Browse code

update documentation

87875172 authored on 09/05/2019 17:14:39
Showing 25 changed files

... ...
@@ -129,6 +129,7 @@ importFrom(scales,hue_pal)
129 129
 importFrom(stringi,stri_list2matrix)
130 130
 importFrom(umap,umap)
131 131
 importFrom(umap,umap.defaults)
132
+importFrom(withr,with_seed)
132 133
 useDynLib(celda,"_colSumByGroup")
133 134
 useDynLib(celda,"_colSumByGroupChange")
134 135
 useDynLib(celda,"_colSumByGroup_numeric")
... ...
@@ -601,9 +601,11 @@ setGeneric("celdaTsne",
601 601
 #'  for umap. Default 20.
602 602
 #' @param modules Integer vector. Determines which features modules to use for
603 603
 #'  tSNE. If NULL, all modules will be used. Default NULL.
604
+#' @param seed Integer. Passed to \link[withr]{with_seed}. For reproducibility,
605
+#'  a default value of 12345 is used. If NULL, no calls to
606
+#'  \link[withr]{with_seed} are made.
604 607
 #' @param umapConfig An object of class "umapConfig" specifying parameters to
605 608
 #'  the UMAP algorithm.
606
-#' @param ... Additional parameters.
607 609
 #' @return Numeric Matrix of dimension `ncol(counts)` x 2, colums representing
608 610
 #'  the "X" and "Y" coordinates in the data's t-SNE represetation.
609 611
 #' @examples
... ...
@@ -619,6 +621,7 @@ setGeneric("celdaUmap",
619 621
         minClusterSize = 100,
620 622
         initialDims = 20,
621 623
         modules = NULL,
624
+        seed = 12345,
622 625
         umapConfig = umap::umap.defaults) {
623 626
         standardGeneric("celdaUmap")
624 627
     })
... ...
@@ -795,7 +795,6 @@ setMethod("factorizeMatrix", signature(celdaMod = "celda_C"),
795 795
 #'  to each cell population in each sample. Default 1.
796 796
 #' @param beta Numeric. Concentration parameter for Phi. Adds a pseudocount to
797 797
 #'  each feature in each cell population. Default 1.
798
-#' @param ... Additional parameters.
799 798
 #' @return Numeric. The log likelihood for the given cluster assignments
800 799
 #' @seealso `celda_C()` for clustering cells
801 800
 #' @examples
... ...
@@ -1141,7 +1140,6 @@ setMethod("celdaTsne", signature(celdaMod = "celda_C"),
1141 1140
 #'  \link[withr]{with_seed} are made.
1142 1141
 #' @param umapConfig An object of class "umap.config" specifying parameters to
1143 1142
 #'  the UMAP algorithm.
1144
-#' @param ... Additional parameters.
1145 1143
 #' @seealso `celda_C()` for clustering cells and `celdaHeatmap()` for displaying
1146 1144
 #'  expression.
1147 1145
 #' @examples
... ...
@@ -986,7 +986,6 @@ setMethod("factorizeMatrix", signature(celdaMod = "celda_CG"),
986 986
 #'  each feature in each module. Default 1.
987 987
 #' @param gamma Numeric. Concentration parameter for Eta. Adds a pseudocount to
988 988
 #'  the number of features in each module. Default 1.
989
-#' @param ... Additional parameters.
990 989
 #' @return The log likelihood for the given cluster assignments
991 990
 #' @seealso `celda_CG()` for clustering features and cells
992 991
 #' @examples
... ...
@@ -758,7 +758,6 @@ setMethod("factorizeMatrix", signature(celdaMod = "celda_G"),
758 758
 #'  each feature in each module. Default 1.
759 759
 #' @param gamma Numeric. Concentration parameter for Eta. Adds a pseudocount to
760 760
 #'  the number of features in each module. Default 1.
761
-#' @param ... Additional parameters.
762 761
 #' @keywords log likelihood
763 762
 #' @return The log-likelihood for the given cluster assignments.
764 763
 #' @seealso `celda_G()` for clustering features
... ...
@@ -7,7 +7,7 @@
7 7
 \usage{
8 8
 \S4method{celdaTsne}{celda_C}(counts, celdaMod, maxCells = 25000,
9 9
   minClusterSize = 100, initialDims = 20, modules = NULL,
10
-  perplexity = 20, maxIter = 2500)
10
+  perplexity = 20, maxIter = 2500, seed = 12345)
11 11
 }
12 12
 \arguments{
13 13
 \item{counts}{Integer matrix. Rows represent features and columns represent
... ...
@@ -34,6 +34,10 @@ tSNE. If NULL, all modules will be used. Default NULL.}
34 34
 
