@@ -57,3 +57,4 @@ NeedsCompilation: yes

 RoxygenNote: 6.1.1

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

 BugReports: https://github.com/amcdavid/CellaRepertorium/issues

+Roxygen: list(markdown = TRUE)

@@ -28,18 +28,39 @@ valid_KeyedTbl = function(tbl, keys){

 #' @param cell_pk character vector naming fields in `cell_tbl` that uniquely identify a cell barcode

 #' @param cluster_tbl A data frame that provide cluster assignments for each contig

 #' @param cluster_pk If `cluster_tbl` was provided, a character vector naming fields in `cluster_tbl` that uniquely identify a cluster

-#'

 #' @return \code{ContigCellDB}

+#'

+#' @section Accessors/mutators:

+#' See \code{\link[=ContigCellDB-mutate]{$,ContigCellDB-method}} for more on how to access and mutate slots.

+#' At the moment, there is not a good way to combine objects without manually touching slots with `@`,

+#' but a `rbind` method is in the offing.

 #' @export

 #' @importFrom S4Vectors List SimpleList

 #' @importFrom tibble as_tibble

 #' @importFrom methods new slot slot<- validObject

 #' @rdname ContigCellDB-fun

-#'

+#' @seealso \code{\link[=ContigCellDB-mutate]{$,ContigCellDB-method}}

 #' @examples

 #' data(contigs_qc)

-#' ContigCellDB(contigs_qc, contig_pk = c('barcode', 'pop', 'sample', 'contig_id'),

+#' contigs_qc

+#'

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

 #'  cell_pk = c('barcode', 'pop', 'sample'))

+#'  cdb

+#'

+#'  # everything that was in contigs_qc

+#'  cdb$contig_tbl

+#'

+#'  # Only the cell_pk are included by default (until clustering/canonicalization)

+#'  cdb$cell_tbl

+#'

+#'  # Empty, since no cluster_pk was specified

+#'  cdb$cluster_tbl

+#'

+#'  # Keys

+#'  cdb$contig_pk

+#'  cdb$cell_pk

+#'  cdb$cluster_pk

 ContigCellDB = function(contig_tbl, contig_pk, cell_tbl, cell_pk, cluster_tbl, cluster_pk = character()){

     valid_KeyedTbl(contig_tbl, contig_pk)

     equalized = FALSE

@@ -73,9 +94,9 @@ ContigCellDB_10XVDJ = function(contig_tbl, contig_pk = c('barcode', 'contig_id')

 #' @param x A ContigCellDB object

 #' @param name a slot of a ContigCellDB object (one of  `c('contig_tbl', 'cell_tbl', 'contig_pk', 'cell_pk', 'cluster_tbl', 'cluster_pk')`)

 #'

-#' @return Slot of ContigCellDB

+#' @return Update or return a slot of [ContigCellDB()]

 #' @export

-#'

+#' @aliases ContigCellDB-mutate

 #' @examples

 #' ccdb_ex$contig_tbl

 #' ccdb_ex$cell_tbl

@@ -88,13 +109,8 @@ setMethod("$", signature = c(x = 'ContigCellDB'), function(x, name){

     }

 })

-#' Access public members of ContigCellDB object

-#'

-#' @param x A ContigCellDB object

-#' @param name Name of a slot for a ContigCellDB object (one of  `c('contig_tbl', 'cell_tbl', 'contig_pk', 'cell_pk', 'cluster_tbl', 'cluster_pk')`)

 #' @param value The value assigned to a slot of ContigCellDB object

-#'

-#' @return A ContigCellDB object

+#' @rdname cash-ContigCellDB-method

 #' @export

 #'

 #' @examples

@@ -19,7 +19,6 @@ globalVariables('cluster_idx')

 #' You may need to lower it below 5 for AAseq with identity less than .7.

 #' @param min_length Minimum length for sequences to be clustered.  An error if something smaller is passed.

 #' @param s fraction of shorter sequence covered by alignment.

-#' @param name program name (?)

 #' @param showProgress show a status bar

 #' @param only_index if TRUE only return the integer cluster indices, otherwise return a tibble.

 #' @param ... other arguments that can be passed to cdhit, see https://github.com/weizhongli/cdhit/wiki/3.-User's-Guide#CDHIT for details.  These will override any default values.

@@ -41,8 +40,9 @@ globalVariables('cluster_idx')

 #' cdhit(aaseq,identity = 1, G = 0, aL = .9, aS = .9,  only_index = TRUE)[1:10]

 #' # a tibble

 #' tbl = cdhit(aaseq, identity = 1, G = 0, aL = .9, aS = .9, only_index = FALSE)

-cdhit = function(seqs, identity = NULL, kmerSize = NULL, min_length = 6, s = 1, name = 'CD-Hit', only_index = FALSE, showProgress = interactive(), ...) {

+cdhit = function(seqs, identity = NULL, kmerSize = NULL, min_length = 6, s = 1, only_index = FALSE, showProgress = interactive(), ...) {

     if(any(width(seqs) < min_length)) stop("Some sequences shorter than `min_length`; remove these or decrease min_length")

+    name = 'CD-Hit'

     uopts = list(...)

     options = list()

     options$i <- tempfile()

@@ -78,12 +78,17 @@ cdhit = function(seqs, identity = NULL, kmerSize = NULL, min_length = 6, s = 1,

         dplyr::group_by(cluster_idx) %>% dplyr::mutate(n_cluster = dplyr::n())

 }

-##' @describeIn cdhit Run `cdhit` on `ClusterContigDB` object

-##' @param object An object of class `ClusterContigDB`

+

+##' Use [cdhit()] to cluster a [ContigCellDB()]

+##'

+##' @param object An object of class [ContigCellDB()]

 ##' @param sequence_key `character` naming the column in the `contig_tbl` containing the sequence to be clustered

 ##' @param type one of 'DNA' or 'AA'

 ##' @param cluster_name `character` specifying key, and name for the clustering.

+##' @return [ContigCellDB()]

+##' @inheritDotParams cdhit -seqs -only_index

 ##' @export

+##' @seealso [cdhit()]

 ##' @examples

 ##' res = CellaRepertorium:::cdhit_ccdb(ccdb_ex, 'cdr3_nt', type = 'DNA',

 ##' cluster_name = 'DNA97', identity = .965, min_length = 12, G = 1)

@@ -1,11 +1,11 @@

 #' Cluster contigs by germline properties

 #'

-#' @param ccdb `ContigCellDB`

+#' @param ccdb [ContigCellDB()]

 #' @param segment_keys fields in `contig_tbl` that identify a cluster

 #' @param cluster_name name of cluster to be added to `cluster_tbl`

 #'

-#' @return `ContigCellDB`

+#' @return [ContigCellDB()]

 #' @export

 #'

 #' @examples

@@ -24,16 +24,16 @@ globalVariables(c('fc', 'd(medoid)', 'is_medoid', 'n_cluster'))

 # Also canonicalize..

 #' Perform additional clustering of sequences within groups

 #'

-#' @param ccdb A ContigCellDB object

+#' @param ccdb A [ContigCellDB()] object

 #' @param sequence_key `character` naming column in `contig_tbl` with sequence

 #' @param type 'AA' or 'DNA'

 #' @param max_affinity `numeric` naming the maximal affinity for the sparse affinity matrix that is constructed.  Not currently used.

 #' @param keep_clustering_details `logical` -- should output of `fine_cluster_seqs` be kept as a list column

-#' @param ... passed to `fine_cluster_seqs`

+#' @inheritDotParams fine_cluster_seqs -seqs -type -cluster_fun -cluster_method

 #' @importFrom dplyr select bind_cols

 #'

 #' @example inst/examples/small_cluster_example.R

-#' @return `ContigCellDB` object with updated `contig_tbl` and `cluster_tbl`

+#' @return [ContigCellDB()] object with updated `contig_tbl` and `cluster_tbl`

 #' @export

 fine_clustering = function(ccdb, sequence_key, type, max_affinity = NULL, keep_clustering_details = FALSE, ...){

     contig_tbl = ccdb$contig_tbl

@@ -89,23 +89,25 @@ left_join_warn = function(x, y, by, overwrite = FALSE, join = left_join, ...){

 #' Find a canonical contig to represent a cluster

 #'

-#' @param ccdb `ContigCellDB`

-#' @param contig_filter_args an expression passed to dplyr::filter.  Unlike `filter`, multiple criteria must be `&` together, rather than using commas to separate.

-#' that act on `ccdb$contig_tbl``

+#' @param ccdb [ContigCellDB()]

+#' @param contig_filter_args an expression passed to [dplyr::filter()].

+#' Unlike `filter`, multiple criteria must be `&` together, rather than using

+#' commas to separate. These act on `ccdb$contig_tbl`

 #' @param tie_break_keys (optional) `character` naming fields in `contig_tbl`

 #' that are used sort the contig table in descending order.

 #' Used to break ties if `contig_filter_args` does not return a unique contig

 #' for each cluster

 #' @param order The rank order of the contig, based on `tie_break_keys`

-#' to return

+#' to return.  If `tie_break_keys` included an ordered factor (such as chain)

+#' this could be used to return the second chain.

 #' @param representative an optional field from `contig_tbl` that will be made

 #' unique. Serve as a surrogate `cluster_pk`.

 #' @param contig_fields Optional fields from `contig_tbl` that will be copied into

 #' the `cluster_tbl` from the canonical contig.

 #'

-#' @return `ContigCellDB`

+#' @return [ContigCellDB()]

 #' @export

-#' @seealso canonicalize_cell

+#' @seealso [canonicalize_cell()]

 #' @example inst/examples/small_cluster_example.R

 canonicalize_cluster = function(ccdb, contig_filter_args = is_medoid,

 tie_break_keys = character(), order = 1, representative = ccdb$cluster_pk[1], contig_fields = c('cdr3', 'cdr3_nt', 'chain', 'v_gene', 'd_gene', 'j_gene')){

@@ -140,20 +142,20 @@ tie_break_keys = character(), order = 1, representative = ccdb$cluster_pk[1], co

 #' @param type character either `AA` or `DNA` specifying type of `seqs`

 #' @param big_memory_brute attempt to cluster more than 4000 sequences?  Clustering is quadratic, so this will take a long time and might exhaust memory

 #' @param method one of 'substitutionMatrix' or 'levenshtein'

-#' @param substitution_matrix a character vector naming a substition matrix available in Biostrings, or a substitution matrix itself

+#' @param substitution_matrix a character vector naming a substitution matrix available in Biostrings, or a  substitution matrix itself

 #' @param cluster_fun `character`, one of "hclust" or "none", determining if distance matrices should also be clustered with `hclust`

 #' @param cluster_method character passed to `hclust`

 #'

-#' @seealso hclust, stringDist

-#' @return `list` containing

+#' @seealso [hclust()], [Biostrings::stringDist()]

+#' @return `list`

 #' @export

 #' @import Biostrings

 #' @examples

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

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

-#' cls = fine_cluster_seqs(aaseq)

+#' cls = fine_cluster_seqs(aaseq, cluster_fun = 'hclust')

 #' plot(cls$cluster)

-fine_cluster_seqs = function(seqs, type = 'AA', big_memory_brute = FALSE, method = 'levenshtein', substitution_matrix = 'BLOSUM100', cluster_fun = 'hclust', cluster_method = 'complete'){

+fine_cluster_seqs = function(seqs, type = 'AA', big_memory_brute = FALSE, method = 'levenshtein', substitution_matrix = 'BLOSUM100', cluster_fun = 'none', cluster_method = 'complete'){

     if(length(seqs) > 4000 & !big_memory_brute) stop("Won't try to cluster ", length(seqs), " sequences unless `big_memory_brute` = TRUE.  (Make sure you actually have lots of memory!)")

     type = match.arg(type, choices = c('AA', 'DNA'))

     cluster_fun = match.arg(cluster_fun, c('hclust', 'none'))

@@ -204,7 +206,7 @@ fine_cluster_seqs = function(seqs, type = 'AA', big_memory_brute = FALSE, method

 #' Calculate the entropy of a vector

 #'

 #' @param v categorical vector

-#' @param pseudo_count number of pseudo counts to add on, to stablize empty categories

+#' @param pseudo_count number of pseudo counts to add on, to stabilize empty categories

 #' @param na.action how to handle NA values

 #'

 #' @return the sample entropy

@@ -3,8 +3,13 @@

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

 #' and are serialized to serve as an examples for other vignettes and documentation.

