change way to decide the open/nuc/bg states

macs3-project · Oct 4, 2022 · 27e4cb3 · 27e4cb3
1 parent 77ffc3c
commit 27e4cb3
Show file tree

Hide file tree

Showing 4 changed files with 294 additions and 1,175 deletions.
diff --git a/MACS3/Commands/hmmratac_cmd.py b/MACS3/Commands/hmmratac_cmd.py
@@ -1,4 +1,4 @@
-# Time-stamp: <2022-10-04 15:13:57 Tao Liu>
+# Time-stamp: <2022-10-04 16:58:30 Tao Liu>
 
 """Description: Main HMMR command
 
@@ -243,8 +243,15 @@ def run( args ):
         options.info( f"#   HMM converged: {hmm_model.monitor_.converged}")
 
         # label hidden states
-        i_open_region = np.where(hmm_model.means_ == max(hmm_model.means_[0:3,0]))[0][0]
-        i_background_region = np.where(hmm_model.transmat_ == min(hmm_model.transmat_[0:3, i_open_region]))[0][0]
+        means_sum = np.sum( hmm_model.means_, axis=1 )
+
+        # first, the state with the highest overall emission is the open state
+        i_open_region = np.where( means_sum == max(means_sum) )[0][0]
+
+        # second, the state with lowest overall emission is the bg state 
+        i_background_region = np.where( means_sum == min(means_sum) )[0][0]
+
+        # last one is the nuc state (note it may not be accurate though
         i_nucleosomal_region = list(set([0, 1, 2]) - set([i_open_region, i_background_region]))[0]
 
         # write hmm into model file

diff --git a/MACS3/Signal/BedGraph.pyx b/MACS3/Signal/BedGraph.pyx
@@ -1,6 +1,6 @@
 # cython: language_level=3
 # cython: profile=True
-# Time-stamp: <2022-09-29 09:07:23 Tao Liu>
+# Time-stamp: <2022-10-04 15:46:00 Tao Liu>
 
 """Module for BedGraph data class.
 
@@ -981,7 +981,7 @@ cdef class bedGraphTrackI:
              int32_t pre_p, p1, p2, i
              float32_t v1, v2
              bytes chrom
-             object ret
+             list ret
 
         assert isinstance(bdgTrack2,bedGraphTrackI), "not a bedGraphTrackI object"
 

diff --git a/MACS3/Signal/HMMR_Signal_Processing.pyx b/MACS3/Signal/HMMR_Signal_Processing.pyx
@@ -1,6 +1,6 @@
 # cython: language_level=3
 # cython: profile=True
-# Time-stamp: <2022-09-29 14:58:12 Tao Liu>
+# Time-stamp: <2022-10-04 16:14:23 Tao Liu>
 
 """Module description:
 
@@ -155,23 +155,19 @@ cpdef list extract_signals_from_regions( list signals, object regions, int binsi
     assert len( extracted_data[0] ) == len( extracted_data[1] )
     assert len( extracted_data[0] ) == len( extracted_data[2] )
     assert len( extracted_data[0] ) == len( extracted_data[3] )
-    #nnn =len( extracted_len[0] )
-    #debug( f"{n} bins, {nn}, {nnn}" )
     counter = 0
     prev_c = extracted_len[0][0]
     c = 0
     for i in range( nn ):
         ret_training_bins.append( extracted_positions[0][i] )
         ret_training_data.append(
-            [ max( 0.0001, abs(round(extracted_data[0][i], 4))),
-              max( 0.0001, abs(round(extracted_data[1][i], 4))),
-              max( 0.0001, abs(round(extracted_data[2][i], 4))),
-              max( 0.0001, abs(round(extracted_data[3][i], 4))) ] )
+            [ max( 0.0001, extracted_data[0][i] ),
+              max( 0.0001, extracted_data[1][i] ),
+              max( 0.0001, extracted_data[2][i] ),
+              max( 0.0001, extracted_data[3][i] ) ] )
         c = extracted_len[0][i]
-        #print(f"{extracted_positions[0][i]} {extracted_len[0][i]}")
         if counter != 0 and c != prev_c:
             ret_training_lengths.append( counter )
-            #print(f"### add a bin length {counter}")
             counter = 0
         prev_c = c
         counter +=  1