35 35
 \item{maxIter}{Integer. Maximum number of iterations in tSNE generation.
36 36
 Default 2500.}
37
+
38
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
39
+a default value of 12345 is used. If NULL, no calls to
40
+\link[withr]{with_seed} are made.}
37 41
 }
38 42
 \value{
39 43
 A two column matrix of t-SNE coordinates
... ...
@@ -7,7 +7,7 @@
7 7
 \usage{
8 8
 \S4method{celdaTsne}{celda_CG}(counts, celdaMod, maxCells = 25000,
9 9
   minClusterSize = 100, initialDims = 20, modules = NULL,
10
-  perplexity = 20, maxIter = 2500)
10
+  perplexity = 20, maxIter = 2500, seed = 12345)
11 11
 }
12 12
 \arguments{
13 13
 \item{counts}{Integer matrix. Rows represent features and columns represent
... ...
@@ -34,6 +34,10 @@ tSNE. If NULL, all modules will be used. Default NULL.}
34 34
 
35 35
 \item{maxIter}{Integer. Maximum number of iterations in tSNE generation.
36 36
 Default 2500.}
37
+
38
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
39
+a default value of 12345 is used. If NULL, no calls to
40
+\link[withr]{with_seed} are made.}
37 41
 }
38 42
 \value{
39 43
 A two column matrix of t-SNE coordinates
... ...
@@ -7,7 +7,7 @@
7 7
 \usage{
8 8
 \S4method{celdaTsne}{celda_G}(counts, celdaMod, maxCells = 25000,
9 9
   minClusterSize = 100, initialDims = 20, modules = NULL,
10
-  perplexity = 20, maxIter = 2500)
10
+  perplexity = 20, maxIter = 2500, seed = 12345)
11 11
 }
12 12
 \arguments{
13 13
 \item{counts}{Integer matrix. Rows represent features and columns represent
... ...
@@ -34,6 +34,10 @@ tSNE. If NULL, all modules will be used. Default NULL.}
34 34
 
35 35
 \item{maxIter}{Integer. Maximum number of iterations in tSNE generation.
36 36
 Default 2500.}
37
+
38
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
39
+a default value of 12345 is used. If NULL, no calls to
40
+\link[withr]{with_seed} are made.}
37 41
 }
38 42
 \value{
39 43
 A two column matrix of t-SNE coordinates.
... ...
@@ -6,7 +6,7 @@
6 6
 \title{umap for celda_C}
7 7
 \usage{
8 8
 \S4method{celdaUmap}{celda_C}(counts, celdaMod, maxCells = 25000,
9
-  minClusterSize = 100, modules = NULL,
9
+  minClusterSize = 100, modules = NULL, seed = 12345,
10 10
   umapConfig = umap::umap.defaults)
11 11
 }
12 12
 \arguments{
... ...
@@ -26,10 +26,12 @@ threshold. Default 100.}
26 26
 \item{modules}{Integer vector. Determines which features modules to use for
27 27
 UMAP. If NULL, all modules will be used. Default NULL.}
28 28
 
