#Unix Essentials: Hands-on
#Parsing HBI array data 

#Goal: Process a gene expression file to get information such as genes of interest, sort by expression values, and subset the data for further investigation. 
#THIS SYMBOL "#" PRECEDES A COMMENT LINE

#0. In your browser open the page:
	http://jura.wi.mit.edu/bio/education/hot_topics/unix_essentials_2015/UnixEssentials_HandsOn.txt
	#You can copy paste the commands from that page as we need them
	


#1. Log into tak. See handouts. 

#2. Go to the BaRC’s training folder:

	cd /nfs/BaRC_training 
      
	#Create a folder with your login name with mkdir command:
	
	mkdir your_login_name 
	#[Note: Replace your_login_name with your tak login name] 
	
	#Go to the directory that you just created:
	
	cd your_login_name 


	#Check where you are:
	
	pwd
      
#3. Copy the HBI data we will be working with
 
	cp ../HBI.partial.txt  .
	#If you are following this instructions after the Hot Topics is over then use this command:
	#cp /nfs/BaRC_Public/Hot_Topics/Unix_Essentials_Oct2015/HBI.partial.txt  .

#4. View the file in your favorite editor. What is the first field? 

	gedit HBI.partial.txt & 
	
	more HBI.partial.txt 
 
	head -1  HBI.partial.txt   | cut -f1

#5. How many genes are in the HBI data? [Note: header line] 

	wc -l HBI.partial.txt 
		
#6. Get the first column, and columns 20-22 and output it to a file called HBI.partial.new.txt, use this new file for the rest of the questions

	cut -f 1,20-22  HBI.partial.txt > HBI.partial.new.txt
	  
#7.  What tissues are included in the new file?

	head -1 HBI.partial.new.txt
      
#8. Are there any duplicate genes? [Hint: uniq needs a sorted list]

	cut -f 1  HBI.partial.new.txt  | sort  |   uniq -d 
	  
#9. Sort the expression values based on the second column. Which gene has the highest expression level?
	#  [Note: the difference in using the sort options –g (general numeric sort) and –n (numerical sort)]
	
      sort -k 2,2gr  HBI.partial.new.txt | head
	  
#10. Get all the genes that begin only with "ZNF" from the original file, and output to a new file. Make sure to include the header line by appending just the header to the new file first. [Hint: use grep]
	
	head -1 HBI.partial.new.txt > ZNF_genes.txt
	grep "^ZNF" HBI.partial.new.txt >> ZNF_genes.txt
      

#11. At the end of the class make a folder with your name in your lab folder and copy all the material to lab it. Refer to the hand out for the location of your lab folder on Tak.  
	#These are example commands: 
	
	mkdir /lab/PIname_lab/username
	mkdir /lab/PI_name_lab/username/unix_essentials_class
	cp –r * /lab/PI_name_lab/username/unix_essentials_class