Seq.info defaults and data.rd fixes

Author: ConnorChato

Diff for: .Rhistory

@@ -1,3 +1,45 @@
+h <- 40
+#simulate
+lhs <- maximinLHS(h,3)
+#minimum and maximum values for each parameter
+threshold.min <- 0.02
+threshold.max <- 0.07
+expansion.min <- 2
+expansion.max <- 10
+inflation.min <- 2
+inflation.max <- 10
+# generate a “parameter set” by rescaling our simulated latin hypercube sample
+params.set <- cbind(
+threshold = lhs[ ,1] * (threshold.max-threshold.min) + threshold.min,
+expansion = lhs[ ,2] * (expansion.max-expansion.min) + expansion.min,
+inflation = lhs[ ,3]*(inflation.max-inflation.min) + inflation.min
+)
+min(params.set[,1])
+#choose number of points
+h <- 40
+#simulate
+lhs <- maximinLHS(h,3)
+#minimum and maximum values for each parameter
+threshold.min <- 0.02
+threshold.max <- 0.07
+expansion.min <- 2
+expansion.max <- 10
+inflation.min <- 2
+inflation.max <- 10
+# generate a “parameter set” by rescaling our simulated latin hypercube sample
+params.set <- cbind(
+threshold = lhs[ ,1] * (threshold.max-threshold.min) + threshold.min,
+expansion = lhs[ ,2] * (expansion.max-expansion.min) + expansion.min,
+inflation = lhs[ ,3]*(inflation.max-inflation.min) + inflation.min
+)
+min(params.set[,1])
+#choose number of points
+h <- 40
+#simulate
+lhs <- maximinLHS(h,3)
+#minimum and maximum values for each parameter
+threshold.min <- 0.02
+threshold.max <- 0.07
 expansion.min <- 2
 expansion.max <- 10
 inflation.min <- 2
@@ -460,53 +502,11 @@ inflation = lhs[ ,3]*(inflation.max-inflation.min) + inflation.min
 )
 min(params.set[,1])
 setwd("MountainPlot/")
-ls
-devtools::load_all()
 devtools::load_all()
-ls
-devtools::run_examples()
-system("inst/pplacer -h")
-devtools::run_examples()
-testthat::test_local()
-seq.info.ex
-seq.info <- pull.headers(alignment.ex, var.names = c("ID", "CollectionDate", "Subtype"),
-var.transformations =list(as.character, as.Date, as.factor))
-seq.info
-seq.info
-alignment.ex
-str(alignment.ex)
+old.tree.ex
+old.tree.ex
 alignment.ex
-cluster.ex
-devtools::load_all()
-generate.all()
-devtools::load_all()
-cluster.ex
-devtools::load_all()
-cluster.ex
-generate.all()
-cluster.ex
-load("data/cluster.ex")
-load("data/cluster.ex.RData")
-cluster.ex
-cluster.ex <- component.cluster.set <- component.cluster(graph.ex, dist.thresh = 0.03)
-save(cluster.ex, file="data/cluster.ex.RData")
-devtools::load_all()
-cluster.ex
-cluster.ex
-cluster.ex <- component.cluster.set <- component.cluster(graph.ex, dist.thresh = 0.06)
-save(cluster.ex, file="data/cluster.ex.RData")
-devtools::load_all()
-cluster.ex
-cluster.ex
-cluster.ex <- component.cluster.set <- component.cluster(graph.ex, dist.thresh = 0.05)
-save(cluster.ex, file="data/cluster.ex.RData")
-devtools::load_all()
-cluster.ex
-cluster.ex
-cluster.ex <- component.cluster.set <- component.cluster(graph.ex, dist.thresh = 0.055)
-cluster.ex
-cluster.ex
-save(cluster.ex, file="data/cluster.ex.RData")
-cluster.ex$Subtype
-graph.ex\
-graph.ex
+full.tree.ex
+full.tree.ex$node.label
+full.tree.ex$tip.label
+seq.info.ex