29
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
30
+a default value of 12345 is used. If NULL, no calls to
31
+\link[withr]{with_seed} are made.}
32
+
29 33
 \item{umapConfig}{An object of class "umap.config" specifying parameters to
30 34
 the UMAP algorithm.}
31
-
32
-\item{...}{Additional parameters.}
33 35
 }
34 36
 \value{
35 37
 A two column matrix of umap coordinates
... ...
@@ -6,7 +6,7 @@
6 6
 \title{umap for celda_CG}
7 7
 \usage{
8 8
 \S4method{celdaUmap}{celda_CG}(counts, celdaMod, maxCells = 25000,
9
-  minClusterSize = 100, modules = NULL,
9
+  minClusterSize = 100, modules = NULL, seed = 12345,
10 10
   umapConfig = umap::umap.defaults)
11 11
 }
12 12
 \arguments{
... ...
@@ -26,6 +26,10 @@ threshold. Default 100.}
26 26
 \item{modules}{Integer vector. Determines which features modules to use for
27 27
 tSNE. If NULL, all modules will be used. Default NULL.}
28 28
 
29
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
30
+a default value of 12345 is used. If NULL, no calls to
31
+\link[withr]{with_seed} are made.}
32
+
29 33
 \item{umapConfig}{Object of class `umap.config`. Configures parameters for
30 34
 umap. Default `umap::umap.defaults`.}
31 35
 }
... ...
@@ -6,7 +6,7 @@
6 6
 \title{umap for celda_G}
7 7
 \usage{
8 8
 \S4method{celdaUmap}{celda_G}(counts, celdaMod, maxCells = 25000,
9
-  minClusterSize = 100, modules = NULL,
9
+  minClusterSize = 100, modules = NULL, seed = 12345,
10 10
   umapConfig = umap::umap.defaults)
11 11
 }
12 12
 \arguments{
... ...
@@ -26,6 +26,10 @@ threshold. Default 100.}
26 26
 \item{modules}{Integer vector. Determines which features modules to use for
27 27
 tSNE. If NULL, all modules will be used. Default NULL.}
28 28
 
29
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
30
+a default value of 12345 is used. If NULL, no calls to
31
+\link[withr]{with_seed} are made.}
32
+
29 33
 \item{umapConfig}{Object of class `umap.config`. Configures parameters for
30 34
 umap. Default `umap::umap.defaults`.}
31 35
 }
... ...
@@ -5,7 +5,8 @@
5 5
 \title{Embeds cells in two dimensions using umap.}
6 6
 \usage{
7 7
 celdaUmap(counts, celdaMod, maxCells = 25000, minClusterSize = 100,
8
-  initialDims = 20, modules = NULL, umapConfig = umap::umap.defaults)
8
+  initialDims = 20, modules = NULL, seed = 12345,
9
+  umapConfig = umap::umap.defaults)
9 10
 }
10 11
 \arguments{
11 12
 \item{counts}{Integer matrix. Rows represent features and columns represent
... ...
@@ -28,10 +29,12 @@ for umap. Default 20.}
28 29
 \item{modules}{Integer vector. Determines which features modules to use for
29 30
 tSNE. If NULL, all modules will be used. Default NULL.}
30 31
 
32
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
33
+a default value of 12345 is used. If NULL, no calls to
34
+\link[withr]{with_seed} are made.}
35
+
31 36
 \item{umapConfig}{An object of class "umapConfig" specifying parameters to
32 37
 the UMAP algorithm.}
33
-
34
-\item{...}{Additional parameters.}
35 38
 }
36 39
 \value{
37 40
 Numeric Matrix of dimension `ncol(counts)` x 2, colums representing
... ...
@@ -6,7 +6,7 @@
6 6
 \usage{
7 7
 celda_C(counts, sampleLabel = NULL, K, alpha = 1, beta = 1,
8 8
   algorithm = c("EM", "Gibbs"), stopIter = 10, maxIter = 200,
9
-  splitOnIter = 10, splitOnLast = TRUE, nchains = 3,
9
+  splitOnIter = 10, splitOnLast = TRUE, seed = 12345, nchains = 3,
10 10
   zInitialize = c("split", "random", "predefined"),
11 11
   countChecksum = NULL, zInit = NULL, logfile = NULL,
12 12
   verbose = TRUE)
... ...
@@ -49,6 +49,10 @@ a cell population should be reassigned and another cell population should be
49 49
 split into two clusters. If a split occurs, then `stopIter` will be reset.
50 50
 Default TRUE.}
51 51
 
