# This file explains how each file in inst/extdata was created.

## File: singlecell_subset.rds
# Step 1: Download the GSE109262_RAW.tar file from https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE109262
# Step 2: Unpack the .tar file resulting in a folder called GSE109262_RAW.
# Step 3: Create two subfolders inside GSE109262_RAW named 'met' and 'acc'.
# Step 4: Move all files having 'met' in the filename to the 'met' folder; and all 'acc' files to the 'acc' folder.
# Step 5: (code)
### library(methylscaper)
### singlecell_subset <- subsetSC("~/Downloads/GSE109262_RAW/", chromosome="19", 
###    startPos = 8967041-20000, endPos = 8967041+20000, updateProgress = NULL)
### saveRDS(singlecell_subset, file="methylscaper/inst/ext/singlecell_subset.rds", compress = 'xz')




## File: singlemolecule_example.rds
# Code:
### library(methylscaper)
### seq_file <- system.file("extdata", "seq_file.fasta", package = "methylscaper")
### ref_file <- system.file("extdata", "ref.Pacbio.fa", package = "methylscaper")
### library(seqinr)
### reads_sm <- seqinr::read.fasta(seq_file)
### ref_seq <- seqinr::read.fasta(ref_file)
### singlemolecule_example <- runAlign(fasta=reads_sm, ref=ref_seq)
### saveRDS(singlemolecule_example, file="methylscaper/inst/ext/singlemolecule_example.rds", compress = 'xz')



## File: seq_file.fasta
# Sequences of all reads generated by the MAPit-BGS experiment using a 454 sequencing. Sequences were extracted 
# into the .fasta file from the .fastq file.

## File: reference.fa
# This is the sequence of the promoter region of the EMP2AIP1 gene in human hg19.

