Skip to content
This repository was archived by the owner on Oct 14, 2025. It is now read-only.

Commit 695bb83

Browse files
multimericmultimeric
committed
Better downsampling, vignette plot layout
1 parent 99c521a commit 695bb83

File tree

3 files changed

+92
-110
lines changed

3 files changed

+92
-110
lines changed

‎R/dev.R‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -216,11 +216,11 @@ downsample_metadata <- function(output = "sample_meta.parquet"){
216216
# Remove datasets that only have 1 matching cell, which will
217217
# break downstream
218218
dplyr::filter(dplyr::n() > 1) |>
219-
dplyr::pull(.data$file_id_db)
220-
219+
dplyr::pull(.data$file_id_db) |> unique()
220+
221221
dataset_sizes |>
222222
dplyr::filter(.data$file_id_db %in% all_ids) |>
223-
dplyr::slice_min(n=1, order_by = .data$n, with_ties = FALSE) |>
223+
dplyr::slice_min(n=50, order_by = .data$n) |>
224224
dplyr::pull(.data$file_id_db)
225225
}) |>
226226
purrr::reduce(union)
@@ -229,7 +229,7 @@ downsample_metadata <- function(output = "sample_meta.parquet"){
229229
dplyr::filter(.data$file_id_db %in% minimal_file_ids) |>
230230
dplyr::arrange(.data$file_id_db, .data$sample_) |>
231231
dplyr::collect() |>
232-
arrow::write_parquet("sample_meta.parquet")
232+
arrow::write_parquet(output)
233233

234234
NULL
235235
}

‎README.md‎

Lines changed: 73 additions & 85 deletions
Original file line numberDiff line numberDiff line change
@@ -38,22 +38,23 @@ library(CuratedAtlasQueryR)
3838
### Load the metadata
3939