 #' @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. anno_file: Path to original csv file, pop: Mouse strain. sample: An artificial "replicate" from the original data defined by subsampling with replacement, celltype:The putative cell type of the contig.

+#'  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.

+#'

+#'  1. `anno_file`: Path to original csv file

+#'  2. `pop`: Mouse strain.

+#'  3. `sample`: An artificial "replicate" from the original data defined by subsampling with replacement

+#'  4. `celltype`: The putative cell type of the contig.

 #'

 "contigs_qc"

@@ -6,7 +6,7 @@ globalVariables(c('prev'))

 #' 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`

 #' @param cell_identifiers `character` vector specifying columns in `tbl` that identify a cell

-#' @param cluster_idx `character` specifying the column in `tbl` that identifies a clsuter

+#' @param cluster_idx `character` specifying the column in `tbl` that identifies a cluster

 #' @param order return the 1st, 2nd, 3rd, etc, most common chain-cluster

 #'

 #' @return `data.frame` with columns from `cell_identifiers` and a single `cluster_idx` for each cell

@@ -38,14 +38,14 @@ canonicalize_by_chain = function(tbl,  cell_identifiers = 'barcode', sort_factor

 #' Find a canonical contig to represent a cell

 #'

-#' Using filtering in `...` and sorting in `tie_break_keys` and `order` find a

+#' Using filtering in `contig_filter_args` and sorting in `tie_break_keys` and `order` find a

 #' single, canonical contig to represent each cell

 #' Fields in `contig_fields` will be copied over to the `cell_tbl`.

 #' @inheritParams canonicalize_cluster

 #'

 #' @return `ContigCellDB` with additional fields in `cell_tbl`

 #' @export

-#' @seealso canonicalize_cluster

+#' @seealso [canonicalize_cluster()]

 #' @examples

 #' # Report beta chain with highest umi-count, breaking ties with reads

 #' beta = canonicalize_cell(ccdb_ex, chain == 'TRB',

@@ -136,7 +136,7 @@ get_canonical_representative = function(seqs, medoid_idx, warn_if_distinct = FAL

 #' @return list of tables.  The `cell_tbl` is keyed by the `cell_identifiers`, with fields "cluster_idx.1", "cluster_idx.2", etc, IDing the contigs present in each cell. "cluster_idx.1_fct" and "cluster_idx.2_fct" cast these fields to factors and are reordered to maximize the number of pairs along the diagonal. The `idx1_tbl` and `idx2_tbl` report information (passed in about the `cluster_idx` by `feature_tbl`.)  The `cluster_pair_tbl` reports all pairings found of contigs, and the number of times observed.

 #' @export

 #'

-#' @seealso canonicalize_by_prevalence, canonicalize_by_chain

+#' @seealso [canonicalize_by_prevalence()], [canonicalize_by_chain()]

 #' @importFrom tibble as_data_frame

 #' @importFrom dplyr bind_rows left_join ungroup summarize anti_join

 #' @importFrom stringr str_length str_c

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

-#' Calculate number of cluster-subject singletons

+#' Calculate number of cluster-subject singletons for the purposes of permutation testing

 #'

 #' @param cluster_idx factor-like cluster variable

 #' @param subject factor-like subject

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

 #' @return average number of singletons

 #' @export

 #'

-#' @seealso cluster_permute_test

+#' @seealso [cluster_permute_test()]

 purity = function(cluster_idx, subject) {

     n_label_cluster = dplyr::bind_cols(cluster_idx = cluster_idx, subject = subject) %>%

         group_by(cluster_idx, subject) %>% summarize(n = n()) %>% ungroup()

@@ -31,7 +31,7 @@ purity = function(cluster_idx, subject) {

 #' @param alternative `character` naming the direction `statistic` should be fall under the alternative hypothesis

 #'

 #' @return 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).

-#' @seealso purity

+#' @seealso [purity()]

 #' @export

 #'

 #' @examples

@@ -27,29 +27,34 @@ Requires R >= 3.5.

 ## Data requirements and package structure

 The fundamental unit this package operates on is the **contig**, which is a section of contiguously stitched reads from a single **cell**.  Each contig belongs to one (and only one) cell, however, cells generate multiple contigs.  

+<img src = man/figures/contig_schematic.png />

-```{r, echo = FALSE}

-knitr::include_graphics('vignettes/img/contig_schematic.png')

-```

-Contigs can also belong to a **cluster**.  Because of these two many-to-one mappings, these data can be thought as a series of ragged arrays.  The links between them mean they are relational data. A `ContigCellDB` object wraps each of these objects as a sequence of three `data.frames` (well, `tibbles`, actually).   `ContigCellDB` also tracks columns (the primary keys) that unique identify each row in each of these tables.  The `contig_tbl` is the `tibble` containing **contigs**, the `cell_tbl` contains the **cells**, and the `cluster_tbl` contains the **clusters**.  

+Contigs can also belong to a **cluster**.  Because of these two many-to-one mappings, these data can be thought as a series of ragged arrays.  The links between them mean they are relational data. A `ContigCellDB()` object wraps each of these objects as a sequence of three `data.frames` (well, `dplyr::tibble()`, actually).   `ContigCellDB()` also tracks columns (the primary keys) that unique identify each row in each of these tables.  The `contig_tbl` is the `tibble` containing **contigs**, the `cell_tbl` contains the **cells**, and the `cluster_tbl` contains the **clusters**.  

-The `contig_pk`, `cell_pk` and `cluster_pk` identify the columns that identify a contig, cell and cluster, respectively.  These will serve as foreign keys that link the three tables together.

+The `contig_pk`, `cell_pk` and `cluster_pk` specify the columns that identify a contig, cell and cluster, respectively.  These will serve as foreign keys that link the three tables together.

 The tables are kept in sync so that subsetting the contigs will subset the cells, and clusters, and vice-versa.

-```{r, echo = FALSE}

-knitr::include_graphics('vignettes/img/table_schematic.png')

-```

+<img src = man/figures/table_schematic.png />

-Of course, each of these tables can contain many other columns that will serve as covariates for various analyses, such as the CDR3 sequence, or the identity of the V, D and J regions.  Various derived quantities that describe cells and clusters can also be calculated, and added to these tables, such as the medoid of a cluster --  a contig that  minimizes the average distance to all other clusters. 

+Of course, each of these tables can contain many other columns that will serve as covariates for various analyses, such as the **CDR3** sequence, or the identity of the **V**, **D** and **J** regions.  Various derived quantities that describe cells and clusters can also be calculated, and added to these tables, such as the **medoid** of a cluster --  a contig that minimizes the average distance to all other clusters. 

-## Functions

+## Some functions of interest

+Mainly, this package seeks to enforce proper schema of single cell repertoire 

+data and stay out the user's way for various summaries they might conduct.  

 [a screencap of something interesting?]

-*  `cdhit_ccdb`: An R interface to CDhit, which was originally ported by Thomas Lin Pedersen.

-*  `fine_clustering`: clustering CDR3 by edit distances (possibly using empirical amino acid substitution matrices)

-*  `cluster_permute_test`: permutation tests of cluster statistics

-*  `pairing_tables`: Generate pairings of contigs within each cell in a way that they can be plotted

+However, there are a variety of specialized functions, as well:

+*  `cdhit_ccdb()`: An R interface to CDhit, which was originally ported by Thomas Lin Pedersen.

+*  `fine_clustering()`: clustering CDR3 by edit distances (possibly using empirical amino acid substitution matrices)

+*  `canonicalize_cell()`: Return a single contig for each cell, e.g., for combining VDJ information with 5'-based single cell expressoin

+*  `cluster_permute_test()`: permutation tests of cluster statistics

+*  `pairing_tables()`: Generate pairings of contigs within each cell in a way that they can be plotted

+

+## Inferfacing related packages for clonal analyses

+*  To combine repertoire information with expression of endogenuous mRNAs, this package has been used with `SingleCellExperiment::SingleCellExperiment()` and [Seurat](https://satijalab.org/seurat/) after generating various cell canonicalizations.

+*  Functionality is under development facilitate submitting actual contig `fasta` to tools such as the IGMT's [HighV-QUEST](http://imgt.org/HighV-QUEST/home.action)

+*  Many tools from the [Immcantation](https://alakazam.readthedocs.io/en/version-0.2.11/) suite can work directly on `ContigCellDB()` objects.

@@ -18,19 +18,18 @@ Requires R \>= 3.5.

 The fundamental unit this package operates on is the **contig**, which

 is a section of contiguously stitched reads from a single **cell**. Each

 contig belongs to one (and only one) cell, however, cells generate

-multiple contigs.

-

-![](vignettes/img/contig_schematic.png)<!-- -->

+multiple contigs.  

+<img src = man/figures/contig_schematic.png />

 Contigs can also belong to a **cluster**. Because of these two

 many-to-one mappings, these data can be thought as a series of ragged

 arrays. The links between them mean they are relational data. A

-`ContigCellDB` object wraps each of these objects as a sequence of three

-`data.frames` (well, `tibbles`, actually). `ContigCellDB` also tracks

-columns (the primary keys) that unique identify each row in each of

-these tables. The `contig_tbl` is the `tibble` containing **contigs**,

-the `cell_tbl` contains the **cells**, and the `cluster_tbl` contains

-the **clusters**.

+`ContigCellDB()` object wraps each of these objects as a sequence of

+three `data.frames` (well, `tibbles`, actually). `ContigCellDB` also

+tracks columns (the primary keys) that unique identify each row in each

+of these tables. The `contig_tbl` is the `tibble` containing

+**contigs**, the `cell_tbl` contains the **cells**, and the

+`cluster_tbl` contains the **clusters**.

 The `contig_pk`, `cell_pk` and `cluster_pk` identify the columns that

 identify a contig, cell and cluster, respectively. These will serve as

@@ -38,7 +37,7 @@ foreign keys that link the three tables together. The tables are kept in

 sync so that subsetting the contigs will subset the cells, and clusters,

 and vice-versa.

