hs_gff <- "reference/hg38_91.gff"
hs_gff_annot <- sm(load_gff_annotations(hs_gff, id_col="gene_id"))
hs_annot <- sm(load_biomart_annotations())$annotation
hs_annot$ID <- hs_annot$geneID
rownames(hs_annot) <- make.names(hs_annot[["ensembl_gene_id"]], unique=TRUE)
dim(hs_annot)

## [1] 197995     12

hs_size_dist <- plot_histogram(hs_annot[["cds_length"]])
hs_size_dist +
  ggplot2::scale_x_continuous(limits=c(0, 20000))

## Warning: Removed 103681 rows containing non-finite values (stat_bin).

## Warning: Removed 103681 rows containing non-finite values (stat_density).

## Warning: Removed 2 rows containing missing values (geom_bar).

hs_go_biomart <- sm(load_biomart_go())

hs_lengths <- hs_annot[, c("ensembl_gene_id", "cds_length")]
colnames(hs_lengths) <- c("ID", "width")

rownames(hs_annot) <- make.names(
  paste0(hs_annot[["ensembl_transcript_id"]], ".",
         hs_annot[["transcript_version"]]),
  unique=TRUE)
hs_tx_gene <- hs_annot[, c("ensembl_gene_id", "ensembl_transcript_id")]
hs_tx_gene[["id"]] <- rownames(hs_tx_gene)
hs_tx_gene <- hs_tx_gene[, c("id", "ensembl_gene_id")]
new_hs_annot <- hs_annot
rownames(new_hs_annot) <- make.names(hs_annot[["ensembl_gene_id"]], unique=TRUE)

hs_expt <- create_expt("sample_sheets/macrophage_transcriptome_data_sources_20190607.xlsx",
                       gene_info=new_hs_annot,
                       tx_gene_map=hs_tx_gene,
                       file_column="salmonfile")

## Reading the sample metadata.

## Did not find the condition column in the sample sheet.

## Filling it in as undefined.

## Did not find the batch column in the sample sheet.

## Filling it in as undefined.

## The sample definitions comprises: 44 rows(samples) and 29 columns(metadata fields).

## Reading count tables.

## Using the transcript to gene mapping.

## Reading salmon data with tximport.

## Finished reading count tables.

## Matched 19629 annotations and counts.

## Bringing together the count matrix and gene information.

## The mapped IDs are not the rownames of your gene information, changing them now.

## Some annotations were lost in merging, setting them to 'undefined'.

## The final expressionset has 19629 rows and 28 columns.

cds_entries <- fData(hs_expt)
cds_entries <- cds_entries[["gene_biotype"]] == "protein_coding"
hs_cds_expt <- hs_expt
hs_cds_expt$expressionset <- hs_cds_expt$expressionset[cds_entries, ]
new_cds_entries <- fData(hs_cds_expt)

pander::pander(sessionInfo())
message(paste0("This is hpgltools commit: ", get_git_commit()))
this_save <- paste0(gsub(pattern="\\.Rmd", replace="", x=rmd_file), "-v", ver, ".rda.xz")
message(paste0("Saving to ", this_save))
tmp <- sm(saveme(filename=this_save))

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