minor bug fixed

irycisBioinfo · Jan 31, 2021 · 018f594 · 018f594
1 parent 0a73f93
commit 018f594
Show file tree

Hide file tree

Showing 55 changed files with 97 additions and 118 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -2,9 +2,11 @@ Package: pato
 Type: Package
 Title: Pangenome Analysis Toolkit
 Version: 1.0.2
-Author: Alba Talavera Rodríguez
-	Miguel Diez Fernandez de Bobadilla
+Author: Miguel Diez Fernandez de Bobadilla
+	Alba Talavera Rodríguez
 	Lucia Chacon Vargas
+	Fernando Baquero
+	Teresa M. Coque
 	Val F. Lanza <[email protected]>
 Maintainer: Val F. Lanza <[email protected]>
 Description: PATO is a R package designed to analyze pangenomes (set of genomes)

diff --git a/NAMESPACE b/NAMESPACE
@@ -40,9 +40,7 @@ export(snps_map)
 export(snps_pairwaise)
 export(twins)
 export(umap_plot)
-import(Biostrings)
 import(ape)
-import(data.table)
 import(dbscan)
 import(doParallel)
 import(dplyr)
@@ -64,4 +62,5 @@ import(threejs)
 import(tibble)
 import(tidyr)
 import(uwot)
+importFrom(data.table,fread)
 importFrom(randomcoloR,distinctColorPalette)
diff --git a/R/accnet.R b/R/accnet.R
@@ -30,9 +30,8 @@
 #'
 #' @import dplyr
 #' @import tidyr
-#' @import tibble
 #' @import dtplyr
-#' @import data.table
+#'
 #'
 accnet <- function(mmseqs,threshold = 0.8, singles = TRUE)
 {

diff --git a/R/accnet_enrichment_analysis.R b/R/accnet_enrichment_analysis.R
@@ -37,8 +37,6 @@
 #' @import dplyr
 #' @import tidyr
 #' @import tibble
-#' @import dtplyr
-#' @import data.table
 #'
 accnet_enrichment_analysis <- function(data,cluster, padj_method = "BY")
 {

diff --git a/R/accnet_with_padj.R b/R/accnet_with_padj.R
@@ -14,8 +14,6 @@
 #' @import dplyr
 #' @import tidyr
 #' @import tibble
-#' @import dtplyr
-#' @import data.table
 #'
 accnet_with_padj <- function(data)
 {

diff --git a/R/annotate.R b/R/annotate.R
@@ -50,8 +50,6 @@
 #' @import dplyr
 #' @import tidyr
 #' @import tibble
-#' @import dtplyr
-#' @import data.table
 #'
 annotate <- function(data, type = "nucl", database =c("AbR","VF_A","VF_B"), query = "all")
 {

diff --git a/R/as.data.frame.nr_list.R b/R/as.data.frame.nr_list.R
@@ -5,7 +5,7 @@
 #' @return A `data.frame`
 #' @export
 #'
-#' @examples
+#' 
 as.data.frame.nr_list <- function(data)
 {
   return(data.frame(

diff --git a/R/classifier.R b/R/classifier.R
@@ -13,12 +13,12 @@
 #' @return Classifier returns a data.frame with the best hit for each input genome.
 #' @export
 #'
-#' @examples
+#'
 #' @import dplyr
 #' @import tidyr
 #' @import tibble
 #' @import dtplyr
-#' @import data.table
+#' @importFrom  data.table fread
 
 classifier <- function(file_list, n_cores, type ="nucl", max_dist = 0.06)
 {

diff --git a/R/cluster_accnet.R b/R/cluster_accnet.R
@@ -13,9 +13,11 @@
 #' @import tibble
 #' @import uwot
 #' @import mclust
-#' @import data.table
+#' @importFrom data.table fread
 #' @import dbscan
 #' @import parallelDist
+#'
+#'
 cluster_accnet <- function(data, method, n_cluster, d_reduction, ...)
 {
   Dist <-

diff --git a/R/cluster_files_from_distance.R b/R/cluster_files_from_distance.R
@@ -13,7 +13,7 @@
 #' @import dtplyr
 #' @import tidyr
 #' @import tibble
-#' @import data.table
+#' @importFrom data.table fread
 #' @import igraph
 #'
 cluster_files_from_distance <- function(files, file_type, distance, n_cores, folder)

diff --git a/R/cluster_knnn.R b/R/cluster_knnn.R
@@ -9,7 +9,7 @@
 #' @import dplyr
 #' @import tidyr
 #' @import tibble
-#' @import data.table
+#' @importFrom data.table fread
 cluster_knnn <- function(data,method)
 {
 

diff --git a/R/cluster_mash.R b/R/cluster_mash.R
@@ -13,7 +13,7 @@
 #' @import tibble
 #' @import uwot
 #' @import mclust
-#' @import data.table
+#' @importFrom data.table fread
 #' @import dbscan
 #'
 cluster_mash <- function(data, method, n_cluster,d_reduction,...)