-![](vignettes/img/table_schematic.png)<!-- -->

+<img src = man/figures/table_schematic.png />

 Of course, each of these tables can contain many other columns that will

 serve as covariates for various analyses, such as the CDR3 sequence, or

@@ -12,13 +12,14 @@ reference:

   contents:

    - '`cluster_germline`'

    - '`fine_clustering`'

-   - '`cdhit`'

+   - '`cdhit_ccdb`'

    - '`pairing_tables`'

 - title: Canonicalization

   desc: "Methods to return single contigs for cells or clusters"

   contents:

    - '`canonicalize_cell`'

    - '`canonicalize_cluster`'

+   - '`ig_chain_recode`'

 - title: Statistical testing

   contents:

    - '`cluster_permute_test`'

@@ -27,15 +28,12 @@ reference:

   contents:

    - '`ccdb_ex`'

    - '`contigs_qc`'

-   - '`canonicalize_by_prevalence`'

 - title: Internal or WIP

   desc: "Functions that may be made internal, removed, or with interfaces subject to change."

   contents:

-  - '`cluster_germline`'

-  - '`cluster_permute_test`'

+  - '`canonicalize_by_prevalence`'

   - '`.cluster_permute_test`'

   - '`entropy`'

-  - '`ig_chain_recode`'

   - '`fancy_name_contigs`'

   - '`fine_cluster_seqs`'

   - '`get_canonical_representative`'

@@ -30,7 +30,7 @@

       </button>

       <span class="navbar-brand">

         <a class="navbar-link" href="../index.html">CellaRepertorium</a>

-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Released version">0.3.1</span>

+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Released version">0.3.2</span>

       </span>

     </div>

@@ -134,7 +134,7 @@

 <h1 class="hasAnchor">

 <a href="#cluster-cdr3-protein-sequences" class="anchor"></a>Cluster CDR3 protein sequences</h1>

 <div class="sourceCode" id="cb4"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb4-1" data-line-number="1"></a>

-<a class="sourceLine" id="cb4-2" data-line-number="2">aa80 =<span class="st"> </span>CellaRepertorium<span class="op">:::</span><span class="kw"><a href="../reference/cdhit.html">cdhit_ccdb</a></span>(cdb, <span class="st">'cdr3'</span>, <span class="dt">type =</span> <span class="st">'AA'</span>, <span class="dt">cluster_name =</span> <span class="st">'aa80'</span>, <span class="dt">identity =</span> <span class="fl">.8</span>)</a>

+<a class="sourceLine" id="cb4-2" data-line-number="2">aa80 =<span class="st"> </span><span class="kw"><a href="../reference/cdhit_ccdb.html">cdhit_ccdb</a></span>(cdb, <span class="st">'cdr3'</span>, <span class="dt">type =</span> <span class="st">'AA'</span>, <span class="dt">cluster_name =</span> <span class="st">'aa80'</span>, <span class="dt">identity =</span> <span class="fl">.8</span>)</a>

 <a class="sourceLine" id="cb4-3" data-line-number="3">aa80 =<span class="st"> </span><span class="kw"><a href="../reference/fine_clustering.html">fine_clustering</a></span>(aa80, <span class="dt">sequence_key =</span> <span class="st">'cdr3'</span>, <span class="dt">type =</span> <span class="st">'AA'</span>, <span class="dt">keep_clustering_details =</span> <span class="ot">TRUE</span>)</a>

 <a class="sourceLine" id="cb4-4" data-line-number="4"><span class="co">#&gt; Calculating intradistances on 988 clusters.</span></a>

 <a class="sourceLine" id="cb4-5" data-line-number="5"><span class="co">#&gt; Summarizing</span></a>

@@ -146,12 +146,12 @@

 <a class="sourceLine" id="cb4-11" data-line-number="11"><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot.html">ggplot</a></span>(aa80<span class="op">$</span>cluster_tbl <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(n_cluster<span class="op">&gt;</span><span class="dv">1</span>) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://tidyr.tidyverse.org/reference/gather.html">gather</a></span>(key, value, <span class="op">-</span>aa80, <span class="op">-</span>fc) , <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">x =</span> value))<span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/facet_wrap.html">facet_wrap</a></span>(<span class="op">~</span>key, <span class="dt">scales =</span> <span class="st">'free'</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/geom_histogram.html">geom_histogram</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/scale_continuous.html">scale_y_sqrt</a></span>()</a>

 <a class="sourceLine" id="cb4-12" data-line-number="12"><span class="co">#&gt; `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.</span></a></code></pre></div>

 <p><img src="cdr3_clustering_files/figure-html/unnamed-chunk-4-1.png" width="700"></p>

-<p>We cluster the CDR3 translated amino acid residues with the program <a href="http://weizhongli-lab.org/cdhit_suite/cgi-bin/index.cgi?cmd=cd-hit">CD-HIT</a>. A sequence is included in a cluster if it matches by 100% similiarity and has the same CDR3 length. Note that this can and should be relaxed – especially in the beta chain we see “near clones” that only differ by a residue or two, seemingly in stylized places.</p>

+<p>We cluster the CDR3 translated amino acid residues with the program <a href="http://weizhongli-lab.org/cdhit_suite/cgi-bin/index.cgi?cmd=cd-hit">CD-HIT</a>. A sequence is included in a cluster if it matches by 100% similarity and has the same CDR3 length. Note that this can and should be relaxed – especially in the beta chain we see “near clones” that only differ by a residue or two, seemingly in stylized places.</p>

 </div>

 <div id="cluster-cdr3-dna-sequences" class="section level1">

 <h1 class="hasAnchor">

 <a href="#cluster-cdr3-dna-sequences" class="anchor"></a>Cluster CDR3 DNA sequences</h1>

-<div class="sourceCode" id="cb5"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb5-1" data-line-number="1">cdb =<span class="st"> </span>CellaRepertorium<span class="op">:::</span><span class="kw"><a href="../reference/cdhit.html">cdhit_ccdb</a></span>(cdb, <span class="st">'cdr3_nt'</span>, <span class="dt">type =</span> <span class="st">'DNA'</span>, <span class="dt">cluster_name =</span> <span class="st">'DNA97'</span>, <span class="dt">identity =</span> <span class="fl">.965</span>, <span class="dt">min_length =</span> MIN_CDR3_AA<span class="op">*</span><span class="dv">3-1</span>, <span class="dt">G =</span> <span class="dv">1</span>)</a>

+<div class="sourceCode" id="cb5"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb5-1" data-line-number="1">cdb =<span class="st"> </span><span class="kw"><a href="../reference/cdhit_ccdb.html">cdhit_ccdb</a></span>(cdb, <span class="st">'cdr3_nt'</span>, <span class="dt">type =</span> <span class="st">'DNA'</span>, <span class="dt">cluster_name =</span> <span class="st">'DNA97'</span>, <span class="dt">identity =</span> <span class="fl">.965</span>, <span class="dt">min_length =</span> MIN_CDR3_AA<span class="op">*</span><span class="dv">3-1</span>, <span class="dt">G =</span> <span class="dv">1</span>)</a>

 <a class="sourceLine" id="cb5-2" data-line-number="2">cdb =<span class="st"> </span><span class="kw"><a href="../reference/fine_clustering.html">fine_clustering</a></span>(cdb, <span class="dt">sequence_key =</span> <span class="st">'cdr3_nt'</span>, <span class="dt">type =</span> <span class="st">'DNA'</span>)</a>

 <a class="sourceLine" id="cb5-3" data-line-number="3"><span class="co">#&gt; Calculating intradistances on 1342 clusters.</span></a>

 <a class="sourceLine" id="cb5-4" data-line-number="4"><span class="co">#&gt; Summarizing</span></a>

@@ -163,7 +163,7 @@

 <div id="cluster-by-v-j-identity" class="section level1">

 <h1 class="hasAnchor">

 <a href="#cluster-by-v-j-identity" class="anchor"></a>Cluster by V-J identity</h1>

-<div class="sourceCode" id="cb6"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb6-1" data-line-number="1">germline_cluster =<span class="st"> </span>CellaRepertorium<span class="op">:::</span><span class="kw"><a href="../reference/cluster_germline.html">cluster_germline</a></span>(cdb, <span class="dt">segment_keys =</span> <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(<span class="st">'v_gene'</span>, <span class="st">'j_gene'</span>, <span class="st">'chain'</span>), <span class="dt">cluster_name =</span> <span class="st">'segment_idx'</span>)</a>

+<div class="sourceCode" id="cb6"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb6-1" data-line-number="1">germline_cluster =<span class="st"> </span><span class="kw"><a href="../reference/cluster_germline.html">cluster_germline</a></span>(cdb, <span class="dt">segment_keys =</span> <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(<span class="st">'v_gene'</span>, <span class="st">'j_gene'</span>, <span class="st">'chain'</span>), <span class="dt">cluster_name =</span> <span class="st">'segment_idx'</span>)</a>

 <a class="sourceLine" id="cb6-2" data-line-number="2"><span class="co">#&gt; Warning in replace_cluster_tbl(ccdb, cluster_tbl, cl_con_tbl, cluster_pk =</span></a>

 <a class="sourceLine" id="cb6-3" data-line-number="3"><span class="co">#&gt; cluster_name): Replacing `cluster_tbl` with DNA97, .</span></a></code></pre></div>

 <p>We can cluster by any other feature of the contigs. Here we cluster each contig based on the chain and V-J genes. This gives us the set of observed V-J pairings:</p>

@@ -178,53 +178,26 @@

 <p>Number of pairs</p>

 <div class="sourceCode" id="cb8"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb8-1" data-line-number="1"><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot.html">ggplot</a></span>(germline_cluster<span class="op">$</span>cluster_tbl <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(chain <span class="op">==</span><span class="st"> 'TRB'</span>), <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">x =</span> v_gene, <span class="dt">y =</span> j_gene, <span class="dt">fill =</span> avg_distance)) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/geom_tile.html">geom_tile</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/theme.html">theme</a></span>(<span class="dt">axis.text.x =</span> <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/element.html">element_text</a></span>(<span class="dt">angle =</span> <span class="dv">90</span>))</a></code></pre></div>

 <p><img src="cdr3_clustering_files/figure-html/unnamed-chunk-8-1.png" width="700"></p>

-<p>Average Levenstein distance of CDR3 within each pair</p>

+<p>Average Levenstein distance of CDR3 within each pair. This might be turned into a z-score by fitting a weighted linear model with sum-to-zero contrasts and returning the pearson residuals. This could determine if a pairing has an unexpected small, or large, within cluster distance.</p>

 </div>

-<div id="some-simple-phylogenetic-relationship" class="section level1">

+<div id="oligo-clusters" class="section level1">

 <h1 class="hasAnchor">

-<a href="#some-simple-phylogenetic-relationship" class="anchor"></a>Some simple phylogenetic relationship</h1>

-<div class="sourceCode" id="cb9"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb9-1" data-line-number="1"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/library">library</a></span>(ggdendro)</a>

-<a class="sourceLine" id="cb9-2" data-line-number="2"></a>

-<a class="sourceLine" id="cb9-3" data-line-number="3"><span class="co"># This should be turned into a function in the package somehow</span></a>

-<a class="sourceLine" id="cb9-4" data-line-number="4"><span class="co"># But plot arguments will be super-variable</span></a>

