version 3.2.0

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: rehh
 Maintainer: Alexander Klassmann <[email protected]>
 Author: Mathieu Gautier, Alexander Klassmann and Renaud Vitalis
-Version: 3.1.2
+Version: 3.2.0
 License: GPL (>= 2)
 Title: Searching for Footprints of Selection using 'Extended Haplotype
         Homozygosity' Based Tests
@@ -18,23 +18,18 @@ Description: Population genetic data such as 'Single Nucleotide
         'Rsb' (Tang 2007) <doi:10.1371/journal.pbio.0050171> and 
         'XP-EHH' (Sabeti 2007) <doi:10.1038/nature06250>, targeted
         at differential selection between two populations. 
-        Various plotting functions are also included to facilitate
-        visualization and interpretation of these statistics. 
-        Due to changes in the API, albeit mostly minor, 
-        versions 3.X are not compatible with versions 2.0.X.
-        Note: optionally, vcf files can be imported using package vcfR. That package
-        is currently removed from CRAN, but can still be installed from 
-        <https://github.com/knausb/vcfR> following instructions there.
+        Various plotting functions are included to facilitate
+        visualization and interpretation of these statistics.
 Depends: R (>= 2.10)
 Imports: methods, rehh.data
 Suggests: ape, bookdown, data.table, gap, knitr, qqman, rmarkdown,
         R.utils, testthat, vcfR
 VignetteBuilder: knitr
 NeedsCompilation: yes
-Packaged: 2020-07-17 09:16:17 UTC; alex
-RoxygenNote: 7.1.0
+Packaged: 2020-11-01 09:31:22 UTC; alex
+RoxygenNote: 7.1.1
 URL: https://CRAN.R-project.org/package=rehh,
         https://gitlab.com/oneoverx/rehh
-BugReports: https://gitlab.com/oneoverx/rehh/issues
+BugReports: https://gitlab.com/oneoverx/rehh/-/issues
 Repository: CRAN
-Date/Publication: 2020-07-17 10:30:03 UTC
+Date/Publication: 2020-11-01 10:00:02 UTC