52
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
53
+a default value of 12345 is used. If NULL, no calls to
54
+\link[withr]{with_seed} are made.}
55
+
52 56
 \item{nchains}{Integer. Number of random cluster initializations. Default 3.}
53 57
 
54 58
 \item{zInitialize}{Chararacter. One of 'random', 'split', or 'predefined'.
... ...
@@ -7,8 +7,9 @@
7 7
 celda_CG(counts, sampleLabel = NULL, K, L, alpha = 1, beta = 1,
8 8
   delta = 1, gamma = 1, algorithm = c("EM", "Gibbs"),
9 9
   stopIter = 10, maxIter = 200, splitOnIter = 10,
10
-  splitOnLast = TRUE, nchains = 3, zInitialize = c("split", "random",
11
-  "predefined"), yInitialize = c("split", "random", "predefined"),
10
+  splitOnLast = TRUE, seed = 12345, nchains = 3,
11
+  zInitialize = c("split", "random", "predefined"),
12
+  yInitialize = c("split", "random", "predefined"),
12 13
   countChecksum = NULL, zInit = NULL, yInit = NULL, logfile = NULL,
13 14
   verbose = TRUE)
14 15
 }
... ...
@@ -57,6 +58,10 @@ a cell population or feature module should be reassigned and another cell
57 58
 population or feature module should be split into two clusters. If a split
58 59
 occurs, then 'stopIter' will be reset. Default TRUE.}
59 60
 
61
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
62
+a default value of 12345 is used. If NULL, no calls to
63
+\link[withr]{with_seed} are made.}
64
+
60 65
 \item{nchains}{Integer. Number of random cluster initializations. Default 3.}
61 66
 
62 67
 \item{zInitialize}{Chararacter. One of 'random', 'split', or 'predefined'.
... ...
@@ -5,9 +5,9 @@
5 5
 \title{Feature clustering with Celda}
6 6
 \usage{
7 7
 celda_G(counts, L, beta = 1, delta = 1, gamma = 1, stopIter = 10,
8
-  maxIter = 200, splitOnIter = 10, splitOnLast = TRUE, nchains = 3,
9
-  yInitialize = c("split", "random", "predefined"),
10
-  countChecksum = NULL, yInit = NULL, logfile = NULL,
8
+  maxIter = 200, splitOnIter = 10, splitOnLast = TRUE,
9
+  seed = 12345, nchains = 3, yInitialize = c("split", "random",
10
+  "predefined"), countChecksum = NULL, yInit = NULL, logfile = NULL,
11 11
   verbose = TRUE)
12 12
 }
13 13
 \arguments{
... ...
@@ -42,6 +42,10 @@ a cell population should be reassigned and another cell population should be
42 42
 split into two clusters. If a split occurs, then `stopIter` will be reset.
43 43
 Default TRUE.}
44 44
 
45
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
46
+a default value of 12345 is used. If NULL, no calls to
47
+\link[withr]{with_seed} are made.}
48
+
45 49
 \item{nchains}{Integer. Number of random cluster initializations. Default 3.}
46 50
 
