# Copyright Hunter Moseley, 2000. All rights reserved. # Written by Hunter Moseley 8/1/2000 # "Mostly" ReWritten by Gurmukh Sahota 02/01/2001 # Modified by Hunter Moseley 6/12/2001 # Modified by Gurmukh Sahota 06/18/2001 # fixed the cmap_conversion_hash (some wrong names) # Modified by Gurmukh Sahota 07/01/2001 # added hack for name_array where inconsistent with current residue shifts (write_bmrb_file) # added hack for non-existant _Atom_type (using first letter of shift name) (write_bmrb_file) # modified the multiplicity hash for increased atomType inclusions and some typo's. # modified deMultiplicate so that it now accepts -1 residues and demultiplicates accordingly. # # BMRBParsing.pm # Contains subroutines for reading and writing BMRB files. # # Subroutines: # read_bmrb_file - reads a bmrb file and returns a hash of records (Residue is a hash). # write_bmrb_file - prints a bmrb file out to $filename # convert_bmrb_shift_names - converts the bmrb shift names using the given shift_conversion_hash. # adjust_by_reference - Adjusts the carbon chemical shifts to DSS standard based on their current reference. # convert_residue_names - Converts residue names in the bmrb file structure from 3-letter to 1-letter and visa versa # package BMRBParsing; require Exporter; @ISA = qw(Exporter); @EXPORT = qw(); @EXPORT_OK = qw(clone read_bmrb_file write_bmrb_file adjust_by_reference convert_bmrb_shift_names convert_residue_names readBMRBasCMAP deMultiplicate convertBMRBtoCMap); %EXPORT_TAGS = ( ALL => [@EXPORT_OK] ); use strict; use Dumpvalue qw(:ALL); my $dumper = new Dumpvalue; # useful hashes # LEU HG => 1, MET CD => 0, LEU CE => 0 my %multiplicity = ("A" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 1, "CA" => 1, "CB" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1}, "C" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "CA" => 1, "CB" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1, "SG" => 1, "HG" => 1}, "D" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "HD" => 1, "HD2" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1, "OD" => 2, "OD1" => 1, "OD2" => 1}, "E" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "HG" => 2, "HG2" => 1, "HG3" => 1, "HE" => 1, "HE2" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CD" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1, "OE" => 2, "OE1" => 1, "OE2" => 1}, "F" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "HD" => 2, "HD1" => 1, "HD2" => 1, "HE" => 2, "HE1" => 1, "HE2" => 1, "HZ" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CD" => 2, "CE" => 2, "CZ" => 1, "CD1" => 1, "CD2" => 1, "CE1" => 1, "CE2" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1}, "G" => { "H" => 1, "HN" => 1, "HA2" => 1, "HA3" => 1, "CA" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1}, "H" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "HD" => 2, "HD1" => 1, "HD2" => 1, "HE" => 2, "HE1" => 1, "HE2" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CD" => 1, "CE" => 1, "CD2" => 1, "CE1" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1, "ND" => 1, "ND1" => 1, "NE" => 1, "NE2" => 1}, "I" => {"H" => 1, "HN" => 1, "HA" => 1, "HB" => 1, "HG" => 3, "HG12" => 1, "HG13" => 1, "HG2" => 1, "HD" => 1, "HD1" => 1, "CA" => 1, "CB" => 1, "CG" => 2, "CD" => 1, "CG1" => 1, "CG2" => 1, "CD1" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1}, "K" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "HG" => 2, "HG2" => 1, "HG3" => 1, "HD" => 2, "HD2" => 1, "HD3" => 1, "HE" => 2, "HE2" => 1, "HE3" => 1, "HZ" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CD" => 1, "CE" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1, "NZ" => 1}, "L" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "HG" => 1, "HD" => 2, "HD1" => 1, "HD2" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CD" => 2, "CD1" => 1, "CD2" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1}, "M" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "HG" => 2, "HG2" => 1, "HG3" => 1, "HE" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CE" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1, "SD" => 1}, "N" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "HD" => 2, "HD2" => 2, "HD21" => 1, "HD22" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CE" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1, "ND" => 1, "ND2" => 1, "OD" => 1, "OD1" => 1}, "P" => { "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "HG" => 2, "HG2" => 1, "HG3" => 1, "HD" => 2, "HD2" => 1, "HD3" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CD" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1}, "Q" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "HG" => 2, "HG2" => 1, "HG3" => 1, "HE" => 2, "HE2" => 2, "HE21" => 1, "HE22" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CD" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1, "NE" =>1, "NE2" => 1, "OE" => 1, "OE1" => 1}, "R" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "HG" => 2, "HG2" => 1, "HG3" => 1, "HD" => 2, "HD2" => 1, "HD3" => 1, "HE" => 1, "HH" => 4, "HH1" => 2, "HH11" => 1, "HH12" => 1, "HH2" => 2, "HH21" => 1, "HH22" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CD" => 1, "CZ" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1, "NE" => 1, "NH" => 2, "NH1" => 1, "NH2" => 1}, "S" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "HG" => 1, "CA" => 1, "CB" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1, "OG" => 1}, "T" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 1, "HG" =>2, "HG1" => 1, "HG2" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CG2" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1, "OG" => 1, "OG1" => 1}, "V" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 1, "HG" => 2, "HG1" => 1, "HG2" => 1, "CA" => 1, "CB" => 1, "CG" => 2, "CG1" => 1, "CG2" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1}, "W" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "HD" => 1, "HD1" => 1, "HE" => 2, "HE1" => 1, "HE3" => 1, "HZ" => 2, "HZ2" => 1, "HZ3" => 1, "HH" => 1, "HH2" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CD" => 2, "CE" => 2, "CZ" => 2, "CH" => 