MD5

@@ -1,95 +1,103 @@
-4be95bfe5393b4ad0d988f9076587813 *DESCRIPTION
-479cda305f23caf8bd3f42caa2013c3e *NAMESPACE
-c3bdce8419097ef74d75dedfadbb2264 *NEWS.md
-d778a01442f62a331f42f43636d35c9a *R/as.newick.R
-791804c313fb1e1bc68e7c5b95ecc92d *R/calc_candidate_regions.R
-f64accc80d3c07213985e6eebd0969a7 *R/calc_ehh.R
-adf2e4d9478c23d89b6a1f64cbb8e645 *R/calc_ehhs.R
+8e4fd944b954c1f38c17b5b3ce560700 *DESCRIPTION
+60535cbfb654e4815b8af2877be13a28 *NAMESPACE
+481b516368c4630b1471c79c49cf4f20 *NEWS.md
+49fb7dde709b7d56d950cfa481eee11e *R/as.newick.R
+c489a95c70ee3f7a9b21c5e4e1701e00 *R/calc_candidate_regions.R
+a5184787be940979ca4d87c32a69a6c5 *R/calc_ehh.R
+d846b662a796c555a11a05a253237219 *R/calc_ehhs.R
 7fc6137f3a9052c916c600103630f747 *R/calc_furcation.R
 8652c8e385335d536e351d10ccba7767 *R/calc_haplen.R
-647a736449be2f7cb9ef08fc31691ad5 *R/calc_pairwise_haplen.R
+1b9d3c5e76519a3101f08b58125167d3 *R/calc_pairwise_haplen.R
 c0a7134ed354a1cc6e2d92cff7cb528b *R/calc_region_stats.R
-aebc3fea50b8605b1d1aa3aaf21776bd *R/data2haplohh.R
+dc4dfe02470f10724b4702d7bad63153 *R/calc_sfs_tests.R
+db41e0abae0d42d719592911a8db10d7 *R/data2haplohh.R
 3caea4a19997c6f248290697f797b4a1 *R/distribplot.R
 ef5e101f1c8c4891d5991bf2fd0257b4 *R/extract_regions.R
 e5d4611c5eeb4e3f839683a3f665e214 *R/freqbinplot.R
 810c2aca58d223d852d957d0fe236b0a *R/furcation-class.R
 b9dd5b7b760f2fdb3441fcf332fd8f9a *R/haplohh-class.R
+10eddc406dc337e263f6e745a1c8d002 *R/haplohh2sweepfinder.R
 6eebd3fac16bb154d1ea834dd0289c26 *R/ies2xpehh.R
 0b91ea1dff6639b4c3b4f13dea539637 *R/ihh2ihs.R
 1fc5288e0bd273f896e5daef79a8838e *R/ines2rsb.R
-1ab4dd6448b5781c7abf510cd5be6750 *R/make.example.files.R
-f1138821f4d4882da57c5499764342fd *R/manhattanplot.R
+39ac154b20c0400cd5632b5268de2892 *R/make.example.files.R
+14aae5afa388353eb0abee02d930773c *R/manhattanplot.R
 de8aebb14b907da33b6e6483acb05467 *R/plot.ehh.R
 c461be69e8d0960110dbd2e2c214c809 *R/plot.ehhs.R
 f8018a6adb6442dd197b00f6f50d62d4 *R/plot.furcation.R
 562bf90c94616972a745c618e3002078 *R/plot.haplen.R
-46f5794ea7ee74e36c779522aa2d6ab2 *R/plot.haplohh.R
-d0c64f19c95d71847c72b56a14db8de9 *R/rehh.R
-e232bea3e5d1d83fdf560f24d01deb18 *R/scan_hh.R
-f31185006802c7467a9f6a8cc8c92fa8 *R/scan_hh_full.R
-d857d3be60093cc3900f1d221fd867fc *R/subset.haplohh.R
+f0e6d5dc46aa06ec2aa75a551187cee9 *R/plot.haplohh.R
+b0695663334e80f7f38654bd355b7c32 *R/rehh.R
+eb17387a546704c5510ba46856b6ca93 *R/scan_hh.R
+50902c106c1f1a7e23f3534f6f639290 *R/scan_hh_full.R
+c8aaf488db328f7ea21ecb7ea309e4ee *R/subset.haplohh.R
 9d53dfc94e3a08334b06091ab986217d *R/update_haplohh.R
-8228a460ed62d771a05ec3e1e9a7cb59 *build/vignette.rds
+28612d69e6e3c076a5bac689ddabec2b *build/vignette.rds
 bbd50c8eb813216188dce7896d1490d3 *data/datalist
 91be48fb8754c805321891b9374459f3 *data/haplohh_cgu_bta12.RData
 8439f1531106aeabce40b21067a1ac5e *inst/CITATION
-ae04d6c09732f0e29be34d966896d3d4 *inst/doc/examples.R
-347ed7fd5246ab0a51b07eb65c551f51 *inst/doc/examples.Rmd
-a66b153a90d0c7ba1cfc0e6d7d993e13 *inst/doc/examples.html
-0aca4270ed980c2b91db059f72ce8512 *inst/doc/rehh.R
-0cb9f06cbea7141d8522641178da4b54 *inst/doc/rehh.Rmd
-4c42ce24a6e5e3c0f331df7518413c4d *inst/doc/rehh.html
+ec7fb3bdabc787abe3be7512729a1e2f *inst/doc/examples.R
+4d69844ff06315aff3356db7f85edd4c *inst/doc/examples.Rmd
+dec90acf8e63ab73cfe08ef0fc212cfa *inst/doc/examples.html
+e4ac37fc09893fb1d5297d231923ba02 *inst/doc/rehh.R
+602994925b401f0fe98262d30ff9d6e8 *inst/doc/rehh.Rmd
+b9da2d6fdd34b4a4b7b0f4e4addbac14 *inst/doc/rehh.html
