Update repeat expansion database to provide separate files for hg19 a…

…nd grch37 and add new loci Former-commit-id: 4c16f47
bahlolab · Jun 30, 2019 · e4be33d · e4be33d
1 parent 308fd90
commit e4be33d
Show file tree

Hide file tree

Showing 16 changed files with 78 additions and 39 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,8 +1,8 @@
 Package: exSTRa
 Type: Package
 Title: Expanded STR algorithm: detecting expansions in Illumina sequencing data
-Version: 0.88.6
-Date: 2019-01-21
+Version: 0.89.0
+Date: 2019-06-26
 Author: Rick Tankard
 Maintainer: Rick Tankard <[email protected]>
 Description: Detecting expansions with paired-end Illumina sequencing data.

diff --git a/R/read_exstra_db.R b/R/read_exstra_db.R
@@ -14,7 +14,7 @@
 #' @seealso \code{\link{read_score}}
 #' 
 #' @examples
-#' read_exstra_db(system.file("extdata", "repeat_expansion_disorders.txt", package = "exSTRa")) 
+#' read_exstra_db(system.file("extdata", "repeat_expansion_disorders_hg19.txt", package = "exSTRa")) 
 #' 
 #' @export
 #' @include read_exstra_db_xlsx.R

diff --git a/R/read_score.R b/R/read_score.R
@@ -26,7 +26,7 @@
 #' @examples 
 #' str_score <- read_score (
 #'     file = system.file("extdata", "HiSeqXTen_WGS_PCR_2.txt", package = "exSTRa"), 
-#'     database = system.file("extdata", "repeat_expansion_disorders.txt", package = "exSTRa"), 
+#'     database = system.file("extdata", "repeat_expansion_disorders_hg19.txt", package = "exSTRa"), 
 #'     groups.regex = c(control = "^WGSrpt_0[24]$", case = ""), 
 #'     filter.low.counts = TRUE
 #' )
@@ -40,7 +40,7 @@
 #' # Defining cases by sample name directly:
 #' str_score_HD_cases <- read_score (
 #'     file = system.file("extdata", "HiSeqXTen_WGS_PCR_2.txt", package = "exSTRa"), 
-#'     database = system.file("extdata", "repeat_expansion_disorders.txt", package = "exSTRa"),
+#'     database = system.file("extdata", "repeat_expansion_disorders_hg19.txt", package = "exSTRa"),
 #'     groups.samples = list(case = c("WGSrpt_10", "WGSrpt_12")),
 #'     filter.low.counts = TRUE
 #' )
@@ -51,7 +51,7 @@
 #' 
 #' # for greater control, use object from read_exstra_db() instead
 #' str_db <- read_exstra_db(
-#'             system.file("extdata", "repeat_expansion_disorders.txt", package = "exSTRa")
+#'             system.file("extdata", "repeat_expansion_disorders_hg19.txt", package = "exSTRa")
 #'           )
 #' str_score <- read_score (
 #'     file = system.file("extdata", "HiSeqXTen_WGS_PCR_2.txt", package = "exSTRa"), 

diff --git a/README.md b/README.md
@@ -24,9 +24,9 @@ At present, the pipeline requires:
 - Sorting 
 - PCR duplicate marking (recommended)
 
-A database of repeats is required, with known disorder loci included.
-An example script to generate a database of all STRs genome wide, or those in genes that are expressed in the brain, is provide in `inst/tools/prepare_exSTRa_input_db.R`.
-These input database files can also be [downloaded from FigShare](https://figshare.com/s/0bf679a187d5f3cc2b2c).
+A database of repeats is required, with files for the known disorder loci included for hg19 or GRCh37 in the `inst/extdata` directory.
+A database of all STRs genome wide in available to [download from FigShare](https://figshare.com/s/bb1e6358781bb3ca12c2).
+An example script to generate this database of all STRs genome wide, or those in genes that are expressed in the brain, is provide in `inst/tools/prepare_exSTRa_input_db.R`.
 
 Use the Perl scripts and modules from https://github.com/bahlolab/Bio-STR-exSTRa to analyse reads in BAM files. This generates STR counts. 
 In the future this functionality may be included within the R exSTRa package. 