1, "CD1" => 1, "CD2" => 1, "CE2" => 1, "CE3" => 1, "CZ2" => 1, "CZ3" => 1, "CH2" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1, "NE" => 1, "NE1" => 1}, "Y" => { "H" => 1, "HN" => 1, "HA" => 1, "HB" => 2, "HB2" => 1, "HB3" => 1, "HD" => 2, "HD1" => 1, "HD2" => 1, "HE" => 2, "HE1" => 1, "HE2" => 1, "HH" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CD" => 2, "CE" => 2, "CZ" => 1, "CD1" => 1, "CD2" => 1, "CE1" => 1, "CE2" => 1, "C" => 1, "CO" => 1, "N" => 1, "N15" => 1, "OH" => 1} ); my %aa_name_conversion = ( "ala" => "A", "arg" => "R", "asn" => "N", "asp" => "D", "cys" => "C", "gln" => "Q", "glu" => "E", "gly" => "G", "his" => "H", "ile" => "I", "leu" => "L", "lys" => "K", "met" => "M", "phe" => "F", "pro" => "P", "ser" => "S", "thr" => "T", "trp" => "W", "tyr" => "Y", "val" => "V", "a" => "A", "r" => "R", "n" => "N", "d" => "D", "c" => "C", "q" => "Q", "e" => "E", "g" => "G", "h" => "H", "i" => "I", "l" => "L", "k" => "K", "m" => "M", "f" => "F", "p" => "P", "s" => "S", "t" => "T", "w" => "W", "y" => "Y", "v" => "V"); my %aa_name_conversion2 = ("A" => "Ala", "R" => "Arg", "N" => "Asn", "D" => "Asp", "C" => "Cys", "Q" => "Gln", "E" => "Glu", "G" => "Gly", "H" => "His", "I" => "Ile", "L" => "Leu", "K" => "Lys", "M" => "Met", "F" => "Phe", "P" => "Pro", "S" => "Ser", "T" => "Thr", "W" => "Trp", "Y" => "Tyr", "V" => "Val", "ALA" => "Ala", "ARG" => "Arg", "ASN" => "Asn", "ASP" => "Asp", "CYS" => "Cys", "GLN" => "Gln", "GLU" => "Glu", "GLY" => "Gly", "HIS" => "His", "ILE" => "Ile", "LEU" => "Leu", "LYS" => "Lys", "MET" => "Met", "PHE" => "Phe", "PRO" => "Pro", "SER" => "Ser", "THR" => "Thr", "TRP" => "Trp", "TYR" => "Tyr", "VAL" => "Val" ); my %degeneracy_shift_conversion = ( "ala" => { "H" => "H", "HA" => "HA", "HB" => "HB", "C" => "C", "CA" => "CA", "CB" => "CB", "N" => "N" }, "arg" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "HG2" => "HG", "HG3" => "HG", "HD" => "HD", "HD2" => "HD", "HD3" => "HD", "HE" => "HE", "HH" => "HH", "HH11" => "HH", "HH12" => "HH", "HH21" => "HH", "HH22" => "HH", "C" => "C", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "CZ" => "CZ", "N" => "N", "NE" => "NE", "NH" => "NH", "NH1" => "NH", "NH2" => "NH" }, "asn" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HD2" => "HD2", "HD21" => "HD2", "HD22" => "HD2", "C" => "C", "CA" => "CA", "CB" => "CB", "CG" => "CG", "N" => "N", "ND2" => "ND2" }, "asp" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "C" => "C", "CA" => "CA", "CB" => "CB", "CG" => "CG", "N" => "N" }, "cys" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "C" => "C", "CA" => "CA", "CB" => "CB", "N" => "N" }, "gln" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "HG2" => "HG", "HG3" => "HG", "HE2" => "HE2", "HE21" => "HE2", "HE22" => "HE2", "C" => "C", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "N" => "N", "NE2" => "NE2" }, "glu" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "HG2" => "HG", "HG3" => "HG", "C" => "C", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "N" => "N" }, "gly" => { "H" => "H", "HA" => "HA", "HA2" => "HA", "HA3" => "HA", "C" => "C", "CA" => "CA", "N" => "N" }, "his" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HD1" => "HD1", "HD2" => "HD2", "HE1" => "HE1", "HE2" => "HE2", "C" => "C", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD2" => "CD2", "CE1" => "CE1", "N" => "N", "ND1" => "ND1", "NE2" => "NE2" }, "ile" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HG1" => "HG", "HG12" => "HG", "HG13" => "HG", "HG2" => "HG", "HD"=>"HD", "HD1" => "HD", "C" => "C", "CA" => "CA", "CB" => "CB", "CG1" => "CG", "CG2" => "CG", "CD1" => "CD", "CD"=>"CD", "N" => "N" }, "leu" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "HD" => "HD", "HD1" => "HD", "HD2" => "HD", "C" => "C", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "CD1" => "CD", "CD2" => "CD", "N" => "N" }, "lys" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "HG2" => "HG", "HG3" => "HG", "HD" => "HD", "HD2" => "HD", "HD3" => "HD", "HE" => "HE", "HE2" => "HE", "HE3" => "HE", "HZ" => "HZ", "C" => "C", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "CE" => "CE", "N" => "N", "NZ" => "NZ" }, "met" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "HG2" => "HG", "HG3" => "HG", "HE" => "HE", "C" => "C", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CE" => "CE", "N" => "N" }, "phe" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HD" => "HD", "HD1" => "HD", "HD2" => "HD", "HE1" => "HE", "HE2" => "HE", "HZ" => "HZ", "C" => "C", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "CD1" => "CD", "CD2" => "CD", "CE1" => "CE", "CE2" => "CE", "CZ" => "CZ", "N" => "N" }, "pro" => { "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "HG2" => "HG", "HG3" => "HG", "HD" => "HD", "HD2" => "HD", "HD3" => "HD", "C" => "C", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "N" => "N" }, "ser" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "C" => "C", "CA" => "CA", "CB" => "CB", "N" => "N" }, "thr" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HG1" => "HG1", "HG2" => "HG2", "C" => "C", "CA" => "CA", "CB" => "CB", "CG2" => "CG2", "N" => "N" }, "trp" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HD1" => "HD1", "HE1" => "HE1", "HE3" => "HE3", "HZ2" => "HZ2", "HZ3" => "HZ3", "HH2" => "HH2", "C" => "C", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD1" => "CD1", "CD2" => "CD2", "CE2" => "CE2", "CE3" => "CE3", "CZ2" => "CZ2", "CZ3" => "CZ3", "CH2" => "CH2", "N" => "N", "NE1" => "NE1" }, "tyr" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HD" => "HD", "HD1" => "HD", "HD2" => "HD", "HE" => "HE", "HE1" => "HE", "HE2" => "HE", "HH" => "HH", "C" => "C", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "CD1" => "CD", "CD2" => "CD", "CE" => "CE", "CE1" => "CE", "CE2" => "CE", "CZ" => "CZ", "N" => "N" }, "val" => { "H" => "H", "HA" => "HA", "HB" => "HB", "HG" => "HG", "HG1" => "HG", "HG2" => "HG", "C" => "C", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CG1" => "CG", "CG2" => "CG", "N" => "N" } ); my %cmap_shift_conversion = ( "ala" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "C" => "CO", "CA" => "CA", "CB" => "CB", "N" => "N15", "HN" => "HN", "CO" => "CO", "N15" => "N15" }, "arg" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "HG2" => "HG", "HG3" => "HG", "HD" => "HD", "HD2" => "HD", "HD3" => "HD", "HE" => "HE", "HH" => "HH", "HH1" => "HH", "HH11" => "HH", "HH2" => "HH", "HH12" => "HH", "HH21" => "HH", "HH22" => "HH", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "CZ" => "CZ", "N" => "N15", "NE" => "NE", "NH" => "NH", "NH1" => "NH", "NH2" => "NH", "HN" => "HN", "CO" => "CO", "N15" => "N15" }, "asn" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HD2" => "HD", "HD21" => "HD", "HD22" => "HD", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG" => "CG", "N" => "N15", "ND2" => "ND", "HN" => "HN", "CO" => "CO", "N15" => "N15", "ND" => "ND", "HD" => "HD" }, "asp" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG" => "CG", "N" => "N15", "HN" => "HN", "CO" => "CO", "N15" => "N15", "OD1" => "OD", "OD2" => "OD", "HD2" => "HD", "OD" => "OD", "HD" => "HD"}, "cys" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "C" => "CO", "CA" => "CA", "CB" => "CB", "N" => "N15", "HN" => "HN", "CO" => "CO", "N15" => "N15", "SG" => "SG" }, "gln" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "HG2" => "HG", "HG3" => "HG", "HE2" => "HE", "HE21" => "HE", "HE22" => "HE", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "N" => "N15", "NE2" => "NE", "HN" => "HN", "CO" => "CO", "N15" => "N15", "NE" => "NE", "HE" => "HE", "OE1" => "OE", "OE" => "OE"}, "glu" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "HG2" => "HG", "HG3" => "HG", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "N" => "N15", "HN" => "HN", "CO" => "CO", "N15" => "N15", "OE1" => "OE", "OE2" => "OE", "OE" => "OE", "HE2" => "HE", "HE" => "HE"}, "gly" => { "H" => "HN", "HA" => "HA", "HA2" => "HA", "HA3" => "HA", "C" => "CO", "CA" => "CA", "N" => "N15", "HN" => "HN", "CO" => "CO", "N15" => "N15" }, "his" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HD1" => "HD", "HD2" => "HD", "HE1" => "HE", "HE2" => "HE", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD2" => "CD", "CE1" => "CE", "N" => "N15", "ND1" => "ND", "NE2" => "NE", "ND" => "ND", "NE" => "NE", "CD" => "CD", "HN" => "HN", "CO" => "CO", "N15" => "N15", "CE" => "CE", "HD" => "HD", "HE" => "HE" }, "ile" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HG1" => "HG", "HG12" => "HG", "HG13" => "HG", "HG2" => "HG", "HD1" => "HD", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG1" => "CG", "CG2" => "CG", "CD1" => "CD", "N" => "N15", "HD" => "HD", "HN" => "HN", "CO" => "CO", "N15" => "N15", "HG" => "HG", "CD" => "CD", "CG" => "CG" }, "leu" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "HD" => "HD", "HD1" => "HD", "HD2" => "HD", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "CD1" => "CD", "CD2" => "CD", "N" => "N15", "HN" => "HN", "CO" => "CO", "N15" => "N15"}, "lys" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "HG2" => "HG", "HG3" => "HG", "HD" => "HD", "HD2" => "HD", "HD3" => "HD", "HE" => "HE", "HE2" => "HE", "HE3" => "HE", "HZ" => "HZ", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "CE" => "CE", "N" => "N15", "NZ" => "NZ", "HN" => "HN", "CO" => "CO", "N15" => "N15" }, "met" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "HG2" => "HG", "HG3" => "HG", "HE" => "HE", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CE" => "CE", "N" => "N15", "HN" => "HN", "CO" => "CO", "N15" => "N15" , "SD" => "SD"}, "phe" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HD" => "HD", "HD1" => "HD", "HD2" => "HD", "HE1" => "HD", "HE2" => "HD", "HZ" => "HZ", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "CD1" => "CD", "CD2" => "CD", "CE1" => "CE", "CE2" => "CE", "CZ" => "CZ", "N" => "N15", "HN" => "HN", "CO" => "CO", "N15" => "N15" }, "pro" => { "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "HG2" => "HG", "HG3" => "HG", "HD" => "HD", "HD2" => "HD", "HD3" => "HD", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "N" => "N15", "HN" => "HN", "CO" => "CO", "N15" => "N15" }, "ser" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HG" => "HG", "C" => "CO", "CA" => "CA", "CB" => "CB", "N" => "N15", "HN" => "HN", "CO" => "CO", "N15" => "N15", "OG" => "OG" }, "thr" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HG1" => "HG", "HG2" => "HG", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG2" => "CG", "N" => "N15", "HN" => "HN", "CO" => "CO", "N15" => "N15", "CG" => "CG", "HG" => "HG" }, "trp" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HD1" => "HD", "HE1" => "HE", "HE3" => "HE", "HZ2" => "HZ", "HZ3" => "HZ", "HH2" => "HH", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD1" => "CD", "CD2" => "CD", "CE2" => "CE", "CE3" => "CE", "CZ2" => "CZ", "CZ3" => "CZ", "CH2" => "CH", "N" => "N15", "NE1" => "NE", "CZ" => "CZ", "HZ" => "HZ", "CD" => "CD", "HN" => "HN", "CO" => "CO", "N15" => "N15", "HE" => "HE", "HH" => "HH", "NE" => "NE", "CE" => "CE", "HD" => "HD", "CH" => "CH" }, "tyr" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HB2" => "HB", "HB3" => "HB", "HD" => "HD", "HD1" => "HD", "HD2" => "HD", "HE" => "HE", "HE1" => "HE", "HE2" => "HE", "HH" => "HH", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CD" => "CD", "CD1" => "CD", "CD2" => "CD", "CE" => "CE", "CE1" => "CE", "CE2" => "CE", "CZ" => "CZ", "N" => "N15", "HN" => "HN", "CO" => "CO", "N15" => "N15", "OH" => "OH" }, "val" => { "H" => "HN", "HA" => "HA", "HB" => "HB", "HG" => "HG", "HG1" => "HG", "HG2" => "HG", "C" => "CO", "CA" => "CA", "CB" => "CB", "CG" => "CG", "CG1" => "CG", "CG2" => "CG", "N" => "N15", "HN" => "HN", "CO" => "CO", "N15" => "N15" } ); my @shift_name_order = ("HN", "N15", "CO", "CA", "CB", "CG", "CD", "CE", "CZ", "CH", "HA", "HB", "HG", "HD", "HE", "HZ", "HH", "CO-1", "CA-1", "CB-1", "CG-1", "CD-1", "CE-1", "CZ-1", "CH-1", "HA-1", "HB-1", "HG-1", "HD-1", "HE-1", "HZ-1", "HH-1"); # clone # clones a bmrb_hlist. # # $original_hlist - the original $bmrb_hlist # $cloned_hlist - the cloned $bmrb_hlist sub clone { my $original_hlist = shift @_; my $cloned_hlist = shift @_; $$cloned_hlist{"filename"} = $$original_hlist{"filename"}; @{$$cloned_hlist{"name_array"}} = @{$$original_hlist{"name_array"}}; foreach