forked from satijalab/seurat
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathvisualization.R
9222 lines (9085 loc) · 282 KB
/
visualization.R
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#' @importFrom utils globalVariables
#' @importFrom ggplot2 fortify GeomViolin ggproto
#' @importFrom SeuratObject DefaultDimReduc
#'
NULL
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
# Generics
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
#' @importFrom methods setGeneric
#'
setGeneric(
name = '.PrepImageData',
def = function(data, cells, ...) {
standardGeneric(f = '.PrepImageData')
}
)
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
# Heatmaps
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
#' Dimensional reduction heatmap
#'
#' Draws a heatmap focusing on a principal component. Both cells and genes are sorted by their
#' principal component scores. Allows for nice visualization of sources of heterogeneity in the dataset.
#'
#' @inheritParams DoHeatmap
#' @param dims Dimensions to plot
#' @param nfeatures Number of genes to plot
#' @param cells A list of cells to plot. If numeric, just plots the top cells.
#' @param reduction Which dimensional reduction to use
#' @param balanced Plot an equal number of genes with both + and - scores.
#' @param projected Use the full projected dimensional reduction
#' @param ncol Number of columns to plot
#' @param fast If true, use \code{image} to generate plots; faster than using ggplot2, but not customizable
#' @param assays A vector of assays to pull data from
#' @param combine Combine plots into a single \code{\link[patchwork]{patchwork}ed}
#' ggplot object. If \code{FALSE}, return a list of ggplot objects
#'
#' @return No return value by default. If using fast = FALSE, will return a
#' \code{\link[patchwork]{patchwork}ed} ggplot object if combine = TRUE, otherwise
#' returns a list of ggplot objects
#'
#' @importFrom patchwork wrap_plots
#' @export
#' @concept visualization
#'
#' @seealso \code{\link[graphics]{image}} \code{\link[ggplot2]{geom_raster}}
#'
#' @examples
#' data("pbmc_small")
#' DimHeatmap(object = pbmc_small)
#'
DimHeatmap <- function(
object,
dims = 1,
nfeatures = 30,
cells = NULL,
reduction = 'pca',
disp.min = -2.5,
disp.max = NULL,
balanced = TRUE,
projected = FALSE,
ncol = NULL,
fast = TRUE,
raster = TRUE,
slot = 'scale.data',
assays = NULL,
combine = TRUE
) {
ncol <- ncol %||% ifelse(test = length(x = dims) > 2, yes = 3, no = length(x = dims))
plots <- vector(mode = 'list', length = length(x = dims))
assays <- assays %||% DefaultAssay(object = object)
disp.max <- disp.max %||% ifelse(
test = slot == 'scale.data',
yes = 2.5,
no = 6
)
if (!DefaultAssay(object = object[[reduction]]) %in% assays) {
warning("The original assay that the reduction was computed on is different than the assay specified")
}
cells <- cells %||% ncol(x = object)
if (is.numeric(x = cells)) {
cells <- lapply(
X = dims,
FUN = function(x) {
cells <- TopCells(
object = object[[reduction]],
dim = x,
ncells = cells,
balanced = balanced
)
if (balanced) {
cells$negative <- rev(x = cells$negative)
}
cells <- unlist(x = unname(obj = cells))
return(cells)
}
)
}
if (!is.list(x = cells)) {
cells <- lapply(X = 1:length(x = dims), FUN = function(x) {return(cells)})
}
features <- lapply(
X = dims,
FUN = TopFeatures,
object = object[[reduction]],
nfeatures = nfeatures,
balanced = balanced,
projected = projected
)
features.all <- unique(x = unlist(x = features))
if (length(x = assays) > 1) {
features.keyed <- lapply(
X = assays,
FUN = function(assay) {
features <- features.all[features.all %in% rownames(x = object[[assay]])]
if (length(x = features) > 0) {
return(paste0(Key(object = object[[assay]]), features))
}
}
)
features.keyed <- Filter(f = Negate(f = is.null), x = features.keyed)
features.keyed <- unlist(x = features.keyed)
} else {
features.keyed <- features.all
DefaultAssay(object = object) <- assays
}
data.all <- FetchData(
object = object,
vars = features.keyed,
cells = unique(x = unlist(x = cells)),
slot = slot
)
data.all <- MinMax(data = data.all, min = disp.min, max = disp.max)
data.limits <- c(min(data.all), max(data.all))
