@@ -1,3 +1,5 @@

 ^.*\.Rproj$

 ^\.Rproj\.user$

 extdata/.*\.json$

+^data-raw$

+extdata/refdata-cellranger-vdj-GRCh38-alts-ensembl-2.0.0/

@@ -3,3 +3,6 @@

 .DS_Store

 *.so

 .Rproj.user

+data-raw/*.csv

+data-raw/*.json

+inst/doc

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

 Package: CellaRepertorium

 Type: Package

 Title: Methods for clustering and analyzing high-throughput single cell immune cell repertoires (RepSeq)

-Version: 0.2.1

+Version: 0.2.2

 Author: Andrew McDavid

 Maintainer: Andrew McDavid <Andrew_McDavid@urmc.rochester.edu>

 Description: Methods to cluster and analyze high-throughput single cell immune cell repertoires,

@@ -11,6 +11,7 @@ Description: Methods to cluster and analyze high-throughput single cell immune c

 License: GPL-3

 Encoding: UTF-8

 LazyData: true

+Depends: R (>= 3.5.0)

 Imports:

    dplyr,

    tibble,

@@ -21,10 +22,17 @@ Imports:

    methods,

    rlang,

    purrr,

-   Matrix

+   Matrix,

+   S4Vectors

 Suggests: 

-   testthat,

-   readr

-RoxygenNote: 6.1.0

+    testthat,

+    readr,

+    knitr,

+    rmarkdown,

+    ggplot2,

+    BiocStyle,

+    tidyr

+RoxygenNote: 6.1.1

 LinkingTo: Rcpp

 NeedsCompilation: yes

+VignetteBuilder: knitr

@@ -1,5 +1,7 @@

 # Generated by roxygen2: do not edit by hand

+export(ContigCellDB)

+export(ContigCellDB_10XVDJ)

 export(canonicalize_by_chain)

 export(canonicalize_by_prevalence)

 export(cdhit)

@@ -12,6 +14,8 @@ export(modal_category)

 export(np)

 export(pairing_tables)

 import(Biostrings)

+importFrom(S4Vectors,List)

+importFrom(S4Vectors,SimpleList)

 importFrom(dplyr,"%>%")

 importFrom(dplyr,anti_join)

 importFrom(dplyr,bind_rows)

new file mode 100644

@@ -0,0 +1,41 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/AllClasses.R

+\name{ContigCellDB}

+\alias{ContigCellDB}

+\alias{ContigCellDB_10XVDJ}

+\title{Construct a ContigCellDB}

+\usage{

+ContigCellDB(contig_tbl, contig_pk, cell_tbl, cell_pk,

+  cluster_tbls = List(), cluster_pk = List())

+

+ContigCellDB_10XVDJ(contig_tbl, contig_pk = c("barcode", "contig_id"),

+  cell_pk = "barcode")

+}

+\arguments{

+\item{contig_tbl}{a data frame of contigs, and additional fields describing their properties}

+

+\item{contig_pk}{character vector naming fields in `contig_tbl` that uniquely identify a row/contig}

+

+\item{cell_tbl}{a data frame of cell barcodes, and (optional) additional fields describing their properties}

+

+\item{cell_pk}{character vector naming fields in `cell_tbl` that uniquely identify a cell barcode}

+

+\item{cluster_tbls}{An optional list of data frames that provide cluster assignments for each contig}

+

+\item{cluster_pk}{If `cluster_tbls` was provided, a list of character vector naming fields in `cluster_tbls` that uniquely identify a cluster}

+}

+\value{

+\code{ContigCellDB}

+}

+\description{

+Construct a ContigCellDB

+}

+\section{Functions}{

+\itemize{

+\item \code{ContigCellDB_10XVDJ}: provide defaults that correspond to identifiers in 10X VDJ data

+}}

+

+\examples{

+data(contigs_qc)

+ContigCellDB(contigs_qc, contig_pk = c('barcode', 'pop', 'sample', 'contig_id'), cell_pk = c('barcode', 'pop', 'sample'))

