Single-cell transcriptomic characterization of a gastrulating human embryo

Jialei Duan

2022-01-24

---

Tyser, R.C.V., Mahammadov, E., Nakanoh, S., Vallier, L., Scialdone, A., and Srinivas, S. (2021). Single-cell transcriptomic characterization of a gastrulating human embryo. Nature 600, 285–289.

• BioProject Accession: PRJEB40781
• AEArrayExpress Accession: E-MTAB-9388

---

Load required packages.

library(tidyverse)
library(Matrix)
library(patchwork)
library(extrafont)

Sys.time()

[1] "2022-01-24 21:10:13 CST"

Data preparation

Functions loading

source(
    file = file.path(
        SCRIPT_DIR,
        "utilities.R"
    )
)

plot_embedding_highlight <- function(embedding, x, y, label, n_cols = 3) {
    cell_metadata_selected <- x
    selected_column <- y

    purrr::map(levels(cell_metadata_selected[[selected_column]]), \(x) {
        values <- embedding |>
            dplyr::left_join(cell_metadata_selected) |>
            dplyr::mutate(
                value = case_when(
                    .data[[selected_column]] == x ~ "1",
                    .data[[selected_column]] != x ~ "0"
                )
            ) |>
            dplyr::pull(value) |>
            as.integer() |>
            as.factor()

        plot_embedding(
            embedding = embedding[, c(x_column, y_column)],
            color_values = values,
            label = glue::glue(
                "{label}; ",
                "{x}: {sum(as.integer(as.character(values)), na.rm = TRUE)}"
            ),
            label_position = NULL,
            show_color_value_labels = FALSE,
            show_color_legend = FALSE,
            geom_point_size = GEOM_POINT_SIZE,
            sort_values = TRUE,
            shuffle_values = FALSE,
            rasterise = RASTERISED,
            legend_size = 2
        ) +
            theme_customized(
                legend_key_size = 2,
                legend_text_size = 5
            ) +
            scale_color_manual(
                na.translate = TRUE,
                values = c("grey70", "salmon"),
                na.value = "#7F7F7F"
            ) +
            ggplot2::annotate(
                geom = "text",
                x = Inf,
                y = Inf,
                label = sum(as.integer(as.character(values)), na.rm = TRUE),
                size = 5 / ggplot2::.pt,
                hjust = 1,
                vjust = 1,
                na.rm = FALSE
            )
    }) |>
        purrr::reduce(`+`) +
        patchwork::plot_layout(ncol = n_cols) +
        patchwork::plot_annotation(
            theme = ggplot2::theme(plot.margin = ggplot2::margin())
        )
}

Data loading

PROJECT_DIR <- "/Users/jialei/Dropbox/Data/Projects/UTSW/Peri-implantation"

Matrix

ad <- reticulate::import(module = "anndata", convert = TRUE)
print(ad$`__version__`)

[1] "0.7.6"

adata_files <- purrr::map(c("PRJEB40781", "PRJEB11202", "PRJNA555602"), \(x) {
    file.path(
        PROJECT_DIR,
        "raw",
        "public",
        x,
        "matrix",
        "adata.h5ad"
    )
})
purrr::map_lgl(adata_files, file.exists)

[1] TRUE TRUE TRUE

BACKED <- NULL
matrix_readcount_use <- purrr::map(adata_files, function(x) {
    ad$read_h5ad(
        filename = x, backed = BACKED
    ) |>
        convert_adata()
}) |>
    purrr::reduce(cbind)

dim(matrix_readcount_use)

[1] 33538 12690

Metadata

BACKED <- "r"
cell_metadata <- purrr::map(adata_files, function(x) {
    ad$read_h5ad(
        filename = x, backed = BACKED
    )$obs |>
        tibble::rownames_to_column(var = "cell") |>
        dplyr::select(cell, everything())
}) |>
    dplyr::bind_rows() |>
    dplyr::select(-batch)

cell_metadata |> head() |> knitr::kable()

cell	num_umis	num_features	mt_percentage
ERS5181934	169252	7589	0.0378016
ERS5181935	1477974	4231	0.0069426
ERS5181936	1178979	4251	0.0039034
ERS5181937	1187514	3902	0.0184217
ERS5181938	1794419	3900	0.0309978
ERS5181939	1379323	3622	0.0074674

Check memory usage.

purrr::walk(list(matrix_readcount_use, cell_metadata), function(x) {
    print(object.size(x), units = "auto", standard = "SI")
})

828.5 MB
1.3 MB

Clustering of a CS7 human gastrula

Cell metadata & embedding

cell_metadata_PRJEB40781 <- vroom::vroom(
    file = file.path(
        PROJECT_DIR,
        "raw",
        "public",
        "PRJEB40781",
        "matrix",
        "cell_metadata.csv"
    )
) |>
    dplyr::mutate(
        lineage = factor(lineage)
    )

Rows: 1195 Columns: 9
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (9): cell, run, source_name, developmental_stage, individual, sex, sampl...

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

EMBEDDING_FILE <- "embedding_ncomponents15_ccc1_seed20210719.csv.gz"

embedding_1195 <- vroom::vroom(
    file = file.path(
        PROJECT_DIR,
        "raw/public/PRJEB40781",
        "clustering/PRJEB40781/star/exploring",
        "Scanpy_Harmony",
        EMBEDDING_FILE
    )
)

embedding_1195 |> head() |> knitr::kable()

cell	batch	louvain	leiden	x_tsne	y_tsne	x_fitsne	y_fitsne	x_umap_min_dist=0.5	y_umap_min_dist=0.5	x_umap_min_dist=0.1	y_umap_min_dist=0.1	x_phate	y_phate	x_pacmap	y_pacmap
ERS5181934	PRJEB40781	0	4	-11.813729	51.55556	-31.9981458	33.08672	-2.8858435	4.266404	-1.4608202	5.649869	-0.0309265	0.0201407	-26.585844	8.177488
ERS5181935	PRJEB40781	1	5	-40.629002	26.28880	-1.1851437	42.71939	-1.8841287	12.546277	1.1891274	13.144535	-0.0408448	0.0005910	8.549566	4.448987
ERS5181936	PRJEB40781	1	5	-35.980461	17.89327	3.2214120	34.88544	-0.0097796	11.680841	2.3955772	12.497228	-0.0226495	0.0095925	7.491635	2.627760
ERS5181937	PRJEB40781	0	4	-7.327799	45.82777	-32.1619202	26.77324	-1.5390446	4.038341	-0.6339243	5.905377	-0.0366031	0.0086555	-26.781113	10.432706
ERS5181938	PRJEB40781	0	4	-16.172386	43.02077	-22.0980915	33.24122	-2.4133680	6.631270	-1.9704382	7.099248	-0.0310294	0.0047329	-24.548060	9.166805
ERS5181939	PRJEB40781	1	5	-34.458740	20.99207	-0.1236553	35.16477	-0.7037168	11.084229	1.9258376	12.283741	-0.0283207	0.0038721	8.132697	2.670102