my $atom_type (keys %{$$original_hlist{"reference"}}) { @{$$cloned_hlist{"reference"}{$atom_type}} = @{$$original_hlist{"reference"}{$atom_type}} if (exists $$original_hlist{"reference"}{$atom_type}); } $$cloned_hlist{"reference_fields"} = $$original_hlist{"reference_fields"}; $$cloned_hlist{"reference_shift_index"} = $$original_hlist{"reference_shift_index"}; $$cloned_hlist{"sequence"} = $$original_hlist{"sequence"}; $$cloned_hlist{"sequence_startpos"} = $$original_hlist{"sequence_startpos"}; foreach my $residue (keys %{$$original_hlist{"rlist"}}) { $$cloned_hlist{"rlist"}{$residue}{"name"} = $$original_hlist{"rlist"}{$residue}{"name"}; $$cloned_hlist{"rlist"}{$residue}{"author_name"} = $$original_hlist{"rlist"}{$residue}{"author_name"} if (exists $$original_hlist{"rlist"}{$residue}{"author_name"}); $$cloned_hlist{"rlist"}{$residue}{"aa"} = $$original_hlist{"rlist"}{$residue}{"aa"}; $$cloned_hlist{"rlist"}{$residue}{"author_index"} = $$original_hlist{"rlist"}{$residue}{"author_index"} if (exists $$original_hlist{"rlist"}{$residue}{"author_index"}) ; $$cloned_hlist{"rlist"}{$residue}{"index"} = $$original_hlist{"rlist"}{$residue}{"index"}; foreach my $shift_name (keys % {$$original_hlist{"rlist"}{$residue}{"shifts"}}) { $$cloned_hlist{"rlist"}{$residue}{"shifts"}{$shift_name}{"atom_type"} = $$original_hlist{"rlist"}{$residue}{"shifts"}{$shift_name}{"atom_type"}; if (exists $$original_hlist{"rlist"}{$residue}{"shifts"}{$shift_name}{"list"}) { @{$$cloned_hlist{"rlist"}{$residue}{"shifts"}{$shift_name}{"list"}} = @{$$original_hlist{"rlist"}{$residue}{"shifts"}{$shift_name}{"list"}}; } } $$cloned_hlist{"rlist"}{$residue}{"next"} = $$original_hlist{"rlist"}{$residue}{"next"}; $$cloned_hlist{"rlist"}{$residue}{"prev"} = $$original_hlist{"rlist"}{$residue}{"prev"}; } return; } # read_bmrb_file # reads a bmrb file and returns a hash of records (Residue is a hash). # # $$bmrb_hlist{"filename"} - name of bmrb file used to build hash of residue names. # $$bmrb_hlist{"name_array"} - list of residue names in their proper order. # $$bmrb_hlist{"reference"}{"atom_type"} - hash list of references (array of fields) by atom type. # $$bmrb_hlist{"reference_fields"} - list and order of reference fields. # $$bmrb_hlist{"reference_shift_index"} - index of chemical shift value in reference fields array. # $$bmrb_hlist{"sequence"} - array of amino acid sequence (single letter code). # $$bmrb_hlist{"sequence_startpos"} - starting author_index (or index if no author_index). # $$bmrb_hlist{"rlist"} - hash list of residue_names to residues. # $$residue{"name"} - name of residue (uses index in name) # $$residue{"author_name"} - name of residue (uses author_index in name) # $$residue{"aa"} - amino acid of residue # $$residue{"author_index"} - author designated residue number # $$residue{"index"} - residue number # $$residue{"shifts"} - hash of shifts # $$residue{"shifts"}{$shift_name}{"atom_type"} - atom_type of shift. # $$residue{"shifts"}{$shift_name}{"list"} - array of shift values. # $$residue{"shifts"}{$shift_name}{"ambiguity_code"} - ambiguity code for the shift_name. # $$residue{"next"} - name of the next residue. # $$residue{"prev"} - name of the previous residue. # # Parameters: # $filename - bmrb file to read. # $read_options - reference to hash of read options (optional). # $$read_options{"convert_aa_name"} - convert aa names from single letter to three letter. # $$read_options{"convert_shift_names"} - convert shift names to degenerate naming scheme. # $$read_options{"shift_conversion_hash"} - ref to hash of shift name conversions. # $$read_options{"bmrb_hlist"} - reference to bmrb_hlist to fill. sub read_bmrb_file { my $filename = shift @_; my $read_options = {}; if (@_) { $read_options = shift @_; } my $convert_aa_names = 1; if (exists $$read_options{"convert_aa_names"} && ! $$read_options{"convert_aa_names"}) { $convert_aa_names = 0; } my $convert_shift_names = 0; if (exists $$read_options{"convert_shift_names"} && $$read_options{"convert_shift_names"}) { $convert_shift_names = 1; } my $shift_conversion_hash = \%degeneracy_shift_conversion; if (exists $$read_options{"shift_conversion_hash"} && ref $$read_options{"shift_conversion_hash"} eq "HASH") { $shift_conversion_hash = $$read_options{"shift_conversion_hash"}; } my $bmrb_hlist; if (exists $$read_options{"bmrb_hlist"} && ref $$read_options{"bmrb_hlist"} eq "HASH") { $bmrb_hlist = $$read_options{"bmrb_hlist"}; } else { $bmrb_hlist = {}; $$bmrb_hlist{"filename"} = $filename; } local *STARFILE; if ($filename eq "-") { *STARFILE = *STDIN; } else { open (STARFILE, "<$filename") || die "unable to open $filename"; } # skip junk while (my $line = ) { # print $line; chomp $line; # hash of column names to their column positions. my $columns = {}; # find the column definition section if ($line =~ m/^\s*?loop_\s*?$/) { # initialize position counter. my $count = 0; # read the whole definition section. End when is a null or space filled element. # keep track of position using count and columns hash while ($line = ) { chomp($line); last if ($line =~ /^\s*$/); # HACK ADDED FOR AUTOASSIGN's BMRB WRITING last if ($line !~ /^\s*?_/); # Remove flanking spaces $line =~ s/^\s*(.*?)\s*$/$1/; # uppercase letter after the _, to make life easier later. $line =~ s/^(\_.)/uc($1)/e; # store line's position and "new" content. next line, so next position $$columns{$line} = $count++; } } # Check to see whether the columns elements contain certain key elements and then parse accordingly. # As of 01-02-2001, _Residue_author_seq_code adds additional optional info if it is there. if ( &contains($columns, '_Residue_label', '_Residue_seq_code', '_Chem_shift_value', '_Atom_type', '_Atom_name', '_Chem_shift_ambiguity_code') ) { &read_bmrb_shift_lines(\*STARFILE, $columns, $convert_aa_names, $convert_shift_names, $shift_conversion_hash, $bmrb_hlist); } elsif ( &contains($columns, '_Residue_label', '_Residue_author_seq_code', '_Chem_shift_value', '_Atom_type', '_Atom_name', '_Chem_shift_ambiguity_code') ) { &read_bmrb_shift_lines(\*STARFILE, $columns, $convert_aa_names, $convert_shift_names, $shift_conversion_hash, $bmrb_hlist); } # elsif ( &contains($columns, '_Residue_label', '_Residue_author_seq_code', '_Residue_seq_code') ) # { &read_bmrb_residue_list_format(\*STARFILE, $columns, $convert_aa_names, $bmrb_hlist); } elsif ( &contains($columns, '_Residue_label', '_Residue_seq_code') ) { &read_bmrb_residue_list_format(\*STARFILE, $columns, $convert_aa_names, $bmrb_hlist); } elsif ( &contains($columns, '_Residue_label', '_Residue_author_seq_code') ) { &read_bmrb_residue_list_format(\*STARFILE, $columns, $convert_aa_names, $bmrb_hlist); } elsif ( &contains($columns, 'save_[Cc]hem(ical)?