trendsceek || 识别基因空间表达趋势

生信技能树jimmy

发布于 2021-02-09 07:29:17

79500

代码可运行

文章被收录于专栏：单细胞天地单细胞天地

运行总次数：0

代码可运行

作者 | 周运来

Identification of spatial expression trends in single-cell gene expression data

空间转录组技术使得我们可以在组织成像的基础上考察基因表达情况，同时也需要新的分析策略。trendsceek是一种基于标记点过程的方法，识别具有显著空间表达趋势的基因。trendsceek在空间转录组和顺序荧光原位杂交数据中都能很好地发现空间差异基因，并在单细胞RNA-seq数据的低维投影（TSNE/umap）中揭示了显著的基因表达梯度和热点。

library(trendsceek)
library(Seurat)
library(SeuratData)

AvailableData()

stxBrain.SeuratData::anterior1 -> sto 
head(sto@images$anterior1@coordinates)

                   tissue row col imagerow imagecol
AAACAAGTATCTCCCA-1      1  50 102     7475     8501
AAACACCAATAACTGC-1      1  59  19     8553     2788
AAACAGAGCGACTCCT-1      1  14  94     3164     7950
AAACAGCTTTCAGAAG-1      1  43   9     6637     2099
AAACAGGGTCTATATT-1      1  47  13     7116     2375
AAACATGGTGAGAGGA-1      1  62   0     8913     1480

pp = pos2pp(sto@images$anterior1@coordinates[,c(2,3)])
log.fcn = log10
counts_sub[1:2,1:4]
pp = set_marks(pp, as.matrix(sto@assays$Spatial@counts), log.fcn = log.fcn)

min.ncells.expr = 3
min.expr = 5
counts_filt = genefilter_exprmat(as.matrix(sto@assays$Spatial@counts), min.expr, min.ncells.expr)
dim(counts_filt)

quantile.cutoff = 0.9 ##filter out the most lowly expressed genes from the fitting
method = 'glm' ##For (robust) linear regression set to 'rlm'
vargenes_stats = calc_varstats(counts_filt, counts_filt, quant.cutoff = quantile.cutoff, method = method)

n.top2plot = 10
topvar.genes = rownames(vargenes_stats[['real.stats']])[1:n.top2plot]
pp2plot = pp_select(pp, topvar.genes)
plot.ercc.points = FALSE
plot_cv2vsmean(vargenes_stats, topvar.genes, plot.ercc.points = plot.ercc.points)

min.count = 1
counts_norm = deseq_norm(as.matrix(sto@assays$Spatial@counts), min.count)
counts_sub = counts_norm[topvar.genes, ]
dim(counts_sub)
plot_pp_scatter(pp2plot, log_marks = FALSE, scale_marks = FALSE, pal.direction = -1)
nrand = 100
ncores = 1

##run
trendstat_list = trendsceek_test(pp2plot, nrand, ncores)
trendstat_list

 head(trendstat_list$sig_genes_list$Vmark)
           gene  test earlystop max.env.rel.dev max.rel.dev   min.pval nsim_max nsim_stop      p.bh      p.bo rank
S100a5   S100a5 Vmark         0        6.898791  0.29728032 0.00990099        2         2 0.0110011 0.0990099    1
Fabp7     Fabp7 Vmark         0        5.392828  0.12836321 0.00990099        2         2 0.0110011 0.0990099    2
Ptgds     Ptgds Vmark         0        3.491384  0.09823452 0.00990099        2         2 0.0110011 0.0990099    3
Clca3a1 Clca3a1 Vmark         0        3.075842  0.35753230 0.00990099        2         2 0.0110011 0.0990099    4
Ttr         Ttr Vmark         0        2.962141  0.10187457 0.00990099        2         2 0.0110011 0.0990099    5
Kl           Kl Vmark         0        1.762761  0.11802672 0.00990099        2         2 0.0110011 0.0990099    6

alpha = 0.05 ##Benjamini-Hochberg
sig_list = extract_sig_genes(trendstat_list, alpha)
lapply(sig_list, nrow)
sig_genes = sig_list[['markcorr']][, 'gene']
plot_trendstats(trendstat_list, sig_genes[1])

plot_pp_scatter(pp_sig, log_marks = FALSE, scale_marks = FALSE, pal.direction = -1,pointsize.factor = 1)

References

[1] https://github.com/edsgard/trendsceek [2] Edsgärd D. et al., Identification of spatial expression trends in single-cell gene expression data, Nature Methods, 2018: doi:10.1038/nmeth.4634

本文参与腾讯云自媒体同步曝光计划，分享自微信公众号。

原始发表：2021-01-25，如有侵权请联系 cloudcommunity@tencent.com 删除

cell