ups

scripts/lpls/plots_lpls.py

@@ -1,6 +1,7 @@
 import pylab
 import matplotlib
 import networkx as nx
+import scipy
 
 def plot_corrloads(R, pc1=0,pc2=1,s=20, c='b', zorder=5,expvar=None,ax=None,drawback=True, labels=None):
     """ Correlation loading plot."""
@@ -56,3 +57,31 @@ def plot_dag(edge_dict, node_color='b', node_size=30,labels=None,nodelist=None,p
         
     nx.draw_networkx(G,pos, with_labels=with_labels, node_size=node_size, node_color=node_color, nodelist=nodelist)
     
+
+def plot_ZXcorr(gene_ids, term_ids, gene2go, X, D, scale=True):
+    """ Plot correlation/covariance between genes as a function of
+    semantic difference.
+
+    input: X (n, p) data matrix
+           D (p, p) gene-gene sematic similarity matrix
+    """
+    D = scipy.corrcoef(X)
+    term2ind = dict(enumerate(term_ids))
+    for i, gene_i in enumerate(gene_ids):
+        for j, gene_j in enumerate(gene_ids):
+            if j<i:
+                r2 = D[i,j]
+                terms_i = gene2go[gene_i]
+                terms_j = gene2go[gene_j]
+                for ti, term in enumerate(term_ids):
+                    if term in terms_i:
+                        pass
+
+
+def clustering_index(T, Yg):
+    pass
+                
+                
+                
+                
+    

scripts/lpls/yeast_annot.py

@@ -1,44 +0,0 @@
-
-def smdb_annot(orflist=None, input_fname='registry.genenames.tab', output_fname='yeast.annot'):
-
-    """Reads registry.genenames.tab from the Stanford yeast
-    microarray database.
-
-    Available from:
-    ftp://genome-ftp.stanford.edu/pub/yeast/data_download/gene_registry/registry.genenames.tab
-    
-    input: orf -- list of orfs (open reading frames)
-           file -- (optional) file to fetch info from
-           
-    registry.genames contains:
-
-    0 = Locus name 
-    1 = Other name
-    2 = Description 
-    3 = Gene product
-    4 = Phenotype
-    5 = ORF name
-    6 = SGDID
-    
-    NB! Other name, Gene product and Phenotype may have more
-    than one mapping. These are separated by |
-
-    Output: writes an annotation file
-
-    """
-    outfile = open(output_fname, 'w')
-    header = "Orf\tLocus_id\tOther_name\tDescription\tGene_product\tPhenotype\tSGD_ID\n"
-    outfile.write(header)
-    text = open(input_fname, 'r').read().splitlines()
-    for line in text:
-        els = line.split('\t')
-        orf_name = els.pop(5)
-        if orf_name!='': # we dont care about non-named orfs
-            if orflist and orf_name not in orflist:
-                break
-            for e in els:
-                if e !='':
-                    outfile.write(str(e) + "\t")
-                else:
-                    outfile.write("NA")
-            f.write("\n")