# if (check.plot && any(c(length(x = features.keyed), length(x = cells[[1]])) > 700)) {
# choice <- menu(c("Continue with plotting", "Quit"), title = "Plot(s) requested will likely take a while to plot.")
# if (choice != 1) {
# return(invisible(x = NULL))
# }
# }
if (fast) {
nrow <- floor(x = length(x = dims) / 3.01) + 1
orig.par <- par()$mfrow
par(mfrow = c(nrow, ncol))
}
for (i in 1:length(x = dims)) {
dim.features <- c(features[[i]][[2]], rev(x = features[[i]][[1]]))
dim.features <- rev(x = unlist(x = lapply(
X = dim.features,
FUN = function(feat) {
return(grep(pattern = paste0(feat, '$'), x = features.keyed, value = TRUE))
}
)))
dim.cells <- cells[[i]]
data.plot <- data.all[dim.cells, dim.features]
if (fast) {
SingleImageMap(
data = data.plot,
title = paste0(Key(object = object[[reduction]]), dims[i]),
order = dim.cells
)
} else {
plots[[i]] <- SingleRasterMap(
data = data.plot,
raster = raster,
limits = data.limits,
cell.order = dim.cells,
feature.order = dim.features
)
}
}
if (fast) {
par(mfrow = orig.par)
return(invisible(x = NULL))
}
if (combine) {
plots <- wrap_plots(plots, ncol = ncol, guides = "collect")
}
return(plots)
}
#' Feature expression heatmap
#'
#' Draws a heatmap of single cell feature expression.
#'
#' @param object Seurat object
#' @param features A vector of features to plot, defaults to \code{VariableFeatures(object = object)}
#' @param cells A vector of cells to plot
#' @param disp.min Minimum display value (all values below are clipped)
#' @param disp.max Maximum display value (all values above are clipped); defaults to 2.5
#' if \code{slot} is 'scale.data', 6 otherwise
#' @param group.by A vector of variables to group cells by; pass 'ident' to group by cell identity classes
#' @param group.bar Add a color bar showing group status for cells
#' @param group.colors Colors to use for the color bar
#' @param slot Data slot to use, choose from 'raw.data', 'data', or 'scale.data'
#' @param assay Assay to pull from
# @param check.plot Check that plotting will finish in a reasonable amount of time
#' @param label Label the cell identies above the color bar
#' @param size Size of text above color bar
#' @param hjust Horizontal justification of text above color bar
#' @param vjust Vertical justification of text above color bar
#' @param angle Angle of text above color bar
#' @param raster If true, plot with geom_raster, else use geom_tile. geom_raster may look blurry on
#' some viewing applications such as Preview due to how the raster is interpolated. Set this to FALSE
#' if you are encountering that issue (note that plots may take longer to produce/render).
#' @param draw.lines Include white lines to separate the groups
#' @param lines.width Integer number to adjust the width of the separating white lines.
#' Corresponds to the number of "cells" between each group.
#' @param group.bar.height Scale the height of the color bar
#' @param combine Combine plots into a single \code{\link[patchwork]{patchwork}ed}
#' ggplot object. If \code{FALSE}, return a list of ggplot objects
#'
#' @return A \code{\link[patchwork]{patchwork}ed} ggplot object if
#' \code{combine = TRUE}; otherwise, a list of ggplot objects
#'
#' @importFrom stats median
#' @importFrom scales hue_pal
#' @importFrom ggplot2 annotation_raster coord_cartesian scale_color_manual
#' ggplot_build aes_string geom_text
#' @importFrom patchwork wrap_plots
#' @export
#' @concept visualization
#'
#' @examples
#' data("pbmc_small")
#' DoHeatmap(object = pbmc_small)
#'
DoHeatmap <- function(
object,
features = NULL,
cells = NULL,
group.by = 'ident',
group.bar = TRUE,
group.colors = NULL,
disp.min = -2.5,
disp.max = NULL,
slot = 'scale.data',
assay = NULL,
label = TRUE,
size = 5.5,
hjust = 0,
vjust = 0,
angle = 45,
raster = TRUE,
draw.lines = TRUE,
lines.width = NULL,
group.bar.height = 0.02,
combine = TRUE
) {
assay <- assay %||% DefaultAssay(object = object)
DefaultAssay(object = object) <- assay
cells <- cells %||% colnames(x = object[[assay]])
if (is.numeric(x = cells)) {
cells <- colnames(x = object)[cells]
}
features <- features %||% VariableFeatures(object = object)
features <- rev(x = unique(x = features))
disp.max <- disp.max %||% ifelse(
test = slot == 'scale.data',
yes = 2.5,
no = 6
)
# make sure features are present
possible.features <- rownames(x = GetAssayData(object = object, slot = slot))
if (any(!features %in% possible.features)) {
bad.features <- features[!features %in% possible.features]
features <- features[features %in% possible.features]
if(length(x = features) == 0) {
stop("No requested features found in the ", slot, " slot for the ", assay, " assay.")