-<a class="sourceLine" id="cb9-5" data-line-number="5"><span class="co"># Maybe just return the `hc` object?</span></a>

-<a class="sourceLine" id="cb9-6" data-line-number="6">dendro_plot =<span class="st"> </span><span class="cf">function</span>(ccdb, idx, <span class="dt">method =</span> <span class="st">'complete'</span>){</a>

-<a class="sourceLine" id="cb9-7" data-line-number="7">    h =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(ccdb<span class="op">$</span>cluster_tbl, <span class="op">!!</span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/tidyeval.html">sym</a></span>(ccdb<span class="op">$</span>cluster_pk) <span class="op">==</span><span class="st"> </span>idx) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/pull.html">pull</a></span>(fc) <span class="op">%&gt;%</span><span class="st"> </span>.[[<span class="dv">1</span>]]</a>

-<a class="sourceLine" id="cb9-8" data-line-number="8">    quer =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(ccdb<span class="op">$</span>contig_tbl, <span class="op">!!</span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/tidyeval.html">sym</a></span>(ccdb<span class="op">$</span>cluster_pk) <span class="op">==</span><span class="st"> </span>idx)</a>

-<a class="sourceLine" id="cb9-9" data-line-number="9">    hc =<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/stats/topics/hclust">hclust</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/stats/topics/dist">as.dist</a></span>(h<span class="op">$</span>distance_mat), <span class="dt">method =</span> method) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/ggdendro/topics/dendro_data">dendro_data</a></span>(<span class="dt">type =</span> <span class="st">"rectangle"</span>)</a>

-<a class="sourceLine" id="cb9-10" data-line-number="10">    hc<span class="op">$</span>labels =<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/cbind">cbind</a></span>(hc<span class="op">$</span>labels, quer)</a>

-<a class="sourceLine" id="cb9-11" data-line-number="11">   <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot.html">ggplot</a></span>(hc<span class="op">$</span>segments, <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">x=</span>x, <span class="dt">y=</span>y)) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/geom_segment.html">geom_segment</a></span>(<span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">xend=</span>xend, <span class="dt">yend=</span>yend)) <span class="op">+</span><span class="st"> </span></a>

-<a class="sourceLine" id="cb9-12" data-line-number="12"><span class="st">  </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggtheme.html">theme_classic</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/geom_text.html">geom_text</a></span>(<span class="dt">data =</span> hc<span class="op">$</span>labels, <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">color =</span> sample, <span class="dt">label =</span> fancy_name), <span class="dt">size =</span> <span class="dv">3</span>, <span class="dt">angle =</span> <span class="dv">60</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/scale_continuous.html">scale_x_continuous</a></span>(<span class="dt">breaks =</span> <span class="ot">NULL</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/labs.html">ylab</a></span>(<span class="st">'AA Distance'</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/labs.html">xlab</a></span>(<span class="st">''</span>)</a>

-<a class="sourceLine" id="cb9-13" data-line-number="13">}</a>

-<a class="sourceLine" id="cb9-14" data-line-number="14"></a>

-<a class="sourceLine" id="cb9-15" data-line-number="15">MIN_OLIGO =<span class="st"> </span><span class="dv">7</span></a>

-<a class="sourceLine" id="cb9-16" data-line-number="16">to_plot =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(aa80<span class="op">$</span>cluster_tbl, n_cluster <span class="op">&gt;=</span><span class="st"> </span>MIN_OLIGO)</a>

-<a class="sourceLine" id="cb9-17" data-line-number="17"></a>

-<a class="sourceLine" id="cb9-18" data-line-number="18"><span class="kw"><a href="https://purrr.tidyverse.org/reference/map.html">map</a></span>(to_plot<span class="op">$</span>aa80, <span class="op">~</span><span class="st"> </span><span class="kw">dendro_plot</span>(aa80, .))</a>

-<a class="sourceLine" id="cb9-19" data-line-number="19"><span class="co">#&gt; [[1]]</span></a></code></pre></div>

-<p><img src="cdr3_clustering_files/figure-html/unnamed-chunk-9-1.png" width="700"></p>

-<pre><code>#&gt; 

-#&gt; [[2]]</code></pre>

-<p><img src="cdr3_clustering_files/figure-html/unnamed-chunk-9-2.png" width="700"></p>

-<pre><code>#&gt; 

-#&gt; [[3]]</code></pre>

-<p><img src="cdr3_clustering_files/figure-html/unnamed-chunk-9-3.png" width="700"></p>

-<pre><code>#&gt; 

-#&gt; [[4]]</code></pre>

-<p><img src="cdr3_clustering_files/figure-html/unnamed-chunk-9-4.png" width="700"></p>

-<div class="sourceCode" id="cb13"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb13-1" data-line-number="1">aa80 =<span class="st"> </span><span class="kw"><a href="../reference/canonicalize_cluster.html">canonicalize_cluster</a></span>(aa80, <span class="dt">representative =</span> <span class="st">'cdr3'</span>, <span class="dt">contig_fields =</span> <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(<span class="st">'cdr3'</span>, <span class="st">'cdr3_nt'</span>, <span class="st">'chain'</span>, <span class="st">'v_gene'</span>, <span class="st">'d_gene'</span>, <span class="st">'j_gene'</span>))</a></code></pre></div>

-<p>Pull the fields listed in <code>contig_fields</code> into the <code>cluster_tbl</code>, using the values found in the medoid contig</p>

-<div class="sourceCode" id="cb14"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb14-1" data-line-number="1">oligo_clusters =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(aa80<span class="op">$</span>cluster_tbl, n_cluster <span class="op">&gt;=</span><span class="st"> </span>MIN_OLIGO)</a>

-<a class="sourceLine" id="cb14-2" data-line-number="2">oligo_contigs =<span class="st"> </span>aa80</a>

-<a class="sourceLine" id="cb14-3" data-line-number="3">oligo_contigs<span class="op">$</span>contig_tbl =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/join.html">semi_join</a></span>(oligo_contigs<span class="op">$</span>contig_tbl, oligo_clusters, <span class="dt">by =</span> <span class="st">'aa80'</span>)</a>

-<a class="sourceLine" id="cb14-4" data-line-number="4">oligo_contigs</a>

-<a class="sourceLine" id="cb14-5" data-line-number="5"><span class="co">#&gt; ContigCellDB of 54 contigs; 54 cells; and 4 clusters.</span></a>

-<a class="sourceLine" id="cb14-6" data-line-number="6"><span class="co">#&gt; Contigs keyed by barcode, pop, sample, contig_id; cells keyed by barcode, pop, sample.</span></a></code></pre></div>

+<a href="#oligo-clusters" class="anchor"></a>Oligo clusters</h1>

+<p>Next, we will examine the clusters that are found in many contigs. First we will get a canonical contig to represent each cluster. This will be the medoid contig, by default.</p>

+<div class="sourceCode" id="cb9"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb9-1" data-line-number="1">aa80 =<span class="st"> </span><span class="kw"><a href="../reference/canonicalize_cluster.html">canonicalize_cluster</a></span>(aa80, <span class="dt">representative =</span> <span class="st">'cdr3'</span>, <span class="dt">contig_fields =</span> <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(<span class="st">'cdr3'</span>, <span class="st">'cdr3_nt'</span>, <span class="st">'chain'</span>, <span class="st">'v_gene'</span>, <span class="st">'d_gene'</span>, <span class="st">'j_gene'</span>))</a></code></pre></div>

+<p><code>aa80</code> now includes the fields listed in <code>contig_fields</code> in the <code>cluster_tbl</code>, using the values found in the medoid contig.</p>

+<div class="sourceCode" id="cb10"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb10-1" data-line-number="1">MIN_OLIGO =<span class="st"> </span><span class="dv">7</span></a>

+<a class="sourceLine" id="cb10-2" data-line-number="2">oligo_clusters =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(aa80<span class="op">$</span>cluster_tbl, n_cluster <span class="op">&gt;=</span><span class="st"> </span>MIN_OLIGO)</a>

+<a class="sourceLine" id="cb10-3" data-line-number="3">oligo_contigs =<span class="st"> </span>aa80</a>

+<a class="sourceLine" id="cb10-4" data-line-number="4">oligo_contigs<span class="op">$</span>contig_tbl =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/join.html">semi_join</a></span>(oligo_contigs<span class="op">$</span>contig_tbl, oligo_clusters, <span class="dt">by =</span> <span class="st">'aa80'</span>)</a>

+<a class="sourceLine" id="cb10-5" data-line-number="5">oligo_contigs</a>

+<a class="sourceLine" id="cb10-6" data-line-number="6"><span class="co">#&gt; ContigCellDB of 54 contigs; 54 cells; and 4 clusters.</span></a>

+<a class="sourceLine" id="cb10-7" data-line-number="7"><span class="co">#&gt; Contigs keyed by barcode, pop, sample, contig_id; cells keyed by barcode, pop, sample.</span></a></code></pre></div>

 <p>Get contigs/cells/clusters found at least 7 times (across contigs). Note that replacing <code>contig_tbl</code> with the subset selected with the <code>semi_join</code> also automatically subsetted the <code>cell_tbl</code> and <code>cluster_tbl</code>.</p>

-<div class="sourceCode" id="cb15"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb15-1" data-line-number="1">oligo_clusters =<span class="st"> </span>oligo_contigs<span class="op">$</span>contig_tbl <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/group_by.html">group_by</a></span>(aa80) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/summarise.html">summarize</a></span>(<span class="st">`</span><span class="dt">n subjects observed</span><span class="st">`</span> =<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/length">length</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/unique">unique</a></span>(sample))) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/join.html">left_join</a></span>(oligo_clusters)</a>

-<a class="sourceLine" id="cb15-2" data-line-number="2"><span class="co">#&gt; Joining, by = "aa80"</span></a>

-<a class="sourceLine" id="cb15-3" data-line-number="3"></a>

-<a class="sourceLine" id="cb15-4" data-line-number="4">knitr<span class="op">::</span><span class="kw"><a href="https://www.rdocumentation.org/packages/knitr/topics/kable">kable</a></span>(oligo_clusters <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/select.html">select</a></span>(aa80<span class="op">:</span>cdr3, chain<span class="op">:</span>j_gene, avg_distance, n_cluster))</a></code></pre></div>

+<div class="sourceCode" id="cb11"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb11-1" data-line-number="1">oligo_clusters =<span class="st"> </span>oligo_contigs<span class="op">$</span>contig_tbl <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/group_by.html">group_by</a></span>(aa80) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/summarise.html">summarize</a></span>(<span class="st">`</span><span class="dt">n subjects observed</span><span class="st">`</span> =<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/length">length</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/unique">unique</a></span>(sample))) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/join.html">left_join</a></span>(oligo_clusters)</a>

+<a class="sourceLine" id="cb11-2" data-line-number="2"><span class="co">#&gt; Joining, by = "aa80"</span></a>

+<a class="sourceLine" id="cb11-3" data-line-number="3"></a>

+<a class="sourceLine" id="cb11-4" data-line-number="4">knitr<span class="op">::</span><span class="kw"><a href="https://www.rdocumentation.org/packages/knitr/topics/kable">kable</a></span>(oligo_clusters <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/select.html">select</a></span>(aa80<span class="op">:</span>cdr3, chain<span class="op">:</span>j_gene, avg_distance, n_cluster))</a></code></pre></div>

