# update last-1542

# switched rbh2kaks to fully use MSA2dist
kullrich · Mar 28, 2024 · 666dd78 · 666dd78
1 parent 36c0454
commit 666dd78
Show file tree

Hide file tree

Showing 91 changed files with 555 additions and 940 deletions.
diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
@@ -4,7 +4,7 @@ before_script:
  - apt-get update
  - apt-get -y install libcurl4-openssl-dev libssl-dev libxml2-dev libglu1-mesa-dev libssh2-1-dev libfontconfig1-dev libharfbuzz-dev libfribidi-dev libgit2-dev libfreetype6-dev libpng-dev libtiff5-dev libjpeg-dev pandoc r-cran-devtools r-cran-testthat r-cran-curl r-bioc-biostrings
  - R -e "dir(); getwd(); sessionInfo(); install.packages('pkgdown'); devtools::install()"
- - R -e "setwd(paste0(find.package('CRBHits'), '/extdata/')); system(paste0('unzip last-1521.zip')); setwd(paste0(find.package('CRBHits'), '/extdata/last-1521/')); system('make')"
+ - R -e "setwd(paste0(find.package('CRBHits'), '/extdata/')); system(paste0('unzip last-1542.zip')); setwd(paste0(find.package('CRBHits'), '/extdata/last-1542/')); system('make')"
  - R -e "setwd(paste0(find.package('CRBHits'), '/extdata/')); system(paste0('tar -xvf KaKs_Calculator2.0_src.tar.gz')); setwd(paste0(find.package('CRBHits'), '/extdata/KaKs_Calculator2.0_src/src/')); system('make clean'); system('make')"
  - R -e "setwd(paste0(find.package('CRBHits'), '/extdata/')); system(paste0('unzip dagchainer.zip')); setwd(paste0(find.package('CRBHits'), '/extdata/dagchainer/')); system('make')"
 

diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: CRBHits
 Title: Conditional reciprocal best hits (CRBHits) in R
-Version: 0.0.5
+Version: 0.0.6
 Authors@R: 
  person(given = "Kristian K",
  family = "Ullrich",
@@ -48,7 +48,6 @@ biocViews: Software, Alignment, Genetics
 NeedsCompilation: yes
 SystemRequirements:
  LAST (https://anaconda.org/bioconda/last),
- KaKs_Calculator2.0 (https://anaconda.org/bioconda/kakscalculator2),
  DAGchainer (https://anaconda.org/bioconda/dagchainer),
  GNU make,
  libcurl (deb: libcurl4-openssl-dev or CentOS: libcurl-devel),
@@ -60,4 +59,4 @@ URL:
  https://gitlab.gwdg.de/mpievolbio-it/crbhits,
  https://mpievolbio-it.pages.gwdg.de/crbhits/
 BugReports: https://gitlab.gwdg.de/mpievolbio-it/crbhits/issues
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.1
diff --git a/NAMESPACE b/NAMESPACE
@@ -5,7 +5,6 @@ export(aa2rbh)
 export(aadir2orthofinder)
 export(aafile2rbh)
 export(cds2genepos)
-export(cds2kaks)
 export(cds2rbh)
 export(cdsdir2orthofinder)
 export(cdsfile2aafile)
@@ -20,8 +19,6 @@ export(filter_tcov)
 export(gff2longest)
 export(gtf2longest)
 export(isoform2longest)
-export(makePostalignedSeqs)
-export(make_KaKs_Calculator2)
 export(make_dagchainer)
 export(make_last)
 export(make_vignette)
@@ -35,17 +32,13 @@ importFrom(Biostrings,AAString)
 importFrom(Biostrings,AAStringSet)
 importFrom(Biostrings,DNAString)
 importFrom(Biostrings,DNAStringSet)
-importFrom(Biostrings,pairwiseAlignment)
 importFrom(Biostrings,readAAStringSet)
 importFrom(Biostrings,readDNAStringSet)
 importFrom(Biostrings,subseq)
 importFrom(Biostrings,width)
 importFrom(Biostrings,writeXStringSet)
 importFrom(MSA2dist,cds2aa)
 importFrom(MSA2dist,cds2codonaln)
-importFrom(MSA2dist,codonmat2pnps)
-importFrom(MSA2dist,dnastring2aln)
-importFrom(MSA2dist,dnastring2codonmat)
 importFrom(MSA2dist,dnastring2kaks)
 importFrom(curl,curl_download)
 importFrom(doParallel,registerDoParallel)
@@ -89,7 +82,6 @@ importFrom(parallel,makeForkCluster)
 importFrom(parallel,stopCluster)
 importFrom(readr,read_tsv)
 importFrom(rlang,.data)
-importFrom(seqinr,kaks)
 importFrom(stats,median)
 importFrom(stats,setNames)
 importFrom(stats,splinefun)

