# Samples in GEO NCBI database:
# GSM3900810
# GSM3900821

# https://bioinfogp.cnb.csic.es/courses/quedateencasa/

oliveros@cnb.csic.es

# Paired-end reads
#	FFFF_1.fastq.gz
#	FFFF_2.fastq.gz

# Single-end reads
#	FFFF.fastq.gz
	
# .FASTQ (.FQ): short-reads (eg. illumina)
# .FASTA (.FA,.FNA): biological sequences (eg. chromosomes)
# .GFF (.GFF3, .GTF):genomic elements coordinates (eg. genes)

# Experiment:
# https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE133136

# In R (Rconsole Rstudio...):
# Archivo -> Cambiar dir...
# File    -> Change dir...
# Misc    -> Change Working Directory... 
# Session -> Set Working Directory...

# (browse your hard disk to choose the working directory)

>dir() [ENTER] (To see files and folders in the working directory)
>dir("fastq")  (To see files and folders in the indicated path)

>install.packages("R.utils")
#	"package ‘R.utils’ successfully unpacked and MD5 sums checked"

>library("R.utils")           

>install.packages("BiocManager")   # To install Bioconductor packages

>library("BiocManager")                               

>BiocManager::install("Rbowtie2")  # To align FASTQ files against FASTA files
# Update all/some/none? [a/s/n]:   # <- The answer is "n"

>library("Rbowtie2")

>BiocManager::install("Rsamtools") # To manipulate aligned results (.BAM files)
# Update all/some/none? [a/s/n]:   # <- The answer is "n"

>library("Rsamtools")          

##### HASTA LAS 12:30 #####
#####   CONTINUAMOS   #####

>library("R.utils")
>library("BiocManager")
>library("Rsamtools")

>gunzip("chromosomes/Saccharomyces_cerevisiae.R64-1-1.dna.toplevel.fa.gz", remove=FALSE)

>gunzip("fastq/1M_SRR9336468_1.fastq.gz", remove=FALSE)

>gunzip("fastq/1M_SRR9336468_2.fastq.gz", remove=FALSE)

>bowtie2_build("chromosomes/Saccharomyces_cerevisiae.R64-1-1.dna.toplevel.fa",
                bt2Index = "chromosomes/yeast",
               overwrite = TRUE)

>bowtie2(bt2Index="chromosomes/yeast",
             samOutput = "1M_SRR9336468.sam",
                  seq1 = "fastq/1M_SRR9336468_1.fastq",
                  seq2 = "fastq/1M_SRR9336468_2.fastq",
                  "--threads=3")                         # <- use 3 CPUs... faster!!)

>asBam("1M_SRR9336468.sam")   # converting SAM file into BAM file (more compact)

#### IGV ####

Genomes -> Load Genome from file...   (Choose FASTA file in "chromosomes" folder)
File -> Load File...                  (Choose GFF3 file in "genes" folder=

Select one chromosome
Right mouse at left in the genes track: Choose "Expanded" to view all genes properly

File -> Load File...                  (Choose BAM file in working directory)

### IMPORTANT: .bam.bai file must be present in the same directory as .bam !!!!