._gene_id_name = gene_id_name
+        workflow.Function.__init__(self, 'gene2go', 'gene->GO')
+        # load data at init
+        try:
+            fname = "/home/flatberg/fluents/data/gene2go.pcl"
+            self._gene2go = cPickle.load(open(fname))
+        except:
+            logger.log("notice", "could not load mapping")
+        
+    def run(self):
+        selection = main.project.get_selection()
+        if not selection.has_key(self._gene_id_name):
+            logger.log("notice", "Expected gene ids: %s, but got. %s" %(self._gene_id_name, selection.keys()))
+            return None
+        if len(selection[self._gene_id_name])==0:
+            logger.log("notice", "No selected genes to query")
+            return None
+
+        gene_ids = selection[self._gene_id_name]
+        go_ids = set()
+        for gene in gene_ids:
+            go_ids_new = self._gene2go.get(gene, [])
+            if not go_ids_new:
+                logger.log("notice", "Could not find any goterms for %s" %gene)
+            go_ids.update(self._gene2go.get(gene, []))
+        main.project.set_selection('go-terms', go_ids)
+        logger.log("notice", "GO terms updated")
+
+
+class MapGO2Gene(workflow.Function):
+    def __init__(self, ont='bp', gene_id_name='go-terms'):
+        self._ont = ont
+        self._gene_id_name = gene_id_name
+        workflow.Function.__init__(self, 'go2gene', 'GO->gene')
+        # load data at init
+        try:
+            fname = "/home/flatberg/fluents/data/go2gene.pcl"
+            self._go2gene = cPickle.load(open(fname))
+        except:
+            logger.log("notice", "could not load mapping")
+        
+    def run(self):
+        selection = main.project.get_selection()
+        if not selection.has_key(self._gene_id_name):
+            logger.log("notice", "Expected gene ids: %s, but got. %s" %(self._gene_id_name, selection.keys()))
+            return None
+        if len(selection[self._gene_id_name])==0:
+            logger.log("notice", "No selected genes to query")
+            return None
+
+        go_ids = selection[self._gene_id_name]
+        gene_ids = set()
+        for go in go_ids:
+            if not self._go2gene.get(go,[]):
+                logger.log("notice", "Could not find any gene ids for %s" %go)
+            gene_ids.update(self._go2gene.get(go,[]))
+        main.project.set_selection('gene_ids', gene_ids)
+        logger.log("notice", "GO terms updated")