diff --git a/R/aa2rbh.R b/R/aa2rbh.R
@@ -16,7 +16,7 @@
 #' @param searchtool specify sequence search algorithm last, mmseqs2 or diamond
 #' [default: last]
 #' @param lastpath specify the PATH to the last binaries
-#' [default: /extdata/last-1521/bin/]
+#' [default: /extdata/last-1542/bin/]
 #' @param lastD last option D: query letters per random alignment
 #' [default: 1e6]
 #' @param mmseqs2path specify the PATH to the mmseqs2 binaries
@@ -80,7 +80,7 @@
 #' @references Rost B. (1999). Twilight zone of protein sequence alignments.
 #' \emph{Protein Engineering}, \bold{12(2)}, 85-94.
 #' @examples
-#' ## compile last-1521 within CRBHits
+#' ## compile last-1542 within CRBHits
 #' CRBHits::make_last()
 #' ## load example sequence data
 #' data("ath", package="CRBHits")
@@ -111,7 +111,7 @@
 aa2rbh <- function(aa1, aa2,
  searchtool="last",
  lastpath=paste0(find.package("CRBHits"),
- "/extdata/last-1521/bin/"),
+ "/extdata/last-1542/bin/"),
  lastD=1e6,
  mmseqs2path=NULL,
  mmseqs2sensitivity=5.7,

diff --git a/R/aadir2orthofinder.R b/R/aadir2orthofinder.R
@@ -14,7 +14,7 @@
 #' @param searchtool specify sequence search algorithm last, mmseqs2 or diamond
 #' [default: last]
 #' @param lastpath specify the PATH to the last binaries
-#' [default: /extdata/last-1453/bin/]
+#' [default: /extdata/last-1542/bin/]
 #' @param lastD last option D: query letters per random alignment
 #' [default: 1e6]
 #' @param mmseqs2path specify the PATH to the mmseqs2 binaries
@@ -66,7 +66,7 @@
 #' @references Rost B. (1999). Twilight zone of protein sequence alignments.
 #' \emph{Protein Engineering}, \bold{12(2)}, 85-94.
 #' @examples
-#' ## compile last-1453 within CRBHits
+#' ## compile last-1542 within CRBHits
 #' CRBHits::make_last()
 #' @export aadir2orthofinder
 #' @author Kristian K Ullrich
@@ -75,7 +75,7 @@ aadir2orthofinder <- function(dir,
  file_ending="*",
  searchtool="last",
  lastpath=paste0(find.package("CRBHits"),
- "/extdata/last-1453/bin/"),
+ "/extdata/last-1542/bin/"),
  lastD=1e6,
  mmseqs2path=NULL,
  mmseqs2sensitivity=5.7,

diff --git a/R/aafile2rbh.R b/R/aafile2rbh.R
@@ -17,7 +17,7 @@
 #' @param searchtool specify sequence search algorithm last, mmseqs2 or diamond
 #' [default: last]
 #' @param lastpath specify the PATH to the last binaries
-#' [default: /extdata/last-1521/bin/]
+#' [default: /extdata/last-1542/bin/]
 #' @param lastD last option D: query letters per random alignment
 #' [default: 1e6]
 #' @param mmseqs2path specify the PATH to the mmseqs2 binaries
@@ -81,7 +81,7 @@
 #' @references Rost B. (1999). Twilight zone of protein sequence alignments.
 #' \emph{Protein Engineering}, \bold{12(2)}, 85-94.
 #' @examples
-#' ## compile last-1521 within CRBHits
+#' ## compile last-1542 within CRBHits
 #' CRBHits::make_last()
 #' ## load example sequence data
 #' athfile <- system.file("fasta", "ath.aa.fasta.gz", package="CRBHits")
@@ -110,7 +110,7 @@
 aafile2rbh <- function(aafile1, aafile2,
  searchtool="last",
  lastpath=paste0(find.package("CRBHits"),
- "/extdata/last-1521/bin/"),
+ "/extdata/last-1542/bin/"),
  lastD=1e6,
  mmseqs2path=NULL,
  mmseqs2sensitivity=5.7,