Visualization

x_column <- "x_umap_min_dist=0.1"
y_column <- "y_umap_min_dist=0.1"

GEOM_POINT_SIZE <- 1.25
EMBEDDING_TITLE_PREFIX <- "UMAP"
RASTERISED <- TRUE

Clustering

p_embedding_leiden <- plot_embedding(
    embedding = embedding_1195[, c(x_column, y_column)],
    color_values = embedding_1195$leiden |> as.factor(),
    label = paste(EMBEDDING_TITLE_PREFIX, "Leiden", sep = "; "),
    label_position = NULL,
    show_color_value_labels = TRUE,
    show_color_legend = FALSE,
    geom_point_size = GEOM_POINT_SIZE,
    sort_values = FALSE,
    shuffle_values = TRUE,
    rasterise = RASTERISED
) +
    theme_customized()

# CB_POSITION <- c(0.8, 0.995)
p_embedding_UMI <- plot_embedding(
    embedding = embedding_1195[, c(x_column, y_column)],
    color_values = embedding_1195 |>
        dplyr::left_join(
            cell_metadata
        ) |>
        dplyr::pull(num_umis) |>
        {
            \(x) log10(x)
        }(),
    label = paste(EMBEDDING_TITLE_PREFIX, "UMI", sep = "; "),
    label_position = NULL,
    show_color_value_labels = FALSE,
    show_color_legend = TRUE,
    geom_point_size = GEOM_POINT_SIZE / 1.5,
    sort_values = TRUE,
    shuffle_values = FALSE,
    rasterise = RASTERISED,
    legend_size = 2
) +
    theme_customized(
        legend_key_size = 2,
        legend_text_size = 5
    )

p_embedding_MT <- plot_embedding(
    embedding = embedding_1195[, c(x_column, y_column)],
    color_values = embedding_1195 |>
        dplyr::left_join(cell_metadata) |>
        dplyr::pull(mt_percentage),
    label = paste(EMBEDDING_TITLE_PREFIX, "MT %", sep = "; "),
    label_position = NULL,
    show_color_value_labels = FALSE,
    show_color_legend = TRUE,
    geom_point_size = GEOM_POINT_SIZE,
    sort_values = TRUE,
    shuffle_values = FALSE,
    rasterise = RASTERISED,
    legend_size = 2
) +
    theme_customized(
        legend_key_size = 2,
        legend_text_size = 5
    )

p_embedding_sampling_site <- plot_embedding(
    embedding = embedding_1195[, c(x_column, y_column)],
    color_values = embedding_1195 |>
        dplyr::left_join(
            cell_metadata_PRJEB40781
        ) |>
        dplyr::pull(sampling_site) |>
        as.factor(),
    label = paste(EMBEDDING_TITLE_PREFIX, "Sampling site", sep = "; "),
    label_position = NULL,
    show_color_value_labels = FALSE,
    show_color_legend = TRUE,
    geom_point_size = GEOM_POINT_SIZE / 1.5,
    sort_values = FALSE,
    shuffle_values = TRUE,
    rasterise = RASTERISED
) +
    theme_customized()

embedding_1195 |>
    dplyr::left_join(
        cell_metadata |>
            dplyr::select(cell, num_umis:mt_percentage)
    ) |>
    dplyr::left_join(
        cell_metadata_PRJEB40781
    ) |>
    dplyr::group_by(
        leiden
    ) |>
    dplyr::summarise(
        num_cells = dplyr::n(),
        median_umis = median(num_umis),
        median_features = median(num_features),
        median_mt_percentage = median(mt_percentage)
    ) |>
    gt::gt() |>
    gt::tab_options(table.font.size = "median") |>
    gt::summary_rows(
        columns = c(num_cells),
        fns = list(
            Sum = ~ sum(.)
        ),
        decimals = 0
    ) |>
    gt::summary_rows(
        columns = c("median_umis", "median_features", "median_mt_percentage"),
        fns = list(
            Median = ~ median(.)
        ),
        decimals = 2
    )

	leiden	num_cells	median_umis	median_features	median_mt_percentage
	0	189	883508.0	2581.0	0.008930657
	1	138	996283.5	4297.5	0.006288449
	2	134	836131.0	4346.0	0.010772693
	3	115	887650.0	4906.0	0.007057741
	4	96	916361.0	4618.5	0.014087410
	5	85	1110656.0	3667.0	0.005815362
	6	81	763755.0	5965.0	0.008891377
	7	79	938071.0	4924.0	0.006874891
	8	79	746953.0	5211.0	0.008341437
	9	72	1010636.5	4530.0	0.004510133
	10	60	940026.0	3409.5	0.009846117
	11	34	1028500.0	4321.5	0.005531307
	12	33	728519.0	4344.0	0.014426759
Sum	—	1,195	—	—	—
Median	—	—	916,361.00	4,346.00	0.01

purrr::reduce(
    list(
        p_embedding_leiden,
        p_embedding_sampling_site,
        p_embedding_UMI,
        p_embedding_MT
    ),
    `+`
) +
    patchwork::plot_layout(ncol = 2) +
    patchwork::plot_annotation(
        theme = ggplot2::theme(plot.margin = ggplot2::margin())
    )

Lineage

embedding_1195 |>
    dplyr::left_join(
        cell_metadata
    ) |>
    dplyr::left_join(cell_metadata_PRJEB40781) |>
    dplyr::group_by(lineage) |>
    dplyr::summarise(
        num_cells = dplyr::n(),
        median_umis = median(num_umis),
        median_features = median(num_features),
        median_mt_percentage = median(mt_percentage)
    ) |>
    gt::gt() |>
    gt::tab_options(table.font.size = "90%") |>
    gt::summary_rows(
        columns = c(num_cells),
        fns = list(
            Sum = ~ sum(.)
        ),
        decimals = 0
    ) |>
    gt::summary_rows(
        columns = c("median_umis", "median_features", "median_mt_percentage"),
        fns = list(
            Median = ~ median(.)
        ),
        decimals = 2
    )

	lineage	num_cells	median_umis	median_features	median_mt_percentage
	advanced mesoderm	164	993741.0	4164.5	0.006218430
	axial mesoderm	23	853681.0	4181.0	0.007745421
	ectodermal cell	29	996476.0	4314.0	0.005143689
	emergent mesoderm	185	911736.0	4184.0	0.007838085
	endodermal cell	135	989383.0	4837.0	0.005348267
	epiblast cell	133	790584.0	5607.0	0.009357085
	erythrocyte	32	716602.0	4345.5	0.014388710
	hemogenic endothelial progenitor	111	925287.0	4498.0	0.013978306
	nascent mesoderm	98	787231.5	4479.0	0.008292312
	primitive streak	202	826282.5	3781.0	0.010169492
	yolk sac mesoderm	83	1124901.0	3778.0	0.006017290
Sum	—	1,195	—	—	—
Median	—	—	911,736.00	4,314.00	0.01