Diff for: R/data.R

@@ -3,26 +3,22 @@
 #'A dataset containing 10 HIV1, subtype B polymerase sequences collected in Northern Alberta Canada.
 #'This a 10 sequence sample from popset# 1033910942 on NCBI's genbank Archive
 #'
-#'@format An ape DNA object: 10 DNA sequences in binary format stored in a list. All sequences of same length: 1017 
-#'
-#'@source \url{https://www.ncbi.nlm.nih.gov/popset?DbFrom=nuccore&Cmd=Link&LinkName=nuccore_popset&IdsFromResult=1033912042}
+#' @format An ape DNA object: 10 DNA sequences in binary format stored in a list. All sequences of same length: 1017 
+#' @source \url{ https://www.ncbi.nlm.nih.gov/popset?DbFrom=nuccore&Cmd=Link&LinkName=nuccore_popset&IdsFromResult=1033912042 }
 "alignment.ex"
 
-
 #'An example set of sequence meta.data corresponding to alignment.ex
 #'
-#'A dataset describing 10 different HIV1 pol sequences collected in Northern Alberta Cabada.
+#'A dataset describing 10 different HIV1 pol sequences collected in Northern Alberta Canada.
 #'
 #' @format A data.table object with 9 variables:
 #' \describe{
-#' \item{ID} {Accession IDs (characters) of sequences}
-#' \item{CollectionDate} {Collection date of sequences. Full dates given as yyyy-mm-dd}
-#' \item{Subtype} {Subtypes (factors) within a cluster}
+#' \item{ID}{Accession IDs (characters) of sequences}
+#' \item{CollectionDate}{Collection date of sequences. Full dates given as yyyy-mm-dd}
+#' \item{Subtype}{Subtypes (factors) within a cluster}
 #' \item{Header}{The original headers from the alignement. This matches meta data to sequences}
-#' \
 #' }
-"cluster.ex"
-
+"seq.info.ex"
 
 #'An example set of clusters, built using component.cluster
 #'
@@ -33,15 +29,14 @@
 #' @format A data.table object with 9 variables:
 #' \describe{
 #' \item{ClusterID}{ The unique identifier number for this cluster. A numberic}
-#' \item{ID} {A list of vectors, each containing the accession IDs (characters) of sequences within a cluster}
-#' \item{CollectionDate} {A list of vectors, each containing the collection date of sequences within a cluster}
-#' \item{Subtype} {A list of vectors, each containing the subtypes (factors) within a cluster}
+#' \item{ID}{A list of vectors, each containing the accession IDs (characters) of sequences within a cluster}
+#' \item{CollectionDate}{A list of vectors, each containing the collection date of sequences within a cluster}
+#' \item{Subtype}{A list of vectors, each containing the subtypes (factors) within a cluster}
 #' \item{Header}{A list of vectors, each containing the original headers from the alignement used to build this set of clusters}
-#' \item{Size} {The original size of this cluster before being updated with new cases. This simply the number of sequences within the cluster}
-#' \item{Growth} {The growth of the cluster after new cases are added}
-#' \item{DistThresh} {The pairwise distance threshold used to create this complete set of clusters. Corresponds to a setID as an input parameter}
-#' \item{SetID} {The unique identifier for this set of clusters. A numeric}
-#' \
+#' \item{Size}{The original size of this cluster before being updated with new cases. This simply the number of sequences within the cluster}
+#' \item{Growth}{The growth of the cluster after new cases are added}
+#' \item{DistThresh}{The pairwise distance threshold used to create this complete set of clusters. Corresponds to a setID as an input parameter}
+#' \item{SetID}{The unique identifier for this set of clusters. A numeric}
 #' }
 "cluster.ex"
 
@@ -50,7 +45,6 @@
 #'This implementation of a graph is a list, describing a set of sequences and the distances between them. 
 #'See create.graph for more information on how this graph was created using alignment.ex as input
 #'
-#'
 #' @format A list of 3 variables
 #' \describe{
 #' \item{seq.info}{ See seq.info.ex, a data.table containing sequence meta data}
@@ -59,7 +53,6 @@
 #' In order to ensure that clusters do not merge upon growth, a new sequence may only
 #' join up to one old cluster. By default, new sequences join the cluster of the 
 #' sequence they are most similar to. }
-#' \
 #' }
 "graph.ex"
 