}
warning("The following features were omitted as they were not found in the ", slot,
" slot for the ", assay, " assay: ", paste(bad.features, collapse = ", "))
}
data <- as.data.frame(x = as.matrix(x = t(x = GetAssayData(
object = object,
slot = slot)[features, cells, drop = FALSE])))
object <- suppressMessages(expr = StashIdent(object = object, save.name = 'ident'))
group.by <- group.by %||% 'ident'
groups.use <- object[[group.by]][cells, , drop = FALSE]
# group.use <- switch(
# EXPR = group.by,
# 'ident' = Idents(object = object),
# object[[group.by, drop = TRUE]]
# )
# group.use <- factor(x = group.use[cells])
plots <- vector(mode = 'list', length = ncol(x = groups.use))
for (i in 1:ncol(x = groups.use)) {
data.group <- data
group.use <- groups.use[, i, drop = TRUE]
if (!is.factor(x = group.use)) {
group.use <- factor(x = group.use)
}
names(x = group.use) <- cells
if (draw.lines) {
# create fake cells to serve as the white lines, fill with NAs
lines.width <- lines.width %||% ceiling(x = nrow(x = data.group) * 0.0025)
placeholder.cells <- sapply(
X = 1:(length(x = levels(x = group.use)) * lines.width),
FUN = function(x) {
return(RandomName(length = 20))
}
)
placeholder.groups <- rep(x = levels(x = group.use), times = lines.width)
group.levels <- levels(x = group.use)
names(x = placeholder.groups) <- placeholder.cells
group.use <- as.vector(x = group.use)
names(x = group.use) <- cells
group.use <- factor(x = c(group.use, placeholder.groups), levels = group.levels)
na.data.group <- matrix(
data = NA,
nrow = length(x = placeholder.cells),
ncol = ncol(x = data.group),
dimnames = list(placeholder.cells, colnames(x = data.group))
)
data.group <- rbind(data.group, na.data.group)
}
lgroup <- length(levels(group.use))
plot <- SingleRasterMap(
data = data.group,
raster = raster,
disp.min = disp.min,
disp.max = disp.max,
feature.order = features,
cell.order = names(x = sort(x = group.use)),
group.by = group.use
)
if (group.bar) {
# TODO: Change group.bar to annotation.bar
default.colors <- c(hue_pal()(length(x = levels(x = group.use))))
if (!is.null(x = names(x = group.colors))) {
cols <- unname(obj = group.colors[levels(x = group.use)])
} else {
cols <- group.colors[1:length(x = levels(x = group.use))] %||% default.colors
}
if (any(is.na(x = cols))) {
cols[is.na(x = cols)] <- default.colors[is.na(x = cols)]
cols <- Col2Hex(cols)
col.dups <- sort(x = unique(x = which(x = duplicated(x = substr(
x = cols,
start = 1,
stop = 7
)))))
through <- length(x = default.colors)
while (length(x = col.dups) > 0) {
pal.max <- length(x = col.dups) + through
cols.extra <- hue_pal()(pal.max)[(through + 1):pal.max]
cols[col.dups] <- cols.extra
col.dups <- sort(x = unique(x = which(x = duplicated(x = substr(
x = cols,
start = 1,
stop = 7
)))))
}
}
group.use2 <- sort(x = group.use)
if (draw.lines) {
na.group <- RandomName(length = 20)
levels(x = group.use2) <- c(levels(x = group.use2), na.group)
group.use2[placeholder.cells] <- na.group
cols <- c(cols, "#FFFFFF")
}
pbuild <- ggplot_build(plot = plot)
names(x = cols) <- levels(x = group.use2)
# scale the height of the bar
y.range <- diff(x = pbuild$layout$panel_params[[1]]$y.range)
y.pos <- max(pbuild$layout$panel_params[[1]]$y.range) + y.range * 0.015
y.max <- y.pos + group.bar.height * y.range
x.min <- min(pbuild$layout$panel_params[[1]]$x.range) + 0.1
x.max <- max(pbuild$layout$panel_params[[1]]$x.range) - 0.1
plot <- plot +
annotation_raster(
raster = t(x = cols[group.use2]),
xmin = x.min,
xmax = x.max,
ymin = y.pos,
ymax = y.max
) +
coord_cartesian(ylim = c(0, y.max), clip = 'off') +
scale_color_manual(
values = cols[-length(x = cols)],
name = "Identity",
na.translate = FALSE
)
if (label) {
x.max <- max(pbuild$layout$panel_params[[1]]$x.range)
# Attempt to pull xdivs from x.major in ggplot2 < 3.3.0; if NULL, pull from the >= 3.3.0 slot
x.divs <- pbuild$layout$panel_params[[1]]$x.major %||% attr(x = pbuild$layout$panel_params[[1]]$x$get_breaks(), which = "pos")