p_embedding_lineage <- plot_embedding(
    embedding = embedding_1195[, c(x_column, y_column)],
    color_values = embedding_1195 |>
        dplyr::left_join(
            cell_metadata_PRJEB40781
        ) |>
        dplyr::pull(lineage) |>
        as.factor(),
    label = paste(EMBEDDING_TITLE_PREFIX, "Lineage", sep = "; "),
    label_position = NULL,
    show_color_value_labels = FALSE,
    show_color_legend = TRUE,
    geom_point_size = GEOM_POINT_SIZE / 1.5,
    sort_values = FALSE,
    shuffle_values = TRUE,
    rasterise = RASTERISED
) +
    theme_customized()

list(
    p_embedding_lineage,
    purrr::map(levels(cell_metadata_PRJEB40781$lineage), \(x) {
        values <- embedding_1195 |>
            dplyr::left_join(cell_metadata_PRJEB40781) |>
            dplyr::mutate(
                value = dplyr::case_when(
                    lineage == x ~ "1",
                    TRUE ~ "0"
                )
            ) |>
            dplyr::pull(value)
        plot_embedding(
            embedding = embedding_1195[, c(x_column, y_column)],
            color_values = factor(values),
            label = glue::glue(
                "{EMBEDDING_TITLE_PREFIX}; {x}: {sum(as.integer(values))}"
            ),
            label_position = NULL,
            show_color_value_labels = FALSE,
            show_color_legend = FALSE,
            geom_point_size = GEOM_POINT_SIZE,
            sort_values = TRUE,
            rasterise = RASTERISED,
            legend_size = 2
        ) +
            theme_customized(
                legend_key_size = 2,
                legend_text_size = 5
            ) +
            scale_color_manual(
                values = c("grey70", "salmon")
            )
    })
) |>
    purrr::reduce(`+`) +
    patchwork::plot_layout(ncol = 2) +
    patchwork::plot_annotation(
        theme = ggplot2::theme(plot.margin = ggplot2::margin())
    )

Composition

p_barplot_composition_sampling_site <- calc_group_composition(
    data = embedding_1195 |>
        dplyr::left_join(
            cell_metadata_PRJEB40781
        ),
    x = "leiden",
    group = "sampling_site"
) |>
    dplyr::mutate(
        leiden = factor(leiden)
    ) |>
    plot_barplot(
        x = "leiden",
        y = "percentage",
        z = "sampling_site",
        legend_ncol = 1
    )

p_barplot_composition_lineage <- calc_group_composition(
    data = embedding_1195 |>
        dplyr::left_join(
            cell_metadata_PRJEB40781
        ),
    x = "leiden",
    group = "lineage"
) |>
    dplyr::mutate(
        leiden = factor(leiden)
    ) |>
    plot_barplot(
        x = "leiden",
        y = "percentage",
        z = "lineage",
        legend_ncol = 1
    )

list(
    p_barplot_composition_sampling_site,
    p_barplot_composition_lineage
) |>
    purrr::reduce(`+`) +
    patchwork::plot_layout(ncol = 1, guides = "collect") +
    patchwork::plot_annotation(
        theme = ggplot2::theme(plot.margin = ggplot2::margin())
    )

Expression

FEATURES_SELECTED <- c(
    "ENSG00000204531_POU5F1",
    "ENSG00000111704_NANOG",
    "ENSG00000171872_KLF17",
    "ENSG00000186103_ARGFX",
    #
    "ENSG00000164736_SOX17",
    "ENSG00000125798_FOXA2",
    "ENSG00000136574_GATA4",
    "ENSG00000134853_PDGFRA",
    #
    "ENSG00000179348_GATA2",
    "ENSG00000070915_SLC12A3",
    "ENSG00000165556_CDX2",
    "ENSG00000007866_TEAD3"
)

purrr::map(FEATURES_SELECTED, \(x) {
    selected_feature <- x

    cat(selected_feature, "\n")
    values <- log10(
        calc_cpm(
            matrix_readcount_use[, embedding_1195$cell]
        )[selected_feature, ] + 1
    )

    plot_embedding(
        embedding = embedding_1195[, c(x_column, y_column)],
        color_values = values,
        label = paste(
            EMBEDDING_TITLE_PREFIX,
            selected_feature |> stringr::str_remove(pattern = "^E.+_"),
            sep = "; "
        ),
        label_position = NULL,
        show_color_value_labels = FALSE,
        show_color_legend = TRUE,
        geom_point_size = GEOM_POINT_SIZE,
        sort_values = TRUE,
        shuffle_values = FALSE,
        rasterise = RASTERISED,
        legend_size = 2
    ) +
        scale_color_viridis_c(
            na.value = "grey80"
        ) +
        theme_customized(
            legend_key_size = 2,
            legend_text_size = 5
        )
}) |>
    purrr::reduce(`+`) +
    patchwork::plot_layout(ncol = 3, byrow = FALSE) +
    patchwork::plot_annotation(
        theme = ggplot2::theme(plot.margin = ggplot2::margin())
    )

ENSG00000204531_POU5F1 
ENSG00000111704_NANOG 
ENSG00000171872_KLF17 
ENSG00000186103_ARGFX 
ENSG00000164736_SOX17 
ENSG00000125798_FOXA2 
ENSG00000136574_GATA4 
ENSG00000134853_PDGFRA 
ENSG00000179348_GATA2 
ENSG00000070915_SLC12A3 
ENSG00000165556_CDX2 
ENSG00000007866_TEAD3 