4040
``` r
41-
metadata <- get_metadata(cache_directory = "/stornext/Home/data/allstaff/m/milton.m/HCAquery/fake_cache")
41+
# Note: in real applications you should use the default value of remote_url
42+
metadata <- get_metadata(remote_url = METADATA_URL)
4243
metadata
43-
#> # Source: table</stornext/Home/data/allstaff/m/milton.m/HCAquery/fake_cache/metadata.0.2.3.parquet> [?? x 56]
44+
#> # Source: table</vast/scratch/users/milton.m/cache/R/CuratedAtlasQueryR/metadata.0.2.3.parquet> [?? x 56]
4445
#> # Database: DuckDB 0.7.1 [unknown@Linux 3.10.0-1160.88.1.el7.x86_64:R 4.2.1/:memory:]
4546
#> cell_ sample_ cell_…¹ cell_…² confi…³ cell_…⁴ cell_…⁵ cell_…⁶ sampl…⁷ _samp…⁸
4647
#> <chr> <chr> <chr> <chr> <dbl> <chr> <chr> <chr> <chr> <chr>
47-
#> 1 ACGC… 188e17… classi… cd14 m… 1 cd14 m… monocy… classi… d035c6… HGR000…
48-
#> 2 GACT… 188e17… classi… cd14 m… 1 cd14 m… monocy… classi… d035c6… HGR000…
49-
#> 3 TGTC… 188e17… classi… cd14 m… 1 cd14 m… monocy… classi… d035c6… HGR000…
50-
#> 4 GTTA… 188e17… classi… cd14 m… 1 cd14 m… monocy… classi… d035c6… HGR000…
51-
#> 5 CTCG… 188e17… classi… cd14 m… 1 cd14 m… monocy… classi… d035c6… HGR000…
52-
#> 6 CAAC… 188e17… classi… cd14 m… 1 cd14 m… monocy… classi… d035c6… HGR000…
53-
#> 7 GGTG… 188e17… classi… cd14 m… 1 cd14 m… monocy… classi… d035c6… HGR000…
54-
#> 8 GGTG… 188e17… classi… cd14 m… 1 cd14 m… monocy… classi… d035c6… HGR000…
55-
#> 9 GCTG… 188e17… classi… cd14 m… 1 cd14 m… monocy… interm… d035c6… HGR000…
56-
#> 10 ACCT… 188e17… classi… cd14 m… 1 cd14 m… monocy… classi… d035c6… HGR000…
48+
#> 1 8387… 7bd7b8… natura… immune… 5 cd8 tem gmp natura… 842ce7… Q59___…
49+
#> 2 1768… 7bd7b8… natura… immune… 5 cd8 tem cd8 tcm natura… 842ce7… Q59___…
50+
#> 3 6329… 7bd7b8… natura… immune… 5 cd8 tem clp termin… 842ce7… Q59___…
51+
#> 4 5027… 7bd7b8… natura… immune… 5 cd8 tem clp natura… 842ce7… Q59___…
52+
#> 5 7956… 7bd7b8… natura… immune… 5 cd8 tem clp natura… 842ce7… Q59___…
53+
#> 6 4305… 7bd7b8… natura… immune… 5 cd8 tem clp termin… 842ce7… Q59___…
54+
#> 7 2126… 933f96… natura… ilc 1 nk nk natura… c250bf… AML3__…
55+
#> 8 3114… 933f96… natura… immune… 5 mait nk natura… c250bf… AML3__…
56+
#> 9 1407… 933f96… natura… immune… 5 mait clp natura… c250bf… AML3__…
57+
#> 10 2911… 933f96… natura… nk 5 nk clp natura… c250bf… AML3__…
5758
#> # … with more rows, 46 more variables: assay <chr>,
5859
#> # assay_ontology_term_id <chr>, file_id_db <chr>,
5960
#> # cell_type_ontology_term_id <chr>, development_stage <chr>,
@@ -70,14 +71,20 @@ The `metadata` variable can then be re-used for all subsequent queries.
7071
``` r
7172
metadata |>
7273
dplyr::distinct(tissue, file_id)
73-
#> # Source: SQL [4 x 2]
74+
#> # Source: SQL [10 x 2]
7475
#> # Database: DuckDB 0.7.1 [unknown@Linux 3.10.0-1160.88.1.el7.x86_64:R 4.2.1/:memory:]
75-
#> tissue file_id
76-
#> <chr> <chr>
77-
#> 1 blood 1042ba0a-98c5-4816-897d-e192eb9303e3
78-
#> 2 lung parenchyma 6661ab3a-792a-4682-b58c-4afb98b2c016
79-
#> 3 respiratory airway 6661ab3a-792a-4682-b58c-4afb98b2c016
80-
#> 4 nose 6661ab3a-792a-4682-b58c-4afb98b2c016
76+
#> tissue file_id
77+
#> <chr> <chr>
78+
#> 1 bone marrow 1ff5cbda-4d41-4f50-8c7e-cbe4a90e38db
79+
#> 2 lung parenchyma 6661ab3a-792a-4682-b58c-4afb98b2c016
80+
#> 3 respiratory airway 6661ab3a-792a-4682-b58c-4afb98b2c016