x <- data.frame(group = sort(x = group.use), x = x.divs)
label.x.pos <- tapply(X = x$x, INDEX = x$group, FUN = function(y) {
if (isTRUE(x = draw.lines)) {
mean(x = y[-length(x = y)])
} else {
mean(x = y)
}
})
label.x.pos <- data.frame(group = names(x = label.x.pos), label.x.pos)
plot <- plot + geom_text(
stat = "identity",
data = label.x.pos,
aes_string(label = 'group', x = 'label.x.pos'),
y = y.max + y.max * 0.03 * 0.5 + vjust,
angle = angle,
hjust = hjust,
size = size
)
plot <- suppressMessages(plot + coord_cartesian(
ylim = c(0, y.max + y.max * 0.002 * max(nchar(x = levels(x = group.use))) * size),
clip = 'off')
)
}
}
plot <- plot + theme(line = element_blank())
plots[[i]] <- plot
}
if (combine) {
plots <- wrap_plots(plots)
}
return(plots)
}
#' Hashtag oligo heatmap
#'
#' Draws a heatmap of hashtag oligo signals across singlets/doublets/negative cells. Allows for the visualization of HTO demultiplexing results.
#'
#' @param object Seurat object. Assumes that the hash tag oligo (HTO) data has been added and normalized, and demultiplexing has been run with HTODemux().
#' @param classification The naming for metadata column with classification result from HTODemux().
#' @param global.classification The slot for metadata column specifying a cell as singlet/doublet/negative.
#' @param assay Hashtag assay name.
#' @param ncells Number of cells to plot. Default is to choose 5000 cells by random subsampling, to avoid having to draw exceptionally large heatmaps.
#' @param singlet.names Namings for the singlets. Default is to use the same names as HTOs.
#' @param raster If true, plot with geom_raster, else use geom_tile. geom_raster may look blurry on
#' some viewing applications such as Preview due to how the raster is interpolated. Set this to FALSE
#' if you are encountering that issue (note that plots may take longer to produce/render).
#' @return Returns a ggplot2 plot object.
#'
#' @importFrom ggplot2 guides
#' @export
#' @concept visualization
#'
#' @seealso \code{\link{HTODemux}}
#'
#' @examples
#' \dontrun{
#' object <- HTODemux(object)
#' HTOHeatmap(object)
#' }
#'
HTOHeatmap <- function(
object,
assay = 'HTO',
classification = paste0(assay, '_classification'),
global.classification = paste0(assay, '_classification.global'),
ncells = 5000,
singlet.names = NULL,
raster = TRUE
) {
DefaultAssay(object = object) <- assay
Idents(object = object) <- object[[classification, drop = TRUE]]
if (ncells > ncol(x = object)) {
warning("ncells (", ncells, ") is larger than the number of cells present in the provided object (", ncol(x = object), "). Plotting heatmap for all cells.")
} else {
object <- subset(
x = object,
cells = sample(x = colnames(x = object), size = ncells)
)
}
classification <- object[[classification]]
singlets <- which(x = object[[global.classification]] == 'Singlet')
singlet.ids <- sort(x = unique(x = as.character(x = classification[singlets, ])))
doublets <- which(object[[global.classification]] == 'Doublet')
doublet.ids <- sort(x = unique(x = as.character(x = classification[doublets, ])))
heatmap.levels <- c(singlet.ids, doublet.ids, 'Negative')
object <- ScaleData(object = object, assay = assay, verbose = FALSE)
data <- FetchData(object = object, vars = singlet.ids)
Idents(object = object) <- factor(x = classification[, 1], levels = heatmap.levels)
plot <- SingleRasterMap(
data = data,
raster = raster,
feature.order = rev(x = singlet.ids),
cell.order = names(x = sort(x = Idents(object = object))),
group.by = Idents(object = object)
) + guides(color = FALSE)
return(plot)
}
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
# Expression by identity plots
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
#' Single cell ridge plot
#'
#' Draws a ridge plot of single cell data (gene expression, metrics, PC
#' scores, etc.)