Integration with other datasets

EMBEDDING_FILE <- glue::glue(
    "embedding_ncomponents18_ccc1_seed20210719.csv.gz"
)

embedding <- vroom::vroom(
    file = file.path(
        PROJECT_DIR,
        "raw",
        "public",
        "PRJEB40781",
        "clustering",
        "PRJEB40781_PRJEB11202_PRJNA555602",
        "exploring",
        "Scanpy_Harmony",
        EMBEDDING_FILE
    )
) |>
    dplyr::mutate(
        study = dplyr::case_when(
            batch %in% c("GSM3956280", "GSM3956281") ~ "PRJNA555602",
            TRUE ~ batch
        ),
        study = factor(study)
    )

embedding |> head() |> knitr::kable()

cell	batch	louvain	leiden	x_tsne	y_tsne	x_fitsne	y_fitsne	x_umap_min_dist=0.5	y_umap_min_dist=0.5	x_umap_min_dist=0.1	y_umap_min_dist=0.1	x_phate	y_phate	x_pacmap	y_pacmap	study
ERS1079290	PRJEB11202	0	19	-150.2465	-18.62910	27.94793	79.28939	12.40074	12.95675	11.14121	11.96352	0.0427350	0.1054535	31.80464	-4.146411	PRJEB11202
ERS1079291	PRJEB11202	0	19	-150.2385	-18.49208	27.92819	79.37267	12.41068	12.95666	11.13023	11.92452	0.0434268	0.1081072	31.78716	-4.166779	PRJEB11202
ERS1079292	PRJEB11202	0	19	-147.8795	-19.04842	30.05652	79.86405	12.61402	12.26652	11.15786	11.73332	0.0409260	0.0984688	31.50010	-4.484898	PRJEB11202
ERS1079293	PRJEB11202	0	19	-149.7783	-18.68170	28.24631	79.39974	12.48569	12.89126	11.15059	11.93826	0.0425165	0.1046245	31.78120	-4.173330	PRJEB11202
ERS1079294	PRJEB11202	0	19	-150.5415	-18.74879	27.79565	79.13129	12.47731	13.07006	11.14075	11.96297	0.0436986	0.1091239	31.82615	-4.122645	PRJEB11202
ERS1079295	PRJEB11202	0	19	-150.5609	-18.77508	27.80425	79.12818	12.36641	13.06700	11.12697	11.95156	0.0440238	0.1103717	31.83826	-4.109794	PRJEB11202

studies <- tibble::tribble(
    ~bioproject, ~citation,
    "PRJEB11202", "Petropoulos et al. 2016",
    "PRJEB40781", "Tyser et al. 2021",
    "PRJNA555602", "Zheng et al. 2019",
    "PRJNA431392", "Zhou et al. 2019",
    "PRJNA737139", "Kagawa et al. 2021",
    "PRJNA632839", "Yu et al. 2021",
    "PRJNA658478", "Liu et al. 2021",
    "PRJNA720968", "Yanagida et al. 2021",
    "PRJNA667174", "Fan et al. 2021",
    "PRJNA738498", "Sozen et al. 2021",
    "PRJNA737139", "Kagawa et al. 2021"
)

studies <- setNames(
    object = studies$citation,
    nm = studies$bioproject
)

embedding |>
    dplyr::count(study, name = "num_cells") |>
    dplyr::mutate(
        study = studies[study]
    ) |>
    gt::gt() |>
    # gt::tab_options(table.font.size = "median") |>
    gt::summary_rows(
        columns = c(num_cells),
        fns = list(
            Sum = ~ sum(.)
        ),
        decimals = 0
    )

	study	num_cells
	Petropoulos et al. 2016	1529
	Tyser et al. 2021	1195
	Zheng et al. 2019	9966
Sum	—	12,690

Metadata

# PRJEB11202; Petropoulos et al. 2016
cell_metadata_PRJEB11202 <- vroom::vroom(
    file = file.path(
        PROJECT_DIR,
        "raw",
        "public",
        "PRJEB11202",
        "matrix/cell_metadata.csv"
    )
) |>
    dplyr::mutate(
        developmental_stage = stringr::str_remove(
            string = individual,
            pattern = "\\..+$"
        ),
        developmental_stage = factor(
            developmental_stage,
            levels = stringr::str_sort(
                unique(developmental_stage),
                numeric = TRUE
            )
        ),
        #
        lineage = factor(
            inferred_lineage,
            levels = c(
                "epiblast",
                "primitive_endoderm",
                "trophectoderm",
                "not_applicable"
            )
        )
    ) |>
    dplyr::select(
        cell, lineage, developmental_stage
    )

# PRJNA555602; Zheng et al. 2019
cell_metadata_PRJNA555602 <- vroom::vroom(
    file = file.path(
        PROJECT_DIR,
        "raw",
        "public",
        "PRJNA555602",
        "matrix/cell_metadata.csv"
    )
) |>
    dplyr::mutate(
        lineage = dplyr::case_when(
            # amniotic ectoderm-like cells
            rna_snn_res_0.3 == 0 ~ "Transwell-AMLC",
            # mesoderm-like cell 2
            rna_snn_res_0.3 == 1 ~ "MeLC2",
            rna_snn_res_0.3 == 2 ~ "Human ES cell",
            # mesoderm-like cell 1
            rna_snn_res_0.3 == 3 ~ "MeLC1",
            # human PGC-like cells
            rna_snn_res_0.3 == 4 ~ "hPGCLC",
            rna_snn_res_0.3 == 5 ~ "AMLC"
        ),
        lineage = factor(
            lineage,
            levels = c(
                "Human ES cell",
                "hPGCLC",
                "MeLC1",
                "MeLC2",
                "AMLC",
                "Transwell-AMLC"
            )
        ),
        source = dplyr::case_when(
            orig_ident == "10X_Embryoid" ~ "Embryoid",
            orig_ident == "10X_H9_Amnion" ~ "H9_Amnion"
        ),
        source = factor(source)
    )

Visualization

Clustering

x_column <- "x_pacmap"
y_column <- "y_pacmap"
EMBEDDING_TITLE_PREFIX <- "PaCMAP"
GEOM_POINT_SIZE <- 0.4

p_embedding_leiden <- plot_embedding(
    embedding = embedding[, c(x_column, y_column)],
    color_values = embedding$leiden |> as.factor(),
    label = glue::glue("{EMBEDDING_TITLE_PREFIX}; Leiden"),
    label_position = NULL,
    show_color_value_labels = TRUE,
    show_color_legend = FALSE,
    geom_point_size = GEOM_POINT_SIZE,
    sort_values = FALSE,
    shuffle_values = FALSE,
    rasterise = RASTERISED
) +
    theme_customized()

p_embedding_UMI <- plot_embedding(
    embedding = embedding[, c(x_column, y_column)],
    color_values = log10(
        Matrix::colSums(matrix_readcount_use[, embedding$cell])
    ),
    label = glue::glue("{EMBEDDING_TITLE_PREFIX}; UMI"),
    label_position = NULL,
    show_color_value_labels = FALSE,
    show_color_legend = TRUE,
    geom_point_size = GEOM_POINT_SIZE * 1,
    geom_point_alpha = 1,
    sort_values = TRUE,
    shuffle_values = FALSE,
    label_size = 2.5,
    label_hjust = 0,
    label_vjust = 0,
    rasterise = RASTERISED,
    legend_size = 2,
    legend_ncol = 1
) +
    theme_customized(
        legend_key_size = 2,
        legend_text_size = 5
    )