81+
#> 4 nose 6661ab3a-792a-4682-b58c-4afb98b2c016
82+
#> 5 renal pelvis dc9d8cdd-29ee-4c44-830c-6559cb3d0af6
83+
#> 6 kidney dc9d8cdd-29ee-4c44-830c-6559cb3d0af6
84+
#> 7 renal medulla dc9d8cdd-29ee-4c44-830c-6559cb3d0af6
85+
#> 8 cortex of kidney dc9d8cdd-29ee-4c44-830c-6559cb3d0af6
86+
#> 9 kidney blood vessel dc9d8cdd-29ee-4c44-830c-6559cb3d0af6
87+
#> 10 lung a2796032-d015-40c4-b9db-835207e5bd5b
8188
```
8289

8390
## Download single-cell RNA sequencing counts
@@ -287,10 +294,14 @@ HLA-A across all tissues
287294
#> ℹ Reading files.
288295
#> ℹ Compiling Single Cell Experiment.
289296
#> Warning: Transformation introduced infinite values in continuous y-axis
297+
#> Warning in min(x): no non-missing arguments to min; returning Inf
298+
#> Warning in max(x): no non-missing arguments to max; returning -Inf
290299

291300
![](/stornext/Home/data/allstaff/m/milton.m/HCAquery/README_files/figure-gfm/unnamed-chunk-14-1.png)<!-- -->
292301

293302
#> Warning: Transformation introduced infinite values in continuous y-axis
303+
#> Warning in min(x): no non-missing arguments to min; returning Inf
304+
#> Warning in max(x): no non-missing arguments to max; returning -Inf
294305

295306
![](/stornext/Home/data/allstaff/m/milton.m/HCAquery/README_files/figure-gfm/unnamed-chunk-14-2.png)<!-- -->
296307

@@ -311,14 +322,14 @@ counts |>
311322
metadata |>
312323

313324
# Filter and subset
314-
filter(cell_type_harmonised=="nk") |>
325+
dplyr::filter(cell_type_harmonised=="nk") |>
315326

316327
# Get counts per million for HCA-A gene
317328
get_single_cell_experiment(assays = "cpm", features = "HLA-A") |>
318329

319-
# Plot (styling code have been omitted)
320-
join_features("HLA-A", shape = "wide") |>
321-
ggplot(aes( tissue_harmonised, `HLA.A`,color = file_id)) +
330+
# Plot (styling code have been omitted)
331+
tidySingleCellExperiment::join_features("HLA-A", shape = "wide") |>
332+
ggplot(aes(tissue_harmonised, `HLA.A`,color = file_id)) +
322333
geom_jitter(shape=".")
323334
#> ℹ Realising metadata.
324335
#> ℹ Synchronising files
@@ -341,62 +352,39 @@ function returns a data frame with one row per dataset, including the
341352
data frame.
342353

343354
``` r
344-
harmonised <- get_metadata() |> dplyr::filter(tissue == "kidney blood vessel")
355+
harmonised <- metadata |> dplyr::filter(tissue == "kidney blood vessel")
345356
unharmonised <- get_unharmonised_metadata(harmonised)
346357
unharmonised
347-
#> # A tibble: 4 × 2
358+
#> # A tibble: 1 × 2
348359
#> file_id unharmonised
349360
#> <chr> <list>
350-
#> 1 63523aa3-0d04-4fc6-ac59-5cadd3e73a14 <tbl_dck_[,17]>
351-
#> 2 8fee7b82-178b-4c04-bf23-04689415690d <tbl_dck_[,12]>
352-
#> 3 dc9d8cdd-29ee-4c44-830c-6559cb3d0af6 <tbl_dck_[,14]>
353-
#> 4 f7e94dbb-8638-4616-aaf9-16e2212c369f <tbl_dck_[,14]>
361+
#> 1 dc9d8cdd-29ee-4c44-830c-6559cb3d0af6 <tbl_dck_[,14]>
354362
```
355363

356364
Notice that the columns differ between each dataset’s data frame:
357365

358366
``` r
359367
dplyr::pull(unharmonised) |> head(2)
360368
#> [[1]]
361-
#> # Source: SQL [?? x 17]
369+
#> # Source: SQL [?? x 14]
362370
#> # Database: DuckDB 0.7.1 [unknown@Linux 3.10.0-1160.88.1.el7.x86_64:R 4.2.1/:memory:]
363371
#> cell_ file_id donor…¹ donor…² libra…³ mappe…⁴ sampl…⁵ suspe…⁶ suspe…⁷ autho…⁸
