# 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. # # 90% Rewritten by Hunter Moseley 11/17/2001 # Copyright Hunter Moseley, 2001. All rights reserved. # Modified by Hunter Moseley 3/18/2002 (800 more lines). # Copyright Gurmukh Sahota, 2002. All rights reserved. # Modified by Gurmukh Sahota 05/13/2002. Adding coupling_constant and secondary_structure saveframes # and fixed some "exists" bugs and a last in the monomeric_polymer # # 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 update_shift_ids convertAtomNameBMRBtoCMap convertSSelemBMRBtoCMap convertJBMRBtoCMap residueNameofIndex); %EXPORT_TAGS = ( ALL => [@EXPORT_OK] ); use strict; #use Dumpvalue qw(:ALL); #my $dumper = new Dumpvalue; # useful hashes 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, "HD" => 2, "HD1" => 1, "HD2" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CD" => 2, "CE" => 1, "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" => 1, "HG2" => 1, "HG3" => 1, "HE" => 1, "CA" => 1, "CB" => 1, "CG" => 1, "CD" => 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_J_conversion = ( "3JHNHA" => "J3HNHA" ); my %cmap_sse_conversion = ( "loop" => "-", "alpha-helix" => "h", "turn" => "t", "beta-sheet" => "s" ); 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", "HE" => "HE", "HE1" => "HE", "HE2" => "HE", "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 @CMAP_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"); my %BMRB_shift_name_ordering = ( "H" => 1, "HA" => 2, "HA2" => 3, "HA3" => 4, "HB" => 5, "HB2" => 6, "HB3" => 7, "HG" => 8, "HG1" => 9, "HG12" => 10, "HG13" => 11, "HG2" => 12, "HG3" => 13, "HD1" => 14, "HD2" => 15, "HD21" => 16, "HD22" => 17, "HD3" => 18, "HE" => 19, "HE1" => 20, "HE2" => 21, "HE21" => 22, "HE22" => 23, "HE3" => 24, "HZ" => 25, "HZ2" => 26, "HZ3" => 27, "HH" => 28, "HH11" => 29, "HH12" => 30, "HH2" => 31, "HH21" => 32, "HH22" => 33, "C" => 34, "CA" => 35, "CB" => 36, "CG" => 37, "CG1" => 38, "CG2" => 39, "CD" => 40, "CD1" => 41, "CD2" => 42, "CE" => 43, "CE1" => 44, "CE2" => 45, "CE3" => 46, "CZ" => 47, "CZ2" => 48, "CZ3" => 49, "CH2" => 50, "N" => 51, "ND1" => 52, "ND2" => 53, "NE" => 54, "NE1" => 55, "NE2" => 56, "NZ" => 57, "NH1" => 58, "NH2" => 59 ); ; my $coupling_constants_saveframe = { "id" => { "bmrbFieldName" => "_Coupling_constant.ID", "required" => 1 }, "type" => { "bmrbFieldName" => "_Coupling_constant.Coupling_constant_code", "required" => 1 }, "Atom1residueNumber" => { "bmrbFieldName" => "_Coupling_constant.Atom_1_chem_comp_seq_num", "required" => 1 }, "Atom1residueName" => { "bmrbFieldName" => "_Coupling_constant.Atom_1_chem_comp_index_ID", "required" => 1 }, "Atom1atomName" => { "bmrbFieldName" => "_Coupling_constant.Atom_1_atom_ID", "required" => 1 }, "Atom1atomType" => { "bmrbFieldName" => "_Coupling_constant.Atom_1_atom_type", "required" => 0 }, "Atom1ambiguity" => { "bmrbFieldName" => "_Coupling_constant.Atom_1_ambiguity_code", "required" => 0 }, "Atom2residueNumber" => { "bmrbFieldName" => "_Coupling_constant.Atom_2_chem_comp_seq_num", "required" => 1 }, "Atom2residueName" => { "bmrbFieldName" => "_Coupling_constant.Atom_2_chem_comp_index_ID", "required" => 1 }, "Atom2atomName" => { "bmrbFieldName" => "_Coupling_constant.Atom_2_atom_ID", "required" => 1 }, "Atom2atomType" => { "bmrbFieldName" => "_Coupling_constant.Atom_2_atom_type", "required" => 0 }, "Atom2ambiguity" => { "bmrbFieldName" => "_Coupling_constant.Atom_2_ambiguity_code", "required" => 0 }, "value" => { "bmrbFieldName" => "_Coupling_constant.Val", "required" => 1 }, "minValue" => { "bmrbFieldName" => "_Coupling_constant.Min_val", "required" => 0 }, "maxValue" => { "bmrbFieldName" => "_Coupling_constant.Max_val", "required" => 0 }, "error" => { "bmrbFieldName" => "_Coupling_constant.Val_err", "required" => 1 } }; my $secondary_structure_saveframe = { "id" => { "bmrbFieldName" => "_Secondary_struct.ID", "required" => 1 }, "startResidueNumber" => { "bmrbFieldName" => "_Secondary_struct.Beginning_chem_comp_seq_num", "required" => 1 }, "startResidueName" => { "bmrbFieldName" => "_Secondary_struct.Beginning_chem_comp_index_ID", "required" => 1 }, "endResidueNumber" => { "bmrbFieldName" => "_Secondary_struct.Last_chem_comp_seq_num", "required" => 1 }, "endResidueName" => { "bmrbFieldName" => "_Secondary_struct.Last_chem_comp_index_ID", "required" => 1 }, "sseName" => { "bmrbFieldName" => "_Secondary_struct.Secondary_struct_name", "required" => 0 }, "sseCode" => { "bmrbFieldName" => "_Secondary_struct.Secondary_struct_code", "required" => 1 }, "method" => { "bmrbFieldName" => "_Secondary_struct.Selection_method_ID", "required" => 0 } }; # 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 @_; # generic cloning code my @clone_stack; push @clone_stack, { "type" => "HASH", "clone" => $cloned_hlist, "range" => [ keys %$original_hlist ], "index" => 0, "original" => $original_hlist }; while(@clone_stack) { my $index = $clone_stack[$#clone_stack]{"index"}; if ($index < @{$clone_stack[$#clone_stack]{"range"}}) # clone a part of the current hash or array { # get new value my $test_value; if ($clone_stack[$#clone_stack]{"type"} eq "HASH") { $test_value = $clone_stack[$#clone_stack]{"original"}{$clone_stack[$#clone_stack]{"range"}[$index]}; } elsif ($clone_stack[$#clone_stack]{"type"} eq "ARRAY") { $test_value = $clone_stack[$#clone_stack]{"original"}[$index]; } my $test_ref = ref($test_value); if ($test_ref eq "HASH") # test value is a hash { push @clone_stack, {"type" => "HASH", "clone" => {}, "range" => [ keys %$test_value ], "index" => 0, "original" => $test_value }; } elsif ($test_ref eq "ARRAY") # test value is an array { push @clone_stack, {"type" => "ARRAY", "clone" => [], "range" => $test_value, "index" => 0, "original" => $test_value }; } elsif ($clone_stack[$#clone_stack]{"type"} eq "HASH") # clone section is a hash { $clone_stack[$#clone_stack]{"clone"}{$clone_stack[$#clone_stack]{"range"}[$index]} = $test_value; $clone_stack[$#clone_stack]{"index"}++; } else # clone section is an array { $clone_stack[$#clone_stack]{"clone"}[$index] = $test_value; $clone_stack[$#clone_stack]{"index"}++; } } else # pop finished cloned section. { if (@clone_stack > 1) { my $index = $clone_stack[$#clone_stack - 1]{"index"}; if($clone_stack[$#clone_stack - 1]{"type"} eq "HASH") # handle hashes { $clone_stack[$#clone_stack - 1]{"clone"}{$clone_stack[$#clone_stack - 1]{"range"}[$index]} = $clone_stack[$#clone_stack]{"clone"}; } else # handle arrays { $clone_stack[$#clone_stack - 1]{"clone"}[$index] = $clone_stack[$#clone_stack]{"clone"}; } } pop @clone_stack; if (@clone_stack) { $clone_stack[$#clone_stack]{"index"}++; } } } 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"} - string of the amino acid sequence (single letter code). # $$bmrb_hlist{"residue_count"} - the number of residues in the polymer. # $$bmrb_hlist{"sequence_startpos"} - starting author_index (or index if no author_index). # $$bmrb_hlist{"ambiguity_lists"} - array of ambiguity lists (optional). # $$bmrb_hlist{"molecule_type"} - molecule_type; polymer. # $$bmrb_hlist{"polymer_class"} - polymer_class; DNA, RNA, protein, etc. # $$bmrb_hlist{"common_name"} - common name for the molecule (optional). # $$bmrb_hlist{"skip_processing"} - flag indicating that processing of usable save frames was skipped (optional). # # $$bmrb_hlist{"save_frames"} - list of save_frames. # $$save_frame{"name"} - name of the save_frame. # $$save_frame{"type"} - type of save_frame. # $$save_frame{"text"} - list of text lines of the save_frame. # $$save_frame{"sections"} - (optional) orderred list of sections of the save_frame. # $$section{"type"} - type of section. # $$section{"value"} - value of the section, if it has a value. # $$section{"extra_tags"} - (optional) lists of tags of extra data. # $$section{"all_tags"} - (optional) lists of tags of data. # $$save_frame{"data"} - organized data structure of save frame data (only for certain save frame types). # $$save_frame{"data"} (secondary structure) - array of a secondary structure save frame. # $$ss_elem{"id"} - secondary structure id # $$ss_elem{"startResidueNumber"} - beginning residue number of SSE # $$ss_elem{"startResidueName"} - beginning residue name of SSE # $$ss_elem{"endResidueNumber"} - ending residue number of SSE # $$ss_elem{"endResidueName"} - ending residue name of SSE # $$ss_elem{"sseName"} - SSE name # $$ss_elem{"sseCode"} - SSE codes (loop, alpha-helix, beta-sheet) # $$ss_elem{"method"} - method of secondary structure determination # $$save_frame{"data"} (coupling constants) - array of a coupling constant save frame. # $$cc_elem{"id"} - coupling constants id # $$cc_elem{"type"} - description of type of coupling constants # $$cc_elem{"Atom1residueNumber"} - residue number for Atom1 # $$cc_elem{"Atom1residueName"} - residue name for Atom1 # $$cc_elem{"Atom1atomName"} - atom name for Atom1 # $$cc_elem{"Atom1atomType"} - atom type for Atom1 # $$cc_elem{"Atom1ambiguity"} - atom ambiguity for Atom1 # $$cc_elem{"Atom2residueNumber"} - residue number for Atom2 # $$cc_elem{"Atom2residueName"} - residue name for Atom2 # $$cc_elem{"Atom2atomName"} - atom name for Atom2 # $$cc_elem{"Atom2atomType"} - atom type for Atom2 # $$cc_elem{"Atom2ambiguity"} - atom ambiguity for Atom2 # $$cc_elem{"value"} - coupling constant value # $$cc_elem{"minValue"} - coupling constant minimum value # $$cc_elem{"maxValue"} - coupling constant maximum value # $$cc_elem{"error"} - coupling constant measurement error (uncertainty) # $$save_frame{"data"} (spectral peak list) - organized hash of a spectral peak list save frame. # $$peak_list{"entry_id"} - entry id. # $$peak_list{"peak_list_id"} - spectral peak list id. # $$peak_list{"index_array"} - array of peak indexes. # $$peak_list{"details"} - array of lines describing details for the peak list. # $$peak_list{"num_dimensions"} - number of