@@ -1,25 +1,30 @@

 Package: CellaRepertorium

 Type: Package

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

-Version: 0.1.0

+Version: 0.2.0

 Author: Andrew McDavid

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

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

     especially from the 10X Genomics VDJ solution. 

+    Contains an R interface to CD-HIT (Li and Godzik 2006).

     Tests for specific expansion, as well as omnibus oligoclonality under hypergeometric models.

 License: GPL-3

 Encoding: UTF-8

 LazyData: true

 Imports:

-   httr,

-   readr,

    dplyr,

    tibble,

    stringr,

    Biostrings,

-   progress,

-   Rcpp

-Suggests: testthat

+   Rcpp,

+   reshape2,

+   methods,

+   rlang,

+   purrr,

+   Matrix

+Suggests: 

+   testthat,

+   readr

 RoxygenNote: 6.1.0

 LinkingTo: Rcpp

 NeedsCompilation: yes

@@ -5,15 +5,33 @@ export(cluster_permute_test)

 export(entropy)

 export(fancy_name_contigs)

 export(fine_cluster)

+export(get_canonical_chain)

+export(get_canonical_representative)

 export(modal_category)

 export(np)

-export(query_cdhit)

-export(read_cdhit)

+export(pairing_tables)

 import(Biostrings)

-import(httr)

-import(stringr)

 importFrom(dplyr,"%>%")

+importFrom(dplyr,anti_join)

+importFrom(dplyr,bind_rows)

+importFrom(dplyr,group_by)

+importFrom(dplyr,left_join)

+importFrom(dplyr,mutate)

+importFrom(dplyr,summarize)

+importFrom(dplyr,ungroup)

+importFrom(methods,as)

+importFrom(rlang,":=")

+importFrom(rlang,sym)

+importFrom(rlang,syms)

+importFrom(stats,as.dist)

+importFrom(stats,dist)

+importFrom(stats,hclust)

+importFrom(stats,na.fail)

+importFrom(stats,sd)

+importFrom(stringr,str_c)

+importFrom(stringr,str_length)

+importFrom(stringr,str_replace_all)

+importFrom(tibble,as_data_frame)

 importFrom(tibble,data_frame)

 importFrom(utils,data)

-importFrom(utils,download.file)

 useDynLib(CellaRepertorium)

@@ -1,6 +1,6 @@

 # CellaRepertorium

-These package contains methods for clustering and analyzing single cell rep seq data, especially as generated by [10X genomics VDJ solution](https://support.10xgenomics.com/single-cell-vdj).  

+This package contains methods for clustering and analyzing single cell RepSeq data, especially as generated by [10X genomics VDJ solution](https://support.10xgenomics.com/single-cell-vdj).  

 ## Functions

@@ -4,21 +4,26 @@

 \alias{cluster_permute_test}

 \title{Tests for independence between clusters and labels using permutation}

 \usage{

-cluster_permute_test(clusters, labels, statistic, n_perm = 1000, ...)

+cluster_permute_test(clusters, labels, covariates, statistic,

+  n_perm = 1000, alternative = c("two.sided", "less", "greater"), ...)

 }

 \arguments{

 \item{clusters}{\code{factor} of length n}

 \item{labels}{\code{factor} of length n}

-\item{statistic}{function of \code{clusters} and \code{labels} that returns a \code{numeric} of length 1.  Currently, a two-tailed test is always run.}

+\item{covariates}{optional \code{factor} of length n.}

+

+\item{statistic}{function of \code{clusters}, \code{labels} and optionally \code{covariates} that returns a \code{numeric} of length 1.}

 \item{n_perm}{number of permutations.}

+\item{alternative}{`character` naming the direction `statistic` should be fall under the alternative hypothesis}

+

 \item{...}{passed to \code{statistic}}

 }

 \value{

-a list containing the observed value of the statistic, its expectation (under independence), a two-sided p-value, and the monte carlo standard error (of the expected value).

+a list containing the observed value of the statistic, its expectation (under independence), a p-value, and the monte carlo standard error (of the expected value).

