update 04_acuracy.ipynb

data/RNA16.react

@@ -5542,80 +5542,81 @@
 120	NA
 
 >tRNA-asp
-1	0.169603636
-2	0.06167405
-3	0.077092562
-4	0.138766612
-5	0.123348099
-6	0.107929587
-7	0.138766612
-8	0.169603636
-9	0.231277686
-10	0.246696198
-11	0.231277686
-12	0.308370248
-13	0.277533223
-14	0.277533223
-15	0.231277686
-16	0.477973884
-17	0.632159008
-18	0.817181157
-19	1.002203305
-20	0.832599669
-21	0.431718347
-22	0.354625785
-23	0.339207273
-24	0.354625785
-25	0.215859173
-26	0.277533223
-27	0.092511074
-28	0.107929587
-29	1.295155041
-30	0.308370248
-31	2.266521321
-32	1.942732561
-33	1.433921652
-34	1.433921652
-35	0.462555372
-36	0.493392397
-37	0.138766612
-38	0.416299835
-39	0.585903471
-40	0.107929587
-41	0.154185124
-42	0.092511074
-43	0.154185124
-44	0.215859173
-45	NA
-46	0.262114711
-47	0.123348099
-48	0.092511074
-49	0.107929587
-50	0.092511074
-51	0.092511074
-52	0.169603636
-53	1.279736528
-54	0.508810909
-55	0.370044297
-56	0.169603636
-57	0.38546281
-58	0.308370248
-59	0.092511074
-60	0.107929587
-61	0.06167405
-62	0.138766612
-63	0.169603636
-64	0.123348099
-65	0.154185124
-66	0.077092562
-67	0.169603636
-68	0.138766612
-69	0.077092562
-70	0.046255537
-71	1.125551405
-72	0.277533223
-73	0.64757752
-74	1.819384462
+1	0.134
+2	0.044
+3	0.057
+4	0.114
+5	0.094
+6	0.09
+7	0.107
+8	0.131
+9	0.186
+10	0.198
+11	0.187
+12	0.256
+13	0.225
+14	0.221
+15	0.189
+16	0.387
+17	0.513
+18	0.665
+19	0.811
+20	0.672
+21	0.353
+22	0.292
+23	0.27
+24	0.281
+25	0.176
+26	0.228
+27	0.081
+28	0.084
+29	-999
+30	1.051
+31	-999
+32	-999
+33	1.83
+34	1.568
+35	1.163
+36	1.163
+37	0.376
+38	0.396
+39	0.113
+40	0.343
+41	0.472
+42	0.088
+43	0.119
+44	0.069
+45	0.12
+46	0.174
+47	0.208
+48	0.098
+49	0.08
+50	0.084
+51	0.074
+52	0.079
+53	0.132
+54	1.04
+55	0.412
+56	0.306
+57	0.136
+58	0.306
+59	0.253
+60	0.076
+61	0.081
+62	0.048
+63	0.107
+64	0.134
+65	0.099
+66	0.127
+67	0.06
+68	0.143
+69	0.111
+70	0.067
+71	0.035
+72	0.909
+73	0.224
+74	0.529
+75	1.475
 
 >tRNAphe
 1	0

data/RNA16_original_data/RNA16_format.py

@@ -3,15 +3,23 @@
 #####
 import argparse
 parser = argparse.ArgumentParser(description='shape annotation')
-parser.add_argument('--bpseq',  type=str, default='BPseq', help='path to folder containing .bpseq files')
-parser.add_argument('--seq',  type=str,  default='seq', help='path to folder containing .seq files')
-parser.add_argument('--shape',  type=str, default='shape', help='path to folder containing .shape files ')
+#parser.add_argument('--bpseq',  type=str, default='BPseq', help='path to folder containing .bpseq files')
+#parser.add_argument('--seq',  type=str,  default='seq', help='path to folder containing .seq files')
+#parser.add_argument('--shape',  type=str, default='shape', help='path to folder containing .shape files ')
+parser.add_argument('bpseq',  type=str, default='BPseq', help='path to folder containing .bpseq files')
+parser.add_argument('seq',  type=str,  default='seq', help='path to folder containing .seq files')
+parser.add_argument('shape',  type=str, default='shape', help='path to folder containing .shape files ')
+
 args = parser.parse_args()
 