#'
#' @param object Seurat object
#' @param features Features to plot (gene expression, metrics, PC scores,
#' anything that can be retreived by FetchData)
#' @param cols Colors to use for plotting
#' @param idents Which classes to include in the plot (default is all)
#' @param sort Sort identity classes (on the x-axis) by the average
#' expression of the attribute being potted, can also pass 'increasing' or 'decreasing' to change sort direction
#' @param assay Name of assay to use, defaults to the active assay
#' @param group.by Group (color) cells in different ways (for example, orig.ident)
#' @param y.max Maximum y axis value
#' @param same.y.lims Set all the y-axis limits to the same values
#' @param log plot the feature axis on log scale
#' @param ncol Number of columns if multiple plots are displayed
#' @param slot Slot to pull expression data from (e.g. "counts" or "data")
#' @param layer Layer to pull expression data from (e.g. "counts" or "data")
#' @param stack Horizontally stack plots for each feature
#' @param combine Combine plots into a single \code{\link[patchwork]{patchwork}ed}
#' ggplot object. If \code{FALSE}, return a list of ggplot
#' @param fill.by Color violins/ridges based on either 'feature' or 'ident'
#'
#' @return A \code{\link[patchwork]{patchwork}ed} ggplot object if
#' \code{combine = TRUE}; otherwise, a list of ggplot objects
#'
#' @export
#' @concept visualization
#'
#' @examples
#' data("pbmc_small")
#' RidgePlot(object = pbmc_small, features = 'PC_1')
#'
RidgePlot <- function(
object,
features,
cols = NULL,
idents = NULL,
sort = FALSE,
assay = NULL,
group.by = NULL,
y.max = NULL,
same.y.lims = FALSE,
log = FALSE,
ncol = NULL,
slot = deprecated(),
layer = 'data',
stack = FALSE,
combine = TRUE,
fill.by = 'feature'
) {
if (is_present(arg = slot)) {
deprecate_soft(
when = '5.0.0',
what = 'RidgePlot(slot = )',
with = 'RidgePlot(layer = )'
)
layer <- slot %||% layer
}
return(ExIPlot(
object = object,
type = 'ridge',
features = features,
idents = idents,
ncol = ncol,
sort = sort,
assay = assay,
y.max = y.max,
same.y.lims = same.y.lims,
cols = cols,
group.by = group.by,
log = log,
layer = layer,
stack = stack,
combine = combine,
fill.by = fill.by
))
}
#' Single cell violin plot
#'
#' Draws a violin plot of single cell data (gene expression, metrics, PC
#' scores, etc.)
#'
#' @inheritParams RidgePlot
#' @param pt.size Point size for points
#' @param alpha Alpha value for points
#' @param split.by A factor in object metadata to split the plot by, pass 'ident'
#' to split by cell identity'
#' @param split.plot plot each group of the split violin plots by multiple or
#' single violin shapes.
#' @param adjust Adjust parameter for geom_violin
#' @param flip flip plot orientation (identities on x-axis)
#' @param add.noise determine if adding a small noise for plotting
#' @param raster Convert points to raster format. Requires 'ggrastr' to be installed.