diff --git a/data-raw/exstra_known.R b/data-raw/exstra_known.R
@@ -1,2 +1,2 @@
 # Read in the known repeat expansion disorder loci dataset
-exstra_known <- read_exstra_db(system.file("extdata", "repeat_expansion_disorders.txt", package = "exSTRa"))
+exstra_known <- read_exstra_db(system.file("extdata", "repeat_expansion_disorders_hg19.txt", package = "exSTRa"))
diff --git a/data-raw/exstra_wgs_pcr_2.R b/data-raw/exstra_wgs_pcr_2.R
@@ -1,7 +1,7 @@
 # The WGS_PCR_2 data data read in
 exstra_wgs_pcr_2 <- read_score (
     system.file("extdata", "HiSeqXTen_WGS_PCR_2.txt", package = "exSTRa"), # doesn't work before first install
-    database = system.file("extdata", "repeat_expansion_disorders.txt", package = "exSTRa"),
+    database = system.file("extdata", "repeat_expansion_disorders_hg19.txt", package = "exSTRa"),
     groups.regex = c(control = "^WGSrpt_0[24]$", case = ""), # here, matches on successive patterns override previous matches # (TODO: maybe should be reversed?)
     filter.low.counts = TRUE
   )

diff --git a/doc/exSTRa.R b/doc/exSTRa.R
@@ -15,7 +15,7 @@ library(exSTRa)
 ## ------------------------------------------------------------------------
 str_score <- read_score (
   file = system.file("extdata", "HiSeqXTen_WGS_PCR_2.txt", package = "exSTRa"), 
-  database = system.file("extdata", "repeat_expansion_disorders.txt", package = "exSTRa"),
+  database = system.file("extdata", "repeat_expansion_disorders_hg19.txt", package = "exSTRa"),
   groups.regex = c(control = "^WGSrpt_0[24]$", case = "")
 )
 

diff --git a/doc/exSTRa.Rmd b/doc/exSTRa.Rmd
@@ -118,7 +118,7 @@ This results in an `exstra_score` object.
 ```{r}
 str_score <- read_score (
   file = system.file("extdata", "HiSeqXTen_WGS_PCR_2.txt", package = "exSTRa"), 
-  database = system.file("extdata", "repeat_expansion_disorders.txt", package = "exSTRa"),
+  database = system.file("extdata", "repeat_expansion_disorders_hg19.txt", package = "exSTRa"),
   groups.regex = c(control = "^WGSrpt_0[24]$", case = "")
 )
 

diff --git a/doc/exSTRa.html.REMOVED.git-id b/doc/exSTRa.html.REMOVED.git-id
@@ -1 +1 @@
-27ff3057312913216fda5bdde43474a65a46189b
+b0661c7cbbe131121ec309c4ca25b71c0fd32624
diff --git a/examples/exSTRa_score_analysis.R b/examples/exSTRa_score_analysis.R
@@ -10,7 +10,7 @@ knitr::opts_chunk$set(fig.width=11, fig.height=11)
 # Read score data and file with loci information
 str_score <- read_score (
   file = system.file("extdata", "HiSeqXTen_WGS_PCR_2.txt", package = "exSTRa"), 
-  database = system.file("extdata", "repeat_expansion_disorders.txt", package = "exSTRa"),  # for greater control, use object from read_exstra_db() instead
+  database = system.file("extdata", "repeat_expansion_disorders_hg19.txt", package = "exSTRa"),  # for greater control, use object from read_exstra_db() instead
   groups.regex = c(control = "^WGSrpt_0[24]$", case = ""), # the group is the first regular expression (regex) to match
   filter.low.counts = TRUE
 )

diff --git a/inst/extdata/repeat_expansion_disorders_grch37.txt b/inst/extdata/repeat_expansion_disorders_grch37.txt
@@ -0,0 +1,31 @@
+### exSTRa repeat expansion disorder GRCh37 database ###																						
+# Last updated 26th June 2019.																						
+# Most fields are for informational purposes and not used by exSTRa.																						