dimensions. # $$peak_list{"experiment_label"} - experiment_label. # $$peak_list{"dimension_descriptions"} - array of dimension descriptions. # $$dim_description{"dim_id"} - dimension id. # $$dim_description{"atom_type"} - atom type. # $$dim_description{"spectral_region"} - spectral region. # $$dim_description{"magnetization_linkage"} - magnetization linkage. # $$dim_description{"sweep_width"} - sweep width. # $$dim_description{"encoding"} - encoding code for composed dimensions. # $$dim_description{"encoding_dimension"} - source dimension for encoding. # $$dim_description{"extra_tags"} - extra tags. # $$peak_list{"plist"} - hash of peak index to peak. # $$peak{"index"} - index for the peak. # $$peak{"dimensions"} - hash of dimension id to dimension. # $$dimension{"dim_id"} - dimension id. # $$dimension{"shift"} - shift value in this dimension. # $$dimension{"shift_error"} - shift standard error in this dimension. # $$dimension{"width"} - peak width in this dimension. # $$dimension{"width_error"} - peak width standard error in this dimension. # $$dimension{"phase"} - peak phase. # $$dimension{"phase_error"} - peak phase standard error. # $$dimension{"decay"} - peak decay rate. # $$dimension{"decay_error"} - peak decay rate standard error. # $$dimension{"derivation_method"} - derivation method. # $$dimension{"assignments"} - array of shift assignments. # $$assignment{"aa"} - amino acid. # $$assignment{"index"} - residue index. # $$assignment{"atom_name"} - atom name. # $$assignment{"set_id"} - set id for handling ambiguous constraints. # $$assignment{"magnetization_linkage"} - magnetization_linkage. # $$assignment{"figure_of_merit"} - figure of merit. # $$assignment{"list_id"} - peak list id. # $$assignment{"list_label"} - peak list label. # $$assignment{"shift_id"} - assigned shift id. # $$assignment{"extra_tags"} - extra tags. # $$dimension{"extra_tags"} - extra_tags. # $$peak{"intensity"} - peak intensity. # $$peak{"intensity_error"} - peak intensity standard error. # $$peak{"figure_of_merit"} - figure of merit. # $$peak{"measurement_method"} - measurement method. # $$peak{"derivation_set"} - derivation set. # $$peak{"extra_tags"} - extra_tags. # # $$bmrb_hlist{"rlist"} - hash list of residue_names to residues. # $$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 # $$residue{"author_index"} - author designated residue number (optional). # $$residue{"insertion_code"} - insertion code for aligning with a native sequence (optional). # $$residue{"segment_definition_code"} - segment code for identifying important group of residues (optional). # $$residue{"index"} - residue number # $$residue{"shifts"} - hash of shifts # $$shift{"atom_type"} - atom_type of shift. # $$shift{"list"} - array of shift values. # $$shift{"idlist"} - array of shift ID's. # $$shift{"ambiguity_code"} - ambiguity code for the shift_name (optional). # $$shift{"error"} - amount of error for the shift value (optional). # $$shift{"extra_tags"} - hash of extra tags for the shift (optional). # $$residue{"next"} - name of the next residue. # $$residue{"prev"} - name of the previous residue. # $$residue{"extra_tags"} - hash of extra tags for the residue (optional). # # 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 @_; } # setting read_options 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 = $$read_options{"shift_conversion_hash"}; } my $skip_processing = 0; if (exists $$read_options{"skip_processing"} && $$read_options{"skip_processing"}) { $skip_processing = 1; } my $limit_save_frames = 0; if (exists $$read_options{"limit_save_frames"} && ref $$read_options{"limit_save_frames"} eq "ARRAY") { $skip_processing = $$read_options{"limit_save_frames"}; } my $delete_save_frames = 0; if (exists $$read_options{"delete_save_frames"} && $$read_options{"delete_save_frames"}) { $delete_save_frames = 1; } 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"; } # divide STARFILE into save_frames. my $save_frames_alist = []; while (my $line = ) { # begin reading a save_frame if ($line =~ /^\s*save_/) { my ($save_frame_name) = ($line =~ /^\s*save_([a-zA-Z0-9_-]*)/); # skip comment and blank lines while (($line = ) && (($line =~ /^\s*$/) ||($line =~ /^\s*\#/))) {} my ($save_frame_type) = ($line =~ /_[Ss]aveframe_[Cc]ategory\s+(\w+)/); if ($save_frame_type eq "") { ($save_frame_type) = ($line =~ /_[Ss]aveframe_[Cc]ategory\s+(\.)/); } if ($save_frame_type eq "") { chomp $line; print STDERR "ERROR LINE: \"",$line,"\"\n"; die "Null _Saveframe_category"; } if (! $limit_save_frames || (grep {$_ eq $save_frame_type; } (@$limit_save_frames))) { my $save_frame = { "type" => $save_frame_type, "name" => $save_frame_name, "text" => [] }; while (my $line = ) { chomp $line; if ($line =~ /^\s*save_/) { last; } push @{$$save_frame{"text"}}, $line; } push @$save_frames_alist, $save_frame; } else { while (my $line = ) { if ($line =~ /^\s*save_/) { last; } } } } } close STARFILE if ($filename ne "-"); # create "save_frames" if it does not exist if (! exists $$bmrb_hlist{"save_frames"}) { $$bmrb_hlist{"save_frames"} = []; } # add newly read save_frames if (! $delete_save_frames) { push @{$$bmrb_hlist{"save_frames"}}, @$save_frames_alist; } # skip processing usable save_frames if indicated in read_options if ($skip_processing) { $$bmrb_hlist{"skip_processing"} = 1; return $bmrb_hlist; } # find and process usable save_frames foreach my $save_frame (@$save_frames_alist) { if ($$save_frame{"type"} eq "assigned_chemical_shifts") { &process_assigned_chemical_shifts_frame($save_frame, $convert_aa_names, $convert_shift_names, $shift_conversion_hash, $bmrb_hlist); } elsif($$save_frame{"type"} eq "monomeric_polymer") { &process_monomeric_polymer_frame($save_frame, $convert_aa_names, $bmrb_hlist); } elsif($$save_frame{"type"} eq "chemical_shift_reference") { &process_chemical_shift_reference_frame($save_frame, $bmrb_hlist); } elsif($$save_frame{"type"} eq "spectral_peak_list") { &process_spectral_peak_list_frame($save_frame); } elsif($$save_frame{"type"} eq "coupling_constants") { &process_coupling_constants_frame($save_frame, $bmrb_hlist); } elsif($$save_frame{"type"} eq "secondary_structure") { &process_secondary_structure_frame($save_frame, $bmrb_hlist); } } # update spectral peak lists assignment info if ((grep {$$_{"type"} eq "assigned_chemical_shifts"; } (@$save_frames_alist)) && (grep {$$_{"type"} eq "spectral_peak_list"; } (@$save_frames_alist))) { &update_spectral_peak_list_frames($bmrb_hlist, [ (grep {$$_{"type"} eq "spectral_peak_list"; } (@$save_frames_alist)) ]); } # 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 ( (! ref $$bmrb_hlist{"name_array"}) || (! @{$$bmrb_hlist{"name_array"}})) { $$bmrb_hlist{"name_array"} = [ sort { ($a =~ /^[a-zA-Z]+(\-?