# default is \code{NULL} which automatically rasterizes if ggrastr is installed and
# number of points exceed 100,000.
#'
#' @return A \code{\link[patchwork]{patchwork}ed} ggplot object if
#' \code{combine = TRUE}; otherwise, a list of ggplot objects
#'
#' @export
#' @concept visualization
#'
#' @seealso \code{\link{FetchData}}
#'
#' @examples
#' data("pbmc_small")
#' VlnPlot(object = pbmc_small, features = 'PC_1')
#' VlnPlot(object = pbmc_small, features = 'LYZ', split.by = 'groups')
#'
VlnPlot <- function(
object,
features,
cols = NULL,
pt.size = NULL,
alpha = 1,
idents = NULL,
sort = FALSE,
assay = NULL,
group.by = NULL,
split.by = NULL,
adjust = 1,
y.max = NULL,
same.y.lims = FALSE,
log = FALSE,
ncol = NULL,
slot = deprecated(),
layer = NULL,
split.plot = FALSE,
stack = FALSE,
combine = TRUE,
fill.by = 'feature',
flip = FALSE,
add.noise = TRUE,
raster = NULL
) {
if (is_present(arg = slot)) {
deprecate_soft(
when = '5.0.0',
what = 'VlnPlot(slot = )',
with = 'VlnPlot(layer = )'
)
layer <- slot %||% layer
}
layer.set <- suppressWarnings(
Layers(
object = object,
search = layer %||% 'data'
)
)
if (is.null(layer) && length(layer.set) == 1 && layer.set == 'scale.data'){
warning('Default search for "data" layer yielded no results; utilizing "scale.data" layer instead.')
}
assay.name <- DefaultAssay(object)
if (is.null(layer.set) & is.null(layer) ) {
warning('Default search for "data" layer in "', assay.name, '" assay yielded no results; utilizing "counts" layer instead.',
call. = FALSE, immediate. = TRUE)
layer.set <- Layers(
object = object,
search = 'counts'
)
}
if (is.null(layer.set)) {
stop('layer "', layer,'" is not found in assay: "', assay.name, '"')
} else {
layer <- layer.set
}
if (
!is.null(x = split.by) &
getOption(x = 'Seurat.warn.vlnplot.split', default = TRUE)
) {
message(
"The default behaviour of split.by has changed.\n",
"Separate violin plots are now plotted side-by-side.\n",
"To restore the old behaviour of a single split violin,\n",
"set split.plot = TRUE.
\nThis message will be shown once per session."
)
options(Seurat.warn.vlnplot.split = FALSE)
}
return(ExIPlot(
object = object,
type = ifelse(test = split.plot, yes = 'splitViolin', no = 'violin'),
features = features,
idents = idents,
ncol = ncol,
sort = sort,
assay = assay,
y.max = y.max,
same.y.lims = same.y.lims,
adjust = adjust,
pt.size = pt.size,
alpha = alpha,
cols = cols,
group.by = group.by,
split.by = split.by,
log = log,
layer = layer,
stack = stack,
combine = combine,
fill.by = fill.by,
flip = flip,
add.noise = add.noise,
raster = raster
))
}
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
# Dimensional reduction plots
#%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
#' Color dimensional reduction plot by tree split
#'
#' Returns a DimPlot colored based on whether the cells fall in clusters
#' to the left or to the right of a node split in the cluster tree.
#'
#' @param object Seurat object
#' @param node Node in cluster tree on which to base the split
#' @param left.color Color for the left side of the split
#' @param right.color Color for the right side of the split
#' @param other.color Color for all other cells
#' @inheritDotParams DimPlot -object
#'
#' @return Returns a DimPlot
#'
#' @export
#' @concept visualization
#'
#' @seealso \code{\link{DimPlot}}
#'
#' @examples
#' \dontrun{
#' if (requireNamespace("ape", quietly = TRUE)) {
#' data("pbmc_small")
#' pbmc_small <- BuildClusterTree(object = pbmc_small, verbose = FALSE)
#' PlotClusterTree(pbmc_small)
#' ColorDimSplit(pbmc_small, node = 5)
#' }
#' }
#'
ColorDimSplit <- function(
object,
node,
left.color = 'red',
right.color = 'blue',
other.color = 'grey50',
...
) {
CheckDots(..., fxns = 'DimPlot')
tree <- Tool(object = object, slot = "BuildClusterTree")
split <- tree$edge[which(x = tree$edge[, 1] == node), ][, 2]
all.children <- sort(x = tree$edge[, 2][!tree$edge[, 2] %in% tree$edge[, 1]])
left.group <- DFT(tree = tree, node = split[1], only.children = TRUE)
right.group <- DFT(tree = tree, node = split[2], only.children = TRUE)
if (any(is.na(x = left.group))) {
left.group <- split[1]
}
if (any(is.na(x = right.group))) {
right.group <- split[2]
}
left.group <- MapVals(v = left.group, from = all.children, to = tree$tip.label)
right.group <- MapVals(v = right.group, from = all.children, to = tree$tip.label)
remaining.group <- setdiff(x = tree$tip.label, y = c(left.group, right.group))
left.cells <- WhichCells(object = object, ident = left.group)
right.cells <- WhichCells(object = object, ident = right.group)
remaining.cells <- WhichCells(object = object, ident = remaining.group)
object <- SetIdent(
object = object,
cells = left.cells,
value = "Left Split"
)
object <- SetIdent(
object = object,
cells = right.cells,
value = "Right Split"
)
object <- SetIdent(
object = object,
cells = remaining.cells,
value = "Not in Split"
)
levels(x = object) <- c("Left Split", "Right Split", "Not in Split")
colors.use = c(left.color, right.color, other.color)
return(DimPlot(object = object, cols = colors.use, ...))