@@ -90,13 +83,12 @@
 #' @format A , phylogenetic tree with 6 tips and 4 internal nodes. Node labels represent certainty
 #' See ape's implementation of phylogenetic tree objects for information about tags within this object.
 #' In addition, there are 4 new objects created by functions within tree.setup.R
+#' \describe{
 #' \item{seq.info}{ See seq.info.ex, a data.table containing sequence meta data}
-#' \item{node.info}{ Grouping of the meta.data present in seq.info assigned to various nodes in the tree, coupled with
-#' information important to clustering, such as mean divergence from root, or node certainty }
-#' \item{path.info} { Information regarding the path of edges from tips to the root of the tree. This is also necessary for some clustering algorithms, 
-#' specifically step.cluster}
-#' \item{growth.info}{ a data.table pairing new sequences, to a single node in the tree
-#' based on placements assigned by guppy and pplacer.  
+#' \item{node.info}{ Grouping of the meta.data present in seq.info assigned to various nodes in the tree, 
+#' coupled with information important to clustering, such as mean divergence from root, or node certainty }
+#' \item{path.info}{ Information regarding the path of edges from tips to the root of the tree. 
+#' This is also necessary for some clustering algorithms, specifically step.cluster}
+#' \item{growth.info}{ a data.table pairing new sequences, to a single node in the tree based on placements assigned by guppy and pplacer.}
 #' }
-"extended.tree.ex"
-
+"extended.tree.ex"

Diff for: R/graph.setup.R

@@ -14,11 +14,15 @@
 #' @return A graph, with sequences and edge info. New sequences are only linked by their minimum retrospective edge
 #' @export
 #' @example examples/create.graph_ex.R
-create.graph <- function(seq.info, edge.info, which.new=numeric(0), growth.resolution = minimum.retrospective.edge) {
+create.graph <- function(seq.info=data.table(), edge.info, which.new=numeric(0), growth.resolution = minimum.retrospective.edge) {
 
   # Check inputs
-  if (!all(colnames(edge.info) %in% colnames(edge.info))) {
-    stop("The pairwise distance matrix does not contain the recognized headers")
+  if (nrow(seq.info)==0){
+    warning("No sequence meta-data included, creating default seq.info input from headers in edge.info")
+    seq.info <- data.table("Header"=colnames(edge.info))
+  }
+  if (!all(colnames(edge.info) %in% seq.info$Header)) {
+    stop("The pairwise distance matrix does not contain all recognized headers from alignment")
   }
 
   # Assemble graph object

Diff for: R/tree.setup.R

@@ -12,7 +12,7 @@
 #' @return The tree annotated with node information and seq.info
 #' @export
 #' @example examples/extend.tree_ex.R
-extend.tree <- function(t, seq.info, mc.cores = 1, log.file=NA, full.align=character(0), locus = "LOCUS") {
+extend.tree <- function(t, seq.info=data.table(), mc.cores = 1, log.file=NA, full.align=character(0), locus = "LOCUS") {
 
   # Root the tree (if unrooted) and resolve multichotomies
   if (!ape::is.rooted(t)) {
@@ -21,6 +21,15 @@ extend.tree <- function(t, seq.info, mc.cores = 1, log.file=NA, full.align=chara
   t <- ape::multi2di(t)
 
   # Check Sequence names inputs
+  if (nrow(seq.info)==0){
+    if(length(full.align)!=0){
+      warning("No sequence meta-data included, creating default seq.info input from headers in alignment")
+      seq.info <- data.table("Header"=names(full.align)) 
+    }else{
+      warning("No sequence meta-data included, creating default seq.info input from tree tip.labels")
+      seq.info <- data.table("Header"=t$tip.label) 
+    }
+  }
   var.names <- colnames(seq.info)
   if (!("Header" %in% var.names)) {
     stop("Header must be contained within var.names")