@@ -12,3 +12,4 @@ manuscript/

 .ignore

 README.Rmd

 R/immcantation-utils.R

+inst/WORDLIST

@@ -64,7 +64,6 @@ LinkingTo:

 VignetteBuilder: 

     knitr

 Encoding: UTF-8

-LazyData: true

 NeedsCompilation: yes

 RoxygenNote: 7.1.1

 URL: https://github.com/amcdavid/CellaRepertorium

@@ -1,7 +1,7 @@

 globalVariables(c('prev'))

 #' For each cell, return a single, canonical chain-cluster

 #'

-#' In single cell data, multiple chains (heavy-light or alpha-beta) are expected.  In some cases, there could be more than two (eg multiple alpha alleles for T cells).

+#' In single cell data, multiple chains (heavy-light or alpha-beta) are expected.  In some cases, there could be more than two (e.g. multiple alpha alleles for T cells).

 #' This picks a cluster id for each cell based on the overall prevalence of cluster ids over all cells in `tbl`.

 #' If order = 1 then the canonical chain-cluster will be the most prevalent, and if order = 2, it will be the 2nd most prevalent, and so on.  Ties are broken arbitrarily (possibly by lexicographic order of `cluster_idx`).

 #' @param tbl `data.frame` containing columns specified in `cell_identifiers`, `cluster_idx` and optionally `chain_identifiers`

@@ -1,3 +1,4 @@

+# ignored words for devtools::spell_check()

 AIRR

 AAseq

 AAStringSet

@@ -24,7 +25,9 @@ Contigs

 csv

 cytometry

 DNAStringSet

-eg

+dbplyr

+dtplyr

+e.g.

 endogenous

 endomorphic

 facto

@@ -57,6 +60,7 @@ Niu

 nucleotides

 Oligo

 oligoclonality

+overrepresentation

 PBMC

 pearson

 Pedersen

@@ -66,9 +70,11 @@ qc

 Recode

 RepSeq

 Roadmap

+Scater

 screencap

 scRNAseq

 seqs

+SingleCellExperiment

 subsampled

 substitutionMatrix

 tcell

@@ -78,6 +84,7 @@ TRA

 TRB

 tbls

 UMI

+umi

 umis

 UMIs

 ungapped

@@ -38,7 +38,7 @@ canonicalize_by_chain(

 \code{data.frame} with columns from \code{cell_identifiers} and a single \code{cluster_idx} for each cell

 }

 \description{

-In single cell data, multiple chains (heavy-light or alpha-beta) are expected.  In some cases, there could be more than two (eg multiple alpha alleles for T cells).

+In single cell data, multiple chains (heavy-light or alpha-beta) are expected.  In some cases, there could be more than two (e.g. multiple alpha alleles for T cells).

 This picks a cluster id for each cell based on the overall prevalence of cluster ids over all cells in \code{tbl}.

 If order = 1 then the canonical chain-cluster will be the most prevalent, and if order = 2, it will be the 2nd most prevalent, and so on.  Ties are broken arbitrarily (possibly by lexicographic order of \code{cluster_idx}).

 }