_shift_reference') ) { &read_bmrb_chemical_shift_reference(\*STARFILE, $columns, $bmrb_hlist); } } # ADDED BY GSS 10/29/2000 for bmr1133.str, but applies to a lot more ... # if at this point, you do not have a name array, then kinda fake one. if ( ($$bmrb_hlist{"name_array"} eq '') ) { @{$$bmrb_hlist{"name_array"}} = sort { ($a =~ /^[a-zA-Z]+(\-?\d+)$/)[0] <=> ($b =~ /^[A-Za-z]+(\-?\d+)$/)[0]; } (keys %{$$bmrb_hlist{"rlist"}}); } # create sequence field $$bmrb_hlist{"sequence"} = []; for(my $x=0; $x < @{$$bmrb_hlist{"name_array"}}; $x++) { my $resname = $$bmrb_hlist{"name_array"}[$x]; my $aa = $$bmrb_hlist{"rlist"}{$resname}{"aa"}; if (exists $aa_name_conversion{lc($aa)}) { $aa = $aa_name_conversion{lc($aa)}; } push @{$$bmrb_hlist{"sequence"}}, $aa; if ($x) { $$bmrb_hlist{"rlist"}{$resname}{"prev"} = $$bmrb_hlist{"name_array"}[$x-1]; } if ($x < (@{$$bmrb_hlist{"name_array"}} - 1)) { $$bmrb_hlist{"rlist"}{$resname}{"next"} = $$bmrb_hlist{"name_array"}[$x+1]; } } # create sequence_startpos field if (exists $$bmrb_hlist{"rlist"}{$$bmrb_hlist{"name_array"}[0]}{"author_index"}) { $$bmrb_hlist{"sequence_startpos"} = $$bmrb_hlist{"rlist"}{$$bmrb_hlist{"name_array"}[0]}{"author_index"}; } else { $$bmrb_hlist{"sequence_startpos"} = $$bmrb_hlist{"rlist"}{$$bmrb_hlist{"name_array"}[0]}{"index"}; } close STARFILE if ($filename ne "-"); return $bmrb_hlist; } # contains # checks to see whether @elements are all in keys of %$columns. return 1 if all found else 0. # # Parameters: # $columns - reference to the hash of the column entries to their order. # @elements - elements to check to see if in $columns sub contains { my $columns = shift @_; my @elements = @_; # Check all elements ... foreach my $elem (@elements) { # if you don't find an element, then fail return 0 if ( scalar(grep /$elem/, keys %$columns) == 0); } # if you found them all, then pass return 1; } # write_bmrb_file # Prints a bmrb file out to $filename # # Parameters: # $bmrb_hlist - reference to bmrb hash structure. # $filename - name of output filename. sub write_bmrb_file { my $bmrb_hlist = shift @_; my $filename = shift @_; local *STARFILE; if ($filename eq "-") { *STARFILE = *STDOUT; } else { open (STARFILE, ">$filename") || die "unable to open $filename"; } my @sorted_residue_names; if (exists $$bmrb_hlist{"name_array"}) { @sorted_residue_names = @{$$bmrb_hlist{"name_array"}}; } else { @sorted_residue_names = sort { ($a =~ /^[a-zA-Z]+(\-?\d+)$/)[0] <=> ($b =~ /^[A-Za-z]+(\-?\d+)$/)[0]; } (keys %{$$bmrb_hlist{"rlist"}}); } # print residues as single letters. print STARFILE "_Mol_residue_sequence\n;\n"; { my $count = 0; foreach my $residue_name (@sorted_residue_names) { my $aa = $$bmrb_hlist{"rlist"}{$residue_name}{"aa"}; print STARFILE $aa_name_conversion{lc($aa)}; $count = ($count +1) % 20; print STARFILE "\n" if (! $count); } print STARFILE"\n" if ($count); } # print sequence with sequence number. print STARFILE";\n\n"; print STARFILE" loop_\n _Residue_seq_code\n _Residue_author_seq_code\n _Residue_label\n\n"; my $count =1; my %residue_seq_code_hlist; foreach my $residue_name (@sorted_residue_names) { my $residue = $$bmrb_hlist{"rlist"}{$residue_name}; if (exists $$residue{"author_index"}) { print STARFILE "$count\t",$$residue{"author_index"},"\t", $aa_name_conversion2{uc($$residue{"aa"})}, "\n"; $residue_seq_code_hlist{$$residue{"author_index"}} = $count; } else { print STARFILE "$count\t",$$residue{"index"},"\t", $aa_name_conversion2{uc($$residue{"aa"})}, "\n"; $residue_seq_code_hlist{$$residue{"index"}} = $count; } $count++; } print STARFILE " stop_\n\n\n"; # print shifts print STARFILE " loop_\n _Atom_shift_assign_ID\n _Residue_seq_code\n _Residue_label\n"; print STARFILE " _Atom_name\n _Atom_type\n _Chem_shift_value\n _Chem_shift_value_error\n"; print STARFILE " _Chem_shift_ambiguity_code\n\n"; my $count = 1; foreach my $residue_name (@sorted_residue_names) { my $residue = $$bmrb_hlist{"rlist"}{$residue_name}; foreach my $shift_name (keys %{$$residue{"shifts"}}) { foreach my $shift_value (@{$$residue{"shifts"}{$shift_name}{"list"}}) { # ADDED BY GSS 07/01/2001. The residue_seq_code_hlist hash makes sure that the next time you read in the data, the name array is consistent with the chemical shift data. print STARFILE "$count\t",$residue_seq_code_hlist{$$residue{"index"}}, "\t", $aa_name_conversion2{uc($$residue{"aa"})}, "\t", $shift_name,"\t"; # ADDED BY GSS 07/01/2001. If you do not have an atomType existing, make it from the first letter of the shift name. if (exists $$residue{"shifts"}{$shift_name}{"atom_type"}) { print STARFILE $$residue{"shifts"}{$shift_name}{"atom_type"},"\t"; } else { print STARFILE ($shift_name =~ /^(.)/)[0], "\t"; } print STARFILE $shift_value,"\t.\t"; if (exists $$residue{"shifts"}{$shift_name}{"ambiguity_code"} && $$residue{"shifts"}{$shift_name}{"ambiguity_code"}) { print STARFILE $$residue{"shifts"}{$shift_name}{"ambiguity_code"}; } else { print STARFILE "1"; } print STARFILE "\n"; $count++; } } } print STARFILE " stop_\n"; close STARFILE; } # convert_bmrb_shift_names # Converts the bmrb shift names using the given shift_conversion_hash. assumes lowercase 3 letter code for Residue type # # Parameters: # $bmrb_hlist - reference to bmrb hash structure. # $shift_conversion_hash - reference to a shift conversion hash. sub convert_bmrb_shift_names { my $bmrb_hlist = shift @_; my $shift_conversion_hash = shift @_; foreach my $residue_name (@{$$bmrb_hlist{"name_array"}}) { my $residue = $$bmrb_hlist{"rlist"}{$residue_name}; my $new_shift_list = {}; foreach my $shift_name_real (keys %{$$residue{"shifts"}}) { my ($shift_name, $suffix) = ($shift_name_real =~ /^([a-zA-Z]+\d*)(\-1)?