364372
#> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
365-
#> 1 4602… 63523a… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
366-
#> 2 4602… 63523a… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
367-
#> 3 4602… 63523a… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
368-
#> 4 4602… 63523a… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
369-
#> 5 4602… 63523a… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
370-
#> 6 4602… 63523a… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
371-
#> 7 4602… 63523a… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
372-
#> 8 4602… 63523a… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
373-
#> 9 4602… 63523a… 19 mon… 463181… 671785… GENCOD… 125234… cell c7485e… CD4 T …
374-
#> 10 4602… 63523a… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
375-
#> # … with more rows, 7 more variables: cell_state <chr>,
376-
#> # reported_diseases <chr>, Short_Sample <chr>, Project <chr>,
377-
#> # Experiment <chr>, compartment <chr>, broad_celltype <chr>, and abbreviated
373+
#> 1 4602… dc9d8c… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
374+
#> 2 4602… dc9d8c… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
375+
#> 3 4602… dc9d8c… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
376+
#> 4 4602… dc9d8c… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
377+
#> 5 4602… dc9d8c… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
378+
#> 6 4602… dc9d8c… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
379+
#> 7 4602… dc9d8c… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
380+
#> 8 4602… dc9d8c… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
381+
#> 9 4602… dc9d8c… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
382+
#> 10 4602… dc9d8c… 27 mon… a8536b… 5ddaea… GENCOD… 61bf84… cell d8a44f… Pelvic…
383+
#> # … with more rows, 4 more variables: reported_diseases <chr>,
384+
#> # Experiment <chr>, Project <chr>, broad_celltype <chr>, and abbreviated
378385
#> # variable names ¹​donor_age, ²​donor_uuid, ³​library_uuid,
379386
#> # ⁴​mapped_reference_annotation, ⁵​sample_uuid, ⁶​suspension_type,
380387
#> # ⁷​suspension_uuid, ⁸​author_cell_type
381-
#>
382-
#> [[2]]
383-
#> # Source: SQL [?? x 12]
384-
#> # Database: DuckDB 0.7.1 [unknown@Linux 3.10.0-1160.88.1.el7.x86_64:R 4.2.1/:memory:]
385-
#> cell_ file_id orig.…¹ nCoun…² nFeat…³ seura…⁴ Project donor…⁵ compa…⁶ broad…⁷
386-
#> <chr> <chr> <chr> <dbl> <chr> <chr> <chr> <chr> <chr> <chr>
387-
#> 1 1069 8fee7b… 4602ST… 16082 3997 25 Experi… Wilms3 non_PT Pelvic…
388-
#> 2 1214 8fee7b… 4602ST… 1037 606 25 Experi… Wilms3 non_PT Pelvic…
389-
#> 3 2583 8fee7b… 4602ST… 3028 1361 25 Experi… Wilms3 non_PT Pelvic…
390-
#> 4 2655 8fee7b… 4602ST… 1605 859 25 Experi… Wilms3 non_PT Pelvic…
391-
#> 5 3609 8fee7b… 4602ST… 1144 682 25 Experi… Wilms3 non_PT Pelvic…
392-
#> 6 3624 8fee7b… 4602ST… 1874 963 25 Experi… Wilms3 non_PT Pelvic…
393-
#> 7 3946 8fee7b… 4602ST… 1296 755 25 Experi… Wilms3 non_PT Pelvic…
394-
#> 8 5163 8fee7b… 4602ST… 11417 3255 25 Experi… Wilms3 non_PT Pelvic…
395-
#> 9 5446 8fee7b… 4602ST… 1769 946 19 Experi… Wilms2 lympho… CD4 T …
396-
#> 10 6275 8fee7b… 4602ST… 3750 1559 25 Experi… Wilms3 non_PT Pelvic…
397-