 <table class="table">

 <thead><tr class="header">

 <th align="right">aa80</th>

@@ -285,21 +258,48 @@

 </tbody>

 </table>

 <p>Report some statistics about these expanded clusters.</p>

-</div>

-<div id="oligo-clusters" class="section level1">

-<h1 class="hasAnchor">

-<a href="#oligo-clusters" class="anchor"></a>Oligo clusters</h1>

-<div class="sourceCode" id="cb16"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb16-1" data-line-number="1">oligo_plot =<span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot.html">ggplot</a></span>(oligo_contigs<span class="op">$</span>contig_tbl, <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">x =</span> representative, <span class="dt">fill =</span> chain)) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/geom_bar.html">geom_bar</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/coord_flip.html">coord_flip</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/scale_brewer.html">scale_fill_brewer</a></span>(<span class="dt">type =</span> <span class="st">'qual'</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggtheme.html">theme_minimal</a></span>()</a>

-<a class="sourceLine" id="cb16-2" data-line-number="2">oligo_plot</a></code></pre></div>

-<p><img src="cdr3_clustering_files/figure-html/unnamed-chunk-13-1.png" width="700"></p>

+<div class="sourceCode" id="cb12"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb12-1" data-line-number="1">oligo_plot =<span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot.html">ggplot</a></span>(oligo_contigs<span class="op">$</span>contig_tbl, <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">x =</span> representative, <span class="dt">fill =</span> chain)) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/geom_bar.html">geom_bar</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/coord_flip.html">coord_flip</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/scale_brewer.html">scale_fill_brewer</a></span>(<span class="dt">type =</span> <span class="st">'qual'</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggtheme.html">theme_minimal</a></span>()</a>

+<a class="sourceLine" id="cb12-2" data-line-number="2">oligo_plot</a></code></pre></div>

+<p><img src="cdr3_clustering_files/figure-html/unnamed-chunk-12-1.png" width="700"></p>

 <p>These always come from a single chain.</p>

-<div class="sourceCode" id="cb17"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb17-1" data-line-number="1">oligo_plot <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">fill =</span>   sample) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/facet_wrap.html">facet_wrap</a></span>(<span class="op">~</span>pop)</a></code></pre></div>

-<p><img src="cdr3_clustering_files/figure-html/unnamed-chunk-14-1.png" width="700"></p>

+<div class="sourceCode" id="cb13"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb13-1" data-line-number="1">oligo_plot <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">fill =</span>   sample) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/facet_wrap.html">facet_wrap</a></span>(<span class="op">~</span>pop)</a></code></pre></div>

+<p><img src="cdr3_clustering_files/figure-html/unnamed-chunk-13-1.png" width="700"></p>

 <p>But come from multiple populations and samples.</p>

+<div id="some-simple-phylogenetic-relationships" class="section level2">

+<h2 class="hasAnchor">

+<a href="#some-simple-phylogenetic-relationships" class="anchor"></a>Some simple phylogenetic relationships</h2>

+<div class="sourceCode" id="cb14"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb14-1" data-line-number="1"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/library">library</a></span>(ggdendro)</a>

+<a class="sourceLine" id="cb14-2" data-line-number="2"></a>

+<a class="sourceLine" id="cb14-3" data-line-number="3"><span class="co"># This should be turned into a function in the package somehow</span></a>

+<a class="sourceLine" id="cb14-4" data-line-number="4"><span class="co"># But plot arguments will be super-variable</span></a>

+<a class="sourceLine" id="cb14-5" data-line-number="5"><span class="co"># Maybe just return the `hc` object?</span></a>

+<a class="sourceLine" id="cb14-6" data-line-number="6">dendro_plot =<span class="st"> </span><span class="cf">function</span>(ccdb, idx, <span class="dt">method =</span> <span class="st">'complete'</span>){</a>

+<a class="sourceLine" id="cb14-7" data-line-number="7">    h =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(ccdb<span class="op">$</span>cluster_tbl, <span class="op">!!</span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/tidyeval.html">sym</a></span>(ccdb<span class="op">$</span>cluster_pk) <span class="op">==</span><span class="st"> </span>idx) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/pull.html">pull</a></span>(fc) <span class="op">%&gt;%</span><span class="st"> </span>.[[<span class="dv">1</span>]]</a>

+<a class="sourceLine" id="cb14-8" data-line-number="8">    quer =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(ccdb<span class="op">$</span>contig_tbl, <span class="op">!!</span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/tidyeval.html">sym</a></span>(ccdb<span class="op">$</span>cluster_pk) <span class="op">==</span><span class="st"> </span>idx)</a>

+<a class="sourceLine" id="cb14-9" data-line-number="9">    hc =<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/stats/topics/hclust">hclust</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/stats/topics/dist">as.dist</a></span>(h<span class="op">$</span>distance_mat), <span class="dt">method =</span> method) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/ggdendro/topics/dendro_data">dendro_data</a></span>(<span class="dt">type =</span> <span class="st">"rectangle"</span>)</a>

+<a class="sourceLine" id="cb14-10" data-line-number="10">    hc<span class="op">$</span>labels =<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/cbind">cbind</a></span>(hc<span class="op">$</span>labels, quer)</a>

+<a class="sourceLine" id="cb14-11" data-line-number="11">   <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot.html">ggplot</a></span>(hc<span class="op">$</span>segments, <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">x=</span>x, <span class="dt">y=</span>y)) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/geom_segment.html">geom_segment</a></span>(<span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">xend=</span>xend, <span class="dt">yend=</span>yend)) <span class="op">+</span><span class="st"> </span></a>

+<a class="sourceLine" id="cb14-12" data-line-number="12"><span class="st">  </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggtheme.html">theme_classic</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/geom_text.html">geom_text</a></span>(<span class="dt">data =</span> hc<span class="op">$</span>labels, <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">color =</span> sample, <span class="dt">label =</span> fancy_name), <span class="dt">size =</span> <span class="dv">3</span>, <span class="dt">angle =</span> <span class="dv">60</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/scale_continuous.html">scale_x_continuous</a></span>(<span class="dt">breaks =</span> <span class="ot">NULL</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/labs.html">ylab</a></span>(<span class="st">'AA Distance'</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/labs.html">xlab</a></span>(<span class="st">''</span>)</a>

+<a class="sourceLine" id="cb14-13" data-line-number="13">}</a>

+<a class="sourceLine" id="cb14-14" data-line-number="14"></a>

+<a class="sourceLine" id="cb14-15" data-line-number="15">to_plot =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(aa80<span class="op">$</span>cluster_tbl, n_cluster <span class="op">&gt;=</span><span class="st"> </span>MIN_OLIGO)</a>

+<a class="sourceLine" id="cb14-16" data-line-number="16"></a>

+<a class="sourceLine" id="cb14-17" data-line-number="17"><span class="kw"><a href="https://purrr.tidyverse.org/reference/map.html">map</a></span>(to_plot<span class="op">$</span>aa80, <span class="op">~</span><span class="st"> </span><span class="kw">dendro_plot</span>(aa80, .))</a>

+<a class="sourceLine" id="cb14-18" data-line-number="18"><span class="co">#&gt; [[1]]</span></a></code></pre></div>

+<p><img src="cdr3_clustering_files/figure-html/unnamed-chunk-14-1.png" width="700"></p>

+<pre><code>#&gt; 

+#&gt; [[2]]</code></pre>

+<p><img src="cdr3_clustering_files/figure-html/unnamed-chunk-14-2.png" width="700"></p>

+<pre><code>#&gt; 

+#&gt; [[3]]</code></pre>

+<p><img src="cdr3_clustering_files/figure-html/unnamed-chunk-14-3.png" width="700"></p>

+<pre><code>#&gt; 

+#&gt; [[4]]</code></pre>

+<p><img src="cdr3_clustering_files/figure-html/unnamed-chunk-14-4.png" width="700"></p>

 </div>

-<div id="formal-testing-for-frequency-differences" class="section level1">

-<h1 class="hasAnchor">

-<a href="#formal-testing-for-frequency-differences" class="anchor"></a>Formal testing for frequency differences</h1>

+<div id="formal-testing-for-frequency-differences" class="section level2">

+<h2 class="hasAnchor">

+<a href="#formal-testing-for-frequency-differences" class="anchor"></a>Formal testing for frequency differences</h2>

 <div class="sourceCode" id="cb18"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb18-1" data-line-number="1"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/library">library</a></span>(lme4)</a>

 <a class="sourceLine" id="cb18-2" data-line-number="2"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/library">library</a></span>(broom)</a>

 <a class="sourceLine" id="cb18-3" data-line-number="3">per_chain_sample =<span class="st"> </span>good_cluster_cells <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/group_by.html">group_by</a></span>(sample, pop, chain) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/summarise.html">summarize</a></span>(<span class="dt">total_cells =</span> <span class="kw"><a href="https://dplyr.tidyverse.org/reference/n.html">n</a></span>(), <span class="dt">weeks_premature =</span> weeks_premature[<span class="dv">1</span>])</a>

@@ -316,9 +316,11 @@

 <a class="sourceLine" id="cb19-3" data-line-number="3"><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot.html">ggplot</a></span>(mm_outj, <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">x =</span> representative, <span class="dt">ymin =</span> ci_lo, <span class="dt">ymax =</span> ci_hi, <span class="dt">y =</span> <span class="kw">clamp</span>(estimate))) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/geom_linerange.html">geom_pointrange</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/facet_wrap.html">facet_wrap</a></span>(<span class="op">~</span>term, <span class="dt">scales =</span> <span class="st">'free'</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/coord_flip.html">coord_flip</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggtheme.html">theme_minimal</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/geom_abline.html">geom_hline</a></span>(<span class="dt">yintercept =</span> <span class="dv">0</span>, <span class="dt">lty =</span> <span class="dv">2</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/labs.html">xlab</a></span>(<span class="st">"Isomorph"</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/labs.html">ylab</a></span>(<span class="st">"log odds of isomorph"</span>)</a></code></pre></div>

 <p>We test if the binomial rate of clone expression differs between CD31+/- or term, for each clone.</p>

 </div>

+</div>

 <div id="clonal-pairs" class="section level1">

 <h1 class="hasAnchor">

 <a href="#clonal-pairs" class="anchor"></a>Clonal pairs</h1>

+<p>Next, we can examine the pairing between <span class="math inline">\(\alpha-\beta\)</span> chains and see if any pairs are found more than once.</p>

 <div class="sourceCode" id="cb20"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb20-1" data-line-number="1">class_colors =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/reexports.html">tibble</a></span>(<span class="dt">chain =</span>  <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/unique">unique</a></span>(aa80<span class="op">$</span>cluster_tbl<span class="op">$</span>chain)) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/mutate.html">mutate</a></span>(<span class="dt">class_color =</span>  RColorBrewer<span class="op">::</span><span class="kw"><a href="https://www.rdocumentation.org/packages/RColorBrewer/topics/ColorBrewer">brewer.pal</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/length">length</a></span>(chain),<span class="st">"Set1"</span>)[<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/seq">seq_along</a></span>(chain)])</a>

