started comparing to RMDetect

models/test_pickle.py

@@ -3,7 +3,7 @@ import networkx as nx
 from matplotlib import pyplot as plt
 
 #g = pickle.load(open("all_graphs_pickled/" + "1FFK" + ".nxpickled", "rb"))
-PDBid = "1Q7Y.A"
+PDBid = "1FJG.A"
 #print("PDB")
 #print(PDBid)
 PDB, chain = PDBid.split(".")

src/carnaval_to_rmdetect.py

@@ -8,7 +8,13 @@ aligned_modulegraphs = pickle.load(open("../models/all_21+_rna3dmotif_106_aligne
 PDB_positions = pickle.load(open("../models/all_21+_rna3dmotif_106_PDB_positions.cPickle", 'rb'))
 PDBs = pickle.load(open("../models/all_21+_rna3dmotif_106_PDB_names.cPickle", 'rb'))
 graphs = pickle.load(open("../models/all_21+_rna3dmotif_106_one_of_each_graph.cPickle", 'rb'))
-module = 1
+#aligned_modulegraphs = pickle.load(open("../models/all_full3_rna3dmotif_aligned_modulegraphs.cPickle", 'rb'))
+#PDB_positions = pickle.load(open("../models/all_full3_rna3dmotif_PDB_positions.cPickle", 'rb'))
+#PDBs = pickle.load(open("../models/all_full3_rna3dmotif_PDB_names.cPickle", 'rb'))
+#graphs = pickle.load(open("../models/all_full3_rna3dmotif_one_of_each_graph.cPickle", 'rb'))
+#print(len(graphs))
+good_ones = [0, 3, 6, 8, 9, 12, 14, 15, 17, 19, 21, 22, 26, 27, 28, 30, 33, 34, 35, 36, 37, 39, 41, 42, 43, 46, 47, 48, 50, 52, 54, 58, 61, 64, 66, 69, 74, 75, 77, 80, 83, 84, 88, 90, 92, 95, 96, 97, 102, 104]
+module = 0
 aln = aligned_modulegraphs[module]
 g = graphs[module]
 
@@ -50,8 +56,8 @@ def get_seqs (g,aln,addresses):
             else:
                 seqs[i] = seqs[i] + '-'
     return seqs
-print("ADDRESSES",addresses)
-print("SEQS")
+#print("ADDRESSES",addresses)
+#print("SEQS")
 seqs = get_seqs(g,aln,addresses)
 print(seqs)
 
@@ -131,20 +137,30 @@ with open("seq.fasta", "a") as f:
 #print(a)
 #a()
 
-#alignment = SeqIO.parse("seq.fasta","fasta")
-#SeqIO.write(alignment,open("module_"+str(module)+".stk","w"),"stockholm")
+alignment = SeqIO.parse("seq.fasta","fasta")
+SeqIO.write(alignment,open("module_"+str(module)+".stk","w"),"stockholm")
 #cons = get_consensus_sequence(seqs)
-print(graphs[module][2].nodes(data=True))
+print(graphs[module][1].nodes(data=True))
 ss= get_ss_from_graph(graphs[module][0])
 print(ss)
-print(PDBs[module][86])
-print(PDB_positions[module][86])
+print(PDBs[module][1])
+print(PDB_positions[module][1])
+seq,dec = get_PDB_sequence(".".join((PDBs[module][1].split(".")[:2])))
+print(seq)
+for pos,i in enumerate(PDBs[module][1:]):
+    #print(i)
+    seq,dec = get_PDB_sequence(".".join((i.split(".")[:2])))
+    if len(seq)>200:
+        print(pos, len(seq))
+        print(seq)
+        print(PDBs[module][pos])
+        print(PDB_positions[module][pos])
+        print("------")
+#TEST : 86,5
 
+me0=[]
+rmdetect0="Never detects"
 
-
-
-#for pos,i in enumerate(PDBs[module][1:]):
-#    #print(i)
-#    seq,dec = get_PDB_sequence(".".join((i.split(".")[:2])))
-#    print(pos, len(seq))
-#TEST : 86
+#python parse_sequences.py -d all_21+_rna3dmotif_106 -seq
+me1 = [1,0,0]
+rmdetect1 = [0,0,0]

src/module_1.stk

@@ -876,4 +876,5 @@ seq290 CUUCGG
 seq291 CUUCGG
 #=GS seq291 AC seq291
 #=GS seq291 DE seq291
+REF_SEQ CGACGAG
 //

src/plot_rna3dmotif_results.py

 import pickle
 import numpy as np
 import matplotlib.pyplot as plt
-from altair import *
+#from altair import *
 import matplotlib.patches as mpatches
 import networkx as nx
 ALL_RESULTS = []
 the_100 = [0, 1, 2, 3, 5, 6, 7, 10, 12, 13, 14, 15, 16, 20, 21, 22, 23, 24, 25, 26, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 41, 42, 43, 44, 45, 46, 47, 49, 50, 51, 53, 54, 55, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 72, 74, 75, 76, 77, 78, 79, 80, 81, 82, 85, 86, 87, 88, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 102, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 115, 116, 117, 118, 119, 121, 122, 123, 124, 126, 127, 128]
+print(len(the_100))
 excellent = [0, 3, 7, 12, 13, 16, 21, 22, 24, 26, 30, 31, 35, 36, 37, 39, 43, 44, 45, 46, 47, 50, 53, 54, 55, 59, 60, 61, 63, 65, 67, 72, 76, 79, 81, 86, 92, 93, 95, 98, 101, 104, 108, 110, 112, 116, 117, 118, 124, 127]
 failed = [8,10,13,16]
 pretty_bad = [10, 15, 20, 29, 32, 34, 42, 49, 58, 69, 80, 88, 97, 100, 105, 109, 111, 125, 126, 128]
 NUL = [8, 10, 13, 16, 15, 20, 42, 80, 97, 100, 109]
 failed =pretty_bad
+
+excellent_100=[]
+decale = 0
+for i in range(the_100[-1]+1):
+    if i in excellent:
+        excellent_100.append(i-decale)
+    if i not in the_100:
+        decale=decale+1
+print(len(excellent_100))
+print(excellent_100)
+exit()
+
 '''
 graphs = pickle.load(open("../models/all_full3_rna3dmotif_one_of_each_graph.cPickle","rb"))
 total = 0
@@ -246,4 +259,4 @@ plt.xlabel("Precision")
 plt.ylabel("Counts")
 plt.show()
 print("EXCELLENT")
-print(excellent)
\ No newline at end of file
+print(excellent)