+# Requires: exSTRa 0.8																						
+locus	long_name	OMIM	inheritance	gene	location	gene_region	motif	norm_low	norm_up	aff_low	aff_up	aff_more	strand	chrom	hg19_start	hg19_end	copyNum	perMatch	perIndel	STR_size_bp	score_size	strcat
+DM1	Myotonic dystrophy 1	160900	AD	DMPK	19q13	3'UTR	CTG	5	37	50	10000	FALSE	-	19	46273463	46273524	20.7	100	0	62	NA	http://strcat.teamerlich.org/chart/chr19/46273463/46273524
+DM2	Myotonic dystrophy 2	602668	AD	ZNF9/CNBP	3q21.3	intron	CCTG	10	26	75	11000	FALSE	-	3	128891420	128891502	20.8	92	0	83	NA	http://strcat.teamerlich.org/chart/chr3/128891420/128891502
+DRPLA	Dentatorubral-pallidoluysian atrophy	125370	AD	DRPLA/ATN1	12p13.31	coding	CAG	7	34	49	88	FALSE	+	12	7045880	7045938	19.7	92	0	59	NA	http://strcat.teamerlich.org/chart/chr12/7045880/7045938
+EPM1A	Myoclonic epilepsy of Unverricht and Lundborg	254800	AR	CSTB	21q22.3	promotor	CCCCGCCCCGCG	2	3	40	80	FALSE	-	21	45196324	45196360	3.1	100	0	37	NA	http://strcat.teamerlich.org/chart/chr21/45196324/45196360
+FRAXA	Fragile-X site A	309550	X	FMR1	Xq27.3	5'UTR	CGG	6	54	200	1000	TRUE	+	X	146993555	146993629	25	90	5	75	NA	http://strcat.teamerlich.org/chart/chrX/146993555/146993629
+FRAXE	Fragile-X site E	309548	X	FMR2	Xq28	5'UTR	CCG	4	39	200	900	FALSE	+	X	147582159	147582204	15.3	100	0	46	NA	http://strcat.teamerlich.org/chart/chrX/147582125/147582273
+FRDA	Friedreich ataxia	229300	AR	FXN	9q13	intron	GAA	6	32	200	1700	FALSE	+	9	71652201	71652220	6.7	100	0	20	NA	http://strcat.teamerlich.org/chart/chr9/71652201/71652220
+FTDALS1	Amyotrophic lateral sclerosis-frontotemporal dementia	105550	AD	C9orf72	9p21	intron	GGGGCC	2	19	250	1600	FALSE	-	9	27573483	27573544	10.8	74	8	62	NA	http://strcat.teamerlich.org/chart/chr9/27573483/27573544
+HD	Huntington disease	143100	AD	HTT	4p16.3	coding	CAG	6	34	36	100	TRUE	+	4	3076604	3076667	21.3	96	0	64	NA	http://strcat.teamerlich.org/chart/chr4/3076604/3076667
+HDL2	Huntington disease-like 2	606438	AD	JPH3	16q24.3	exon	CTG	7	28	66	78	FALSE	+	16	87637889	87637935	15.3	95	4	47	NA	http://strcat.teamerlich.org/chart/chr16/87637889/87637935
+SBMA	Kennedy disease	313200	X	AR	Xq12	coding	CAG	9	35	38	62	FALSE	+	X	66765159	66765261	33.3	86	9	103	NA	http://strcat.teamerlich.org/chart/chrX/66765159/66765261
+SCA1	Spinocerebellar ataxia 1	164400	AD	ATXN1	6p23	coding	CAG	6	38	39	82	FALSE	-	6	16327865	16327955	30.3	95	0	91	NA	http://strcat.teamerlich.org/chart/chr6/16327865/16327955
+SCA2	Spinocerebellar ataxia 2	183090	AD	ATXN2	12q24	coding	CAG	15	24	32	200	FALSE	-	12	112036754	112036823	23.3	97	0	70	NA	http://strcat.teamerlich.org/chart/chr12/112036754/112036823