+}

new file mode 100644

@@ -0,0 +1,23 @@

+% Generated by roxygen2: do not edit by hand

+% Please edit documentation in R/data.R

+\docType{data}

+\name{contigs_qc}

+\alias{contigs_qc}

+\title{Filtered and annotated contigs of TCR from mice}

+\format{A data frame of 3399 contigs and 22 fields,

+ all except 4 are originally defined in https://support.10xgenomics.com/single-cell-vdj/software/pipelines/latest/output/annotation#contig

+ The following fields were defined ex post facto

+ \describe{

+   \item{anno_file}{Path to original csv file}

+   \item{pop}{Mouse strain}

+   \item{sample}{An artificial "replicate" from the original data defined by subsampling with replacement}

+   \item{celltype}{The putative cell type of the contig}

+ }}

+\usage{

+contigs_qc

+}

+\description{

+The details of how these are generated are shown in the vignette mouse_tcell_qc

+and are serialied to serve as an examples for other vignettes and documentation.

+}

+\keyword{datasets}

@@ -4,12 +4,12 @@

 \alias{fancy_name_contigs}

 \title{Generate a legible name for a series of contigs}

 \usage{

-fancy_name_contigs(contig_frame, prefix)

+fancy_name_contigs(contig_tbl, prefix)

 }

 \arguments{

-\item{contig_frame}{An `all_contig_annotations.csv` file, output from VDJ Cell ranger.  Importantly, this should contain columns `chain`, `v_gene`, `d_gene`, `j_gene`}

-

 \item{prefix}{an optional prefix added to each contig, eg, possibly a sample id.}

+

+\item{contig_frame}{An `all_contig_annotations.csv` file, output from VDJ Cell ranger.  Importantly, this should contain columns `chain`, `v_gene`, `d_gene`, `j_gene`}

 }

 \value{

 \code{character}

@@ -19,9 +19,10 @@ Generate a legible name for a series of contigs

 }

 \examples{

 library(dplyr)

-contig_anno_path = system.file('extdata', 'cellranger_contig_annotation.csv', package = 'CellaRepertorium')

+contig_anno_path = system.file('extdata', 'all_contig_annotations_balbc_1.csv.xz',

+    package = 'CellaRepertorium')

 contig_anno = readr::read_csv(contig_anno_path)

 contig_anno = contig_anno \%>\% mutate(fancy_name =

-    fancy_name_contigs(., prefix = paste(sample, pop, sep = '_')))

+    fancy_name_contigs(., prefix = 'b6_1'))

 stopifnot(!any(duplicated(contig_anno$fancy_name)))

 }

@@ -6,7 +6,7 @@

 \usage{

 fine_cluster(seqs, type = "AA", big_memory_brute = FALSE,

   method = "levenshtein", substitution_matrix = "BLOSUM100",

-  cluster = "hclust", cluster_method = "complete")

+  cluster_fun = "hclust", cluster_method = "complete")

 }

 \arguments{

 \item{seqs}{character vector, DNAStringSet or AAStringSet}

@@ -19,6 +19,8 @@ fine_cluster(seqs, type = "AA", big_memory_brute = FALSE,

 \item{substitution_matrix}{a character vector naming a substition matrix available in Biostrings, or a substitution matrix itself}

+\item{cluster_fun}{`character`, one of "hclust" or "none", determining if distance matrices should also be clustered with `hclust`}

+

 \item{cluster_method}{character passed to `hclust`}

 }

 \value{

@@ -65,7 +65,8 @@ cluster_tbl2 = bind_rows(cluster_tbl, cluster_tbl \%>\% mutate(cell_idx = rep(4:

 #all pairs found twice

 pt3 = pairing_tables(cluster_tbl2, 'cell_idx', 'clust_idx', canonicalize_by_prevalence, min_expansion = 1)

 pt3$cell_tbl

-# canonicalize_by_chain by default expects fields umis, reads to break ties, could wrap the function to change this

+# `canonicalize_by_chain` expects fields `umis`, `reads`

+# to break ties,  wrap the function to change this

 cluster_tbl3 = cluster_tbl2 \%>\%

     mutate(umis = 1, reads = 1, chain = rep(c('TRA', 'TRB'), times = 6))

 pt4 = pairing_tables(cluster_tbl3, 'cell_idx', 'clust_idx',