$/); my $res_name = $$residue{"aa"}; $res_name = $$bmrb_hlist{"rlist"}{$$bmrb_hlist{"rlist"}{$residue_name}{"prev"}}{"aa"} if ($suffix ne ""); if (exists $aa_name_conversion2{uc($res_name)}) { $res_name = $aa_name_conversion2{uc($res_name)}; } $res_name = lc($res_name); if (exists $$shift_conversion_hash{$res_name}{$shift_name}) { if (exists $$new_shift_list{$$shift_conversion_hash{$res_name}{$shift_name} . $suffix}) { push @{$$new_shift_list{$$shift_conversion_hash{$res_name}{$shift_name} . $suffix}{"list"}}, @{$$residue{"shifts"}{$shift_name . $suffix}{"list"}}; } else { $$new_shift_list{$$shift_conversion_hash{$res_name}{$shift_name} . $suffix} = $$residue{"shifts"}{$shift_name . $suffix}; } } } $$residue{"shifts"} = $new_shift_list; } } # adjust_by_reference # Adjusts the carbon chemical shifts to DSS standard based on their current reference. # # Parameters: # $bmrb_hlist - bmrb hash structure. # sub adjust_by_reference { my $bmrb_hlist = shift @_; my $carbon_shifting = 0.0; if (exists $$bmrb_hlist{"reference"}{"C"}) { if ($$bmrb_hlist{"reference"}{"C"}[0] eq "TMS") { $carbon_shifting = 1.7; } elsif ($$bmrb_hlist{"reference"}{"C"}[0] eq "TSP") { $carbon_shifting = -0.15; } elsif ($$bmrb_hlist{"reference"}{"C"}[0] eq "dioxane" && exists $$bmrb_hlist{"reference_shift_index"} && ($$bmrb_hlist{"reference"}{"C"}[$$bmrb_hlist{"reference_shift_index"}] == 0)) { $carbon_shifting = 69.3; } } if ($carbon_shifting != 0.0) { foreach my $residue (values %{$$bmrb_hlist{"rlist"}}) { foreach my $shift (values %{$$residue{"shifts"}}) { if ($$shift{"atom_type"} eq "C") { foreach my $value (@{$$shift{"list"}}) { $value += $carbon_shifting; } } } } } } # convert_residue_names # Converts residue names in the bmrb file structure from 3-letter to 1-letter and visa versa # # Parameters: # $bmrb_hlist - bmrb hash structure. # $conversion - 1 or 3 for conversion to 1-letter or 3-letter # sub convert_residue_names { my $bmrb_hlist = shift @_; my $conversion = shift @_; if ($conversion == 1) { my $rlist = {}; foreach my $residue_name (@{$$bmrb_hlist{"name_array"}}) { my $residue = $$bmrb_hlist{"rlist"}{$residue_name}; if (exists $aa_name_conversion{lc($$residue{"aa"})}) { $$residue{"aa"} = $aa_name_conversion{lc($$residue{"aa"})}; $$residue{"name"} = $$residue{"aa"} . $$residue{"index"}; if (exists $$residue{"author_index"}) { $$residue{"author_name"} = $$residue{"aa"} . $$residue{"author_index"}; } $residue_name = $$residue{"name"}; } $$rlist{$residue_name} = $residue; } $$bmrb_hlist{"rlist"} = $rlist; } else { my $rlist = {}; foreach my $residue_name (@{$$bmrb_hlist{"name_array"}}) { my $residue = $$bmrb_hlist{"rlist"}{$residue_name}; if (exists $aa_name_conversion2{uc($$residue{"aa"})}) { $$residue{"aa"} = $aa_name_conversion2{uc($$residue{"aa"})}; $$residue{"name"} = $$residue{"aa"} . $$residue{"index"}; if (exists $$residue{"author_index"}) { $$residue{"author_name"} = $$residue{"aa"} . $$residue{"author_index"}; } $residue_name = $$residue{"name"}; } $$rlist{$residue_name} = $residue; } $$bmrb_hlist{"rlist"} = $rlist; } } # # Routines for internal use only. # # read_bmrb_shift_lines # Reads the shift lines from a bmrb file and puts them in the bmrb hash structure. # # Parameters: # $file - file descriptor to read from. # $convert_aa_names - converts single letter amino acid names to three letter representations if true. # $convert_shift_names - convert shift names to degenerate naming scheme. # $shift_conversion_hash - hash to use for converting shift names. # $bmrb_hlist - bmrb hash structure to fill. # sub read_bmrb_shift_lines { my $file = shift @_; my $column_elements = shift @_; my $convert_aa_names = shift @_; my $convert_shift_names = shift @_; my $shift_conversion_hash = shift @_; my $bmrb_hlist = shift @_; # foreach line in the file until stop_ while (my $line = <$file>) { # chomp the line chomp $line; # skip blank lines next if ($line =~ /^\s*$/); next if ($line =~ /^#/); # last time if stop_ last if ($line =~ /stop_/); # split and split it on spaces my @tokens = split(/\s+/, $line); # get rid of the null element in the beginning caused by the spaces followed by characters while (@tokens && ($tokens[0] eq "")) { shift @tokens; } # print STDERR "BEFORE IF > @tokens < ::", scalar(@tokens), " = ", scalar(keys %$column_elements), ":: \n"; # as long as you have enough tokens to map to the column elements and the residue label is legitimate continue, otherwise next line. next if ((@tokens < scalar(keys %$column_elements)) || ((! exists $aa_name_conversion{lc($tokens[$$column_elements{"_Residue_label"}])}) && (! exists $aa_name_conversion2{uc($tokens[$$column_elements{"_Residue_label"}])})) ); # print STDERR "AFTER IF\n"; # if you are supposed to convert the name and you can, then do so ... if ($convert_aa_names && exists $aa_name_conversion{lc($tokens[$$column_elements{"_Residue_label"}])}) { $tokens[$$column_elements{"_Residue_label"}] = $aa_name_conversion{lc($tokens[$$column_elements{"_Residue_label"}])}; } # get the residue name, by hook or crook. my $residue_name = (exists $$column_elements{"_Residue_seq_code"}) ? $tokens[$$column_elements{"_Residue_label"}] . $tokens[$$column_elements{"_Residue_seq_code"}] : $tokens[$$column_elements{"_Residue_label"}] . $tokens[$$column_elements{"_Residue_author_seq_code"}]; #q print STDERR "YO >> ",$residue_name, "\n"; my $residue; if (! exists $$bmrb_hlist{"rlist"}{$residue_name}) { # Fill the residue hash reference with useful goodies $residue = {}; $$residue{"index"} = (exists $$column_elements{"_Residue_seq_code"}) ? $tokens[$$column_elements{"_Residue_seq_code"}] : $tokens[$$column_elements{"_Residue_author_seq_code"}]; $$residue{"author_index"} = $tokens[$$column_elements{"_Residue_author_seq_code"}] if (exists $$column_elements{"_Residue_author_seq_code"}); $$residue{"aa"} = $tokens[$$column_elements{"_Residue_label"}]; $$residue{"name"} = $$residue{"aa"} . $$residue{"index"}; $$residue{"author_name"} = $$residue{"aa"} . $$residue{"author_index"} if (exists $$residue{"author_index"}); $$bmrb_hlist{"rlist"}{$residue_name} = $residue; } # it already exists, so just reset the stuff that you would essentially re-read else { $residue = $$bmrb_hlist{"rlist"}{$residue_name};} # if you are using a degenerate naming scheme then degenerate it ... if ($convert_shift_names) { my ($new_token, $suffix) = ($tokens[$$column_elements{"_Atom_name"}] =~ /^([a-zA-Z]+\d*)(\-1)??