 529c33971c081bacc8d00072aac22b20 *inst/extdata/bta12_cgu.vcf.gz
 1a13676197023c7796532d96aeff7f76 *inst/extdata/example1.hap
 98aedc74c294ec4769b8e3272200fbbe *inst/extdata/example1.map
 ef932b5c063861aae607ee0a93f33fb1 *inst/extdata/example1.vcf
 259361a2879d15a50f494d8cb2322f95 *inst/extdata/example2.hap
 05fcdbaf97aff8c6125dff9c40770538 *inst/extdata/example2.map
 5e14d8117c9a49dac08ad3970a046373 *inst/extdata/example2.vcf
+47a95eddad7ca90f68a4c35e671957b2 *inst/extdata/example_neutral.vcf
+9adc5ae193051f554e00eda74567486e *inst/extdata/example_sweep.vcf
+ab2d39dc100928b7c1e3a510287bb4c1 *inst/extdata/example_sweep_with_recombination.vcf
 e444d999cd7277d08690d6031446baf1 *inst/extdata/ms.out
 3f1bb468e3b3346d7925ed893f668d22 *man/allelefurcation-class.Rd
 e43b5b616e972b190f596b0791aafdcb *man/as.newick.Rd
 7d199b2def3e6d19e90ffa4128531956 *man/calc_candidate_regions.Rd
-9a1d4d2573383b1af915cd9740433948 *man/calc_ehh.Rd
-877765521fdd1bc21f0fad429f434980 *man/calc_ehhs.Rd
+8ce616089d0acc6279c8acaaf2b30cb7 *man/calc_ehh.Rd
+35d1ec2b344079cf92df525bf932c1d1 *man/calc_ehhs.Rd
 c933fc808090cbc1cade18247471df48 *man/calc_furcation.Rd
 12a719a71c961a21e8de7f5146ac1dc2 *man/calc_haplen.Rd
-36e5218744298abe44f67dbfb6d4c599 *man/calc_pairwise_haplen.Rd
+e6f80fc8df2c011ea38bd46d54b06a74 *man/calc_pairwise_haplen.Rd
 2acaa7c3c89fcb46f3c7e4f370160986 *man/calc_region_stats.Rd
-aae72c0cb9f1bffb913dd8b13d534125 *man/data2haplohh.Rd
+d2af8949d1a198ab26bfe45434be5924 *man/calc_sfs_tests.Rd
+827eda0a35e51d45916607f10511a564 *man/data2haplohh.Rd
 de43ae62050ec49c91c44138fe93b67c *man/distribplot.Rd
 d557df62cd52e701005da0a5f0d8ec7c *man/extract_regions.Rd
 17a00bb024774a6d4ef9491306f79872 *man/freqbinplot.Rd
 21f93e394201b1b91a9de96890fa918a *man/ftree-class.Rd
 33ddd89f9f2b47889d3be980b70747a0 *man/furcation-class.Rd
 128fede3b0de4f84512e35c295433af2 *man/haplen-class.Rd
 9917b0686748d15925dc890f045a076d *man/haplohh-class.Rd
+c4211206daf63a9bfea41eb968dc3fc6 *man/haplohh2sweepfinder.Rd
 b240d6b987257834ba5e9815aadfc537 *man/haplohh_cgu_bta12.Rd
 8f39cb0fa8ff33094b34f5cc094afa8d *man/ies2xpehh.Rd
 53e588ceb4a78d806505251b4fb6f763 *man/ihh2ihs.Rd
 5823cdec432bbd985be9063d46fc6af0 *man/ines2rsb.Rd
-2449dbe55eb56665554d7fc8ee255766 *man/make.example.files.Rd
-704045fb4408191c2962598b09080c7c *man/manhattanplot.Rd
+9bf74e16a8816a0fd0f39fa67e879924 *man/make.example.files.Rd
+af0baef3fee7a181c0b995d3bc65b5e0 *man/manhattanplot.Rd
 96922dd9dbc33bcb024a69e3ec308be7 *man/plot.ehh.Rd
 0091288c2de9b5c909c4f135dd87b1ad *man/plot.ehhs.Rd
 c7933322276a4b8fa37433e050766c4d *man/plot.furcation.Rd
 939fa1dcc75eacda1eef877ee99c9e7b *man/plot.haplen.Rd
-cd8682e4686cbe6130490e25a8e79301 *man/plot.haplohh.Rd
-9d5eba020ec22ee48ef012d9f1a54d70 *man/rehh-package.Rd
+090eca9f26b95024ee2aca3f483caf52 *man/plot.haplohh.Rd
+07fab15f3017f348fcafac0dec82ac39 *man/rehh-package.Rd
 0b3af48394811f7b7e481ca6fd7c63fd *man/remove.example.files.Rd
-a67e3e8c460d7f55dde5243edf351c6c *man/scan_hh.Rd
-9894dd029348f74ae46e2fb658289e24 *man/scan_hh_full.Rd
-ce6e4d831dabbd3ded45ea6a4cdbf433 *man/subset.haplohh.Rd
+c7d8274a12c1b590ad9f210db5bfa52c *man/scan_hh.Rd
+f0afc4cb433d9c6b7fddb600605d1ef7 *man/scan_hh_full.Rd
+3940df1de7b4ad97554a1d03ce8c64e1 *man/subset.haplohh.Rd
 35d96dc7734635751107a32802c872c7 *man/update_haplohh.Rd
 ea195efe5e62727303defe92c7dfd337 *src/CALL_ASNEWICK.c
 3bbb1385892442008a3efa83ed14f25a *src/CALL_EHH.c
 733a9d7f96da43cdd8127c4323bca3dc *src/CALL_EHHS.c
 af8abfa9ecc355a7bd825358ef3afe5e *src/CALL_FURCATION.c
