signal to read changes

src/calculate_offsets.py

@@ -207,6 +207,7 @@ def run(args):
             model_ = obj[header_line_count:]
             for line in model_:
                 values_ = line.split('\t')
+                values_[0] = values_[0].replace('U', 'T')
                 model[values_[0]] = float(values_[1])
             test_array = []
             for base_offset in range(0, kmer_length):
@@ -217,11 +218,17 @@ def run(args):
             max_offset, max_dist = calculate_distance(kmer_length, test_array)
             forward_shift = -1 * max_offset
             reverse_shift = -1 * (kmer_length - max_offset - 1)
-            print("kmer length: {}\nbest base shift (offset) for forward mapped reads: {}\nbest base shift (offset) for reverse mapped reads: {}\ndifference between highest and lowest medians of the distributions: {}".format(kmer_length, forward_shift, reverse_shift, round(max_dist, 4)))
+            if args.rna:
+                print("RNA\nkmer length: {}\nbest base shift (offset) for forward mapped reads: {}\nbest base shift (offset) for reverse mapped reads: {}\ndifference between highest and lowest medians of the distributions: {}".format(kmer_length, reverse_shift, forward_shift, round(max_dist, 4)))
+            else:
+                print("DNA\nkmer length: {}\nbest base shift (offset) for forward mapped reads: {}\nbest base shift (offset) for reverse mapped reads: {}\ndifference between highest and lowest medians of the distributions: {}".format(kmer_length, forward_shift, reverse_shift, round(max_dist, 4)))
             if args.output != "":
                 output_pdf = PdfPages(args.output)
                 print("output file: {}".format(args.output))
-                plt_title = "{}\nkmer length: {}\ndifference between highest and lowest medians of the distributions: {}\nbest base shift (offset) for forward mapped reads (shown below): {}\nbest base shift (offset) for reverse mapped reads (derived): {}\n".format(args.tag_name, kmer_length, str(round(max_dist, 4)), forward_shift, reverse_shift)
+                if args.rna:
+                    plt_title = "RNA\n{}\nkmer length: {}\ndifference between highest and lowest medians of the distributions: {}\nbest base shift (offset) for forward mapped reads (derived): {}\nbest base shift (offset) for reverse mapped reads (shown below): {}\n".format(args.tag_name, kmer_length, str(round(max_dist, 4)), reverse_shift, forward_shift)
+                else:
+                    plt_title = "DNA\n{}\nkmer length: {}\ndifference between highest and lowest medians of the distributions: {}\nbest base shift (offset) for forward mapped reads (shown below): {}\nbest base shift (offset) for reverse mapped reads (derived): {}\n".format(args.tag_name, kmer_length, str(round(max_dist, 4)), forward_shift, reverse_shift)
                 plot_distributions(kmer_length, test_array, output_pdf, plt_title)
                 output_pdf.close()
     else:

src/metric.py

@@ -634,6 +634,17 @@ def run(args):
                     if i < len(ref_pos_dic) - 1:
                         print("\t", end="")
                 print()
+            if args.output_current_1:
+                for i in range(0, len(ref_pos_dic)):
+                    sublist = ref_pos_dic[i]
+                    if not any(np.isnan(x) for x in sublist) and len(sublist) > 0:
+                        rounded_sublist = [round(x, 2) for x in sublist]
+                        print(",".join(map(str, rounded_sublist)), end="")
+                    else:
+                        continue
+                    if i < len(ref_pos_dic) - 1:
+                        print(",", end="")
+                print()
             if args.output_current_column:
                 for i in range(0, len(ref_pos_dic)):
                     sublist = ref_pos_dic[i]
@@ -846,6 +857,26 @@ def run(args):
                     if i < len(ref_pos_dic) - 1:
                         print("\t", end="")
                 print()
+            if args.output_current_1:
+                for i in range(0, len(ref_pos_dic)):
+                    sublist = ref_pos_dic[i]
+                    if not any(np.isnan(x) for x in sublist) and len(sublist) > 0:
+                        rounded_sublist = [round(x, 2) for x in sublist]
+                        print(",".join(map(str, rounded_sublist)), end="")
+                    else:
+                        continue
+                    if i < len(ref_pos_dic) - 1:
+                        print(",", end="")
+                print()
+            if args.output_current_column:
+                for i in range(0, len(ref_pos_dic)):
+                    sublist = ref_pos_dic[i]
+                    if not any(np.isnan(x) for x in sublist) and len(sublist) > 0:
+                        rounded_sublist = [round(x, 2) for x in sublist]
+                        if i in column_raw_samples:
+                            column_raw_samples[i] += rounded_sublist
+                        else:
+                            column_raw_samples[i] = rounded_sublist
     else:
         raise Exception("Error: You should not have ended up here. Please check your arguments")
 
@@ -897,6 +928,7 @@ def argparser():
     parser.add_argument('--extend_0', required=False, action='store_true', help="print matches, deletions, insertions arrays")
     parser.add_argument('--extend_1', required=False, action='store_true', help="print ss string for the given region")
     parser.add_argument('--output_current', required=False, action='store_true', help="print signal values")
+    parser.add_argument('--output_current_1', required=False, action='store_true', help="print signal values without any nans/tabs")
     parser.add_argument('--output_current_column', required=False, action='store_true', help="print signal values per column")
     return parser