+SCA3	Machado-Joseph disease	109150	AD	ATXN3	14q32.1	coding	CAG	13	36	61	84	FALSE	-	14	92537355	92537396	14	84	0	42	NA	http://strcat.teamerlich.org/chart/chr14/92537355/92537396
+SCA6	Spinocerebellar ataxia 6	183086	AD	CACNA1A	19p13	coding	CAG	4	17	21	33	FALSE	-	19	13318673	13318712	13.3	100	0	40	NA	http://strcat.teamerlich.org/chart/chr19/13318673/13318712
+SCA7	Spinocerebellar ataxia 7	164500	AD	ATXN7	3p14.1	coding	CAG	4	35	37	306	FALSE	+	3	63898361	63898392	10.7	100	0	32	NA	http://strcat.teamerlich.org/chart/chr3/63898361/63898392
+SCA8	Spinocerebellar ataxia 8	608768	AD	ATXN8OS/ATXN8	13q21	utRNA	CTG	16	34	74	74	TRUE	+	13	70713516	70713561	15.3	100	0	46	NA	http://strcat.teamerlich.org/chart/chr13/70713516/70713561
+SCA10	Spinocerebellar ataxia 10	603516	AD	ATXN10	22q13.31	intron	ATTCT	10	20	500	4500	FALSE	+	22	46191235	46191304	14	100	0	70	NA	http://strcat.teamerlich.org/chart/chr22/46191235/46191304
+SCA12	Spinocerebellar ataxia 12	604326	AD	PPP2R2B	5q32	promotor	CAG	7	45	55	78	FALSE	-	5	146258291	146258322	10.7	100	0	32	NA	http://strcat.teamerlich.org/chart/chr5/146258291/146258322
+SCA17	Spinocerebellar ataxia 17	607136	AD	TBP	6q27	coding	CAG	25	42	47	63	FALSE	+	6	170870995	170871105	37	94	0	111	NA	http://strcat.teamerlich.org/chart/chr6/170870995/170871105
+SCA36	Spinocerebellar ataxia 36	614153	AD	NOP56	20p13	intron	GGCCTG	3	8	1500	2500	FALSE	+	20	2633379	2633421	7.2	97	0	43	NA	http://strcat.teamerlich.org/chart/chr20/2633379/2633421
+FECD3	Fuchs endothelial corneal dystrophy 3	613267	AD	TCF4	18q21.2	intron	CTG	10	40	50	1300	TRUE	-	18	53253385	53253460	25.3	100	0	76	NA	NA
+FAME1	Familial adult myoclonic epilepsy 1	601068	AD	SAMD12	8q24	intron	TTTCA	0	0	440	3680	FALSE	-	8	119379052	119379155	0.6			3	NA	NA
+FAME6	Familial adult myoclonic epilepsy 6	618074	AD	TNRC6A	16p12.1	intron	TTTCA	0	0			TRUE	+	16	24624851	24624853	0.6			3	NA	NA
+FAME7	Familial adult myoclonic epilepsy 7	618075	AD	RAPGEF2	4q32.1	intron	TTTCA	0	0			TRUE	+	4	160263769	160263770	0.4			2	NA	NA
+CANVAS	Cerebellar ataxia, neuropathy, and vestibular areflexia syndrome	614575	AR	RFC1	4p14	intron	TTCCC	0	0	400	2000	FALSE	-	4	39350045	39350103	11.8			59	NA	NA
diff --git a/inst/extdata/repeat_expansion_disorders.txt → ...tdata/repeat_expansion_disorders_hg19.txt b/inst/extdata/repeat_expansion_disorders.txt → ...tdata/repeat_expansion_disorders_hg19.txt
@@ -1,27 +1,31 @@
-### exSTRa repeat expansion disorder database ###
-# Last updated 18th May 2017.
-# Most fields are for informational purposes and not used by exSTRa.
-# Requires: exSTRa 0.8
+### exSTRa repeat expansion disorder GRCh37 database ###																						
+# Last updated 26th June 2019.																						
+# Most fields are for informational purposes and not used by exSTRa.																						