 28bb39004e7d75cb01ff08c952148e6e *src/CALL_INTEGRAL.c
-d5c7bc8c7d80203979aa6a9237e9346d *src/CALL_PAIRWISE_HAPLEN.c
+60d65393e0384e62cb72f308058ef007 *src/CALL_PAIRWISE_HAPLEN.c
 997866feb635416dba2745e1275b33f0 *src/CALL_SCAN_HH.c
-34549fcae56fa1cf4325ed1c9870b376 *src/CALL_SCAN_HH2.c
+fe0c7dcc2bb11ae05b3ea7080d5aa7d7 *src/CALL_SCAN_HH_FULL.c
+63feb5cece836f3ef515492d15a166af *src/CALL_SFS_TESTS.c
 95e3011e37d9dde0d75f3a3819b2acd3 *src/Makevars
 fba8f42eba26752e28b32338665d7348 *src/asnewick.c
 c091d180d8864d7f3eea26b915784877 *src/asnewick.h
@@ -99,8 +107,10 @@ c091d180d8864d7f3eea26b915784877 *src/asnewick.h
 27c58a2a27960458af14d7c61f0d155e *src/calc_ehhs.h
 08642573b73421d2a0a401769bf8248b *src/calc_furcation.c
 965b71b2edfd728a6a32472cda3e7713 *src/calc_furcation.h
-8ea79b7de0fcb35f571962e17f7567fb *src/calc_pairwise_haplen.c
-00d18c8e73beb8a0c8351110060f1219 *src/calc_pairwise_haplen.h
+a05f2b0184ce0b035a956723f6d92eda *src/calc_pairwise_haplen.c
+3839049affccee8d202be5eb505d366d *src/calc_pairwise_haplen.h
+bbde67f562edd6b5cc23a49ca23ad99a *src/calc_sfs_tests.c
+b779fcb22524d83657d325d4245cbc99 *src/calc_sfs_tests.h
 4c1d8febd6cd04df5b4d22a3e2bd2c09 *src/definitions.h
 d42625e6350dcad51095cf22bf571db8 *src/haplotypes.c
 976fa1c7e90f686dd57ee6229b12c43a *src/haplotypes.h
@@ -110,9 +120,11 @@ d515074159b54f4e8fa71d847f0cc4e3 *src/haplotypes_with_nodes.c
 b8718089aed1c9aadf83d877f9762a5c *src/haplotypes_with_nodes.h
 29441637b9f2e8c074323b102c802683 *src/homozygosity.c
 8a0372f7038e294975eba1db483598ca *src/homozygosity.h
-b6ca1e604a504ee2fdb7aff7621ce855 *src/init.c
+625ba8904f1e83f49b398277e7a524d3 *src/init.c
 77f8dc940762ed75f438205732206fc7 *src/integrate.c
 40f968c6eb88192b40c247c6b9cd6492 *src/integrate.h
+72a80b3450d690a6ac58609f94dd7fcb *src/sfs_moments.c
+a3b3aeea2920660c6e293769c631b068 *src/sfs_moments.h
 7d20b8af53a3a33835b45ed2dde1f2ff *tests/testthat.R
 d10abdbe610dee90be8e7c6a1baf28da *tests/testthat/furcation_F1205400.newick
 26f4662e29cc03d705c9c9e5d81046d6 *tests/testthat/serialized_furcation_F1205400.txt
@@ -121,14 +133,15 @@ d10abdbe610dee90be8e7c6a1baf28da *tests/testthat/furcation_F1205400.newick
 7f87b223f6153b8926956609ba293241 *tests/testthat/setup.R
 a177583dabfe62a659b2d0ff4e5829d8 *tests/testthat/teardown.R
 0f2d4d7ffafcef03cde572357aa3508e *tests/testthat/test_calc_candidate_regions.R
-b333feb96e38279b41a60f9fcb93dd65 *tests/testthat/test_data2haplohh.R
+f8a26c6ede3ff1c7bf965b3d3c9797ea *tests/testthat/test_data2haplohh.R
 a57d331f176ddaa7e7a19fb056cd2626 *tests/testthat/test_error_messages.R
 3c553b425c68132fe5a74a06fc85d3e4 *tests/testthat/test_examples.R
-6adc3c44917659c38b0adddbbf254f18 *tests/testthat/test_furcation.R
+c5d51b0340ebb2dc628e911bcc259f82 *tests/testthat/test_furcation.R
 83461c197932114fbb6185821cdae353 *tests/testthat/test_ihh2ihs.R
-09bd1fc643230fc24c90aac2c2d2f035 *tests/testthat/test_scan_full.R
+c94ab72e812c9daf632b2acb919aa436 *tests/testthat/test_scan_full.R
 06e74a8f326b2099d3ef7b77c1664a89 *tests/testthat/test_scan_hh.R
-347ed7fd5246ab0a51b07eb65c551f51 *vignettes/examples.Rmd
+2641e6bbf68bdd6c97280b3a86dfedcc *tests/testthat/test_sfs_tests.R
+4d69844ff06315aff3356db7f85edd4c *vignettes/examples.Rmd
 80ac2e78110aa3e54fb5ce824bd5574f *vignettes/genetics.csl
-0cb9f06cbea7141d8522641178da4b54 *vignettes/rehh.Rmd
-0ae5b0965175c9ae6cbc11dd9bf5adc5 *vignettes/vignette.bib
+602994925b401f0fe98262d30ff9d6e8 *vignettes/rehh.Rmd
+dc13674ff5df93035a03384f762a946f *vignettes/vignette.bib

