code to filter genes to find those expressed on cell surface

filter_cell_surface.r

library(tidyverse)
library(biomaRt)

genes <- # FILL ME IN ... Should be a vector of gene names
markers <- # FILL ME IN ... Should be a data.frame with at least one column called mgi_symbol

ensembl <- useMart("ensembl", dataset="mmusculus_gene_ensembl")  # Mouse
# GO:0009986 is cell surface
go_cellsurf <- "GO:0009986"
gene.data <- getBM(attributes=c("mgi_symbol", "ensembl_gene_id", "go_id"),
  filters="go", values=go_cellsurf, mart=ensembl) %>%
  dplyr::filter(go_id == go_cellsurf)

markers_cell_surface <- dplyr::filter(markers, gene %in% gene.data$mgi_symbol)