+# Requires: exSTRa 0.8																						
 locus	long_name	OMIM	inheritance	gene	location	gene_region	motif	norm_low	norm_up	aff_low	aff_up	aff_more	strand	chrom	hg19_start	hg19_end	copyNum	perMatch	perIndel	STR_size_bp	score_size	strcat
+DM1	Myotonic dystrophy 1	160900	AD	DMPK	19q13	3'UTR	CTG	5	37	50	10000	FALSE	-	chr19	46273463	46273524	20.7	100	0	62	NA	http://strcat.teamerlich.org/chart/chr19/46273463/46273524
+DM2	Myotonic dystrophy 2	602668	AD	ZNF9/CNBP	3q21.3	intron	CCTG	10	26	75	11000	FALSE	-	chr3	128891420	128891502	20.8	92	0	83	NA	http://strcat.teamerlich.org/chart/chr3/128891420/128891502
+DRPLA	Dentatorubral-pallidoluysian atrophy	125370	AD	DRPLA/ATN1	12p13.31	coding	CAG	7	34	49	88	FALSE	+	chr12	7045880	7045938	19.7	92	0	59	NA	http://strcat.teamerlich.org/chart/chr12/7045880/7045938
+EPM1A	Myoclonic epilepsy of Unverricht and Lundborg	254800	AR	CSTB	21q22.3	promotor	CCCCGCCCCGCG	2	3	40	80	FALSE	-	chr21	45196324	45196360	3.1	100	0	37	NA	http://strcat.teamerlich.org/chart/chr21/45196324/45196360
+FRAXA	Fragile-X site A	309550	X	FMR1	Xq27.3	5'UTR	CGG	6	54	200	1000	TRUE	+	chrX	146993555	146993629	25	90	5	75	NA	http://strcat.teamerlich.org/chart/chrX/146993555/146993629
+FRAXE	Fragile-X site E	309548	X	FMR2	Xq28	5'UTR	CCG	4	39	200	900	FALSE	+	chrX	147582159	147582204	15.3	100	0	46	NA	http://strcat.teamerlich.org/chart/chrX/147582125/147582273
+FRDA	Friedreich ataxia	229300	AR	FXN	9q13	intron	GAA	6	32	200	1700	FALSE	+	chr9	71652201	71652220	6.7	100	0	20	NA	http://strcat.teamerlich.org/chart/chr9/71652201/71652220
+FTDALS1	Amyotrophic lateral sclerosis-frontotemporal dementia	105550	AD	C9orf72	9p21	intron	GGGGCC	2	19	250	1600	FALSE	-	chr9	27573483	27573544	10.8	74	8	62	NA	http://strcat.teamerlich.org/chart/chr9/27573483/27573544
 HD	Huntington disease	143100	AD	HTT	4p16.3	coding	CAG	6	34	36	100	TRUE	+	chr4	3076604	3076667	21.3	96	0	64	NA	http://strcat.teamerlich.org/chart/chr4/3076604/3076667
+HDL2	Huntington disease-like 2	606438	AD	JPH3	16q24.3	exon	CTG	7	28	66	78	FALSE	+	chr16	87637889	87637935	15.3	95	4	47	NA	http://strcat.teamerlich.org/chart/chr16/87637889/87637935
 SBMA	Kennedy disease	313200	X	AR	Xq12	coding	CAG	9	35	38	62	FALSE	+	chrX	66765159	66765261	33.3	86	9	103	NA	http://strcat.teamerlich.org/chart/chrX/66765159/66765261
 SCA1	Spinocerebellar ataxia 1	164400	AD	ATXN1	6p23	coding	CAG	6	38	39	82	FALSE	-	chr6	16327865	16327955	30.3	95	0	91	NA	http://strcat.teamerlich.org/chart/chr6/16327865/16327955
 SCA2	Spinocerebellar ataxia 2	183090	AD	ATXN2	12q24	coding	CAG	15	24	32	200	FALSE	-	chr12	112036754	112036823	23.3	97	0	70	NA	http://strcat.teamerlich.org/chart/chr12/112036754/112036823
 SCA3	Machado-Joseph disease	109150	AD	ATXN3	14q32.1	coding	CAG	13	36	61	84	FALSE	-	chr14	92537355	92537396	14	84	0	42	NA	http://strcat.teamerlich.org/chart/chr14/92537355/92537396
