##gene_set_ngs.sh
##2013-03-14 dmontaner@cipf.es
##GESBAP EXAMPLE

##This script shows the basics for functional profiling of genome wide studies.


##Go to the working directory
cd /home/biouser/gesbap

##and see what is in it
ls

## gesbap.py: the main program to run the Gesbap Functional profiling, it will: 
##   export the evidence from SNPs to genes 
##   perform the segmentation analysis (FatiScan)

## snp-gene.db: a DATABASE containing the information that links SNPs with GENES

## data: directory for examples data 

## Explore the data directory
ls data

cd data

## See the header of all files
head *

## These are examples of gene ANNOTATION files
# human_gene_ontology_biomart_70.txt
# human_gene_ontology_biomart_BP_propagated.txt
# human_gene_ontology_biomart_BP_propagated_filtered.txt


head human_gene_ontology_biomart_BP_propagated_filtered.txt

##Observe how annotations are replicated (all of them should be)
grep GO:0000002 human_gene_ontology_biomart_BP_propagated_filtered.txt

##And also the genes (some of them)
grep ENSG00000005156 human_gene_ontology_biomart_BP_propagated_filtered.txt

##See the other annotations
head human_gene_ontology_biomart_70.txt
head human_gene_ontology_biomart_BP_propagated.txt

##How long are they?
wc -l human_gene_ontology_biomart_70.txt
wc -l human_gene_ontology_biomart_BP_propagated.txt
wc -l human_gene_ontology_biomart_BP_propagated_filtered.txt

##GO propagation expands the number of gene to GO relationships
##Filtering of small functional blocks reduces the number of rows



## significantSNPs-DOM-Inf-v2.txt: is an standard output file form an association study analysis
head significantSNPs-DOM-Inf-v2.txt

## significantSNPs-DOM-Inf-v2.txt AND significantSNPs.txt are SNP ranking files
head significantSNPs-DOM-Inf-v2.txt
head significantSNPs.txt


###Count the rows
wc -l significantSNPs-DOM-Inf-v2.txt
wc -l significantSNPs.txt

##Why is there one more line in significantSNPs-DOM-Inf-v2.txt?
head significantSNPs.txt
head all_nsp_to_gesbap.txt


## significantSNPs-DOM-Inf-v2.txt contains all the SNPs, not just the significant:
wc -l significantSNPs.txt
wc -l all_nsp_to_gesbap.txt

################################################################################


### ANALYSIS ###
cd /home/biouser/gesbap

##make a directory for the results
mkdir res

###RUN the analysis (10 minutes)
./gesbap.py -i data/all_nsp_to_gesbap.txt -o res/NAME_RES


###EXPLORE THE OUTPUT FILES (use an spreadsheet)
cd res
ls 

## NAME_RES.gene_association.txt has the association evidence exported form SNP to gene
head NAME_RES.gene_association.txt

## NAME_RES.fatiscan_significant_terms.txt contains the significant GO terms.
## How many are they?
wc -l NAME_RES.fatiscan_significant_terms.txt 

## NAME_RES.fatiscan_significant_terms_simple.txt is a simplified version
head NAME_RES.fatiscan_significant_terms.txt 


## NAME_RES.fatiscan.txt has the exhaustive results form the analysis