}
#' Dimensional reduction plot
#'
#' Graphs the output of a dimensional reduction technique on a 2D scatter plot where each point is a
#' cell and it's positioned based on the cell embeddings determined by the reduction technique. By
#' default, cells are colored by their identity class (can be changed with the group.by parameter).
#'
#' @param object Seurat object
#' @param dims Dimensions to plot, must be a two-length numeric vector specifying x- and y-dimensions
#' @param cells Vector of cells to plot (default is all cells)
#' @param cols Vector of colors, each color corresponds to an identity class. This may also be a single character
#' or numeric value corresponding to a palette as specified by \code{\link[RColorBrewer]{brewer.pal.info}}.
#' By default, ggplot2 assigns colors. We also include a number of palettes from the pals package.
#' See \code{\link{DiscretePalette}} for details.
#' @param pt.size Adjust point size for plotting
#' @param reduction Which dimensionality reduction to use. If not specified, first searches for umap, then tsne, then pca
#' @param group.by Name of one or more metadata columns to group (color) cells by
#' (for example, orig.ident); pass 'ident' to group by identity class
#' @param split.by A factor in object metadata to split the plot by, pass 'ident'
#' to split by cell identity'
#' @param shape.by If NULL, all points are circles (default). You can specify any
#' cell attribute (that can be pulled with FetchData) allowing for both
#' different colors and different shapes on cells. Only applicable if \code{raster = FALSE}.
#' @param order Specify the order of plotting for the idents. This can be
#' useful for crowded plots if points of interest are being buried. Provide
#' either a full list of valid idents or a subset to be plotted last (on top)
#' @param shuffle Whether to randomly shuffle the order of points. This can be
#' useful for crowded plots if points of interest are being buried. (default is FALSE)
#' @param seed Sets the seed if randomly shuffling the order of points.
#' @param label Whether to label the clusters
#' @param label.size Sets size of labels
#' @param label.color Sets the color of the label text
#' @param label.box Whether to put a box around the label text (geom_text vs
#' geom_label)
#' @param alpha Alpha value for plotting (default is 1)
#' @param repel Repel labels
#' @param cells.highlight A list of character or numeric vectors of cells to
#' highlight. If only one group of cells desired, can simply
#' pass a vector instead of a list. If set, colors selected cells to the color(s)
#' in \code{cols.highlight} and other cells black (white if dark.theme = TRUE);
#' will also resize to the size(s) passed to \code{sizes.highlight}
#' @param cols.highlight A vector of colors to highlight the cells as; will
#' repeat to the length groups in cells.highlight
#' @param sizes.highlight Size of highlighted cells; will repeat to the length
#' groups in cells.highlight. If \code{sizes.highlight = TRUE} size of all
#' points will be this value.
#' @param na.value Color value for NA points when using custom scale
#' @param ncol Number of columns for display when combining plots
#' @param combine Combine plots into a single \code{\link[patchwork]{patchwork}ed}
#' ggplot object. If \code{FALSE}, return a list of ggplot objects
#' @param raster Convert points to raster format, default is \code{NULL} which
#' automatically rasterizes if plotting more than 100,000 cells
#' @param raster.dpi Pixel resolution for rasterized plots, passed to geom_scattermore().
#' Default is c(512, 512).
#'
#' @return A \code{\link[patchwork]{patchwork}ed} ggplot object if
#' \code{combine = TRUE}; otherwise, a list of ggplot objects
#'
#' @importFrom rlang !!
#' @importFrom ggplot2 facet_wrap vars sym labs
#' @importFrom patchwork wrap_plots
#'
#' @export
#' @concept visualization
#'
#' @note For the old \code{do.hover} and \code{do.identify} functionality, please see
#' \code{HoverLocator} and \code{CellSelector}, respectively.