 SCA6	Spinocerebellar ataxia 6	183086	AD	CACNA1A	19p13	coding	CAG	4	17	21	33	FALSE	-	chr19	13318673	13318712	13.3	100	0	40	NA	http://strcat.teamerlich.org/chart/chr19/13318673/13318712
 SCA7	Spinocerebellar ataxia 7	164500	AD	ATXN7	3p14.1	coding	CAG	4	35	37	306	FALSE	+	chr3	63898361	63898392	10.7	100	0	32	NA	http://strcat.teamerlich.org/chart/chr3/63898361/63898392
-SCA17	Spinocerebellar ataxia 17	607136	AD	TBP	6q27	coding	CAG	25	42	47	63	FALSE	+	chr6	170870995	170871105	37	94	0	111	NA	http://strcat.teamerlich.org/chart/chr6/170870995/170871105
-DRPLA	Dentatorubral-pallidoluysian atrophy	125370	AD	DRPLA/ATN1	12p13.31	coding	CAG	7	34	49	88	FALSE	+	chr12	7045880	7045938	19.7	92	0	59	NA	http://strcat.teamerlich.org/chart/chr12/7045880/7045938
-HDL2	Huntington disease-like 2	606438	AD	JPH3	16q24.3	exon	CTG	7	28	66	78	FALSE	+	chr16	87637889	87637935	15.3	95	4	47	NA	http://strcat.teamerlich.org/chart/chr16/87637889/87637935
-FRAXA	Fragile-X site A	309550	X	FMR1	Xq27.3	5'UTR	CGG	6	54	200	1000	TRUE	+	chrX	146993555	146993629	25	90	5	75	NA	http://strcat.teamerlich.org/chart/chrX/146993555/146993629
-FRAXE	Fragile-X site E	309548	X	FMR2	Xq28	5'UTR	CCG	4	39	200	900	FALSE	+	chrX	147582159	147582204	15.3	100	0	46	NA	http://strcat.teamerlich.org/chart/chrX/147582125/147582273
-DM1	Myotonic dystrophy 1	160900	AD	DMPK	19q13	3'UTR	CTG	5	37	50	10000	FALSE	-	chr19	46273463	46273524	20.7	100	0	62	NA	http://strcat.teamerlich.org/chart/chr19/46273463/46273524
-FRDA	Friedreich ataxia	229300	AR	FXN	9q13	intron	GAA	6	32	200	1700	FALSE	+	chr9	71652201	71652220	6.7	100	0	20	NA	http://strcat.teamerlich.org/chart/chr9/71652201/71652220
-DM2	Myotonic dystrophy 2	602668	AD	ZNF9/CNBP	3q21.3	intron	CCTG	10	26	75	11000	FALSE	-	chr3	128891420	128891502	20.8	92	0	83	NA	http://strcat.teamerlich.org/chart/chr3/128891420/128891502
-FTDALS1	Amyotrophic lateral sclerosis-frontotemporal dementia	105550	AD	C9orf72	9p21	intron	GGGGCC	2	19	250	1600	FALSE	-	chr9	27573483	27573544	10.8	74	8	62	NA	http://strcat.teamerlich.org/chart/chr9/27573483/27573544
-SCA36	Spinocerebellar ataxia 36	614153	AD	NOP56	20p13	intron	GGCCTG	3	8	1500	2500	FALSE	+	chr20	2633379	2633421	7.2	97	0	43	NA	http://strcat.teamerlich.org/chart/chr20/2633379/2633421
+SCA8	Spinocerebellar ataxia 8	608768	AD	ATXN8OS/ATXN8	13q21	utRNA	CTG	16	34	74	74	TRUE	+	chr13	70713516	70713561	15.3	100	0	46	NA	http://strcat.teamerlich.org/chart/chr13/70713516/70713561
 SCA10	Spinocerebellar ataxia 10	603516	AD	ATXN10	22q13.31	intron	ATTCT	10	20	500	4500	FALSE	+	chr22	46191235	46191304	14	100	0	70	NA	http://strcat.teamerlich.org/chart/chr22/46191235/46191304
-EPM1A	Myoclonic epilepsy of Unverricht and Lundborg	254800	AR	CSTB	21q22.3	promotor	CCCCGCCCCGCG	2	3	40	80	FALSE	-	chr21	45196324	45196360	3.1	100	0	37	NA	http://strcat.teamerlich.org/chart/chr21/45196324/45196360
 SCA12	Spinocerebellar ataxia 12	604326	AD	PPP2R2B	5q32	promotor	CAG	7	45	55	78	FALSE	-	chr5	146258291	146258322	10.7	100	0	32	NA	http://strcat.teamerlich.org/chart/chr5/146258291/146258322