#> # … with more rows, 2 more variables: author_cell_type <chr>, Sample <chr>, and
398-
#> # abbreviated variable names ¹​orig.ident, ²​nCount_RNA, ³​nFeature_RNA,
399-
#> # ⁴​seurat_clusters, ⁵​donor_id, ⁶​compartment, ⁷​broad_celltype
400388
```
401389

402390
# Cell metadata
@@ -484,13 +472,13 @@ sessionInfo()
484472
#> [8] base
485473
#>
486474
#> other attached packages:
487-
#> [1] ggplot2_3.4.1 tidySingleCellExperiment_1.6.3
488-
#> [3] SingleCellExperiment_1.18.1 SummarizedExperiment_1.26.1
489-
#> [5] Biobase_2.56.0 GenomicRanges_1.48.0
490-
#> [7] GenomeInfoDb_1.32.4 IRanges_2.30.1
491-
#> [9] S4Vectors_0.34.0 BiocGenerics_0.42.0
492-
#> [11] MatrixGenerics_1.8.1 matrixStats_0.63.0
493-
#> [13] ttservice_0.2.2 CuratedAtlasQueryR_0.99.1
475+
#> [1] tidySingleCellExperiment_1.6.3 SingleCellExperiment_1.18.1
476+
#> [3] SummarizedExperiment_1.26.1 Biobase_2.56.0
477+
#> [5] GenomicRanges_1.48.0 GenomeInfoDb_1.32.4
478+
#> [7] IRanges_2.30.1 S4Vectors_0.34.0
479+
#> [9] BiocGenerics_0.42.0 MatrixGenerics_1.8.1
480+
#> [11] matrixStats_0.63.0 ttservice_0.2.2
481+
#> [13] ggplot2_3.4.1 CuratedAtlasQueryR_0.99.1
494482
#>
495483
#> loaded via a namespace (and not attached):
496484
#> [1] plyr_1.8.8 igraph_1.4.1 lazyeval_0.2.2
@@ -521,20 +509,20 @@ sessionInfo()
521509
#> [76] goftest_1.2-3 knitr_1.42 fitdistrplus_1.1-8
522510
#> [79] purrr_1.0.1 RANN_2.6.1 pbapply_1.6-0
523511
#> [82] future_1.30.0 nlme_3.1-157 mime_0.12
524-
#> [85] compiler_4.2.1 rstudioapi_0.14 plotly_4.10.1
525-
#> [88] png_0.1-8 spatstat.utils_3.0-1 tibble_3.1.8
526-
#> [91] bslib_0.4.2 stringi_1.7.12 highr_0.10
527-
#> [94] forcats_1.0.0 lattice_0.20-45 Matrix_1.5-3
528-
#> [97] vctrs_0.5.2 pillar_1.8.1 lifecycle_1.0.3
529-
#> [100] rhdf5filters_1.8.0 spatstat.geom_3.0-3 lmtest_0.9-40
530-
#> [103] jquerylib_0.1.4 RcppAnnoy_0.0.20 data.table_1.14.6
531-
#> [106] cowplot_1.1.1 bitops_1.0-7 irlba_2.3.5.1
532-
#> [109] httpuv_1.6.7 patchwork_1.1.2 R6_2.5.1
533-
#> [112] promises_1.2.0.1 KernSmooth_2.23-20 gridExtra_2.3
534-
#> [115] parallelly_1.33.0 codetools_0.2-18 assertthat_0.2.1
535-
#> [118] MASS_7.3-57 rhdf5_2.40.0 rprojroot_2.0.3
536-
#> [121] withr_2.5.0 SeuratObject_4.1.3 sctransform_0.3.5
537-
#> [124] GenomeInfoDbData_1.2.8 parallel_4.2.1 grid_4.2.1
538-
#> [127] tidyr_1.3.0 rmarkdown_2.20 Rtsne_0.16
539-
#> [130] spatstat.explore_3.0-5 shiny_1.7.4
512+
#> [85] compiler_4.2.1 rstudioapi_0.14 curl_4.3.3
513+
#> [88] plotly_4.10.1 png_0.1-8 spatstat.utils_3.0-1
514+
#> [91] tibble_3.1.8 bslib_0.4.2 stringi_1.7.12
515+
#> [94] highr_0.10 forcats_1.0.0 lattice_0.20-45
516+
#> [97] Matrix_1.5-3 vctrs_0.5.2 pillar_1.8.1
517+
#> [100] lifecycle_1.0.3 rhdf5filters_1.8.0 spatstat.geom_3.0-3
518+
#> [103] lmtest_0.9-40 jquerylib_0.1.4 RcppAnnoy_0.0.20
519+
#> [106] data.table_1.14.6 cowplot_1.1.1 bitops_1.0-7
520+
#> [109] irlba_2.3.5.1 httpuv_1.6.7 patchwork_1.1.2
521+
#> [112] R6_2.5.1 promises_1.2.0.1 KernSmooth_2.23-20
522+
#> [115] gridExtra_2.3 parallelly_1.33.0 codetools_0.2-18
523+
#> [118] assertthat_0.2.1 MASS_7.3-57 rhdf5_2.40.0
524+
#> [121] rprojroot_2.0.3 withr_2.5.0 SeuratObject_4.1.3
525+
#> [124] sctransform_0.3.5 GenomeInfoDbData_1.2.8 parallel_4.2.1
526+
#> [127] grid_4.2.1 tidyr_1.3.0 rmarkdown_2.20
527+
#> [130] Rtsne_0.16 spatstat.explore_3.0-5 shiny_1.7.4
540528
```

