Merge branch 'devel' into master

Author: violafanfani

netZooPy/command_line.py

@@ -158,7 +158,7 @@ def panda(expression, motif, ppi, output, computing='cpu', precision='double',wi
               help='If true, the final PANDA is saved as an adjacency matrix. Works only when save_memory is false')
 @click.option('--old_compatible', is_flag=True, show_default=True,
               help='If true, PANDA is saved without headers. Pass this if you want the same results of netzoopy before v0.9.11')
-def lioness(expression, motif, ppi, output_panda, output_lioness, el, fmt, computing, precision, ncores, save_memory, save_tmp, rm_missing, mode_process,output_type, alpha, panda_start, panda_end, start, end, subset_numbers='', subset_names='',with_header=False, save_single_lioness=False,ignore_final=False, as_adjacency=False, old_compatible=False):
+def lioness(expression, motif, ppi, output_panda, output_lioness, el, fmt, computing, precision, ncores, save_tmp, rm_missing, mode_process,output_type, alpha, panda_start, panda_end, start, end, subset_numbers='', subset_names='',with_header=False, save_single_lioness=False,ignore_final=False, as_adjacency=False, old_compatible=False):    
     """Run Lioness to extract single-sample networks.
     First runs panda using expression, motif and ppi data. 
     Then runs lioness and puts results in the output_lioness folder.

netZooPy/panda/panda.py

@@ -539,6 +539,11 @@ def processData(
             commind1 = ~np.isnan(idx_tfs) & ~np.isnan(idx_genes)
             idx_tfs = [i for (i, v) in zip(idx_tfs, commind1) if v]
             idx_genes = [i for (i, v) in zip(idx_genes, commind1) if v]
+            if (len(idx_genes) == 0) or (len(idx_tfs) == 0):
+                raise Exception('Error when creating the motif network!'
+                             ' Typically this exception is raised if your'
+                             ' expression matrix genes and motif priors'
+                             ' not have any intersection.')
             idx = np.ravel_multi_index(
                 (idx_tfs, idx_genes), self.motif_matrix_unnormalized.shape
             )

tests/test_lioness.py

@@ -94,13 +94,16 @@ def test_lioness():
     assert result.returncode == 0
 
     # 1. Test command line
-    #positional: expression, motif, ppi, output_panda, output_lioness, el, fmt, computing, precision, ncores, save_memory, save_tmp, rm_missing, mode_process,output_type, alpha, panda_start, panda_end, start, end, subset_numbers, subset_names,with_header, save_single_lioness):
-    #            expression, motif, ppi, output_panda, output_lioness, el, fmt, computing, precision, ncores, save_memory, save_tmp, rm_missing, mode_process,output_type, alpha, panda_start, panda_end, start, end, subset_numbers='', subset_names='',with_header=False, save_single_lioness=False,ignore_final=False, as_adjacency=False, old_compatible=False):
-   
-    cmd.lioness.callback(expression_data, motif, ppi, 'panda.txt','lioness_output_cmd',None,'npy','cpu','double',1,False,True,rm_missing,'legacy','network',0.1,1,4,1,None,save_single_lioness=True)
+        #positional: expression, motif, ppi, output_panda, output_lioness, el, fmt, computing, precision, ncores, save_tmp, rm_missing, mode_process,output_type, alpha, panda_start, panda_end, start, end, subset_numbers, subset_names,with_header, save_single_lioness):
+    #            expression, motif, ppi, output_panda, output_lioness, el, fmt, computing, precision, ncores, save_tmp,
+    #            rm_missing, mode_process,output_type, alpha, panda_start, panda_end, start, end, subset_numbers='',
+    #            subset_names='',with_header=False, save_single_lioness=False,ignore_final=False, as_adjacency=False,
+    #            old_compatible=False):
+    
+    cmd.lioness.callback(expression_data, motif, ppi, 'panda.txt','lioness_output_cmd',None,'npy','cpu','double',1,True,rm_missing,'legacy','network',0.1,1,4,1,None,save_single_lioness=True)
     # Now lioness is saved with lioness.sample_name.sample_index
     res = np.load("lioness_output/lioness.1.0.npy")
-    gt = res = np.load("lioness_output_cmd/lioness.1.0.npy")
+    gt  = np.load("lioness_output_cmd/lioness.1.0.npy")
     assert np.allclose(gt, res)
 
     # 2. Testing Lioness with motif set to None to compute Lioness on coexpression networks

tests/test_panda.py

@@ -343,3 +343,66 @@ def test_panda():
     assert(np.allclose(W_gt, W_res, rtol=1e-05, atol=1e-08))
 
 
+def test_incorrect_gene_ids_raises_exception():
+    '''
+    This test checks that an appropriately descriptive exception
+    is raised if one attempts to run PANDA on an expression matrix
+    that does not have genes intersecting with those in the motif
+    prior matrix
+    '''
+
+    # these numbers are arbitrary but don't need to be large
+    # to trigger the exception since it would be raised prior
+    # to any Panda iterations.
+    num_genes = 20 # number of genes in the expression mtx
+    num_samples = 30 # number of samples in the expression mtx
+    num_tfs = 10 # number of transcription factors in the motif prior
+    num_motif_genes = 10 # number of genes in the motif prior
+
+    # create a dataframe of mock expression data
+    exp_mtx_genes = [f'g{_}' for _ in range(num_genes)]
+    exp_mtx_samples = [f's{_}' for _ in range(num_samples)]
+    expression_data = pd.DataFrame(
+        np.random.randint(0, 100, size=(num_genes, num_samples)),
+        index=exp_mtx_genes,
+        columns=exp_mtx_samples
+    )
+
+    # mock motif prior. Note that the genes (2nd col) start with 'G'
+    # instead of 'g' in the expression matrix
+    tf_list = [f'tf{_}' for _ in range(num_tfs)]
+    motif_gene_list = [f'G{_}' for _ in range(num_motif_genes)]
+    motif_data = pd.DataFrame(
+        {
+            0: np.repeat(tf_list, num_motif_genes),
+            1: np.tile(motif_gene_list, num_tfs),
+            2: np.random.random(num_tfs*num_motif_genes)
+        }
+    )
+
+    # mock ppi prior
+    ppi_data = pd.DataFrame(
+        {
+            0: np.repeat(tf_list, num_tfs),
+            1: np.tile(tf_list, num_tfs),
+            2: np.random.random(num_tfs**2)
+        }
+    )
+
+    with pytest.raises(Exception,
+                       match='Error when creating the motif network!.*'):
+        panda_obj1 = Panda(
+            expression_data,
+            motif_data,
+            ppi_data,
+            modeProcess='legacy'
+        )
+
+    with pytest.raises(Exception,
+                       match='Error when creating the motif network!.*'):
+            panda_obj2 = Panda(
+            expression_data,
+            motif_data,
+            ppi_data,
+            modeProcess='intersection'
+        )