diff --git a/R/coincidents.R b/R/coincidents.R
@@ -12,12 +12,12 @@
 #' @return A data.frame with the protein/gene ID ("Target") and the membership (cluster number)
 #' @export
 #'
-#' @examples
+#' 
 #' @import dplyr
 #' @import tidyr
 #' @import tibble
 #' @import dtplyr
-#' @import data.table
+#' @importFrom data.table fread
 #' @import uwot
 #' @import dbscan
 #'

diff --git a/R/core_genome.R b/R/core_genome.R
@@ -20,12 +20,12 @@
 #' @return A core_genome object (a data.frame with two columns: fasta header and sequence)
 #' @export
 #'
-#' @examples
+#' 
 #' @import dplyr
 #' @import tidyr
 #' @import tibble
 #' @import dtplyr
-#' @import data.table
+#' @importFrom data.table fread
 #' @import foreach
 #' @import doParallel
 #' @import parallel

diff --git a/R/core_plots.R b/R/core_plots.R
@@ -26,7 +26,7 @@
 #' @import tibble
 #' @import dtplyr
 #' @import ggplot2
-#' @import data.table
+#' @importFrom data.table fread
 #' @import doParallel
 #' @import foreach
 #'

diff --git a/R/core_snp_genome.R b/R/core_snp_genome.R
@@ -28,7 +28,7 @@
 #' @return core_snp_genome object
 #' @export
 #'
-#' @examples
+#' 
 core_snp_genome <- function(file_list, n_cores, ref, type)
 {
   if(grepl('linux',Sys.getenv("R_PLATFORM"))) ## Linux

diff --git a/R/core_snps_matrix.R b/R/core_snps_matrix.R
@@ -9,7 +9,7 @@
 #' @return A square matrix
 #' @export
 #'
-#' @examples
+#' 
 #' @import stringdist
 #' @import magrittr
 #'

diff --git a/R/dn_ds.R b/R/dn_ds.R
@@ -17,7 +17,7 @@
 #' @return
 #' @export
 #'
-#' @examples
+#' 
 #'
 #'
 dn_ds <- function(mmseq,accnet,min_size =5 ,n_cores,mode = "fast")

diff --git a/R/export_accnet_aln.R b/R/export_accnet_aln.R
@@ -12,7 +12,7 @@
 #'
 #' @export
 #'
-#' @examples
+#' 
 #'
 export_accnet_aln <- function(accnet,file, min_freq =3)
 {

diff --git a/R/export_core_to_fasta.R b/R/export_core_to_fasta.R
@@ -5,7 +5,7 @@
 #'
 #' @export
 #'
-#' @examples
+#' 
 export_core_to_fasta <- function(core_data,file)
 {
 

diff --git a/R/export_to_gephi.R b/R/export_to_gephi.R
@@ -22,7 +22,7 @@
 #' @import tibble
 #' @import dtplyr
 #' @import igraph
-#' @import data.table
+#' @importFrom data.table fread
 export_to_gephi <- function(data, file, cluster)
 {
   if(is(data,"accnet"))

diff --git a/R/extract_non_redundant.R b/R/extract_non_redundant.R
@@ -17,7 +17,7 @@
 #' @import tidyr
 #' @import tibble
 #' @import dtplyr
-#' @import data.table
+#' @importFrom data.table fread
 #'
 extract_non_redundant <- function(data, nr_list)
 {

diff --git a/R/heatmap_of_annotation.R b/R/heatmap_of_annotation.R
@@ -11,7 +11,7 @@
 #'
 #' @export
 #'
-#' @examples
+#' 
 #'
 #' @import dplyr
 #' @import tidyr

diff --git a/R/knnn.R b/R/knnn.R
@@ -17,12 +17,12 @@
 #' @return Returns an \emph{igraph} object.
 #' @export
 #'
-#' @examples
+#' 
 #' @import dplyr
 #' @import tidyr
 #' @import tibble
 #' @import dtplyr
-#' @import data.table
+#' @importFrom data.table fread
 #' @import igraph
 #' @import parallelDist
 

diff --git a/R/load_gff_list.R b/R/load_gff_list.R
@@ -13,13 +13,12 @@
 #' The function returns a \code{gff_list} object the can be used as input for other functions (mmseqs, mash)
 #' @export
 #'
-#' @examples
+#'
 #' @import dplyr
 #' @import tidyr
 #' @import tibble
 #' @import dtplyr
-#' @import data.table
-#' @import Biostrings
+#' @importFrom data.table fread
 #' @import openssl
 #' @import microseq
 #' @import foreach
@@ -36,6 +35,9 @@ load_gff_list <- function(input_files, n_cores)
   cl <- makeCluster(n_cores)
   registerDoParallel(cl)
 
+  on.exit(file.remove(list.files(pattern = "gffTMP")))
+  on.exit(stopCluster(cl), add = T)
+
   input_files <- as_tibble(input_files) %>% rename(File = 1)
   folderName <- paste(getwd(),"/",md5(paste(input_files$File, sep = "",collapse = "")),"_gffList",sep = "",collapse = "")
 
