stranded-wig

Author: telatin

bamtocov.nimble

@@ -1,6 +1,6 @@
 # Package
 
-version       = "2.3.1"
+version       = "2.4.0"
 author        = "Andrea Telatin, Giovanni Birolo"
 description   = "BAM to Coverage"
 license       = "MIT"

bin/covtotarget

@@ -7,6 +7,12 @@ permalink: /history
 This project extends [covtobed](https://github.com/telatin/covtobed),
 reimplementing the core algorithm in Nim.
 
+* 2.4.0
+  * Standed analysis is now supported with Wig-like output 
+* 2.3.0:
+  * Improved Wig support
+  * Improved GTF format detection
+  * Expanded test suite
 * 2.2.0:
   * Support for wiggle output (`--wig STEP` and `--op FUNCT`)
 * 2.1.1:

bin/gff2bed

@@ -707,6 +707,7 @@ Target files:
   -i, --gff-id <ID>            GFF identifier [default: ID]
   --gff-separator <sep>        GFF attributes separator [default: ;]
   --gff                        Force GFF input (otherwise assumed by extension .gff)
+  --gtf                        Force GTF input (otherwise assumed by extension .gtf)
 
 BAM reading options:
   -T, --threads <threads>      BAM decompression threads [default: 0]
@@ -734,15 +735,25 @@ Other options:
   var
     #bams: seq[BAM]
     format_gff = false 
+    format_gtf = false
 
   # Set target format (GFF/BED) using extension or forced by the user
-  if ($args["--regions"]).toLower().contains(".gff") or ($args["--regions"]).toLower().contains(".gtf")  or args["--gff"]:
+  if ($args["--regions"]).toLower().contains(".gff"):
     dbEcho("Parsing target as GFF")
     format_gff = true
+  elif ($args["--regions"]).toLower().contains(".gtf"):
+    format_gtf = true
   else:
     dbEcho("Parsing target as BED")
 
-  
+  if (args["--gtf"] and args["--gff"]) or (format_gff and format_gtf):
+    echo "ERROR: Target format is ambiguous: specify a GFF or GTF target (ideally autoinferred from the extension)"
+    quit(1)
+  elif args["--gtf"]:
+    format_gtf = true
+  elif args["--gff"]:
+    format_gff = true
+
   assert( $args["--op"] in  @["mean", "min", "max"], "--op must be one of mean, min, max, got: " & $args["--op"])
 
   let 
@@ -760,7 +771,9 @@ Other options:
       min_mapping_quality: uint8(parse_int($args["--mapq"])),
       eflag: uint16(parse_int($args["--flag"])),
       physical: bool(args["--physical"]),
-      target: if format_gff: gff_to_table(target_file, gffField, gffSeparator, gffIdentifier) else: bed_to_table(target_file)
+      target: if format_gff: gff_to_table(target_file, gffField, gffSeparator, gffIdentifier) 
+              elif format_gtf: gtf_to_table(target_file, gffField, gffSeparator, gffIdentifier) 
+              else: bed_to_table(target_file)
     )
     output_opts: output_option_t = (
       strand: bool(args["--stranded"]),

docs/5_history.md

@@ -38,7 +38,7 @@ var
   gffField      = "CDS"
   bedOutput     = false
 
-type
+#[ type
   region_t = ref object
     chrom: string
     start: int
@@ -49,6 +49,7 @@ type
 
 proc start(r: region_t): int {.inline.} = return r.start
 proc stop(r: region_t): int {.inline.} = return r.stop
+ ]#
 #proc `$`(m:region_t): string = return "($#-$#:$#, $#)" % [$m.chrom, $m.start, $m.stop, $m.name]
 #proc inc_count(r:region_t) = inc(r.count)
 
@@ -61,7 +62,7 @@ proc overlapLen(reference, feature: region_t): int =
         return feature.stop - feature.start
 
 # Converts a GFF line to region object
-proc gff_line_to_region(line: string): region_t =
+#[ proc gff_line_to_region(line: string): region_t =
   var
    cse = line.strip().split('\t')
 
@@ -157,7 +158,7 @@ proc gff_to_table(bed: string): TableRef[string, seq[region_t]] =
 
   hts.free(kstr.s)
   return bed_regions
- 
+ ]# 
 
 proc processCoverage(f: File, target: TableRef[string, seq[region_t]], normalize: bool, bedout: bool) =
     var
@@ -231,7 +232,7 @@ Arguments:
 
 Options:
 
-  -g, --gff                    Force GFF for input (otherwise autodetected by .gff extension)
+  -g, --gff                    Force GFF for input (otherwise autodetected by .gff/.gtf extension)
   -t, --type <feat>            GFF feature type to parse [default: CDS]
   -i, --id <ID>                GFF identifier [default: ID]
   -l, --norm-len               Normalize by gene length
@@ -251,15 +252,15 @@ Options:
   gffField      = $args["--type"]
   bedOutput     = args["--bed-output"]
 
-  if ($args["<Target>"]).contains(".gff"):
+  if ($args["<Target>"]).contains(".gff") or (($args["<Target>"]).contains(".gtf") ):
     prokkaGff = true
 
 
   if not fileExists($args["<Target>"]):
     stderr.writeLine("FATAL ERROR: Unable to read target regions: ", $args["<Target>"]) 
     quit(1)
 
-  var targetRegions = if prokkaGff == true: gff_to_table($args["<Target>"])
+  var targetRegions = if prokkaGff == true: gff_to_table($args["<Target>"],gffField, gffSeparator, gffIdentifier)
                  else: bed_to_table($args["<Target>"])
 
   var