Merge pull request #56 from MeeshCompBio/master

Two-tail GO, linkage fix, locality fix
LinkageIO · May 17, 2017 · 9572e6d · 9572e6d
2 parents 1024d25 + 8c27c94
commit 9572e6d
Show file tree

Hide file tree

Showing 3 changed files with 26 additions and 3 deletions.
diff --git a/camoco/COB.py b/camoco/COB.py
@@ -28,6 +28,7 @@
 import networkx as nx
 import pandas as pd
 import numpy as np
+from numpy import nan
 import itertools
 from odo import odo
 from scipy.misc import comb 
@@ -1092,8 +1093,11 @@ def locality(self, gene_list, iter_name=None, include_regression=False):
         degree.columns = ['global', 'local']
         degree = degree.sort_values(by='global')
         if include_regression:
+            #set up variables to use astype to aviod pandas sm.OLS error
+            loc_deg = degree['local']
+            glob_deg = degree['global']
             # Add the regression lines
-            ols = sm.OLS(degree['local'], degree['global']).fit()
+            ols = sm.OLS(loc_deg.astype(float), glob_deg.astype(float)).fit()
             degree['resid'] = ols.resid
             degree['fitted'] = ols.fittedvalues
             degree = degree.sort_values(by='resid',ascending=False)
@@ -1499,6 +1503,8 @@ def _calculate_gene_hierarchy(self,method='single'):
         dists = (dists * pcc_std) + pcc_mean
         dists = np.tanh(dists)
         dists = 1 - dists
+        #convert nan to 0's, linkage can only use finite values
+        dists[np.isnan(dists)] = 0
         gc.collect()
         # Find the leaves from hierarchical clustering
         gene_link = linkage(dists, method=method)

diff --git a/camoco/cli/camoco b/camoco/cli/camoco
@@ -720,6 +720,12 @@ if __name__ == '__main__':
         default=None,
         help='Perform Gene Ontology Statistics. (default: None)'
     )
+    health.add_argument(
+        '--two_tailed_GO',
+        action='store_true',
+        default=False,
+        help='Include negative density values for GO statistics (default: False)'
+    )
     health.add_argument(
         '--min-term-size',
         default=10,

diff --git a/camoco/cli/commands/health.py b/camoco/cli/commands/health.py
@@ -157,12 +157,23 @@ def cob_health(args):
                 term.loci = list(filter(lambda x: x in cob, term.loci))
                 if len(term) < args.min_term_size or len(term) > args.max_term_size:
                     continue
+                #set density value for two tailed go so we only test it once
+                density = cob.density(term.loci)
+                #one tailed vs two tailed test
+                if args.two_tailed_GO is True:
+                    #run one tail for only positive values
+                    if density > 0:
+                        density_emp.append(density)
+                    #skip negative density values
+                    else:
+                        continue
+                #if two_tailed_go is not none
+                else:
+                    density_emp.append(density)
                 term_ids.append(term.id)
                 term_sizes.append(len(term))
                 term_desc.append(str(term.desc))
                 # ------ Density 
-                density = cob.density(term.loci)
-                density_emp.append(density)
                 # Calculate PVals
                 density_bs = np.array([
                     cob.density(cob.refgen.random_genes(n=len(term.loci))) \