47 51
 \item{yInitialize}{Chararacter. One of 'random', 'split', or 'predefined'.
... ...
@@ -5,7 +5,8 @@
5 5
 \title{Decontaminate count matrix}
6 6
 \usage{
7 7
 decontX(counts, z = NULL, batch = NULL, maxIter = 200,
8
-  beta = 1e-06, delta = 10, logfile = NULL, verbose = TRUE)
8
+  beta = 1e-06, delta = 10, logfile = NULL, verbose = TRUE,
9
+  seed = 12345)
9 10
 }
10 11
 \arguments{
11 12
 \item{counts}{Numeric/Integer matrix. Observed count matrix, rows represent
... ...
@@ -27,6 +28,10 @@ to be 10.}
27 28
 `logfile`. If NULL, messages will be printed to stdout.  Default NULL.}
28 29
 
29 30
 \item{verbose}{Logical. Whether to print log messages. Default TRUE.}
31
+
32
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
33
+a default value of 12345 is used. If NULL, no calls to
34
+\link[withr]{with_seed} are made.}
30 35
 }
31 36
 \value{
32 37
 A list object which contains the decontaminated count matrix and
... ...
@@ -22,8 +22,6 @@ to each cell population in each sample. Default 1.}
22 22
 
23 23
 \item{beta}{Numeric. Concentration parameter for Phi. Adds a pseudocount to
24 24
 each feature in each cell population. Default 1.}
25
-
26
-\item{...}{Additional parameters.}
27 25
 }
28 26
 \value{
29 27
 Numeric. The log likelihood for the given cluster assignments
... ...
@@ -33,8 +33,6 @@ each feature in each module. Default 1.}
33 33
 
34 34
 \item{gamma}{Numeric. Concentration parameter for Eta. Adds a pseudocount to
35 35
 the number of features in each module. Default 1.}
36
-
37
-\item{...}{Additional parameters.}
38 36
 }
39 37
 \value{
40 38
 The log likelihood for the given cluster assignments
... ...
@@ -22,8 +22,6 @@ each feature in each module. Default 1.}
22 22
 
23 23
 \item{gamma}{Numeric. Concentration parameter for Eta. Adds a pseudocount to
24 24
 the number of features in each module. Default 1.}
25
-
26
-\item{...}{Additional parameters.}
27 25
 }
28 26
 \value{
29 27
 The log-likelihood for the given cluster assignments.
... ...
@@ -29,8 +29,8 @@ in the featureModule. If NULL, plot all features in the module. Default
29 29
 NULL.}
30 30
 
31 31
 \item{normalizedCounts}{Integer matrix. Rows represent features and columns
32
-represent cells. This matrix should correspond to the one provided for 
33
-`counts`, but should be passed through. If NA, normalize `counts`. 
32
+represent cells. This matrix should correspond to the one provided for
33
+`counts`, but should be passed through. If NA, normalize `counts`.
34 34
 Default NA.
35 35
 `normalizeCounts(counts, "proportion", transformationFun=sqrt)`. Use of this
36 36
 parameter is particularly useful for plotting many moduleHeatmaps, where
... ...
@@ -5,7 +5,7 @@
5 5
 \title{Calculate and visualize perplexity of all models in a celdaList, with
6 6
  count resampling}
7 7
 \usage{
8
-resamplePerplexity(counts, celdaList, resample = 5)
8
+resamplePerplexity(counts, celdaList, resample = 5, seed = 12345)
9 9
 }
10 10
 \arguments{
11 11
 \item{counts}{Integer matrix. Rows represent features and columns represent
... ...
@@ -16,6 +16,10 @@ cells. This matrix should be the same as the one used to generate
16 16
 
17 17
 \item{resample}{Integer. The number of times to resample the counts matrix
18 18
 for evaluating perplexity. Default 5.}
19
+
20
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
21
+a default value of 12345 is used. If NULL, no calls to
22
+\link[withr]{with_seed} are made.}
19 23
 }
20 24
 \value{
21 25
 celdaList. Returns the provided `celdaList` with a `perplexity`
... ...
@@ -6,7 +6,7 @@
6 6
 \usage{
7 7
 simulateCellscelda_C(model, S = 5, CRange = c(50, 100),
8 8
   NRange = c(500, 1000), G = 100, K = 5, alpha = 1, beta = 1,
9
-  ...)
9
+  seed = 12345, ...)
10 10
 }
11 11
 \arguments{
12 12
 \item{model}{Character. Options available in `celda::availableModels`.}
... ...
@@ -31,6 +31,10 @@ to each cell population in each sample. Default 1.}
31 31
 \item{beta}{Numeric. Concentration parameter for Phi. Adds a pseudocount to
32 32
 each feature in each cell population. Default 1.}
33 33
 
