read h5 files

library(Seurat)
library(hdf5r)
GSM4411701 <- Read10X_h5("./GSM4411701_ca02_filtered_gene_bc_matrices_h5.h5")
#compare and observe the hierarchy of h5 file is important; Different hierarchy should use different method;
#also, sometimes h5 file needs more modification before generate objects for Seurat.
h5ls("./GSE153184_Fgfr2_KO_aggr_filtered_feature_bc_matrix.h5")
h5ls("./GSM4411701_ca02_filtered_gene_bc_matrices_h5.h5")
h5ls("./GSM4453619_Control1_HPAP022_molecule_info.h5")

{
  library(hdf5r)
  h5_data <- hdf5r::H5File$new('GSM4411701_ca02_filtered_gene_bc_matrices_h5.h5',mode = 'r') 
  feature_matrix <- Matrix::sparseMatrix(
  i=h5_data[['matrix/indices']][],
  p=h5_data[['matrix/indptr']][],
  x=h5_data[['matrix/data']][],
  dimnames = list(
    h5_data[['matrix/features/name']][],
    h5_data[['matrix/barcodes']][]
  ),
  dims = h5_data[['matrix/shape']][],
  index1 = FALSE
)
}

feature_matrix1 <- Matrix::sparseMatrix(
  i=h5_data[['GRCh38/indices']][],
  p=h5_data[['GRCh38/indptr']][],
  x=h5_data[['GRCh38/data']][],
  dimnames = list(
    h5_data[['GRCh38/gene_names']][],
    h5_data[['GRCh38/barcodes']][]
  ),
  dims = h5_data[['GRCh38/shape']][],
  index1 = FALSE
)

{
library(rhdf5)
  # h5ls(.h5 file)  ## list the object within the file to find the data group you want to read
  getwd()
  barcode <- h5read("./GSM4453619_Control1_HPAP022_molecule_info.h5",name = "conf_mapped_uniq_read_pos",bit64conversion='bit64')   #
  write.csv(barcode,file = "barcode.tsv.gz")

  #barcode_corrected_reads, seems like a sparse matrix
  
  feature <- h5read("./H5file//GSM4453619_Control1_HPAP022_molecule_info.h5",name = "gene_names")
  write.csv(feature,file = "genes.tsv.gz")
  matrix <- h5read("./H5file/GSM4453619_Control1_HPAP022_molecule_info.h5",name = "")
  umi <- h5read("./H5file//GSM4453619_Control1_HPAP022_molecule_info.h5",name = "umi")
}

{
library(hdf5r)
library(Matrix)
library(DropletUtils)
}

{
counts_slot <- "umi_corrected_reads"
genes_slot <- "gene"
barcodes_slot <- "barcode"
gene_ids_slot <- "gene_ids"
gene_names_slot <- "gene_names"
}

data_dir <- "./"
h5_files <- list.files(data_dir,pattern = "*h5$")
h5_files  

output_dir <- file.path(data_dir,"out")
dir.create(output_dir)

#required functions
extract_slots <- function(h5_path){
  h5 <- H5File$new(h5_path,mode = "r")
  counts <- h5[[counts_slot]][]
  genes <- h5[[genes_slot]][]
  barcodes <- h5[[barcodes_slot]][]
  gene_ids <- h5[[gene_ids_slot]][]
  gene_names <- h5[[gene_names_slot]][]
  r_barcodes <- data.table::frankv(barcodes,ties.method = "dense")
  if(min(genes)==0 || min(barcodes)==0){index1 <- F} else {index1 <- T}
  return(
    list(
      "counts" = counts,
      "genes" = genes,
      "barcodes" = barcodes,
      "r_barcodes" = r_barcodes,
      "gene_ids" = gene_ids,
      "gene_names" = gene_names,
      "index1" = index1
    )
  )
}
build_sparse_matrix <- function(slots){
    sparse_matrix <- sparseMatrix(
      i=slots[["genes"]],
      j=slots[["r_barcodes"]],
      x=slots[["counts"]],
      repr = "C",
      index1 = slots[["index1"]]
    )
    return(sparse_matrix)
  }
  
#processing
for (file in h5_files){
  print(file)
  sample_name <- sub("\\.h5$","",basename(file))
  sample_path <- file.path(output_dir,sample_name)
  print(sample_name)
  slots <- extract_slots(file)
  counts <- build_sparse_matrix(slots)
  DropletUtils::write10xCounts(sample_path,
                               counts,
                               barcodes = paste0("cell",unique(slots[["barcodes"]])),
                               gene.id =slots[["gene_ids"]],
                               gene.symbol=slots[["gene_names"]],
                               version="3"
                               )
}