 <a class="sourceLine" id="cb20-2" data-line-number="2"><span class="co">#&gt; Warning in RColorBrewer::brewer.pal(length(chain), "Set1"): minimal value for n is 3, returning requested palette with 3 different levels</span></a>

 <a class="sourceLine" id="cb20-3" data-line-number="3"></a>

@@ -328,6 +330,7 @@

 <a class="sourceLine" id="cb20-7" data-line-number="7"><span class="co">#&gt; `forcats::fct_explicit_na`</span></a>

 <a class="sourceLine" id="cb20-8" data-line-number="8"><span class="co">#&gt; Warning: Column `representative` joining factors with different levels,</span></a>

 <a class="sourceLine" id="cb20-9" data-line-number="9"><span class="co">#&gt; coercing to character vector</span></a></code></pre></div>

+<p><code>pairing_tables</code> finds all contig combinations of order <code>table_order</code> across cells. Among those combinations that occur at least <code>min_expansion</code> times, the expanded combinations and and any other combinations that shared an expanded combo.</p>

 <div class="sourceCode" id="cb21"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb21-1" data-line-number="1">pairs_plt =<span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot.html">ggplot</a></span>(pairing_list<span class="op">$</span>cell_tbl, <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">x =</span> cluster_idx<span class="fl">.1</span>_fct, <span class="dt">y =</span> cluster_idx<span class="fl">.2</span>_fct, <span class="dt">color =</span> sample, <span class="dt">shape =</span> pop)) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/geom_jitter.html">geom_jitter</a></span>(<span class="dt">width =</span> <span class="fl">.2</span>, <span class="dt">height =</span> <span class="fl">.2</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggtheme.html">theme_minimal</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/labs.html">xlab</a></span>(<span class="st">'TRB'</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/labs.html">ylab</a></span>(<span class="st">'TRA'</span>)</a>

 <a class="sourceLine" id="cb21-2" data-line-number="2"></a>

 <a class="sourceLine" id="cb21-3" data-line-number="3">feature_tbl =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/join.html">left_join</a></span>(<span class="kw"><a href="https://dplyr.tidyverse.org/reference/bind.html">bind_rows</a></span>(pairing_list<span class="op">$</span>idx1_tbl, pairing_list<span class="op">$</span>idx2_tbl), class_colors)</a>

@@ -352,18 +355,20 @@

 <div id="expanded-clones" class="section level2">

 <h2 class="hasAnchor">

 <a href="#expanded-clones" class="anchor"></a>Expanded clones</h2>

-<div class="sourceCode" id="cb22"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb22-1" data-line-number="1">pairing_list =<span class="st"> </span><span class="kw"><a href="../reference/pairing_tables.html">pairing_tables</a></span>(oligo_clusters_all <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/select.html">select</a></span>(representative, dataset, barcode, chain, umis, reads), <span class="dt">cluster_idx =</span> <span class="st">'representative'</span>, <span class="dt">cell_identifiers =</span> <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(<span class="st">'dataset'</span>, <span class="st">'barcode'</span>), <span class="dt">canonicalize_fun =</span> canonicalize_by_prevalence, <span class="dt">table_order =</span> <span class="dv">2</span>, <span class="dt">orphan_level =</span> <span class="dv">1</span>, <span class="dt">min_expansion =</span> <span class="dv">4</span>, <span class="dt">feature_tbl =</span> feature_tbl, <span class="dt">cell_tbl =</span> good_cells, <span class="dt">cluster_whitelist =</span> <span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(oligo_clusters, n_cluster<span class="op">&gt;</span><span class="dv">8</span>) <span class="op">%&gt;%</span><span class="st"> </span>dplyr<span class="op">::</span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/select.html">select</a></span>(<span class="dt">cluster_idx.1 =</span> representative) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/unique">unique</a></span>())</a>

-<a class="sourceLine" id="cb22-2" data-line-number="2">pairs_plt =<span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot.html">ggplot</a></span>(pairing_list<span class="op">$</span>cell_tbl, <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">x =</span> cluster_idx<span class="fl">.1</span>_fct, <span class="dt">y =</span> cluster_idx<span class="fl">.2</span>_fct, <span class="dt">color =</span> sample, <span class="dt">shape =</span> pop)) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/geom_jitter.html">geom_jitter</a></span>(<span class="dt">width =</span> <span class="fl">.2</span>, <span class="dt">height =</span> <span class="fl">.2</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggtheme.html">theme_minimal</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/labs.html">xlab</a></span>(<span class="st">'TRB'</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/labs.html">ylab</a></span>(<span class="st">'TRA'</span>)</a>

-<a class="sourceLine" id="cb22-3" data-line-number="3"></a>

-<a class="sourceLine" id="cb22-4" data-line-number="4">feature_tbl =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/join.html">left_join</a></span>(<span class="kw"><a href="https://dplyr.tidyverse.org/reference/bind.html">bind_rows</a></span>(pairing_list<span class="op">$</span>idx1_tbl, pairing_list<span class="op">$</span>idx2_tbl), class_colors)</a>

-<a class="sourceLine" id="cb22-5" data-line-number="5"></a>

-<a class="sourceLine" id="cb22-6" data-line-number="6">ylab =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/reexports.html">data_frame</a></span>(<span class="dt">representative =</span>  <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot_build.html">ggplot_build</a></span>(pairs_plt)<span class="op">$</span>layout<span class="op">$</span>panel_params[[<span class="dv">1</span>]]<span class="op">$</span>y.label) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/join.html">left_join</a></span>(feature_tbl) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/mutate.html">mutate</a></span>(<span class="dt">class_color =</span> <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/ifelse">ifelse</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/NA">is.na</a></span>(class_color), <span class="st">'#E41A1C'</span>, class_color))</a>

-<a class="sourceLine" id="cb22-7" data-line-number="7"></a>

-<a class="sourceLine" id="cb22-8" data-line-number="8">xlab =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/reexports.html">data_frame</a></span>(<span class="dt">representative =</span>  <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot_build.html">ggplot_build</a></span>(pairs_plt)<span class="op">$</span>layout<span class="op">$</span>panel_params[[<span class="dv">1</span>]]<span class="op">$</span>x.label) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/join.html">left_join</a></span>(feature_tbl) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/mutate.html">mutate</a></span>(<span class="dt">class_color =</span> <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/ifelse">ifelse</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/NA">is.na</a></span>(class_color), <span class="st">'#E41A1C'</span>, class_color))</a>

-<a class="sourceLine" id="cb22-9" data-line-number="9"></a>

-<a class="sourceLine" id="cb22-10" data-line-number="10">pairs_plt =<span class="st"> </span>pairs_plt <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/theme.html">theme</a></span>(<span class="dt">axis.text.x =</span> <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/element.html">element_text</a></span>(<span class="dt">angle =</span> <span class="dv">90</span>, <span class="dt">color =</span> xlab<span class="op">$</span>class_color, <span class="dt">size =</span> <span class="dv">8</span>), <span class="dt">axis.text.y =</span> <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/element.html">element_text</a></span>(<span class="dt">color =</span> ylab<span class="op">$</span>class_color, <span class="dt">size =</span> <span class="dv">8</span>))</a>

-<a class="sourceLine" id="cb22-11" data-line-number="11"></a>

-<a class="sourceLine" id="cb22-12" data-line-number="12">pairs_plt</a></code></pre></div>

+<div class="sourceCode" id="cb22"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb22-1" data-line-number="1">whitelist =<span class="st"> </span>oligo_clusters <span class="op">%&gt;%</span><span class="st"> </span>dplyr<span class="op">::</span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/select.html">select</a></span>(<span class="dt">cluster_idx.1 =</span> representative) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/unique">unique</a></span>()</a>

+<a class="sourceLine" id="cb22-2" data-line-number="2">pairing_list =<span class="st"> </span><span class="kw"><a href="../reference/pairing_tables.html">pairing_tables</a></span>(aa80, <span class="dt">canonicalize_fun =</span> canonicalize_by_prevalence, <span class="dt">table_order =</span> <span class="dv">2</span>, <span class="dt">orphan_level =</span> <span class="dv">1</span>, <span class="dt">min_expansion =</span> <span class="ot">Inf</span>, <span class="dt">cluster_whitelist =</span> whitelist,  <span class="dt">cluster_keys =</span> <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(<span class="st">'cdr3'</span>, <span class="st">'representative'</span>, <span class="st">'chain'</span>, <span class="st">'v_gene'</span>, <span class="st">'j_gene'</span>, <span class="st">'avg_distance'</span>))</a>

+<a class="sourceLine" id="cb22-3" data-line-number="3">pairs_plt =<span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot.html">ggplot</a></span>(pairing_list<span class="op">$</span>cell_tbl, <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">x =</span> cluster_idx<span class="fl">.1</span>_fct, <span class="dt">y =</span> cluster_idx<span class="fl">.2</span>_fct, <span class="dt">color =</span> sample, <span class="dt">shape =</span> pop)) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/geom_jitter.html">geom_jitter</a></span>(<span class="dt">width =</span> <span class="fl">.2</span>, <span class="dt">height =</span> <span class="fl">.2</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggtheme.html">theme_minimal</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/labs.html">xlab</a></span>(<span class="st">'TRB'</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/labs.html">ylab</a></span>(<span class="st">'TRA'</span>)</a>

+<a class="sourceLine" id="cb22-4" data-line-number="4"></a>

+<a class="sourceLine" id="cb22-5" data-line-number="5">feature_tbl =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/join.html">left_join</a></span>(<span class="kw"><a href="https://dplyr.tidyverse.org/reference/bind.html">bind_rows</a></span>(pairing_list<span class="op">$</span>idx1_tbl, pairing_list<span class="op">$</span>idx2_tbl), class_colors)</a>

+<a class="sourceLine" id="cb22-6" data-line-number="6"></a>

+<a class="sourceLine" id="cb22-7" data-line-number="7">ylab =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/reexports.html">data_frame</a></span>(<span class="dt">representative =</span>  <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot_build.html">ggplot_build</a></span>(pairs_plt)<span class="op">$</span>layout<span class="op">$</span>panel_params[[<span class="dv">1</span>]]<span class="op">$</span>y.label) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/join.html">left_join</a></span>(feature_tbl) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/mutate.html">mutate</a></span>(<span class="dt">class_color =</span> <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/ifelse">ifelse</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/NA">is.na</a></span>(class_color), <span class="st">'#E41A1C'</span>, class_color))</a>

+<a class="sourceLine" id="cb22-8" data-line-number="8"></a>

+<a class="sourceLine" id="cb22-9" data-line-number="9">xlab =<span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/reexports.html">data_frame</a></span>(<span class="dt">representative =</span>  <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot_build.html">ggplot_build</a></span>(pairs_plt)<span class="op">$</span>layout<span class="op">$</span>panel_params[[<span class="dv">1</span>]]<span class="op">$</span>x.label) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/join.html">left_join</a></span>(feature_tbl) <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/mutate.html">mutate</a></span>(<span class="dt">class_color =</span> <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/ifelse">ifelse</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/NA">is.na</a></span>(class_color), <span class="st">'#E41A1C'</span>, class_color))</a>