-SCA8	Spinocerebellar ataxia 8	608768	AD	ATXN8OS/ATXN8	13q21	utRNA	CTG	16	34	74	74	TRUE	+	chr13	70713516	70713561	15.3	100	0	46	NA	http://strcat.teamerlich.org/chart/chr13/70713516/70713561
-
+SCA17	Spinocerebellar ataxia 17	607136	AD	TBP	6q27	coding	CAG	25	42	47	63	FALSE	+	chr6	170870995	170871105	37	94	0	111	NA	http://strcat.teamerlich.org/chart/chr6/170870995/170871105
+SCA36	Spinocerebellar ataxia 36	614153	AD	NOP56	20p13	intron	GGCCTG	3	8	1500	2500	FALSE	+	chr20	2633379	2633421	7.2	97	0	43	NA	http://strcat.teamerlich.org/chart/chr20/2633379/2633421
+FECD3	Fuchs endothelial corneal dystrophy 3	613267	AD	TCF4	18q21.2	intron	CTG	10	40	50	1300	TRUE	-	chr18	53253385	53253460	25.3	100	0	76	NA	NA
+FAME1	Familial adult myoclonic epilepsy 1	601068	AD	SAMD12	8q24	intron	TTTCA	0	0	440	3680	FALSE	-	chr8	119379052	119379155	0.6			3	NA	NA
+FAME6	Familial adult myoclonic epilepsy 6	618074	AD	TNRC6A	16p12.1	intron	TTTCA	0	0			TRUE	+	chr16	24624851	24624853	0.6			3	NA	NA
+FAME7	Familial adult myoclonic epilepsy 7	618075	AD	RAPGEF2	4q32.1	intron	TTTCA	0	0			TRUE	+	chr4	160263769	160263770	0.4			2	NA	NA
+CANVAS	Cerebellar ataxia, neuropathy, and vestibular areflexia syndrome	614575	AR	RFC1	4p14	intron	TTCCC	0	0	400	2000	FALSE	-	chr4	39350045	39350103	11.8			59	NA	NA
diff --git a/inst/tools/prepare_exSTRa_input_db.R b/inst/tools/prepare_exSTRa_input_db.R
@@ -18,6 +18,10 @@ GTEx_median_tpm_file <- ".../path/to/.../GTEx_Analysis_2016-01-15_v7_RNASeQCv1.1
 # Specify median TMP value to use as threshold for which genes are considered expressed in brain
 brain_median_tpm_thresh <- 1
 
+# Specify miminum and maximum motif size (in base pairs) to search for
+min_motif_size <- 2
+max_motif_size <- 6
+
 # Download and install ANNOVAR (http://annovar.openbioinformatics.org/)
 table_annovar_script <- ".../path/to/.../table_annovar.pl"
 humandb_annovar_dir <- ".../path/to/.../humandb"
@@ -29,8 +33,8 @@ simpleRepeat <- readr::read_delim(simpleRepeat_file, delim="\t", col_names=FALSE
 colnames(simpleRepeat) <- c("bin", "chrom", "chromStart", "chromEnd", "name", "period", "copyNum", "consensusSize", "perMatch", "perIndel", "score", "A", "C", "G", "T", "entropy", "sequence")
 simpleRepeat <- as.data.frame(simpleRepeat, stringsAsFactors=FALSE)
 
-# Filter to 2-6 bp pair repeats
-simpleRepeat <- simpleRepeat[(simpleRepeat$period >= 2) & (simpleRepeat$period <= 6), ]
+# Filter based on repeat motif size
+simpleRepeat <- simpleRepeat[(simpleRepeat$consensusSize >= min_motif_size) & (simpleRepeat$consensusSize <= max_motif_size), ]
 
 # Download GTEx portal median TPM table from https://gtexportal.org/home/datasets:
 # GTEx_Analysis_2016-01-15_v7_RNASeQCv1.1.8_gene_median_tpm.gct.gz

diff --git a/man/read_exstra_db.Rd b/man/read_exstra_db.Rd
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		27ff3057312913216fda5bdde43474a65a46189b
		b0661c7cbbe131121ec309c4ca25b71c0fd32624