p_embedding_MT <- plot_embedding(
    embedding = embedding[, c(x_column, y_column)],
    color_values = embedding |>
        dplyr::left_join(
            cell_metadata # |> dplyr::select(-batch)
        ) |>
        dplyr::pull(mt_percentage),
    label = glue::glue("{EMBEDDING_TITLE_PREFIX}; MT %"),
    label_position = NULL,
    show_color_value_labels = FALSE,
    show_color_legend = TRUE,
    geom_point_size = GEOM_POINT_SIZE * 1,
    geom_point_alpha = 1,
    sort_values = TRUE,
    shuffle_values = FALSE,
    label_size = 2.5,
    label_hjust = 0,
    label_vjust = 0,
    rasterise = RASTERISED,
    legend_size = 2,
    legend_ncol = 1
) +
    theme_customized(
        legend_key_size = 2,
        legend_text_size = 5
    )

p_embedding_study <- plot_embedding(
    embedding = embedding[, c(x_column, y_column)],
    color_values = embedding$study,
    label = glue::glue("{EMBEDDING_TITLE_PREFIX}; Study"),
    label_position = NULL,
    show_color_value_labels = FALSE,
    show_color_legend = TRUE,
    geom_point_size = GEOM_POINT_SIZE / 2,
    sort_values = FALSE,
    shuffle_values = TRUE,
    rasterise = RASTERISED,
    legend_size = 2
) +
    theme_customized(
        legend_key_size = 2,
        legend_text_size = 5
    ) +
    scale_color_manual(
        values = scales::hue_pal()(n = length(unique(embedding$batch))),
        labels = studies
    )

embedding |>
    dplyr::left_join(
        cell_metadata |>
            dplyr::select(cell, num_umis:mt_percentage)
    ) |>
    dplyr::group_by(
        leiden
    ) |>
    dplyr::summarise(
        num_cells = dplyr::n(),
        median_umis = median(num_umis),
        median_features = median(num_features),
        median_mt_percentage = median(mt_percentage)
    ) |>
    gt::gt() |>
    # gt::tab_options(table.font.size = "median") |>
    gt::summary_rows(
        columns = c(num_cells),
        fns = list(
            Sum = ~ sum(.)
        ),
        decimals = 0
    ) |>
    gt::summary_rows(
        columns = c("median_umis", "median_features", "median_mt_percentage"),
        fns = list(
            Median = ~ median(.)
        ),
        decimals = 2
    )

	leiden	num_cells	median_umis	median_features	median_mt_percentage
	0	1179	27676.0	5089.0	0.025830026
	1	1156	21609.5	4597.0	0.033986369
	2	1141	22175.0	4243.0	0.043475207
	3	1124	28028.0	5113.0	0.043416238
	4	969	23013.0	4643.0	0.026599176
	5	892	28762.0	4966.5	0.034163936
	6	868	29193.5	5040.0	0.025966430
	7	826	23003.0	4499.5	0.030224185
	8	797	22893.0	4362.0	0.041594258
	9	647	1348781.0	9991.0	0.008139240
	10	602	861400.5	4880.5	0.008097055
	11	472	1787005.5	10772.5	0.006137011
	12	434	24493.5	4661.0	0.035983814
	13	345	31267.0	5475.0	0.039519924
	14	324	1607461.5	10278.0	0.007017669
	15	235	26117.0	4854.0	0.047443806
	16	228	881789.5	2682.5	0.009192114
	17	178	1092848.0	3854.0	0.005902158
	18	131	883583.0	4508.0	0.014213556
	19	84	1570985.0	10117.5	0.007988063
	20	58	958118.0	4789.5	0.004154967
Sum	—	12,690	—	—	—
Median	—	—	29,193.50	4,854.00	0.03

purrr::reduce(
    list(
        p_embedding_leiden,
        p_embedding_study,
        p_embedding_UMI,
        p_embedding_MT
    ),
    `+`
) +
    patchwork::plot_layout(ncol = 2) +
    patchwork::plot_annotation(
        theme = ggplot2::theme(plot.margin = ggplot2::margin())
    )

purrr::map(unique(embedding$study), \(x) {
    plot_embedding(
        embedding = embedding[, c(x_column, y_column)],
        color_values = as.integer(embedding$study == x) |> as.factor(),
        label = glue::glue(
            "{EMBEDDING_TITLE_PREFIX}; {studies[x]}, ",
            "{sum(as.integer(embedding$study == x), na.rm = TRUE)}"
        ),
        label_position = NULL,
        show_color_value_labels = FALSE,
        show_color_legend = FALSE,
        geom_point_size = GEOM_POINT_SIZE,
        sort_values = TRUE,
        shuffle_values = FALSE,
        rasterise = RASTERISED,
        legend_size = 2
    ) +
        theme_customized(
            legend_key_size = 2,
            legend_text_size = 5
        ) +
        scale_color_manual(
            values = c("grey70", "salmon")
        )
}) |>
    purrr::reduce(`+`) +
    patchwork::plot_layout(ncol = 2) +
    patchwork::plot_annotation(
        theme = ggplot2::theme(plot.margin = ggplot2::margin())
    )

embedding |>
    dplyr::left_join(
        cell_metadata |>
            dplyr::select(cell, num_umis:mt_percentage)
    ) |>
    dplyr::group_by(
        study
    ) |>
    dplyr::summarise(
        num_cells = dplyr::n(),
        median_umis = median(num_umis),
        median_features = median(num_features),
        median_mt_percentage = median(mt_percentage)
    ) |>
    dplyr::mutate(
        study = studies[study],
        platform = c("Smart-Seq2", "Smart-Seq2", "10x Genomics")
    ) |>
    dplyr::select(
        study, platform, everything()
    ) |>
    gt::gt() |>
    gt::tab_options(table.font.size = "median") |>
    gt::summary_rows(
        columns = c(num_cells),
        fns = list(
            Sum = ~ sum(.)
        ),
        decimals = 0
    ) |>
    gt::summary_rows(
        columns = c("median_umis", "median_features", "median_mt_percentage"),
        fns = list(
            Median = ~ median(.)
        ),
        decimals = 2
    )

	study	platform	num_cells	median_umis	median_features	median_mt_percentage
	Petropoulos et al. 2016	Smart-Seq2	1529	1551093	10305	0.007144702
	Tyser et al. 2021	Smart-Seq2	1195	899241	4379	0.008164051
	Zheng et al. 2019	10x Genomics	9966	25264	4772	0.034485263
Sum	—	—	12,690	—	—	—
Median	—	—	—	899,241.00	4,772.00	0.01