$/); my $res_name = $$residue{"aa"}; $res_name = $$bmrb_hlist{"rlist"}{$$bmrb_hlist{"rlist"}{$residue_name}{"prev"}}{"aa"} if ($suffix ne ""); if (exists $aa_name_conversion2{uc($res_name)}) { $res_name = $aa_name_conversion2{uc($res_name)}; } # print STDERR "BF>", $residue_name, " | $res_name | " , $tokens[$$column_elements{"_Atom_name"}], " >> ", "$new_token :: $suffix\n"; $tokens[$$column_elements{"_Atom_name"}] = $$shift_conversion_hash{lc($res_name)}{$new_token} . $suffix; # print STDERR "AF>", $residue_name, " | $res_name | " , $tokens[$$column_elements{"_Atom_name"}], " >> ", "$new_token :: $suffix\n"; } # if you do not already have values for the shift and atomtype then setup the atom type. if (! exists $$residue{"shifts"}{$tokens[$$column_elements{"_Atom_name"}]}) { $$residue{"shifts"}{$tokens[$$column_elements{"_Atom_name"}]}{"atom_type"} = $tokens[$$column_elements{"_Atom_type"}]; $$residue{"shifts"}{$tokens[$$column_elements{"_Atom_name"}]}{"ambiguity_code"} = $tokens[$$column_elements{"_Chem_shift_ambiguity_code"}]; $$residue{"shifts"}{$tokens[$$column_elements{"_Atom_name"}]}{"list"} = []; } # if the atom name is defined then push the chemical shift value if ($tokens[$$column_elements{"_Atom_name"}] ne "") {push @{$$residue{"shifts"}{$tokens[$$column_elements{"_Atom_name"}]}{"list"}}, $tokens[$$column_elements{"_Chem_shift_value"}]; } } } # read_bmrb_residue_list_format # Reads the residue list from a bmrb file and puts them in the bmrb hash. # # Parameters: # $file - file descriptor to read from. # $convert_aa_names - converts single letter amino acid names to three letter representations if true. # $bmrb_hlist - bmrb hash structure to fill. # sub read_bmrb_residue_list_format { my $file = shift @_; my $column_elements = shift @_; my $convert_aa_names = shift @_; my $bmrb_hlist = shift @_; # if you do not have a name array then make it a reference to an array. if (! exists $$bmrb_hlist{"name_array"}) { $$bmrb_hlist{"name_array"} = []; } # foreach line do... while (my $line = <$file>) { # take out newline chomp $line; # skip blank lines next if ($line =~ /^\s*$/); # Start at the beginning and when you come to the end Stop. last if ($line =~ /stop_/); # split on spaces my @tokens = split(/\s+/, $line); # get rid of the null element in the beginning caused by the spaces followed by characters while (@tokens && ($tokens[0] eq "")) { shift @tokens; } # as long as you have enough tokens to map to the column elements and the residue label is legitimate continue, otherwise next line. next if ((@tokens < scalar(keys %$column_elements)) || ((! exists $aa_name_conversion{lc($tokens[$$column_elements{"_Residue_label"}])}) && (! exists $aa_name_conversion2{uc($tokens[$$column_elements{"_Residue_label"}])}))); # increment the position counter by the number of column elements, from one block to the next (multiblock lines) for(my $x=0; $x < @tokens; $x += scalar(keys %$column_elements)) { # if you are supposed to convert the line, then do so (3 -> 1 conversion) if ($convert_aa_names && (exists $aa_name_conversion{lc($tokens[$x + $$column_elements{"_Residue_label"}])})) { $tokens[$x + $$column_elements{"_Residue_label"}] = $aa_name_conversion{lc($tokens[$x + $$column_elements{"_Residue_label"}])}; } # the residue name is the label and the sequence code, or author sequence code if the previous is not available my $residue_name = (exists $$column_elements{"_Residue_seq_code"}) ? $tokens[$x+$$column_elements{"_Residue_label"}] . $tokens[$x+$$column_elements{"_Residue_seq_code"}] : $tokens[$x+$$column_elements{"_Residue_label"}] . $tokens[$x+$$column_elements{"_Residue_author_seq_code"}]; # if this has already been defined, then skip next if (grep { $_ eq $residue_name; } @{$$bmrb_hlist{"name_array"}}); # if the residue name is not there, then empty the residue hash reference and fill it. if (! exists $$bmrb_hlist{"rlist"}{$residue_name}) { my $residue = {}; # aa is the element at the current array position + the internal block position of the _Residue_label $$residue{"aa"} = $tokens[$x+$$column_elements{"_Residue_label"}]; # This is built for compatibility where you have either the sequence code or the author's sequence code. # as above, take the position + the internal block position of the used code $$residue{"index"} = (exists $$column_elements{"_Residue_seq_code"}) ? $tokens[$x+$$column_elements{"_Residue_seq_code"}] : $tokens[$x+$$column_elements{"_Residue_author_seq_code"}]; # if you have the author's definition, then save it. if (exists $$column_elements{"_Residue_author_seq_code"}) { $$residue{"author_index"} = $tokens[$x+$$column_elements{"_Residue_author_seq_code"}]; $$residue{"author_name"} = $$residue{"aa"} . $$residue{"author_index"}; } # residue name saved and reference to residue hash saved as well. $$residue{"name"} = $residue_name; $$bmrb_hlist{"rlist"}{$residue_name} = $residue; } # add the residue name to the name array. push @{$$bmrb_hlist{"name_array"}}, $residue_name; } } # create sequence field $$bmrb_hlist{"sequence"} = []; for(my $x=0; $x < @{$$bmrb_hlist{"name_array"}}; $x++) { my $resname = $$bmrb_hlist{"name_array"}[$x]; my $aa = $$bmrb_hlist{"rlist"}{$resname}{"aa"}; if (exists $aa_name_conversion{lc($aa)}) { $aa = $aa_name_conversion{lc($aa)}; } push @{$$bmrb_hlist{"sequence"}}, $aa; if ($x) { $$bmrb_hlist{"rlist"}{$resname}{"prev"} = $$bmrb_hlist{"name_array"}[$x-1]; } if ($x < (@{$$bmrb_hlist{"name_array"}} - 1)) { $$bmrb_hlist{"rlist"}{$resname}{"next"} = $$bmrb_hlist{"name_array"}[$x+1]; } } } # read_bmrb_chemical_shift_reference # Reads the chemical shift reference from a bmrb file and puts them in the bmrb hash structure. # # Parameters: # $file - file descriptor to read from. # $bmrb_hlist - bmrb hash structure to fill. # sub read_bmrb_chemical_shift_reference { my $file = shift @_; my $column_elements = shift @_; my $bmrb_hlist = shift @_; while (my $line = <$file>) { last if ($line =~ /loop_/); } $$bmrb_hlist{"reference_fields"} = []; while (my $line = <$file>) { last if ($line =~ /^\s*$/); my ($token) = ($line =~ /^\s*(\S+)\s*$/); push @{$$bmrb_hlist{"reference_fields"}}, $token; } my @junk = grep { $$bmrb_hlist{"reference_fields"}[$_] =~ /_[Cc]hem_[Ss]hift_[Vv]alue/; } (0..