NAMESPACE

@@ -14,10 +14,12 @@ export(calc_furcation)
 export(calc_haplen)
 export(calc_pairwise_haplen)
 export(calc_region_stats)
+export(calc_sfs_tests)
 export(data2haplohh)
 export(distribplot)
 export(extract_regions)
 export(freqbinplot)
+export(haplohh2sweepfinder)
 export(ies2xpehh)
 export(ihh2ihs)
 export(ines2rsb)

NEWS.md

@@ -1,6 +1,17 @@
+### rehh 3.2.0 (October 30, 2020)
+
+* corrections and extensions of the vignettes
+* added inset between chromosomes in function manhattanplot()
+* added option to highlight specific markers in plot.haplohh()
+* function subset() can filter markers on maximum number of alleles
+* option to set maximal haplotype extension (in base pairs) in function scan_hh_full()
+* added function haplohh2sweepfinder() that extracts allele frequencies which
+can serve as input for the programs SweepFinder or SweeD
+* added function calc_sfs_tests() to calculate Tajima's D and Fay & Wu's H, allowing for data with missing values
+
 ### rehh 3.1.2 (July 17, 2020)
 
-* added option to parse vcf files using package 'data.table' in order to avoid reliance on package 'vcfR' which is currently removed from CRAN (but still available on github: https://github.com/knausb/vcfR)
+* added option to parse vcf files using package 'data.table' in order to avoid reliance on package 'vcfR'
 