#'
#' @aliases TSNEPlot PCAPlot ICAPlot
#' @seealso \code{\link{FeaturePlot}} \code{\link{HoverLocator}}
#' \code{\link{CellSelector}} \code{\link{FetchData}}
#'
#' @examples
#' data("pbmc_small")
#' DimPlot(object = pbmc_small)
#' DimPlot(object = pbmc_small, split.by = 'letter.idents')
#'
DimPlot <- function(
object,
dims = c(1, 2),
cells = NULL,
cols = NULL,
pt.size = NULL,
reduction = NULL,
group.by = NULL,
split.by = NULL,
shape.by = NULL,
order = NULL,
shuffle = FALSE,
seed = 1,
label = FALSE,
label.size = 4,
label.color = 'black',
label.box = FALSE,
repel = FALSE,
alpha = 1,
cells.highlight = NULL,
cols.highlight = '#DE2D26',
sizes.highlight = 1,
na.value = 'grey50',
ncol = NULL,
combine = TRUE,
raster = NULL,
raster.dpi = c(512, 512)
) {
if (!is_integerish(x = dims, n = 2L, finite = TRUE) || !all(dims > 0L)) {
abort(message = "'dims' must be a two-length integer vector")
}
reduction <- reduction %||% DefaultDimReduc(object = object)
# cells <- cells %||% colnames(x = object)
##### Cells for all cells in the assay.
#### Cells function should not only get default layer
cells <- cells %||% Cells(
x = object,
assay = DefaultAssay(object = object[[reduction]])
)
# data <- Embeddings(object = object[[reduction]])[cells, dims]
# data <- as.data.frame(x = data)
dims <- paste0(Key(object = object[[reduction]]), dims)
orig.groups <- group.by
group.by <- group.by %||% 'ident'
data <- FetchData(
object = object,
vars = c(dims, group.by),
cells = cells,
clean = 'project'
)
# cells <- rownames(x = object)
# object[['ident']] <- Idents(object = object)
# orig.groups <- group.by
# group.by <- group.by %||% 'ident'
# data <- cbind(data, object[[group.by]][cells, , drop = FALSE])
group.by <- colnames(x = data)[3:ncol(x = data)]
for (group in group.by) {
if (!is.factor(x = data[, group])) {
data[, group] <- factor(x = data[, group])
}
}
if (!is.null(x = shape.by)) {
data[, shape.by] <- object[[shape.by, drop = TRUE]]
}
if (!is.null(x = split.by)) {
split <- FetchData(object = object, vars = split.by, clean=TRUE)[split.by]
data <- data[rownames(split),]
data[, split.by] <- split
}
if (isTRUE(x = shuffle)) {
set.seed(seed = seed)
data <- data[sample(x = 1:nrow(x = data)), ]
}
plots <- lapply(
X = group.by,
FUN = function(x) {
plot <- SingleDimPlot(
data = data[, c(dims, x, split.by, shape.by)],
dims = dims,
col.by = x,
cols = cols,
pt.size = pt.size,
shape.by = shape.by,
order = order,
alpha = alpha,
label = FALSE,
cells.highlight = cells.highlight,
cols.highlight = cols.highlight,
sizes.highlight = sizes.highlight,
na.value = na.value,
raster = raster,
raster.dpi = raster.dpi
)
if (label) {
plot <- LabelClusters(
plot = plot,
id = x,
repel = repel,
size = label.size,
split.by = split.by,
box = label.box,
color = label.color
)
}
if (!is.null(x = split.by)) {
plot <- plot + FacetTheme() +
facet_wrap(
facets = vars(!!sym(x = split.by)),
ncol = if (length(x = group.by) > 1 || is.null(x = ncol)) {
length(x = unique(x = data[, split.by]))
} else {
ncol
}
)
}
plot <- if (is.null(x = orig.groups)) {
plot + labs(title = NULL)
} else {
plot + CenterTitle()
}
}
)
if (!is.null(x = split.by)) {
ncol <- 1
}
if (combine) {
plots <- wrap_plots(plots, ncol = orig.groups %iff% ncol)
}
return(plots)
}
#' Visualize 'features' on a dimensional reduction plot
#'
#' Colors single cells on a dimensional reduction plot according to a 'feature'
#' (i.e. gene expression, PC scores, number of genes detected, etc.)
#'
#' @inheritParams DimPlot
#' @param order Boolean determining whether to plot cells in order of expression. Can be useful if
#' cells expressing given feature are getting buried.
#' @param features Vector of features to plot. Features can come from:
#' \itemize{
#' \item An \code{Assay} feature (e.g. a gene name - "MS4A1")