Fixed multiple seqs, TODO fix windows

bayespairing/src/parse_sequences.py

@@ -122,21 +122,22 @@ def get_stats(prediction_scores,modules_to_parse,threshold=-5):
     for sequence in prediction_scores:
         hit_dict = {}
         n_sequences=n_sequences+1
-        for window in prediction_scores[sequence]:
-            scored_positions = {}
-            #print(window)
-            for module in window:
-                scored_positions[module] = []
-                #print("SCANNING",module,window[module])
-                
+        #for window in prediction_scores[sequence]:
+        window = prediction_scores[sequence] 
+        scored_positions = {}
+        #print(window)
+        for module in window:
+            scored_positions[module] = []
+            #print("SCANNING",module,window[module])
+            
 
-                mod_number = module
-                if len(window[module])>0:
-                    max_score = sorted(window[module],key=itemgetter(2),reverse=True)[0][2]
-                    if max_score>threshold and window[module][0][1] not in scored_positions[module]:
-                        #print("admissible score")
-                        scored_positions[module].append(window[module][0][1])
-                        hit_dict[module]=True
+            mod_number = module
+            if len(window[module])>0:
+                max_score = sorted(window[module],key=itemgetter(2),reverse=True)[0][2]
+                if max_score>threshold and window[module][0][1] not in scored_positions[module]:
+                    #print("admissible score")
+                    scored_positions[module].append(window[module][0][1])
+                    hit_dict[module]=True
         for mod in hit_dict:
             if hit_dict[mod]:
                 n_hits[mod]+=1
@@ -258,7 +259,7 @@ def run_fasta(input, modules_to_parse, dataset, ss="", arguments={}):
             if len(sequences[0]) < 3000:
                 maxs = run_BP(sequences, ss, modules_to_parse, dataset, "NONE", aln= aln, t= t, samplesize=samplesize, pretrained=pretrained, Lambda=Lambda, Theta=Theta, Delta=Delta, fuzzy=fuzzy, verbose=verbose, first_run=first_run)
                 first_run=False
-                prediction_scores[id] = [maxs]
+                prediction_scores[id] = maxs
                 if interm:
                     print(maxs)
 
@@ -330,7 +331,7 @@ def run_fasta(input, modules_to_parse, dataset, ss="", arguments={}):
             if len(sequences[0]) < 3000:
                 maxs = run_BP(sequences, ss, modules_to_parse, dataset, "NONE", aln= aln, t= t, samplesize=samplesize, pretrained=pretrained, Lambda=Lambda, Theta=Theta, Delta=Delta, fuzzy=fuzzy, verbose=verbose, first_run=first_run)
                 first_run=False
-                prediction_scores[id] = [maxs]
+                prediction_scores[id] = maxs
                 if interm:
                     print(maxs)
 
@@ -398,7 +399,7 @@ def run_fasta(input, modules_to_parse, dataset, ss="", arguments={}):
                     first_run=False
                     if interm:
                         print(maxs)
-                    prediction_scores[id] = [maxs]
+                    prediction_scores[id] = maxs
 
                 else:
                     all_maxes = []
@@ -452,7 +453,7 @@ def run_fasta(input, modules_to_parse, dataset, ss="", arguments={}):
                 if len(seq)<300:
                     maxs = run_BP(seq, ss, modules_to_parse, dataset, "NONE", aln= aln, t= t, samplesize=samplesize, pretrained=pretrained, Lambda=Lambda, Theta=Theta, Delta=Delta, fuzzy=fuzzy, verbose=verbose, first_run=first_run)
                     first_run=False
-                    prediction_scores[id] = [maxs]
+                    prediction_scores[id] = maxs
 
                 else:
                     all_maxes = []
@@ -573,15 +574,16 @@ def check_already_there(results, new_range, new_mod):
 def present_output(all_maxes, threshold, offset=0):
     OUTPUT_STRING = ""
     output = []
-    for m in all_maxes:
+    #for m in all_maxes:
         #print("all_maxes",m)
-        for current_module in sorted(m.keys()):
-            if len(m[current_module])<1:
-                continue
-            for sub_max in m[current_module]:
-                this_max = [round(sub_max[2], 3), seq_ranges(sub_max[1]),sub_max[0]]
-                if this_max[0] > threshold and not check_already_there(output, this_max, current_module):
-                    output.append(["|", current_module, *this_max, "|"])
+    m = all_maxes
+    for current_module in sorted(m.keys()):
+        if len(m[current_module])<1:
+            continue
+        for sub_max in m[current_module]:
+            this_max = [round(sub_max[2], 3), seq_ranges(sub_max[1]),sub_max[0]]
+            if this_max[0] > threshold and not check_already_there(output, this_max, current_module):
+                output.append(["|", current_module, *this_max, "|"])
     output = sorted(output)
     #print(output)
     OUTPUT_STRING=OUTPUT_STRING+("=========================================================================================\n")
@@ -708,8 +710,16 @@ if __name__ == "__main__":
         print(toPrint)
 
         #generate SVG
+        outName = arguments["o"]
         for seqCounter,inputSeqKey in enumerate(list(all_results.keys())):
-            modules_in_svg, chef_ss = bp_chefs_choice(all_results[inputSeqKey],seqInfo[seqCounter],arguments["t"],arguments["o"])
+            if seqCounter>0:
+                finalName = outName+str(counter)
+            else:
+                finalName = outName
+
+            #print("THE HITS")
+            #print(all_results[inputSeqKey])
+            modules_in_svg, chef_ss = bp_chefs_choice(all_results[inputSeqKey],seqInfo[seqCounter],arguments["t"],finalName)
 
 
             #now we need to fill svg hits