Merge 371b3e7 into 2cc658d

CMakeLists.txt

@@ -12,7 +12,7 @@ include(TestHelper)
 #versioning stuff
 set (regtools_VERSION_MAJOR 0)
 set (regtools_VERSION_MINOR 5)
-set (regtools_VERSION_PATCH 0)
+set (regtools_VERSION_PATCH 1)
 
 configure_file (
     "${PROJECT_SOURCE_DIR}/src/version.h.in"

docs/commands/junctions-annotate.md

@@ -20,7 +20,7 @@ Gene Annotation databases such as Ensembl/RefSeq/UCSC etc. The goal of the annot
 ###Options
 | Option  | Description |
 | ------  | ----------- |
-| -E      | Do not skip single exon genes. The default is to skip the single exon genes while annotating junctions.|
+| -S      | Do not skip single exon genes. The default is to skip the single exon genes while annotating junctions.|
 | -o      | File to write output to. STDOUT by default. The output format is described [here](#output)|
 | -h      | Display help message for this command.|
 

docs/commands/junctions-extract.md

@@ -13,11 +13,12 @@ The `junctions extract` command can be used to extract exon-exon junctions from
 | Option  | Description |
 | ------  | ----------- |
 | -a      | Minimum anchor length. 8bp by default. Junctions having a minimum overlap of this much on both ends are reported. Note - the required overlap can be observed amongst separate reads, for example one read might have sufficient left overlap and another read might have sufficient right overlap, this is sufficient for the junction to be reported. No mismatches are allowed in the anchor regions.|
-| -i      | Minimum intron size. 70bp by default. The intron size is the same as junction.end - junction.start. (Not to be confused with chromStart and chromEnd below, the required blockSizes need to be added/subtracted.)|
-| -I      | Maximum intron size. 500,000bp by default. The intron size the same as junction.end - junction.start. (Not to be confused with chromStart and chromEnd below, the required blockSizes need to be added/subtracted.)|
+| -m      | Minimum intron size. 70bp by default. The intron size is the same as junction.end - junction.start. (Not to be confused with chromStart and chromEnd below, the required blockSizes need to be added/subtracted.)|
+| -M      | Maximum intron size. 500,000bp by default. The intron size the same as junction.end - junction.start. (Not to be confused with chromStart and chromEnd below, the required blockSizes need to be added/subtracted.)|
 | -o      | File to write output to. STDOUT by default.|
-| -r      | Region to extract junctions in. This is specified in the format "chr:start-end" If not specified, junctions are extracted from the entire BAM file.|
+| -r      | Region to extract junctions in. This is specified in the format "chr:start-end". If not specified, junctions are extracted from the entire BAM file.|
 | -h      | Display help message for this command.|
+| -s      | Strand specificity of RNA library preparation, where 0 = unstranded, 1 = first-strand/RF, 2 = second-strand/FR. The default is 1 (RF). This option is meant to be used if no XS tags are present in the input BAM.
 
 ###Output
 The output is in the BED12 format which is described in detail [here.](https://genome.ucsc.edu/FAQ/FAQformat.html#format1) Each line is an exon-exon junction as explained below.

docs/commands/variants-annotate.md

@@ -15,8 +15,8 @@ The `regtools variants annotate` command is used to annotate variants of interes
 ###Options
 | Option  | Description |
 | ------  | ----------- |
-| -e      | Maximum distance from the start/end of an exon to annotate a variant as relevant to splicing, the variant is in exonic space, i.e a coding variant. [default = 3] |
 | -i      | Maximum distance from the start/end of an exon to annotate a variant as relevant to splicing, the variant is in intronic space. [default = 2] |
+| -e      | Maximum distance from the start/end of an exon to annotate a variant as relevant to splicing, the variant is in exonic space, i.e a coding variant. [default = 3] |
 | -I      | Annotate variants in intronic space within a transcript (not to be used with -i).
 | -E      | Annotate variants in exonic space within a transcript (not to be used with -e).
 | -S      | Dont skip single exon transcripts. The default is to skip the single exon transcripts. |
@@ -30,7 +30,7 @@ The output file is in the VCF format. The annotation results are described using
 | genes             |A comma separated list of unique genes that the variants falls in.|
 | transcripts       |A comma separated list of transcripts that the variants falls in. |
 | distances         |A comma separated list of distances from the start or stop of an exon. This distance is min(distance_from_start_of_exon, distance_from_end_of_exon). The number of elements in the list is same as the number of transcripts in the 'transcripts' field and in the same order. The distance needs to be less than or equal to the parameters specified by the -i and -e options.|
-| annotations       |A comma separated list of annotations in the same order as the 'transcripts'. The number of elements in this list is the same as the number of transcripts in the 'transcripts' field and in the same order, i.e each annotation corresponds to a different transcript. The valid values for this field are 'splicing_exonic' and 'splicing_intronic'. If the variant lies within the distance specified by '-e' option (3 b.p by default) inside an exon, it is annotated as 'splicing_exonic'. If the variant lies outside the exon within the distance specified by the '-i' option (2 b.p by default), it is annotated as 'splicing_intronic'.|
+| annotations       |A comma separated list of annotations in the same order as the 'transcripts'. The number of elements in this list is the same as the number of transcripts in the 'transcripts' field and in the same order, i.e each annotation corresponds to a different transcript. The valid values for this field are 'splicing_exonic' and 'splicing_intronic'. If the variant lies within the distance specified by '-e' option (3 b.p by default) inside an exon, it is annotated as 'splicing_exonic'. If the variant lies outside the exon within the distance specified by the '-i' option (2 b.p by default), it is annotated as 'splicing_intronic'. Note that even when all intronic or exonic variants are considered with the -I or -E options, they are labelled simply as "intronic" or "exonic", respectively.|
 
 ####Example output line
 ```bash

src/junctions/junctions_annotator.cc

@@ -386,9 +386,9 @@ int JunctionsAnnotator::parse_options(int argc, char *argv[]) {
     optind = 1; //Reset before parsing again.
     int c;
     stringstream help_ss;
-    while((c = getopt(argc, argv, "Eo:h")) != -1) {
+    while((c = getopt(argc, argv, "So:h")) != -1) {
         switch(c) {
-            case 'E':
+            case 'S':
                 skip_single_exon_genes_ = false;
                 break;
             case 'o':
@@ -428,7 +428,7 @@ int JunctionsAnnotator::parse_options(int argc, char *argv[]) {
 //Usage statement for this tool
 int JunctionsAnnotator::usage(ostream& out) {
     out << "Usage:\t\t" << "regtools junctions annotate [options] junctions.bed ref.fa annotations.gtf" << endl;
-    out << "Options:\t" << "-E include single exon genes" << endl;
+    out << "Options:\t" << "-S include single exon genes" << endl;
     out << "\t\t" << "-o FILE\tThe file to write output to. [STDOUT]" << endl;
     out << endl;
     return 0;