‎vignettes/Introduction.Rmd‎

Lines changed: 15 additions & 21 deletions
Original file line numberDiff line numberDiff line change
@@ -215,19 +215,20 @@ single_cell_counts |> HDF5Array::saveHDF5SummarizedExperiment("single_cell_count
215215

216216
We can gather all CD14 monocytes cells and plot the distribution of HLA-A across all tissues
217217

218-
```{r, echo=FALSE}
218+
```{r}
219219
suppressPackageStartupMessages({
220220
library(ggplot2)
221221
})
222222
223223
# Plots with styling
224224
counts <- metadata |>
225225
# Filter and subset
226-
filter(cell_type_harmonised == "cd14 mono") |>
227-
filter(file_id_db != "c5a05f23f9784a3be3bfa651198a48eb") |>
226+
dplyr::filter(cell_type_harmonised == "cd14 mono") |>
227+
dplyr::filter(file_id_db != "c5a05f23f9784a3be3bfa651198a48eb") |>
228228
229229
# Get counts per million for HCA-A gene
230230
get_single_cell_experiment(assays = "cpm", features = "HLA-A") |>
231+
suppressMessages() |>
231232
232233
# Add feature to table
233234
tidySingleCellExperiment::join_features("HLA-A", shape = "wide") |>
@@ -237,7 +238,7 @@ counts <- metadata |>
237238
238239
# Plot by disease
239240
counts |>
240-
dplyr::with_groups(disease, ~ .x |> mutate(median_count = median(`HLA.A`, rm.na=TRUE))) |>
241+
dplyr::with_groups(disease, ~ .x |> dplyr::mutate(median_count = median(`HLA.A`, rm.na=TRUE))) |>
241242
242243
# Plot
243244
ggplot(aes(forcats::fct_reorder(disease, median_count,.desc = TRUE), `HLA.A`,color = file_id)) +
@@ -253,7 +254,7 @@ counts |>
253254
254255
# Plot by tissue
255256
counts |>
256-
dplyr::with_groups(tissue_harmonised, ~ .x |> mutate(median_count = median(`HLA.A`, rm.na=TRUE))) |>
257+
dplyr::with_groups(tissue_harmonised, ~ .x |> dplyr::mutate(median_count = median(`HLA.A`, rm.na=TRUE))) |>
257258
258259
# Plot
259260
ggplot(aes(forcats::fct_reorder(tissue_harmonised, median_count,.desc = TRUE), `HLA.A`,color = file_id)) +
@@ -265,39 +266,32 @@ counts |>
265266
theme_bw() +
266267
theme(axis.text.x = element_text(angle = 60, vjust = 1, hjust = 1)) +
267268
xlab("Tissue") +
268-
ggtitle("HLA-A in CD14 monocytes by tissue")
269+
ggtitle("HLA-A in CD14 monocytes by tissue") +
270+
theme(legend.position = "none")
269271
```
270272

271273
```{r}
272-
library(tidySingleCellExperiment)
273-
library(ggplot2)
274-
275274
counts |>
276275
ggplot(aes( disease, `HLA.A`,color = file_id)) +
277-
geom_jitter(shape=".")
278-
```
279-
280-
```{r, echo=FALSE, message=FALSE, warning=FALSE}
281-
find_figure("HLA_A_disease_plot.png") |> knitr::include_graphics()
276+
geom_jitter(shape=".") +
277+
theme(legend.position = "none")
282278
```
283279

284280
```{r}
285281
metadata |>
286282
287283
# Filter and subset
288-
filter(cell_type_harmonised=="nk") |>
284+
dplyr::filter(cell_type_harmonised=="nk") |>
289285
290286
# Get counts per million for HCA-A gene
291287
get_single_cell_experiment(assays = "cpm", features = "HLA-A") |>
288+
suppressMessages() |>
292289
293290
# Plot (styling code have been omitted)
294291
tidySingleCellExperiment::join_features("HLA-A", shape = "wide") |>
295-
ggplot(aes( tissue_harmonised, `HLA.A`,color = file_id)) +
296-
geom_jitter(shape=".")
297-
```
298-
299-
```{r, echo=FALSE, message=FALSE, warning=FALSE}
300-
find_figure("HLA_A_tissue_plot.png") |> knitr::include_graphics()
292+
ggplot(aes(tissue_harmonised, `HLA.A`,color = file_id)) +
293+
geom_jitter(shape=".") +
294+
theme(legend.position = "none")
301295
```
302296

303297
## Obtain Unharmonised Metadata

0 commit comments

Comments
 (0)