HSMM<- estimateSizeFactors(HSMM)

expressed_genes<- row.names(subset(fData(HSMM),num_cells_expressed >= 10))

length(expressed_genes)

HSMM <- HSMM[expressed_genes,]

valid_cells<- row.names(subset(pData(HSMM),num_genes_expressed >= 200 &Mapped.Fragments > 1000000))

length(valid_cells)

HSMM <- HSMM[,valid_cells]

expdt<- exprs(HSMM)

dim(expdt)

pData(HSMM)$Total_mRNAs<- Matrix::colSums(expdt)

head(pData(HSMM))

dim(HSMM)

valid_cells2<- pData(HSMM)$Total_mRNAs < 1e6

HSMM <- HSMM[,valid_cells2]

upper_bound<- 10^(mean(log10(pData(HSMM)$Total_mRNAs)) +

2*sd(log10(pData(HSMM)$Total_mRNAs)))

lower_bound<- 10^(mean(log10(pData(HSMM)$Total_mRNAs)) -

2*sd(log10(pData(HSMM)$Total_mRNAs)))

qplot(Total_mRNAs,data = pData(HSMM), color = Hours, geom ="density") +

geom_vline(xintercept= lower_bound) +

geom_vline(xintercept = upper_bound)

valid_cells3<- pData(HSMM)$Total_mRNAs > lower_bound & pData(HSMM)$Total_mRNAs< upper_bound

HSMM<- HSMM[,valid_cells3]

dim(HSMM)

L <- log(exprs(HSMM[expressed_genes,]))

M <- Matrix::t(scale(Matrix::t(L)))

cth <- newCellTypeHierarchy()

MYF5_id<- row.names(subset(fData(HSMM), gene_short_name == "MYF5"))

ANPEP_id <-row.names(subset(fData(HSMM),gene_short_name == "ANPEP"))

cth<- addCellType(cth, "Myoblast", classify_func = function(x) {x[MYF5_id,] >= 1 })

cth <- addCellType(cth,"Fibroblast", classify_func = function(x) { x[MYF5_id,] < 1 &x[ANPEP_id,] > 1 })

HSMM<- classifyCells(HSMM, cth, 0.1)

Errorin if (type_res[cell_name] == TRUE) next_nodes <- c(next_nodes,  :

  需要TRUE/FALSE值的地方不可以用缺少值