 ### rehh 3.1.1 (June 19, 2020)
 

R/as.newick.R

@@ -40,26 +40,24 @@ as.newick <-
     }
     if (!is.null(hap.names)) {
       if (length(hap.names) != furcation@nhap) {
-        stop(
-          "Number of specified haplotype names must match the number of haplotypes.",
-          call. = FALSE
-        )
+        stop("Number of specified haplotype names must match the number of haplotypes.",
+             call. = FALSE)
       }
     } else{
       hap.names <- seq_len(furcation@nhap)
     }
-
+    
     ##calculations
     if (side == "left") {
       ftree <- furcation[[allele]]@left
     } else{
       ftree <- furcation[[allele]]@right
     }
-
+    
     ## usage of temporary file is a work-around for
     ## C string streams are missing under Windows
     tmp_file_name <- tempfile()
-
+    
     #calculation and output done by C
     if (.Call(
       "CALL_ASNEWICK",
@@ -76,7 +74,7 @@ as.newick <-
     } else{
       stop("Could not write to a temporary file.", call. = FALSE)
     }
-
+    
     unlink(tmp_file_name)
     return(newick)
   }

R/calc_candidate_regions.R

@@ -109,7 +109,7 @@ calc_candidate_regions <- function(scan,
 
   # perform calculation
   ## remove NA
-  scan <- scan[!is.na(scan[[score_column_nr]]), ]
+  scan <- scan[!is.na(scan[[score_column_nr]]),]
 
   if (ignore_sign) {
     score <- abs(scan[[score_column_nr]])
@@ -148,9 +148,12 @@ calc_candidate_regions <- function(scan,
       }
 
       for (offset in offsets) {
-        breaks <- seq(offset,
-                      max(chr_pos) + window_size - 1,
-                      window_size)
+        breaks <- seq(
+          floor(min(chr_pos) / window_size) * window_size + offset,
+          max(chr_pos) + window_size - 1,
+          window_size
+        )
+
         windows <- cut(chr_pos,
                        breaks = breaks,
                        right = right,
@@ -213,7 +216,7 @@ calc_candidate_regions <- function(scan,
 
       if (nrow(chr_cand_reg) > 1) {
         # sort different offset windows by position
-        chr_cand_reg <- chr_cand_reg[order(chr_cand_reg[[2]]), ]
+        chr_cand_reg <- chr_cand_reg[order(chr_cand_reg[[2]]),]
 
         # join neighboring windows
         if (join_neighbors) {
@@ -246,7 +249,7 @@ calc_candidate_regions <- function(scan,
                                         threshold])
               #e liminate all right neighbors
               chr_cand_reg <- chr_cand_reg[-((i + 1):(i +
-                                                        j)), ]
+                                                        j)),]
             }
             i <- i + 1
           }

R/calc_ehh.R

@@ -44,8 +44,9 @@
 #'}
 #'@references Gautier, M. and Naves, M. (2011). Footprints of selection in the ancestral admixture of a New World Creole cattle breed. \emph{Molecular Ecology}, \strong{20}, 3128-3143.
 #'
-#'Klassmann, A. et al. (2020). Detecting selection using Extended Haplotype
-#'Homozygosity (EHH)-based statistics on unphased or unpolarized data. (submitted).
+#'Klassmann, A. and Gautier, M. (2020). Detecting selection using Extended Haplotype
+#'Homozygosity-based statistics on unphased or unpolarized data (preprint). 
+#'https://doi.org/10.22541/au.160405572.29972398/v1
 #'
 #'Sabeti, P.C. et al. (2002). Detecting recent positive selection in the human genome from haplotype structure. \emph{Nature}, \strong{419}, 832-837.
 #'

R/calc_ehhs.R

@@ -42,8 +42,9 @@
 #'}
 #'@references Gautier, M. and Naves, M. (2011). Footprints of selection in the ancestral admixture of a New World Creole cattle breed. \emph{Molecular Ecology}, \strong{20}, 3128-3143.
 #'
-#'Klassmann, A. et al. (2020). Detecting selection using Extended Haplotype
-#'Homozygosity (EHH)-based statistics on unphased or unpolarized data. (submitted).
+#'Klassmann, A. and Gautier, M. (2020). Detecting selection using Extended Haplotype
+#'Homozygosity-based statistics on unphased or unpolarized data (preprint). 
+#'https://doi.org/10.22541/au.160405572.29972398/v1
 #'
 #'Sabeti, P.C. et al. (2002). Detecting recent positive selection in the human genome from haplotype structure. \emph{Nature}, \strong{419}, 832-837.
 #'