#! /usr/bin/nawk -f
#
#
#	Converts O-readable PDB to protin - readable PDB
#
#
BEGIN	{

}


/^ATOM/ {
	# extract interesting columns
	entry=$0

	# change N-terminal groups back to ACEtyl ARG
	front  = substr(entry, 0, 12)
	ATOM   = substr(entry, 13, 4)
	C      = substr(entry, 17, 1)
	RES    = substr(entry, 18, 3)
	chain  = substr(entry, 21, 2)
	RESnum = substr(entry, 23, 4)
	C      = substr(entry, 27, 1)
	XYZ    = substr(entry, 28, 27)
	occ    = substr(entry, 55, 6)
	B      = substr(entry, 61, 6)
	back   = substr(entry, 67)

	# modify acetylated residue
	if(RESnum == "   0")
	{
	    if(ATOM == " CA ") { RES = "ARG"; ATOM = " CT2"; RESnum = "   1"}
	    if(ATOM == " C  ") { RES = "ARG"; ATOM = " CT1"; RESnum = "   1"}
	    if(ATOM == " O  ") { RES = "ARG"; ATOM = " OT "; RESnum = "   1"}
	}
	# carboxy terminus
	if((ATOM == " N  ")&&(RES == "GLY")&&(occ+0 > 100))
	{
	    # turn bogus residue back into C-terminus
	    ATOM = " OT "
	    RESnum = sprintf("%4d", RESnum-1)
	    RES  = lastRES
	    occ  -= 100
	    occ  = sprintf("%6.2f", occ )
	    chain = lastchain
	}

	# fix selenomethionine 
	if((RES == "MET")&&(ATOM == " SD ")&&(occ > 100))
	{
	    ATOM = "SED "
	    occ -= 100
	}

	# multiple conformers
	if(occ+0 < 1)
	{
	    if(C == " ") C = "A"
	}
	else
	{
	    if(C != " ") skip = 1
	}


	# do something else?

	if(!skip) print front ATOM C RES chain RESnum " " XYZ occ B back

	skip = 0

	lastRESnum = RESnum
	lastRES    = RES
	lastchain  = chain
}

{

    if(! /^ATOM/) print;

}

END {
}