34
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
35
+a default value of 12345 is used. If NULL, no calls to
36
+\link[withr]{with_seed} are made.}
37
+
34 38
 \item{...}{Additional parameters.}
35 39
 }
36 40
 \value{
... ...
@@ -6,7 +6,7 @@
6 6
 \usage{
7 7
 simulateCellscelda_CG(model, S = 5, CRange = c(50, 100),
8 8
   NRange = c(500, 1000), G = 100, K = 5, L = 10, alpha = 1,
9
-  beta = 1, gamma = 5, delta = 1, ...)
9
+  beta = 1, gamma = 5, delta = 1, seed = 12345, ...)
10 10
 }
11 11
 \arguments{
12 12
 \item{model}{Character. Options available in `celda::availableModels`.}
... ...
@@ -39,6 +39,10 @@ the number of features in each module. Default 5.}
39 39
 \item{delta}{Numeric. Concentration parameter for Psi. Adds a pseudocount to
40 40
 each feature in each module. Default 1.}
41 41
 
42
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
43
+a default value of 12345 is used. If NULL, no calls to
44
+\link[withr]{with_seed} are made.}
45
+
42 46
 \item{...}{Additional parameters.}
43 47
 }
44 48
 \value{
... ...
@@ -5,7 +5,7 @@
5 5
 \title{Simulate cells from the celda_G model}
6 6
 \usage{
7 7
 simulateCellscelda_G(model, C = 100, NRange = c(500, 1000), G = 100,
8
-  L = 10, beta = 1, gamma = 5, delta = 1, ...)
8
+  L = 10, beta = 1, gamma = 5, delta = 1, seed = 12345, ...)
9 9
 }
10 10
 \arguments{
11 11
 \item{model}{Character. Options available in `celda::availableModels`.}
... ...
@@ -29,6 +29,10 @@ the number of features in each module. Default 5.}
29 29
 \item{delta}{Numeric. Concentration parameter for Psi. Adds a pseudocount to
30 30
 each feature in each module. Default 1.}
31 31
 
32
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
33
+a default value of 12345 is used. If NULL, no calls to
34
+\link[withr]{with_seed} are made.}
35
+
32 36
 \item{...}{Additional parameters.}
33 37
 }
34 38
 \value{
... ...
@@ -5,7 +5,7 @@
5 5
 \title{Simulate contaminated count matrix}
6 6
 \usage{
7 7
 simulateContaminatedMatrix(C = 300, G = 100, K = 3, NRange = c(500,
8
-  1000), beta = 0.5, delta = c(1, 2))
8
+  1000), beta = 0.5, delta = c(1, 2), seed = 12345)
9 9
 }
10 10
 \arguments{
11 11
 \item{C}{Integer. Number of cells to be simulated. Default to be 300.}
... ...
@@ -25,6 +25,10 @@ be c(500, 1000).}
25 25
 input as a single numeric value, symmetric values for beta distribution are
26 26
 specified; if input as a vector of lenght 2, the two values will be the
27 27
 shape1 and shape2 paramters of the beta distribution respectively.}
28
+
29
+\item{seed}{Integer. Passed to \link[withr]{with_seed}. For reproducibility,
30
+a default value of 12345 is used. If NULL, no calls to
31
+\link[withr]{with_seed} are made.}
28 32
 }
29 33
 \value{
30 34
 A list object containing the real expression matrix and contamination