+<a class="sourceLine" id="cb22-10" data-line-number="10"></a>

+<a class="sourceLine" id="cb22-11" data-line-number="11">pairs_plt =<span class="st"> </span>pairs_plt <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/theme.html">theme</a></span>(<span class="dt">axis.text.x =</span> <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/element.html">element_text</a></span>(<span class="dt">angle =</span> <span class="dv">90</span>, <span class="dt">color =</span> xlab<span class="op">$</span>class_color, <span class="dt">size =</span> <span class="dv">8</span>), <span class="dt">axis.text.y =</span> <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/element.html">element_text</a></span>(<span class="dt">color =</span> ylab<span class="op">$</span>class_color, <span class="dt">size =</span> <span class="dv">8</span>))</a>

+<a class="sourceLine" id="cb22-12" data-line-number="12"></a>

+<a class="sourceLine" id="cb22-13" data-line-number="13">pairs_plt</a></code></pre></div>

+<p>By setting <code>min_expansion = Inf, cluster_whitelist = whitelist</code> we can examine any pairings for a set of cluster_idx, in this case the ones that were seen multiple times. Interestingly (and unlike some human samples) the expanded clusters are <span class="math inline">\(\beta\)</span>-chain, and their <span class="math inline">\(\alpha\)</span> chains are sprinkled quite evenly across clusters.</p>

 </div>

 </div>

 <div id="length-of-cdr3" class="section level1">

@@ -387,7 +392,7 @@

 <a class="sourceLine" id="cb24-12" data-line-number="12"><span class="co">#&gt; coercing into character vector</span></a>

 <a class="sourceLine" id="cb24-13" data-line-number="13"><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggplot.html">ggplot</a></span>(cdr_len <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(group <span class="op">==</span><span class="st"> 'fixed'</span>, term <span class="op">!=</span><span class="st"> '(Intercept)'</span>), <span class="kw"><a href="https://ggplot2.tidyverse.org/reference/aes.html">aes</a></span>(<span class="dt">x =</span> <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/interaction">interaction</a></span>(chain, term), <span class="dt">y =</span> estimate, <span class="dt">ymin =</span> conf.low, <span class="dt">ymax =</span> conf.high)) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/geom_linerange.html">geom_pointrange</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/ggtheme.html">theme_minimal</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/coord_flip.html">coord_flip</a></span>() <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/labs.html">ylab</a></span>(<span class="st">'Length(CDR3 Nt)'</span>) <span class="op">+</span><span class="st"> </span><span class="kw"><a href="https://ggplot2.tidyverse.org/reference/labs.html">xlab</a></span>(<span class="st">'Term/Chain'</span>)</a></code></pre></div>

 <p><img src="cdr3_clustering_files/figure-html/cdr3_len-1.png" width="288"></p>

-<p>We end up with a convergence warning. This is not a suprise, because the <code>samples</code> aren’t actually replicates – they are just subsamples drawn for illustrative purposes. The Balbc mice have .5 fewer nucleotides per contig, on average, and this is not significant.</p>

+<p>We end up with a (harmless) convergence warning about a singular fit. This is expected, because the <code>samples</code> aren’t actually replicates – they are just subsamples drawn for illustrative purposes. The Balbc mice have .5 fewer nucleotides per contig, on average, and this is not significant.</p>

 </div>

   </div>

@@ -401,9 +406,12 @@

       <li><a href="#cluster-cdr3-protein-sequences">Cluster CDR3 protein sequences</a></li>

       <li><a href="#cluster-cdr3-dna-sequences">Cluster CDR3 DNA sequences</a></li>

       <li><a href="#cluster-by-v-j-identity">Cluster by V-J identity</a></li>

-      <li><a href="#some-simple-phylogenetic-relationship">Some simple phylogenetic relationship</a></li>

-      <li><a href="#oligo-clusters">Oligo clusters</a></li>

+      <li>

+<a href="#oligo-clusters">Oligo clusters</a><ul class="nav nav-pills nav-stacked">

+<li><a href="#some-simple-phylogenetic-relationships">Some simple phylogenetic relationships</a></li>

       <li><a href="#formal-testing-for-frequency-differences">Formal testing for frequency differences</a></li>

+      </ul>

+</li>

       <li>

 <a href="#clonal-pairs">Clonal pairs</a><ul class="nav nav-pills nav-stacked">

 <li><a href="#expanded-clones">Expanded clones</a></li>

Binary files a/docs/articles/cdr3_clustering_files/figure-html/plot_expanded-1.png and b/docs/articles/cdr3_clustering_files/figure-html/plot_expanded-1.png differ

new file mode 100644

Binary files /dev/null and b/docs/articles/cdr3_clustering_files/figure-html/unnamed-chunk-12-1.png differ

Binary files a/docs/articles/cdr3_clustering_files/figure-html/unnamed-chunk-13-1.png and b/docs/articles/cdr3_clustering_files/figure-html/unnamed-chunk-13-1.png differ

Binary files a/docs/articles/cdr3_clustering_files/figure-html/unnamed-chunk-14-1.png and b/docs/articles/cdr3_clustering_files/figure-html/unnamed-chunk-14-1.png differ

new file mode 100644

Binary files /dev/null and b/docs/articles/cdr3_clustering_files/figure-html/unnamed-chunk-14-2.png differ

new file mode 100644

Binary files /dev/null and b/docs/articles/cdr3_clustering_files/figure-html/unnamed-chunk-14-3.png differ

new file mode 100644

Binary files /dev/null and b/docs/articles/cdr3_clustering_files/figure-html/unnamed-chunk-14-4.png differ

@@ -60,7 +60,7 @@

       </button>

       <span class="navbar-brand">

         <a class="navbar-link" href="../index.html">CellaRepertorium</a>

-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Released version">0.3.1</span>

+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Released version">0.3.2</span>

       </span>

     </div>

@@ -30,7 +30,7 @@

       </button>

       <span class="navbar-brand">

         <a class="navbar-link" href="../index.html">CellaRepertorium</a>

-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Released version">0.3.1</span>

+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Released version">0.3.2</span>

       </span>

     </div>

Binary files a/docs/articles/mouse_tcell_qc_files/figure-html/unnamed-chunk-5-1.png and b/docs/articles/mouse_tcell_qc_files/figure-html/unnamed-chunk-5-1.png differ

Binary files a/docs/articles/mouse_tcell_qc_files/figure-html/unnamed-chunk-5-2.png and b/docs/articles/mouse_tcell_qc_files/figure-html/unnamed-chunk-5-2.png differ

@@ -60,7 +60,7 @@

       </button>

       <span class="navbar-brand">

         <a class="navbar-link" href="index.html">CellaRepertorium</a>

-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Released version">0.3.1</span>

+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Released version">0.3.2</span>

       </span>

     </div>

@@ -37,7 +37,7 @@

       </button>

       <span class="navbar-brand">

         <a class="navbar-link" href="index.html">CellaRepertorium</a>

-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Released version">0.3.1</span>

+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Released version">0.3.2</span>

       </span>

     </div>

@@ -104,28 +104,34 @@

 <div id="data-requirements-and-package-structure" class="section level2">

 <h2 class="hasAnchor">

 <a href="#data-requirements-and-package-structure" class="anchor"></a>Data requirements and package structure</h2>

-<p>The fundamental unit this package operates on is the <strong>contig</strong>, which is a section of contiguously stitched reads from a single <strong>cell</strong>. Each contig belongs to one (and only one) cell, however, cells generate multiple contigs.</p>

-<p><img src="../../../../Box%20Sync/research/scRNAseq/CellaRepertorium/vignettes/img/contig_schematic.png"><!-- --></p>

-<p>Contigs can also belong to a <strong>cluster</strong>. Because of these two many-to-one mappings, these data can be thought as a series of ragged arrays. The links between them mean they are relational data. A <code>ContigCellDB</code> object wraps each of these objects as a sequence of three <code>data.frames</code> (well, <code>tibbles</code>, actually). <code>ContigCellDB</code> also tracks columns (the primary keys) that unique identify each row in each of these tables. The <code>contig_tbl</code> is the <code>tibble</code> containing <strong>contigs</strong>, the <code>cell_tbl</code> contains the <strong>cells</strong>, and the <code>cluster_tbl</code> contains the <strong>clusters</strong>.</p>

-<p>The <code>contig_pk</code>, <code>cell_pk</code> and <code>cluster_pk</code> identify the columns that identify a contig, cell and cluster, respectively. These will serve as foreign keys that link the three tables together. The tables are kept in sync so that subsetting the contigs will subset the cells, and clusters, and vice-versa.</p>

-<p><img src="../../../../Box%20Sync/research/scRNAseq/CellaRepertorium/vignettes/img/table_schematic.png"><!-- --></p>

-<p>Of course, each of these tables can contain many other columns that will serve as covariates for various analyses, such as the CDR3 sequence, or the identity of the V, D and J regions. Various derived quantities that describe cells and clusters can also be calculated, and added to these tables, such as the medoid of a cluster – a contig that minimizes the average distance to all other clusters.</p>

+<p>The fundamental unit this package operates on is the <strong>contig</strong>, which is a section of contiguously stitched reads from a single <strong>cell</strong>. Each contig belongs to one (and only one) cell, however, cells generate multiple contigs.<br><img src="reference/figures/contig_schematic.png"></p>

+<p>Contigs can also belong to a <strong>cluster</strong>. Because of these two many-to-one mappings, these data can be thought as a series of ragged arrays. The links between them mean they are relational data. A <code><a href="reference/ContigCellDB-fun.html">ContigCellDB()</a></code> object wraps each of these objects as a sequence of three <code>data.frames</code> (well, <code><a href="https://dplyr.tidyverse.org/reference/reexports.html">dplyr::tibble()</a></code>, actually). <code><a href="reference/ContigCellDB-fun.html">ContigCellDB()</a></code> also tracks columns (the primary keys) that unique identify each row in each of these tables. The <code>contig_tbl</code> is the <code>tibble</code> containing <strong>contigs</strong>, the <code>cell_tbl</code> contains the <strong>cells</strong>, and the <code>cluster_tbl</code> contains the <strong>clusters</strong>.</p>

+<p>The <code>contig_pk</code>, <code>cell_pk</code> and <code>cluster_pk</code> specify the columns that identify a contig, cell and cluster, respectively. These will serve as foreign keys that link the three tables together. The tables are kept in sync so that subsetting the contigs will subset the cells, and clusters, and vice-versa.</p>

+<p><img src="reference/figures/table_schematic.png"></p>

+<p>Of course, each of these tables can contain many other columns that will serve as covariates for various analyses, such as the <strong>CDR3</strong> sequence, or the identity of the <strong>V</strong>, <strong>D</strong> and <strong>J</strong> regions. Various derived quantities that describe cells and clusters can also be calculated, and added to these tables, such as the <strong>medoid</strong> of a cluster – a contig that minimizes the average distance to all other clusters.</p>

 </div>

-<div id="functions" class="section level2">

+<div id="some-functions-of-interest" class="section level2">

 <h2 class="hasAnchor">

-<a href="#functions" class="anchor"></a>Functions</h2>

+<a href="#some-functions-of-interest" class="anchor"></a>Some functions of interest</h2>