Cell annotation

Petropoulos et al. 2016

bioproject <- "PRJEB11202"
cell_metadata_selected <- cell_metadata_PRJEB11202

selected_column <- "developmental_stage"
p_embedding_developmental_stage <- plot_embedding(
    embedding = embedding[, c(x_column, y_column)],
    color_values = embedding |>
        dplyr::left_join(cell_metadata_selected) |>
        dplyr::pull(.data[[selected_column]]),
    label = glue::glue(
        "{EMBEDDING_TITLE_PREFIX}; {studies[bioproject]}; ",
        "{selected_column |>
        stringr::str_to_title() |>
        stringr::str_replace(pattern = \"_\", replacement = \" \")}"
    ),
    label_position = NULL,
    show_color_value_labels = FALSE,
    show_color_legend = TRUE,
    geom_point_size = GEOM_POINT_SIZE,
    sort_values = TRUE,
    shuffle_values = FALSE,
    rasterise = RASTERISED,
    legend_size = 2
) +
    theme_customized(
        legend_key_size = 2,
        legend_text_size = 5
    ) +
    scale_color_manual(
        na.translate = TRUE,
        values = scales::hue_pal()(
            n = length(unique(cell_metadata_selected[[selected_column]]))
        ),
        na.value = "#7F7F7F"
    )

selected_column <- "lineage"
p_embedding_lineage <- plot_embedding(
    embedding = embedding[, c(x_column, y_column)],
    color_values = embedding |>
        dplyr::left_join(cell_metadata_selected) |>
        dplyr::pull(.data[[selected_column]]),
    label = glue::glue(
        "{EMBEDDING_TITLE_PREFIX}; {studies[bioproject]}; ",
        "{selected_column |>
        stringr::str_to_title() |>
        stringr::str_replace(pattern = \"_\", replacement = \" \")}"
    ),
    label_position = NULL,
    show_color_value_labels = FALSE,
    show_color_legend = TRUE,
    geom_point_size = GEOM_POINT_SIZE,
    sort_values = TRUE,
    shuffle_values = FALSE,
    rasterise = RASTERISED,
    legend_size = 2
) +
    theme_customized(
        legend_key_size = 2,
        legend_text_size = 5
    ) +
    scale_color_manual(
        na.translate = TRUE,
        values = scales::hue_pal()(
            n = length(unique(cell_metadata_selected[[selected_column]]))
        ),
        na.value = "#7F7F7F"
    )

list(
    p_embedding_lineage,
    p_embedding_developmental_stage
) |>
    purrr::reduce(`+`) +
    patchwork::plot_layout(ncol = 2) +
    patchwork::plot_annotation(
        theme = ggplot2::theme(plot.margin = ggplot2::margin())
    )

Salmon: highlighted group of cells; Light grey: cells belonging to this dataset but not the highlighted group; Dark grey: cells belonging to other datasets.

plot_embedding_highlight(
    embedding = embedding,
    x = cell_metadata_selected,
    y = "lineage",
    label = studies[bioproject],
    n_cols = 2
)

plot_embedding_highlight(
    embedding = embedding,
    x = cell_metadata_selected,
    y = "developmental_stage",
    label = studies[bioproject],
    n_cols = 2
)

Zheng et al. 2019

bioproject <- "PRJNA555602"
cell_metadata_selected <- cell_metadata_PRJNA555602

selected_column <- "source"
p_embedding_developmental_stage <- plot_embedding(
    embedding = embedding[, c(x_column, y_column)],
    color_values = embedding |>
        dplyr::left_join(cell_metadata_selected) |>
        dplyr::pull(.data[[selected_column]]),
    label = glue::glue(
        "{EMBEDDING_TITLE_PREFIX}; {studies[bioproject]}; ",
        "{selected_column |>
        stringr::str_to_title() |>
        stringr::str_replace(pattern = \"_\", replacement = \" \")}"
    ),
    label_position = NULL,
    show_color_value_labels = FALSE,
    show_color_legend = TRUE,
    geom_point_size = GEOM_POINT_SIZE,
    sort_values = FALSE,
    shuffle_values = TRUE,
    rasterise = RASTERISED,
    legend_size = 2
) +
    theme_customized(
        legend_key_size = 2,
        legend_text_size = 5
    ) +
    scale_color_manual(
        na.translate = TRUE,
        values = scales::hue_pal()(
            n = length(unique(cell_metadata_selected[[selected_column]]))
        ),
        na.value = "#7F7F7F"
    )

selected_column <- "lineage"
p_embedding_lineage <- plot_embedding(
    embedding = embedding[, c(x_column, y_column)],
    color_values = embedding |>
        dplyr::left_join(cell_metadata_selected) |>
        dplyr::pull(.data[[selected_column]]),
    label = glue::glue(
        "{EMBEDDING_TITLE_PREFIX}; {studies[bioproject]}; ",
        "{selected_column |>
        stringr::str_to_title() |>
        stringr::str_replace(pattern = \"_\", replacement = \" \")}"
    ),
    label_position = NULL,
    show_color_value_labels = FALSE,
    show_color_legend = TRUE,
    geom_point_size = GEOM_POINT_SIZE,
    sort_values = FALSE,
    shuffle_values = TRUE,
    rasterise = RASTERISED,
    legend_size = 2
) +
    theme_customized(
        legend_key_size = 2,
        legend_text_size = 5
    ) +
    scale_color_manual(
        na.translate = TRUE,
        values = scales::hue_pal()(
            n = length(unique(cell_metadata_selected[[selected_column]]))
        ),
        na.value = "#7F7F7F"
    )

list(
    p_embedding_lineage,
    p_embedding_developmental_stage
) |>
    purrr::reduce(`+`) +
    patchwork::plot_layout(ncol = 2) +
    patchwork::plot_annotation(
        theme = ggplot2::theme(plot.margin = ggplot2::margin())
    )

Tyser et al. 2021

bioproject <- "PRJEB40781"
cell_metadata_selected <- cell_metadata_PRJEB40781

selected_column <- "sampling_site"
p_embedding_sampling_site <- plot_embedding(
    embedding = embedding[, c(x_column, y_column)],
    color_values = embedding |>
        dplyr::left_join(cell_metadata_selected) |>
        dplyr::pull(.data[[selected_column]]),
    label = glue::glue(
        "{EMBEDDING_TITLE_PREFIX}; {studies[bioproject]}; ",
        "{selected_column |>
        stringr::str_to_title() |>
        stringr::str_replace(pattern = \"_\", replacement = \" \")}"
    ),
    label_position = NULL,
    show_color_value_labels = FALSE,
    show_color_legend = TRUE,
    geom_point_size = GEOM_POINT_SIZE,
    sort_values = TRUE,
    shuffle_values = FALSE,
    rasterise = RASTERISED,
    legend_size = 2
) +
    theme_customized(
        legend_key_size = 2,
        legend_text_size = 5
    ) +
    scale_color_manual(
        na.translate = TRUE,
        values = scales::hue_pal()(
            n = length(unique(cell_metadata_selected[[selected_column]]))
        ),
        na.value = "grey70"
    )

