Shell Programming and Scripting

GN   Name=YWHAB;
RC   TISSUE=Keratinocyte;
RC   TISSUE=Thymus;
CC   -!- FUNCTION: Adapter protein implicated in the regulation of a large
CC       spectrum of both general and specialized signaling pathways
GN   Name=YWHAE;
RC   TISSUE=Liver;
RC   TISSUE=Brain;
RC   TISSUE=Heart;
CC   -!- FUNCTION: Adapter protein implicated in the regulation of a large
CC       spectrum of both general and specialized signaling pathways. Binds
CC       to a large number of partners, usually by recognition of a
CC       phosphoserine or phosphothreonine motif. Binding generally results
CC       in the modulation of the activity of the binding partner.

GN	TISSUE	                 FUNCTION		
YWHAB	Keratinocyte;Thymus	Adapter protein implicated in the regulation of a large spectrum of both general and specialized signaling pathways
YWHAE	Liver;Brain;Heart;	Adapter protein implicated in the regulation of a large spectrum of both general and specialized signaling pathways. Binds to a large number of partners, usually by recognition of a phosphoserine or phosphothreonine motif. Binding generally results in the modulation of the activity of the binding partner.

awk '
BEGIN {
	printf "%-8s %-22s %s\n","GN","TISSUE","FUNCTION"
	}
	/^GN/ {
		split($0,a,"[=;]")
		g=a[2]
		GN[g]=1
		}
	/^RC/ {
		split($0,a,"=")
		RC[g]=RC[g] a[2]}
	/^CC/ {
		sub(/-!- FUNCTION:/,x)
		split($0,a,"  +")
		CC[g]=CC[g] a[2]
		}
END {
	for (i in GN) 
		printf "%-8s %-22s %s\n",i,RC[i],CC[i] 
}' file

GN       TISSUE                 FUNCTION
YWHAB    Keratinocyte;Thymus;   Adapter protein implicated in the regulation of a largespectrum of both general and specialized signaling pathways
YWHAE    Liver;Brain;Heart;     Adapter protein implicated in the regulation of a largespectrum of both general and specialized signaling pathways. Bindsto a large number of partners, usually by recognition of aphosphoserine or phosphothreonine motif. Binding generally resultsin the modulation of the activity of the binding partner.

cut -f1 output_file

awk '{print $1}' output_file
GN
YWHAB
YWHAE

awk -F"[=;]" '/^GN/ {print $2}' orgfile
YWHAB
YWHAE