$#{$$bmrb_hlist{"reference_fields"}}); if (@junk) { $$bmrb_hlist{"reference_shift_index"} = pop @junk; } while (my $line = <$file>) { chomp $line; last if ($line =~ /stop_/); my @tokens = grep { defined $_; } (split(/\s+|(\'.*\')/, $line)); while (@tokens && ($tokens[0] eq "")) { shift @tokens; } next if ((@tokens < 3) || ($tokens[1] !~ /^[HCN]$/)); $$bmrb_hlist{"reference"}{$tokens[1]} = [@tokens]; } } ####################################### deMultiplicate ######################################## # Input : a bmrb_hlist type # # Output : a bmrb_hlist type # # Purpose : To return only the proper multiplicity of the bmrb_hlist # ############################################################################################### sub deMultiplicate { my $bmrb_hlist = shift @_; foreach my $residue_name (@{$$bmrb_hlist{"name_array"}}) { foreach my $shift_name_real (keys %{$$bmrb_hlist{"rlist"}{$residue_name}{"shifts"}}) { my $suffix = ""; my $shift_name = ($shift_name_real =~ /^(.*?)(\-1)?$/)[0]; $suffix = "-1" if ($shift_name ne $shift_name_real); if ( ($suffix ne "") && ( exists $multiplicity{$aa_name_conversion{lc($$bmrb_hlist{"rlist"}{$$bmrb_hlist{"rlist"}{$residue_name}{"prev"}}{"aa"})}}{$shift_name} ) ) { splice(@{$$bmrb_hlist{"rlist"}{$residue_name}{"shifts"}{$shift_name_real}{"list"}}, $multiplicity{$aa_name_conversion{lc($$bmrb_hlist{"rlist"}{$$bmrb_hlist{"rlist"}{$residue_name}{"prev"}}{"aa"})}}{$shift_name}); } elsif ( exists $multiplicity{$aa_name_conversion{lc($$bmrb_hlist{"rlist"}{$residue_name}{"aa"})}}{$shift_name_real} ) { splice(@{$$bmrb_hlist{"rlist"}{$residue_name}{"shifts"}{$shift_name_real}{"list"}}, $multiplicity{$aa_name_conversion{lc($$bmrb_hlist{"rlist"}{$residue_name}{"aa"})}}{$shift_name_real}); # print scalar(@{$$bmrb_hlist{"rlist"}{$residue_name}{"shifts"}{$shift_name}{"list"}}), "\n"; } } } } # readBMRBasCMAP # Reads a bmrb file in a CMap naming scheme and returns a BMRB/CMap hash of records. # # Parameters: # $file - bmrb filename to read # $restriction_list - ref to list of atom names to restrict to (optional). sub readBMRBasCMAP { my $input_bmrb_filename = shift @_; my $user_shift_name_list = 0; if (@_ && @{$_[0]}) { my $shift_list = shift @_; $user_shift_name_list = {}; foreach my $shift_name (@$shift_list) { $$user_shift_name_list{$shift_name} = 1; } } # read the bmrb file my %read_options = ( "shift_conversion_hash" => \%cmap_shift_conversion, "convert_aa_names" => 1, "convert_shift_names" => 1 ); my $bmrb_hlist1 = &read_bmrb_file($input_bmrb_filename, \%read_options ); # convert to single letter amino acid names &convert_residue_names($bmrb_hlist1,1); # update "-1" shifts if (ref $user_shift_name_list) { my @previous_shifts = grep {$_ =~ /-1/; } (keys %$user_shift_name_list); if (@previous_shifts) { @previous_shifts = map { my ($shift) = ($_ =~ /^(.+)-1/); $shift; } (@previous_shifts); foreach my $residue (values %{$$bmrb_hlist1{"rlist"}}) { foreach my $shift_name (keys %{$$residue{"shifts"}}) { if (scalar(grep { $shift_name eq $_ } (@previous_shifts)) && exists $$residue{"next"}) { my $prev_residue = $$bmrb_hlist1{"rlist"}{$$residue{"next"}}{"shifts"}{$shift_name . "-1"} = $$residue{"shifts"}{$shift_name}; } } } } } # determine the list of shift names to use my %name_test_hash; foreach my $residue_name (@{$$bmrb_hlist1{"name_array"}}) { foreach my $shift_name (keys %{$$bmrb_hlist1{"rlist"}{$residue_name}{"shifts"}}) { $name_test_hash{$shift_name} = 1; } } $$bmrb_hlist1{"parsedtokens"} = [ grep { (exists $name_test_hash{$_} && (!$user_shift_name_list || exists $$user_shift_name_list{$_})); } @shift_name_order ]; unshift @{$$bmrb_hlist1{"parsedtokens"}}, "AA"; return $bmrb_hlist1; } sub convertBMRBtoCMap { my $bmrb_hlist1 = shift @_; my $user_shift_name_list = 0; if (@_ && @{$_[0]}) { my $shift_list = shift @_; $user_shift_name_list = {}; foreach my $shift_name (@$shift_list) { $$user_shift_name_list{$shift_name} = 1; } } &convert_bmrb_shift_names($bmrb_hlist1, \%cmap_shift_conversion); &convert_residue_names($bmrb_hlist1,1); # update "-1" shifts if (ref $user_shift_name_list) { my @previous_shifts = grep {$_ =~ /-1/; } (keys %$user_shift_name_list); if (@previous_shifts) { @previous_shifts = map { my ($shift) = ($_ =~ /^(.+)-1/); $shift; } (@previous_shifts); foreach my $residue (values %{$$bmrb_hlist1{"rlist"}}) { foreach my $shift_name (keys %{$$residue{"shifts"}}) { if (scalar(grep { $shift_name eq $_ } (@previous_shifts)) && exists $$residue{"next"}) { my $prev_residue = $$bmrb_hlist1{"rlist"}{$$residue{"next"}}{"shifts"}{$shift_name . "-1"} = $$residue{"shifts"}{$shift_name}; } } } } } # determine the list of shift names to use my %name_test_hash; foreach my $residue_name (@{$$bmrb_hlist1{"name_array"}}) { foreach my $shift_name (keys %{$$bmrb_hlist1{"rlist"}{$residue_name}{"shifts"}}) { $name_test_hash{$shift_name} = 1; } } $$bmrb_hlist1{"parsedtokens"} = [ grep { (exists $name_test_hash{$_} && (!$user_shift_name_list || exists $$user_shift_name_list{$_})); } @shift_name_order ]; unshift @{$$bmrb_hlist1{"parsedtokens"}}, "AA"; return $bmrb_hlist1; } sub name_array_consistency { my $bmrb_hlist = shift @_; my @array1 = @{$$bmrb_hlist{"name_array"}}; my @array2 = sort { ($a =~ /^[a-zA-Z]+(\-?\d+)$/)[0] <=> ($b =~ /^[A-Za-z]+(\-?\d+)$/)[0]; } (keys %{$$bmrb_hlist{"rlist"}}); my %seen; my @unique_elems = grep { ! $seen{$_}++ } (@array1, @array2); # If 75% of array2 are duplicates then true. return 1 if (scalar(@unique_elems) < (scalar(@array1) + (0.25 * (scalar(@array2))))); return 0; } # module must return true return 1;