 }

 \description{

 This tests a statistic for association between clusters and labels by permuting the link between the two

@@ -28,12 +33,15 @@ For example, \code{clusters} could be a clonal ID, while \code{labels} is a subj

 }

 \examples{

 library(dplyr)

-purity = function(clusters, labels){

-n_label_cluster = data_frame(labels = labels, clusters = clusters) \%>\% group_by(clusters, si) \%>\% summarize(n = n()) \%>\% ungroup()

+purity = function(clusters, labels, covariates){

+n_label_cluster = data_frame(labels = labels, clusters = clusters) \%>\% group_by(clusters, labels) \%>\% summarize(n = n()) \%>\% ungroup()

 singletons = mean(n_label_cluster$n == 1)

 singletons

 }

 clusters = c(1, 1, 1, 2, 2, 3, 3)

+labels = c('A', 'A', 'B', 'B', 'B', 'C', 'C')

+covariates = c('X', 'X', 'Y', 'Y', 'Y', 'Y', 'Y')

+cluster_permute_test(clusters, labels, statistic = purity, n_perm  = 50)

 }

@@ -5,8 +5,8 @@

 \title{Calculate distances and perform hierarchical clustering on a set of sequences}

 \usage{

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

-  substitution_matrix = "BLOSUM100", cluster = "hclust",

-  cluster_method = "complete")

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

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

 }

 \arguments{

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

@@ -15,7 +15,9 @@ fine_cluster(seqs, type = "AA", big_memory_brute = FALSE,

 \item{big_memory_brute}{attempt to cluster more than 4000 sequences?  Clustering is quadratic, so this will take a long time and might exhaust memory}

-\item{substitution_matrix}{a character vector naming a substition matrix used to weight}

+\item{method}{one of 'substitutionMatrix' or 'levenshtein'}

+

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

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

 }

@@ -30,7 +32,7 @@ The distances between nucleotide sequences is defined to be edit_distance/max(ed

 fasta_path = system.file('extdata', 'demo.fasta', package='CellaRepertorium')

 aaseq = Biostrings::readAAStringSet(fasta_path)[1:100]

 cls = fine_cluster(aaseq)

-plot(cls)

+plot(cls$cluster)

 }

 \seealso{

 hclust, stringDist

deleted file mode 100644

@@ -1,38 +0,0 @@

-% Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/cdhit-methods.R

-\name{query_cdhit}

-\alias{query_cdhit}

-\title{Query the web interface to cdhit}

-\usage{

-query_cdhit(sequences, results_path = NULL, identity_cutoff = 0.9,

-  bandwidth = 20, results_timeout = 120)

-}

-\arguments{

-\item{sequences}{An object of class \code{AAStringSet}}

-

-\item{results_path}{If non-null, a \code{character} specifying a path to a results.  Directories therein must exist. If null, the R temporary directory will be used.}

-

-\item{identity_cutoff}{minimum identity to be clustered together}

-

-\item{bandwidth}{see CDhit docs}

-

-\item{results_timeout}{number of seconds to wait for result}

-}

-\value{

-path to results file

-}

-\description{

-This sends a query to \url{http://weizhong-lab.ucsd.edu/cdhit-web-server/cgi-bin/index.cgi?cmd=cd-hit}

-and returns a link to results.

-}

-\examples{

-\dontrun{

-fasta_path = system.file('extdata', 'demo.fasta', package='CellaRepertorium')

-aaseq = Biostrings::readAAStringSet(fasta_path)

-results_path = query_cdhit(aaseq[1:100])

-read_cdhit(results_path)

-}

-}

-\seealso{

-AAStringSet

-}

deleted file mode 100644

@@ -1,22 +0,0 @@

-% Generated by roxygen2: do not edit by hand

-% Please edit documentation in R/cdhit-methods.R

-\name{read_cdhit}

-\alias{read_cdhit}

-\title{Parse a CD-hit results file as a data.frame}

-\usage{

-read_cdhit(file)

-}

-\arguments{

-\item{file}{path to a file with cdhit results}

-}

-\value{

-\code{data.frame} with columns

-}

-\description{

-Parses a cd-hit (\url{http://weizhong-cluster.ucsd.edu/cdhit_suite/cgi-bin/index.cgi?cmd=cd-hit}) cluster file and returns it as a \code{data.frame}.

-The \code{data.frame} contains the columns `cluster_idx`: the cluster number, `query_idx`: the fasta identifier of the query sequence, `homology_pct`: the percent similarity to the exemplar sequence, `member_idx`, an arbitrary enumeration of each sequence in the a cluster, `len`: the length of the query sequence.

-}

-\examples{

-demo_path = system.file('extdata', 'demo150.clstr.sorted', package='CellaRepertorium')

-out = read_cdhit(demo_path)

-}