 <p>[a screencap of something interesting?]</p>

 <ul>

 <li>

-<code>cdhit_ccdb</code>: An R interface to CDhit, which was originally ported by Thomas Lin Pedersen.</li>

+<code><a href="reference/cdhit_ccdb.html">cdhit_ccdb()</a></code>: An R interface to CDhit, which was originally ported by Thomas Lin Pedersen.</li>

 <li>

-<code>fine_clustering</code>: clustering CDR3 by edit distances (possibly using empirical amino acid substitution matrices)</li>

+<code><a href="reference/fine_clustering.html">fine_clustering()</a></code>: clustering CDR3 by edit distances (possibly using empirical amino acid substitution matrices)</li>

 <li>

-<code>cluster_permute_test</code>: permutation tests of cluster statistics</li>

+<code><a href="reference/canonicalize_cell.html">canonicalize_cell()</a></code>: Return a single contig for each cell, e.g., for combining VDJ information with 5’-based single cell expressoin</li>

 <li>

-<code>pairing_tables</code>: Generate pairings of contigs within each cell in a way that they can be plotted</li>

+<code><a href="reference/cluster_permute_test.html">cluster_permute_test()</a></code>: permutation tests of cluster statistics</li>

+<li>

+<code><a href="reference/pairing_tables.html">pairing_tables()</a></code>: Generate pairings of contigs within each cell in a way that they can be plotted</li>

 </ul>

 </div>

+<div id="inferfacing-related-packages" class="section level2">

+<h2 class="hasAnchor">

+<a href="#inferfacing-related-packages" class="anchor"></a>Inferfacing Related packages</h2>

+<p>To combine repertoire information with expression of endogenuous mRNAs have been measured, this package has been used with <code><a href="https://www.rdocumentation.org/packages/SingleCellExperiment/topics/SingleCellExperiment">SingleCellExperiment::SingleCellExperiment()</a></code> and (<code>Seurat</code>)[<a href="https://satijalab.org/seurat/" class="uri">https://satijalab.org/seurat/</a>] after generating various cell canonicalizations. Many tools from <a href="https://alakazam.readthedocs.io/en/version-0.2.11/"><code>Immcantation</code></a> work directly on <code><a href="reference/ContigCellDB-fun.html">ContigCellDB()</a></code> objects.</p>

+</div>

 </div>

   </div>

@@ -63,7 +63,7 @@

       </button>

       <span class="navbar-brand">

         <a class="navbar-link" href="../index.html">CellaRepertorium</a>

-        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Released version">0.3.1</span>

+        <span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Released version">0.3.2</span>

       </span>

     </div>

@@ -140,7 +140,7 @@

     </tr>

     <tr>

       <th>contig_pk</th>

-      <td><p>character vector naming fields in `contig_tbl` that uniquely identify a row/contig</p></td>

+      <td><p>character vector naming fields in <code>contig_tbl</code> that uniquely identify a row/contig</p></td>

     </tr>

     <tr>

       <th>cell_tbl</th>

@@ -148,7 +148,7 @@

     </tr>

     <tr>

       <th>cell_pk</th>

-      <td><p>character vector naming fields in `cell_tbl` that uniquely identify a cell barcode</p></td>

+      <td><p>character vector naming fields in <code>cell_tbl</code> that uniquely identify a cell barcode</p></td>

     </tr>

     <tr>

       <th>cluster_tbl</th>

@@ -156,7 +156,7 @@

     </tr>

     <tr>

       <th>cluster_pk</th>

-      <td><p>If `cluster_tbl` was provided, a character vector naming fields in `cluster_tbl` that uniquely identify a cluster</p></td>

+      <td><p>If <code>cluster_tbl</code> was provided, a character vector naming fields in <code>cluster_tbl</code> that uniquely identify a cluster</p></td>

     </tr>

     </table>

@@ -170,12 +170,69 @@

 <li><p><code>ContigCellDB_10XVDJ</code>: provide defaults that correspond to identifiers in 10X VDJ data</p></li>

 </ul>

+    <h2 class="hasAnchor" id="accessors-mutators"><a class="anchor" href="#accessors-mutators"></a>Accessors/mutators</h2>

+

+    

+    <p>See <code><a href='cash-ContigCellDB-method.html'>$,ContigCellDB-method</a></code> for more on how to access and mutate slots.

+At the moment, there is not a good way to combine objects without manually touching slots with <code>@</code>,

+but a <code>rbind</code> method is in the offing.</p>

+    

+    <h2 class="hasAnchor" id="see-also"><a class="anchor" href="#see-also"></a>See also</h2>

+

+    <div class='dont-index'><p><code><a href='cash-ContigCellDB-method.html'>$,ContigCellDB-method</a></code></p></div>

+    

     <h2 class="hasAnchor" id="examples"><a class="anchor" href="#examples"></a>Examples</h2>

     <pre class="examples"><div class='input'><span class='fu'><a href='https://www.rdocumentation.org/packages/utils/topics/data'>data</a></span>(<span class='no'>contigs_qc</span>)

-<span class='fu'>ContigCellDB</span>(<span class='no'>contigs_qc</span>, <span class='kw'>contig_pk</span> <span class='kw'>=</span> <span class='fu'><a href='https://www.rdocumentation.org/packages/base/topics/c'>c</a></span>(<span class='st'>'barcode'</span>, <span class='st'>'pop'</span>, <span class='st'>'sample'</span>, <span class='st'>'contig_id'</span>),

- <span class='kw'>cell_pk</span> <span class='kw'>=</span> <span class='fu'><a href='https://www.rdocumentation.org/packages/base/topics/c'>c</a></span>(<span class='st'>'barcode'</span>, <span class='st'>'pop'</span>, <span class='st'>'sample'</span>))</div><div class='output co'>#&gt; ContigCellDB of 1508 contigs; 832 cells; and 0 clusters.

-#&gt; Contigs keyed by barcode, pop, sample, contig_id; cells keyed by barcode, pop, sample.</div></pre>

+<span class='fu'><a href='https://www.rdocumentation.org/packages/utils/topics/head'>head</a></span>(<span class='no'>contigs_qc</span>)</div><div class='output co'>#&gt; <span style='color: #555555;'># A tibble: 6 x 22</span><span>

+#>   anno_file pop   sample barcode is_cell contig_id high_confidence length chain

+#&gt;   </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span>     </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span> </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span>  </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span>   </span><span style='color: #555555;font-style: italic;'>&lt;lgl&gt;</span><span>   </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span>     </span><span style='color: #555555;font-style: italic;'>&lt;lgl&gt;</span><span>            </span><span style='color: #555555;font-style: italic;'>&lt;dbl&gt;</span><span> </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span>

+#&gt; </span><span style='color: #555555;'>1</span><span> /Users/a… b6    4      AAAGTA… TRUE    AAAGTAGT… TRUE               611 TRB  

+#&gt; </span><span style='color: #555555;'>2</span><span> /Users/a… b6    4      AAAGTA… TRUE    AAAGTAGT… TRUE               609 TRB  

+#&gt; </span><span style='color: #555555;'>3</span><span> /Users/a… b6    4      AAAGTA… TRUE    AAAGTAGT… TRUE               538 TRA  

+#&gt; </span><span style='color: #555555;'>4</span><span> /Users/a… b6    4      AACCAT… TRUE    AACCATGC… TRUE               799 TRA  

+#&gt; </span><span style='color: #555555;'>5</span><span> /Users/a… b6    4      AACTGG… TRUE    AACTGGTG… TRUE               634 TRB  

+#&gt; </span><span style='color: #555555;'>6</span><span> /Users/a… b6    4      AACTGG… TRUE    AACTGGTG… TRUE               923 TRA  

+#&gt; </span><span style='color: #555555;'># … with 13 more variables: v_gene </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span style='color: #555555;'>, d_gene </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span style='color: #555555;'>, j_gene </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span style='color: #555555;'>,

+#&gt; #   c_gene </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span style='color: #555555;'>, full_length </span><span style='color: #555555;font-style: italic;'>&lt;lgl&gt;</span><span style='color: #555555;'>, productive </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span style='color: #555555;'>, cdr3 </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span style='color: #555555;'>,

+#&gt; #   cdr3_nt </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span style='color: #555555;'>, reads </span><span style='color: #555555;font-style: italic;'>&lt;dbl&gt;</span><span style='color: #555555;'>, umis </span><span style='color: #555555;font-style: italic;'>&lt;dbl&gt;</span><span style='color: #555555;'>, raw_clonotype_id </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span style='color: #555555;'>,

+#&gt; #   raw_consensus_id </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span style='color: #555555;'>, celltype </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span></div><div class='input'><span class='no'>cdb</span> <span class='kw'>=</span> <span class='fu'>ContigCellDB</span>(<span class='no'>contigs_qc</span>, <span class='kw'>contig_pk</span> <span class='kw'>=</span> <span class='fu'><a href='https://www.rdocumentation.org/packages/base/topics/c'>c</a></span>(<span class='st'>'barcode'</span>, <span class='st'>'pop'</span>, <span class='st'>'sample'</span>, <span class='st'>'contig_id'</span>),

+ <span class='kw'>cell_pk</span> <span class='kw'>=</span> <span class='fu'><a href='https://www.rdocumentation.org/packages/base/topics/c'>c</a></span>(<span class='st'>'barcode'</span>, <span class='st'>'pop'</span>, <span class='st'>'sample'</span>))

+ <span class='no'>cdb</span></div><div class='output co'>#&gt; ContigCellDB of 1508 contigs; 832 cells; and 0 clusters.

+#&gt; Contigs keyed by barcode, pop, sample, contig_id; cells keyed by barcode, pop, sample.</div><div class='input'> <span class='co'># everything that was in contigs_qc</span>

+ <span class='no'>cdb</span>$<span class='no'>contig_tbl</span></div><div class='output co'>#&gt; </span><span style='color: #555555;'># A tibble: 1,508 x 22</span><span>

+#>    anno_file pop   sample barcode is_cell contig_id high_confidence length chain

+#&gt;    </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span>     </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span> </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span>  </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span>   </span><span style='color: #555555;font-style: italic;'>&lt;lgl&gt;</span><span>   </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span>     </span><span style='color: #555555;font-style: italic;'>&lt;lgl&gt;</span><span>            </span><span style='color: #555555;font-style: italic;'>&lt;dbl&gt;</span><span> </span><span style='color: #555555;font-style: italic;'>&lt;chr&gt;</span><span>

+#&gt; </span><span style='color: #555555;'> 1</span><span> /Users/a… b6    4      AAAGTA… TRUE    AAAGTAGT… TRUE               611 TRB  

+#&gt; </span><span style='color: #555555;'> 2</span><span> /Users/a… b6    4      AAAGTA… TRUE    AAAGTAGT… TRUE               609 TRB  

+#&gt; </span><span style='color: #555555;'> 3</span><span> /Users/a… b6    4      AAAGTA… TRUE    AAAGTAGT… TRUE               538 TRA  

+#&gt; </span><span style='color: #555555;'> 4</span><span> /Users/a… b6    4      AACCAT… TRUE    AACCATGC… TRUE               799 TRA  

+#&gt; </span><span style='color: #555555;'> 5</span><span> /Users/a… b6    4      AACTGG… TRUE    AACTGGTG… TRUE               634 TRB