diff --git a/R/cds2kaks.R b/R/cds2kaks.R
diff --git a/R/cds2rbh.R b/R/cds2rbh.R
@@ -15,7 +15,7 @@
 #' @param searchtool specify sequence search algorithm last, mmseqs2 or diamond
 #' [default: last]
 #' @param lastpath specify the PATH to the last binaries
-#' [default: /extdata/last-1521/bin/]
+#' [default: /extdata/last-1542/bin/]
 #' @param lastD last option D: query letters per random alignment
 #' [default: 1e6]
 #' @param mmseqs2path specify the PATH to the mmseqs2 binaries
@@ -95,7 +95,7 @@
 #' @references Rost B. (1999). Twilight zone of protein sequence alignments.
 #' \emph{Protein Engineering}, \bold{12(2)}, 85-94.
 #' @examples
-#' ## compile last-1521 within CRBHits
+#' ## compile last-1542 within CRBHits
 #' CRBHits::make_last()
 #' ## load example sequence data
 #' data("ath", package="CRBHits")
@@ -145,7 +145,7 @@
 cds2rbh <- function(cds1, cds2,
  searchtool="last",
  lastpath=paste0(find.package("CRBHits"),
- "/extdata/last-1521/bin/"),
+ "/extdata/last-1542/bin/"),
  lastD=1e6,
  mmseqs2path=NULL,
  mmseqs2sensitivity=5.7,

diff --git a/R/cdsdir2orthofinder.R b/R/cdsdir2orthofinder.R
@@ -14,7 +14,7 @@
 #' @param searchtool specify sequence search algorithm last, mmseqs2 or diamond
 #' [default: last]
 #' @param lastpath specify the PATH to the last binaries
-#' [default: /extdata/last-1521/bin/]
+#' [default: /extdata/last-1542/bin/]
 #' @param lastD last option D: query letters per random alignment
 #' [default: 1e6]
 #' @param mmseqs2path specify the PATH to the mmseqs2 binaries
@@ -63,7 +63,7 @@
 #' @references Rost B. (1999). Twilight zone of protein sequence alignments.
 #' \emph{Protein Engineering}, \bold{12(2)}, 85-94.
 #' @examples
-#' ## compile last-1521 within CRBHits
+#' ## compile last-1542 within CRBHits
 #' CRBHits::make_last()
 #' @export cdsdir2orthofinder
 #' @author Kristian K Ullrich
@@ -72,7 +72,7 @@ cdsdir2orthofinder <- function(dir,
  file_ending="*",
  searchtool="last",
  lastpath=paste0(find.package("CRBHits"),
- "/extdata/last-1521/bin/"),
+ "/extdata/last-1542/bin/"),
  lastD=1e6,
  mmseqs2path=NULL,
  mmseqs2sensitivity=5.7,

diff --git a/R/cdsfile2rbh.R b/R/cdsfile2rbh.R
@@ -16,7 +16,7 @@
 #' @param searchtool specify sequence search algorithm last, mmseqs2 or diamond
 #' [default: last]
 #' @param lastpath specify the PATH to the last binaries
-#' [default: /extdata/last-1521/bin/]
+#' [default: /extdata/last-1542/bin/]
 #' @param lastD last option D: query letters per random alignment
 #' [default: 1e6]
 #' @param mmseqs2path specify the PATH to the mmseqs2 binaries
@@ -99,7 +99,7 @@
 #' @references Rost B. (1999). Twilight zone of protein sequence alignments.
 #' \emph{Protein Engineering}, \bold{12(2)}, 85-94.
 #' @examples
-#' ## compile last-1521 within CRBHits
+#' ## compile last-1542 within CRBHits
 #' CRBHits::make_last()
 #' ## load example sequence data
 #' athfile <- system.file("fasta", "ath.cds.fasta.gz", package="CRBHits")
@@ -128,7 +128,7 @@
 cdsfile2rbh <- function(cdsfile1, cdsfile2,
  searchtool="last",
  lastpath=paste0(find.package("CRBHits"),
- "/extdata/last-1521/bin/"),
+ "/extdata/last-1542/bin/"),
  lastD=1e6,
  mmseqs2path=NULL,
  mmseqs2sensitivity=5.7,

diff --git a/R/makePostalignedSeqs.R b/R/makePostalignedSeqs.R