selected_column <- "lineage"
p_embedding_lineage <- plot_embedding(
    embedding = embedding[, c(x_column, y_column)],
    color_values = embedding |>
        dplyr::left_join(cell_metadata_selected) |>
        dplyr::pull(.data[[selected_column]]),
    label = glue::glue(
        "{EMBEDDING_TITLE_PREFIX}; {studies[bioproject]}; ",
        "{selected_column |>
        stringr::str_to_title() |>
        stringr::str_replace(pattern = \"_\", replacement = \" \")}"
    ),
    label_position = NULL,
    show_color_value_labels = FALSE,
    show_color_legend = TRUE,
    geom_point_size = GEOM_POINT_SIZE,
    sort_values = TRUE,
    shuffle_values = FALSE,
    rasterise = RASTERISED,
    legend_size = 2
) +
    theme_customized(
        legend_key_size = 2,
        legend_text_size = 5
    ) +
    scale_color_manual(
        na.translate = TRUE,
        values = scales::hue_pal()(
            n = length(unique(cell_metadata_selected[[selected_column]]))
        ),
        na.value = "#7F7F7F"
    )

list(
    p_embedding_lineage,
    p_embedding_sampling_site
) |>
    purrr::reduce(`+`) +
    patchwork::plot_layout(ncol = 2) +
    patchwork::plot_annotation(
        theme = ggplot2::theme(plot.margin = ggplot2::margin())
    )

plot_embedding_highlight(
    embedding = embedding,
    x = cell_metadata_selected,
    y = "lineage",
    label = studies[bioproject],
    n_cols = 2
)

R session info

devtools::session_info()

─ Session info ───────────────────────────────────────────────────────────────
 setting  value
 version  R version 4.1.2 (2021-11-01)
 os       macOS Monterey 12.1
 system   aarch64, darwin20.6.0
 ui       unknown
 language (EN)
 collate  en_US.UTF-8
 ctype    en_US.UTF-8
 tz       America/Chicago
 date     2022-01-24
 pandoc   2.17.0.1 @ /opt/homebrew/bin/ (via rmarkdown)