@@ -99,13 +101,12 @@ load_gff_list <- function(input_files, n_cores)
     ffn_faa <- inner_join(ffn_faa,gff) %>% select(Annot,Sequence) %>% rename(Header = Annot)
 
     writeFasta(ffn_faa, paste(folderName,"/ffn/",pathName,".ffn",sep = "",collapse = "")) ## Write the ffn file
-    ffn_faa <- ffn_faa %>% mutate(Sequence = translate(Sequence))
+    ffn_faa <- ffn_faa %>% mutate(Sequence = microseq::translate(Sequence))
     writeFasta(ffn_faa , paste(folderName,"/faa/",pathName,".faa",sep = "",collapse = "")) ## Write the faa file
   }
 
 
-  on.exit(file.remove(list.files(pattern = "gffTMP")))
-  on.exit(stopCluster(cl), add = T)
+
 
   results <-  list(path = folderName, files = input_files)
   class(results) <- append(class(results),"gff_list")

diff --git a/R/mash.R b/R/mash.R
@@ -26,12 +26,12 @@
 #'
 #' @references Mash: fast genome and metagenome distance estimation using MinHash. Ondov BD, Treangen TJ, Melsted P, Mallonee AB, Bergman NH, Koren S, Phillippy AM. Genome Biol. 2016 Jun 20;17(1):132. doi: 10.1186/s13059-016-0997-x.
 #' @references Mash Screen: High-throughput sequence containment estimation for genome discovery. Ondov BD, Starrett GJ, Sappington A, Kostic A, Koren S, Buck CB, Phillippy AM. BioRxiv. 2019 Mar. doi: 10.1101/557314
-#' @examples
+#' 
 #' @import dplyr
 #' @import tidyr
 #' @import tibble
 #' @import dtplyr
-#' @import data.table
+#' @importFrom data.table fread
 
 
 

diff --git a/R/mmseqs.R b/R/mmseqs.R
@@ -45,12 +45,12 @@
 #' @references Steinegger M and Soeding J. MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nature Biotechnology, doi: 10.1038/nbt.3988 (2017).
 #' @references Steinegger M and Soeding J. Clustering huge protein sequence sets in linear time. Nature Communications, doi: 10.1038/s41467-018-04964-5 (2018).
 #' @references Mirdita M, Steinegger M and Soeding J. MMseqs2 desktop and local web server app for fast, interactive sequence searches. Bioinformatics, doi: 10.1093/bioinformatics/bty1057 (2019)
-#' @examples
+#' 
 #' @import dplyr
 #' @import tidyr
 #' @import tibble
 #' @import dtplyr
-#' @import data.table
+#' @importFrom data.table fread
 #' @import foreach
 #' @import doParallel
 #' @import openssl

diff --git a/R/network_of_annotation.R b/R/network_of_annotation.R
@@ -10,15 +10,15 @@
 #' @return \emph{igraph} object
 #' @export
 #'
-#' @examples
+#' 
 #' @seealso \code{\link{annotate}}
 #'
 #' @import dplyr
 #' @import tidyr
 #' @import tibble
 #' @import dtplyr
 #' @import igraph
-#' @import data.table
+#' @importFrom data.table fread
 #'
 network_of_annotation <- function(data, min_identity = 0.95, max_evalue = 1e-25)
 {

diff --git a/R/non_redundant.R b/R/non_redundant.R
@@ -21,13 +21,13 @@
 #'
 #' @seealso \code{\link{extract_non_redundant}}
 #'
-#' @examples
+#' 
 #' @import dplyr
 #' @import tidyr
 #' @import tibble
 #' @import dtplyr
 #' @import igraph
-#' @import data.table
+#' @importFrom data.table fread
 #' @import parallelDist
 #'
 non_redundant <- function(data, number, fraction, distance, tolerance = 0.05, max_iter = 10000, fast =TRUE, snps)

diff --git a/R/non_redundant_hier.R b/R/non_redundant_hier.R
@@ -24,13 +24,13 @@
 #'
 #' @seealso \code{\link{extract_non_redundant}}
 #'
-#' @examples
+#' 
 #' @import dplyr
 #' @import tidyr
 #' @import tibble
 #' @import dtplyr
 #' @import igraph
-#' @import data.table
+#' @importFrom data.table fread
 #' @import parallelDist
 #'
 non_redundant_hier <- function(data, number, fraction, distance, tolerance = 0.05, partitions = 10,max_iter = 10000, fast =FALSE, snps)

diff --git a/R/non_redundant_pangenomes.R b/R/non_redundant_pangenomes.R
@@ -17,13 +17,13 @@
 #' @import tidyr
 #' @import tibble
 #' @import dtplyr
-#' @import data.table
+#' @importFrom data.table fread
 #' @import igraph
 #
 #' @return
 #' @export
 #'
-#' @examples
+#' 
 non_redundant_pangenomes <- function(file_list, distance, type = "prot", n_cores,sketch = 1000, kmer = 21)
 {
-Original file line number
+Diff line change
@@ Expand Up / @@ -12,7 +12,7 @@ @@
     #'
     #' @export
     #'
-    #' @examples
+    #'
     #'
     export_accnet_aln <- function(accnet,file, min_freq =3)
     {
@@ Expand Down @@