Changed splice junction evidence decision tree

Hierarchy of splice junction evidence:
1. --reference and --splice files
2. --genome sequence motifs
3. XS and ts tags from BAM/SAM input

Author: maschon0

bookend/core/assemble.py

@@ -91,6 +91,9 @@ def __init__(self, args):
                             'sj':None,
                         }
                         config.update(long_defaults)
+                    elif self.input_file.header.get("HD",{}).get("SO",'unsorted') != 'coordinate':
+                        print("ERROR: BAM input reads must be sorted by coordinate.")
+                        sys.exit(1)
 
                     self.dataset = RNAseqDataset(chrom_array=self.input_file.header.references, config=config)
                 elif self.file_type == 'elr.gz':

bookend/core/bam_to_elr.py

@@ -15,7 +15,6 @@
 class BAMtoELRconverter:
     def __init__(self, args):
         """Parses input arguments for converting BAM to ELR"""
-        print(args)
         self.source = args['SOURCE']
         self.genome = args['GENOME']
         self.reference = args['REFERENCE']
@@ -139,6 +138,10 @@ def __init__(self, args):
         if self.source is None:
             self.source = self.bam_in.header['PG'][0]['ID']
 
+        if self.bam_in.header.get("HD",{}).get("SO",'unsorted') == 'coordinate':
+            print("WARNING: BAM sorted by coordinate. Mate pairs will not be merged.")
+            print("Sort by read name (samtools sort -n) if using paired-end reads.")
+        
         self.dataset = RNAseqDataset(
             chrom_array=self.bam_in.header.references, 
             chrom_lengths=list(self.bam_in.header.lengths),