 DEBUG = True
 if DEBUG:
     print 'argparse args: ', args
 
+# to run in Terminal: python RNA16_format.py --bpseq /home/montaser/ShaKer/data/RNA16_original_data/RNA16_dotbracket /home/montaser/ShaKer/data/RNA16_original_data/RNA16_sequences /home/montaser/ShaKer/data/RNA16_original_data/RNA16_shape 
+#/home/montaser/ShaKer/data/RNA16_original_data/RNA16_dotbracket
+#/home/montaser/ShaKer/data/RNA16_original_data/RNA16_sequences
+#/home/montaser/ShaKer/data/RNA16_original_data/RNA16_shape
 
 
 ########
@@ -51,15 +59,13 @@ def dump_fasta(se,dp,stringname):
     print res
 
 def dump_shape(shape,fname):
-    print shape
+    #print shape
     fnames = [ e[:e.find(".")] for e in fname ]
-    fix_data = lambda x: "\n".join([ str(i+1)+"\t"+e.strip() for i,e in enumerate( x.split("\n") ) if e.strip()>0  ])
+    fix_data = lambda x: "\n".join([ str(i+1)+"\t"+e.strip() for i,e in enumerate( x.split("\n") ) if (e.strip()>0 and str(e)!="" ) ])
     dataz = map(fix_data, shape)
     textlist = [">%s\n%s\n\n" % (name,data)  for (name,data) in zip(fnames,dataz)]
     res = ''.join(textlist)
     dump("data.react",res)
-    print res
+    #print res
 
 
-dump_fasta(seqs,bpseq,_)
-dump_shape(shape,_)

data/RNA16_original_data/RNA16_shape/tRNA-asp.shape

@@ -1,74 +1,75 @@
-0.169603636
-0.06167405
-0.077092562
-0.138766612
-0.123348099
-0.107929587
-0.138766612
-0.169603636
-0.231277686
-0.246696198
-0.231277686
-0.308370248
-0.277533223
-0.277533223
-0.231277686
-0.477973884
-0.632159008
-0.817181157
-1.002203305
-0.832599669
-0.431718347
-0.354625785
-0.339207273
-0.354625785
-0.215859173
-0.277533223
-0.092511074
-0.107929587
-1.295155041
-0.308370248
-2.266521321
-1.942732561
-1.433921652
-1.433921652
-0.462555372
-0.493392397
-0.138766612
-0.416299835
-0.585903471
-0.107929587
-0.154185124
-0.092511074
-0.154185124
-0.215859173
--999
-0.262114711
-0.123348099
-0.092511074
-0.107929587
-0.092511074
-0.092511074
-0.169603636
-1.279736528
-0.508810909
-0.370044297
-0.169603636
-0.38546281
-0.308370248
-0.092511074
-0.107929587
-0.06167405
-0.138766612
-0.169603636
-0.123348099
-0.154185124
-0.077092562
-0.169603636
-0.138766612
-0.077092562
-0.046255537
-1.125551405
-0.277533223
-0.64757752
-1.819384462
+0.134
+0.044
+0.057
+0.114
+0.094
+0.09
+0.107
+0.131
+0.186
+0.198
+0.187
+0.256
+0.225
+0.221
+0.189
+0.387
+0.513
+0.665
+0.811
+0.672
+0.353
+0.292
+0.27
+0.281
+0.176
+0.228
+0.081
+0.084
+-999
+1.051
+-999
+-999
+1.83
+1.568
+1.163
+1.163
+0.376
+0.396
+0.113
+0.343
+0.472
+0.088
+0.119
+0.069
+0.12
+0.174
+0.208
+0.098
+0.08
+0.084
+0.074
+0.079
+0.132
+1.04
+0.412
+0.306
+0.136
+0.306
+0.253
+0.076
+0.081
+0.048
+0.107
+0.134
+0.099
+0.127
+0.06
+0.143
+0.111
+0.067
+0.035
+0.909
+0.224
+0.529
+1.475