─ Packages ───────────────────────────────────────────────────────────────────
 package       * version     date (UTC) lib source
 assertthat      0.2.1       2019-03-21 [1] CRAN (R 4.1.1)
 backports       1.4.1       2021-12-13 [1] CRAN (R 4.1.2)
 beeswarm        0.4.0       2021-06-01 [1] CRAN (R 4.1.2)
 bit             4.0.4       2020-08-04 [1] CRAN (R 4.1.1)
 bit64           4.0.5       2020-08-30 [1] CRAN (R 4.1.1)
 brio            1.1.3       2021-11-30 [1] CRAN (R 4.1.2)
 broom           0.7.11      2022-01-03 [1] CRAN (R 4.1.2)
 cachem          1.0.6       2021-08-19 [1] CRAN (R 4.1.1)
 callr           3.7.0       2021-04-20 [1] CRAN (R 4.1.1)
 cellranger      1.1.0       2016-07-27 [1] CRAN (R 4.1.1)
 checkmate       2.0.0       2020-02-06 [1] CRAN (R 4.1.1)
 cli             3.1.1       2022-01-20 [1] CRAN (R 4.1.2)
 colorspace      2.0-2       2021-06-24 [1] CRAN (R 4.1.1)
 crayon          1.4.2       2021-10-29 [1] CRAN (R 4.1.1)
 data.table      1.14.2      2021-09-27 [1] CRAN (R 4.1.1)
 DBI             1.1.2       2021-12-20 [1] CRAN (R 4.1.2)
 dbplyr          2.1.1       2021-04-06 [1] CRAN (R 4.1.1)
 desc            1.4.0       2021-09-28 [1] CRAN (R 4.1.1)
 devtools        2.4.3.9000  2022-01-22 [1] Github (r-lib/devtools@41280ac)
 digest          0.6.29      2021-12-01 [1] CRAN (R 4.1.2)
 dplyr         * 1.0.7.9000  2022-01-12 [1] Github (tidyverse/dplyr@0501335)
 dtplyr          1.2.1       2022-01-19 [1] CRAN (R 4.1.2)
 ellipsis        0.3.2       2021-04-29 [1] CRAN (R 4.1.1)
 evaluate        0.14        2019-05-28 [1] CRAN (R 4.1.1)
 extrafont     * 0.17        2014-12-08 [1] CRAN (R 4.1.1)
 extrafontdb     1.0         2012-06-11 [1] CRAN (R 4.1.1)
 fansi           1.0.2       2022-01-14 [1] CRAN (R 4.1.2)
 farver          2.1.0       2021-02-28 [1] CRAN (R 4.1.1)
 fastmap         1.1.0       2021-01-25 [1] CRAN (R 4.1.1)
 forcats       * 0.5.1.9000  2021-11-29 [1] Github (tidyverse/forcats@b4dade0)
 fs              1.5.2.9000  2021-12-09 [1] Github (r-lib/fs@6d1182f)
 gargle          1.2.0       2021-07-02 [1] CRAN (R 4.1.1)
 generics        0.1.1       2021-10-25 [1] CRAN (R 4.1.1)
 ggbeeswarm      0.6.0       2017-08-07 [1] CRAN (R 4.1.2)
 ggplot2       * 3.3.5       2021-06-25 [1] CRAN (R 4.1.1)
 ggrastr         1.0.1       2021-12-08 [1] Github (VPetukhov/ggrastr@7aed9af)
 glue            1.6.1.9000  2022-01-23 [1] Github (tidyverse/glue@3da70df)
 googledrive     2.0.0       2021-07-08 [1] CRAN (R 4.1.1)
 googlesheets4   1.0.0       2021-07-21 [1] CRAN (R 4.1.1)
 gt              0.3.1.9000  2022-01-17 [1] Github (rstudio/gt@fcabb41)
 gtable          0.3.0.9000  2021-10-28 [1] Github (r-lib/gtable@a0bd272)
 haven           2.4.3       2021-08-04 [1] CRAN (R 4.1.1)
 highr           0.9         2021-04-16 [1] CRAN (R 4.1.1)
 hms             1.1.1       2021-09-26 [1] CRAN (R 4.1.1)
 htmltools       0.5.2       2021-08-25 [1] CRAN (R 4.1.1)
 htmlwidgets     1.5.4       2021-09-08 [1] CRAN (R 4.1.1)
 httr            1.4.2       2020-07-20 [1] CRAN (R 4.1.1)
 jsonlite        1.7.3       2022-01-17 [1] CRAN (R 4.1.2)
 knitr           1.37.1      2021-12-21 [1] https://yihui.r-universe.dev (R 4.1.2)
 labeling        0.4.2       2020-10-20 [1] CRAN (R 4.1.1)
 lattice         0.20-45     2021-09-22 [2] CRAN (R 4.1.2)
 lifecycle       1.0.1       2021-09-24 [1] CRAN (R 4.1.1)
 lubridate       1.8.0       2022-01-20 [1] Github (tidyverse/lubridate@566590f)
 magrittr        2.0.1       2020-11-17 [1] CRAN (R 4.1.1)
 Matrix        * 1.4-0       2021-12-08 [2] CRAN (R 4.1.2)
 memoise         2.0.1       2021-11-26 [1] CRAN (R 4.1.2)
 modelr          0.1.8.9000  2021-10-27 [1] Github (tidyverse/modelr@16168e0)
 munsell         0.5.0       2018-06-12 [1] CRAN (R 4.1.1)
 patchwork     * 1.1.0.9000  2021-10-27 [1] Github (thomasp85/patchwork@79223d3)
 pillar          1.6.4       2021-10-18 [1] CRAN (R 4.1.1)
 pkgbuild        1.3.1       2021-12-20 [1] CRAN (R 4.1.2)
 pkgconfig       2.0.3       2019-09-22 [1] CRAN (R 4.1.1)
 pkgload         1.2.4       2021-11-30 [1] CRAN (R 4.1.2)
 png             0.1-7       2013-12-03 [1] CRAN (R 4.1.1)
 prettyunits     1.1.1       2020-01-24 [1] CRAN (R 4.1.1)
 processx        3.5.2       2021-04-30 [1] CRAN (R 4.1.1)
 ps              1.6.0       2021-02-28 [1] CRAN (R 4.1.1)
 purrr         * 0.3.4       2020-04-17 [1] CRAN (R 4.1.1)
 R.cache         0.15.0      2021-04-30 [1] CRAN (R 4.1.1)
 R.methodsS3     1.8.1       2020-08-26 [1] CRAN (R 4.1.1)
 R.oo            1.24.0      2020-08-26 [1] CRAN (R 4.1.1)
 R.utils         2.11.0      2021-09-26 [1] CRAN (R 4.1.1)
 R6              2.5.1.9000  2021-12-09 [1] Github (r-lib/R6@1b05b89)
 ragg            1.2.1.9000  2021-12-08 [1] Github (r-lib/ragg@c68c666)
 Rcpp            1.0.8       2022-01-13 [1] CRAN (R 4.1.2)
 readr         * 2.1.1       2021-11-30 [1] CRAN (R 4.1.2)
 readxl          1.3.1.9000  2022-01-20 [1] Github (tidyverse/readxl@2ccb82c)
 remotes         2.4.2       2022-01-24 [1] Github (r-lib/remotes@7b0ee01)
 reprex          2.0.1       2021-08-05 [1] CRAN (R 4.1.1)
 reticulate      1.23        2022-01-14 [1] CRAN (R 4.1.2)
 rlang           1.0.0       2022-01-20 [1] Github (r-lib/rlang@f2fbaad)
 rmarkdown       2.11.12     2022-01-24 [1] Github (rstudio/rmarkdown@b53a7ce)
 rprojroot       2.0.2       2020-11-15 [1] CRAN (R 4.1.1)
 rstudioapi      0.13.0-9000 2022-01-15 [1] Github (rstudio/rstudioapi@5d0f087)
 Rttf2pt1        1.3.9       2021-07-22 [1] CRAN (R 4.1.1)
 rvest           1.0.2       2021-10-16 [1] CRAN (R 4.1.1)
 sass            0.4.0       2021-05-12 [1] CRAN (R 4.1.1)
 scales          1.1.1       2020-05-11 [1] CRAN (R 4.1.1)
 sessioninfo     1.2.2       2021-12-06 [1] CRAN (R 4.1.2)
 stringi         1.7.6       2021-11-29 [1] CRAN (R 4.1.2)
 stringr       * 1.4.0.9000  2022-01-24 [1] Github (tidyverse/stringr@85f6140)
 styler        * 1.6.2.9000  2022-01-17 [1] Github (r-lib/styler@9274aed)
 systemfonts     1.0.3.9000  2021-12-07 [1] Github (r-lib/systemfonts@414114e)
 testthat        3.1.2.9000  2022-01-21 [1] Github (r-lib/testthat@54b9db2)
 textshaping     0.3.6       2021-10-13 [1] CRAN (R 4.1.1)
 tibble        * 3.1.6.9000  2022-01-18 [1] Github (tidyverse/tibble@7aa54e6)
 tidyr         * 1.1.4       2021-09-27 [1] CRAN (R 4.1.1)
 tidyselect      1.1.1       2021-04-30 [1] CRAN (R 4.1.1)
 tidyverse     * 1.3.1.9000  2021-12-08 [1] Github (tidyverse/tidyverse@6186fbf)
 tzdb            0.2.0       2021-10-27 [1] CRAN (R 4.1.1)
 usethis         2.1.5.9000  2022-01-20 [1] Github (r-lib/usethis@57b109a)
 utf8            1.2.2       2021-07-24 [1] CRAN (R 4.1.1)
 vctrs           0.3.8       2021-04-29 [1] CRAN (R 4.1.1)
 vipor           0.4.5       2017-03-22 [1] CRAN (R 4.1.2)
 viridisLite     0.4.0       2021-04-13 [1] CRAN (R 4.1.1)
 vroom           1.5.7       2021-11-30 [1] CRAN (R 4.1.2)
 withr           2.4.3       2021-11-30 [1] CRAN (R 4.1.2)
 xfun            0.29        2021-12-14 [1] CRAN (R 4.1.2)
 xml2            1.3.3       2021-11-30 [1] CRAN (R 4.1.2)
 yaml            2.2.1       2020-02-01 [1] CRAN (R 4.1.1)

 [1] /opt/homebrew/lib/R/4.1/site-library
 [2] /opt/homebrew/Cellar/r/4.1.2/lib/R/library

─ Python configuration ───────────────────────────────────────────────────────
 python:         /Users/jialei/.pyenv/shims/python
 libpython:      /Users/jialei/.pyenv/versions/miniforge3-4.10.1-5/lib/libpython3.9.dylib
 pythonhome:     /Users/jialei/.pyenv/versions/miniforge3-4.10.1-5:/Users/jialei/.pyenv/versions/miniforge3-4.10.1-5
 version:        3.9.5 | packaged by conda-forge | (default, Jun 19 2021, 00:24:55)  [Clang 11.1.0 ]
 numpy:          /Users/jialei/.pyenv/versions/miniforge3-4.10.1-5/lib/python3.9/site-packages/numpy
 numpy_version:  1.20.3
 anndata:        /Users/jialei/.pyenv/versions/miniforge3-4.10.1-5/lib/python3.9/site-packages/anndata
 
 NOTE: Python version was forced by RETICULATE_PYTHON

──────────────────────────────────────────────────────────────────────────────