\d+)$/)[0] <=> ($b =~ /^[A-Za-z]+(\-?\d+)$/)[0]; } (keys %{$$bmrb_hlist{"rlist"}}) ]; } # create sequence field if ((! exists $$bmrb_hlist{"sequence"}) || ($$bmrb_hlist{"sequence"} eq "")) { $$bmrb_hlist{"sequence"} = ""; for(my $x=0; $x < @{$$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)}; } $$bmrb_hlist{"sequence"} .= $aa; } } # create residue_count if (! exists $$bmrb_hlist{"residue_count"}) { $$bmrb_hlist{"residue_count"} = scalar(@{$$bmrb_hlist{"name_array"}}); } # create prev & next links for(my $x=0; $x < @{$$bmrb_hlist{"name_array"}}; $x++) { my $resname = $$bmrb_hlist{"name_array"}[$x]; if ($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"}{$$bmrb_hlist{"name_array"}[0]}{"index"}; } return $bmrb_hlist; } # write_bmrb_file # Prints a bmrb file out to $filename # # Parameters: # $bmrb_hlist - reference to bmrb hash structure. # $filename - name of output filename. # $write_options - hash of options. sub write_bmrb_file { my $bmrb_hlist = shift @_; my $filename = shift @_; my $write_options = {}; if (@_) { $write_options = shift @_; } # do nothing if there are no save_frames and "skip_processing" is true if ((! exists $$bmrb_hlist{"save_frames"} || ! @{$$bmrb_hlist{"save_frames"}}) && (exists $$bmrb_hlist{"skip_processing"} && $$bmrb_hlist{"skip_processing"})) { return; } # create empty array of save_frames if it does not exist. if (! exists $$bmrb_hlist{"save_frames"}) { $$bmrb_hlist{"save_frames"} = []; } # update spectral peak lists assignment info if ((grep {$$_{"type"} eq "assigned_chemical_shifts"; } (@{$$bmrb_hlist{"save_frames"}})) && (grep {$$_{"type"} eq "spectral_peak_list"; } (@{$$bmrb_hlist{"save_frames"}}))) { &update_spectral_peak_list_frames($bmrb_hlist, [ (grep {$$_{"type"} eq "spectral_peak_list"; } (@{$$bmrb_hlist{"save_frames"}})) ]); } # create monomeric_polymer save_frame if it does not exist if ( ! (grep {$$_{"type"} eq "monomeric_polymer"; } (@{$$bmrb_hlist{"save_frames"}})) && (exists $$bmrb_hlist{"rlist"} && scalar(%{$$bmrb_hlist{"rlist"}}))) { my $save_frame = { "type" => "monomeric_polymer", "name" => "monomeric_polymer", "sections" => [] }; if (exists $$bmrb_hlist{"common_name"} && ($$bmrb_hlist{"common_name"} ne "")) { $$save_frame{"name"} = $$bmrb_hlist{"common_name"}; $$save_frame{"name"} =~ tr/ /_/s; } my $sections = $$save_frame{"sections"}; push @$sections, { "type" => "text", "value" => [ "" ] }; push @$sections, { "type" => "molecule_type" }; push @$sections, { "type" => "text", "value" => [ "" ] }; push @$sections, { "type" => "polymer_class" }; push @$sections, { "type" => "text", "value" => [ "" ] }; push @$sections, { "type" => "common_name" }; push @$sections, { "type" => "text", "value" => [ "" ] }; push @$sections, { "type" => "residue_count" }; push @$sections, { "type" => "text", "value" => [ "" ] }; push @$sections, { "type" => "sequence" }; push @$sections, { "type" => "text", "value" => [ "" ] }; push @$sections, { "type" => "sequence_loop", "all_tags" => [ "_Residue_seq_code", "_Residue_label"] }; if (exists $$write_options{"extra_tags"} && exists $$write_options{"extra_tags"}{"residues"}) { $$sections[$#$sections]{"extra_tags"} = $$write_options{"extra_tags"}{"residues"}; push @{$$sections[$#$sections]{"all_tags"}}, @{$$write_options{"extra_tags"}{"residues"}}; } if (exists $$write_options{"optional_tags"} && exists $$write_options{"optional_tags"}{"residues"}) { push @{$$sections[$#$sections]{"all_tags"}}, @{$$write_options{"optional_tags"}{"residues"}}; } push @$sections, { "type" => "text", "value" => [ "" ] }; push @{$$bmrb_hlist{"save_frames"}}, $save_frame; } # create chemical_shift_reference save_frame if it does not exist if ( ! (grep {$$_{"type"} eq "chemical_shift_reference"; } (@{$$bmrb_hlist{"save_frames"}})) && (exists $$bmrb_hlist{"reference_fields"} && @{$$bmrb_hlist{"reference_fields"}})) { my $save_frame = { "type" => "chemical_shift_reference", "name" => "chemical_shift_reference", "sections" => [] }; my $sections = $$save_frame{"sections"}; push @$sections, { "type" => "text", "value" => [ "" ] }; push @$sections, { "type" => "reference_loop", "all_tags" => [@{$$bmrb_hlist{"reference_fields"}}] }; push @$sections, { "type" => "text", "value" => [ "" ] }; push @{$$bmrb_hlist{"save_frames"}}, $save_frame; } # create assigned_chemical_shifts save_frame if it does not exist if ( ! (grep {$$_{"type"} eq "assigned_chemical_shifts"; } (@{$$bmrb_hlist{"save_frames"}})) && &has_shifts($bmrb_hlist)) { my $save_frame = { "type" => "assigned_chemical_shifts", "name" => "assigned_chemical_shifts", "sections" => [] }; my $sections = $$save_frame{"sections"}; push @$sections, { "type" => "text", "value" => [ "" ] }; my $chem_section = { "type" => "chemical_shifts_loop" }; if (exists $$write_options{"extra_tags"} && exists $$write_options{"extra_tags"}{"shifts"}) { $$chem_section{"extra_tags"} = $$write_options{"extra_tags"}{"shifts"}; $$chem_section{"all_tags"} = [ "_Atom_shift_assign_ID", "_Residue_seq_code", "_Residue_label", "_Atom_name", "_Atom_type", "_Chem_shift_value", "_Chem_shift_value_error", "_Chem_shift_ambiguity_code", @{$$write_options{"extra_tags"}{"shifts"}} ]; } else { $$chem_section{"all_tags"} = [ "_Atom_shift_assign_ID", "_Residue_seq_code", "_Residue_label", "_Atom_name", "_Atom_type", "_Chem_shift_value", "_Chem_shift_value_error", "_Chem_shift_ambiguity_code" ]; } push @$sections, $chem_section; push @$sections, { "type" => "text", "value" => [ "" ] }; if (exists $$bmrb_hlist{"ambiguity_lists"} && @{$$bmrb_hlist{"ambiguity_lists"}}) { push @$sections, { "type" => "ambiguity_loop" }; push @$sections, { "type" => "text", "value" => [ "" ] }; } push @{$$bmrb_hlist{"save_frames"}}, $save_frame; } # start writing BMRB file local *STARFILE; if ($filename eq "-") { *STARFILE = *STDOUT; } else { open (STARFILE, ">$filename") || die "unable to open $filename"; } # create name_array if it does not exist if (! exists $$bmrb_hlist{"name_array"} || ! (ref $$bmrb_hlist{"name_array"} eq "ARRAY")) { $$bmrb_hlist{"name_array"} = [ sort { ($a =~ /^[a-zA-Z]+(\-?\d+)$/)[0] <=> ($b =~ /^[A-Za-z]+(\-?\d+)$/)[0]; } (keys %{$$bmrb_hlist{"rlist"}}) ]; } # create sequence field if ((! exists $$bmrb_hlist{"sequence"}) || ($$bmrb_hlist{"sequence"} eq "")) { $$bmrb_hlist{"sequence"} = ""; for(my $x=0; $x < @{$$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)}; } $$bmrb_hlist{"sequence"} .= $aa; } } # create residue_count if (! exists $$bmrb_hlist{"residue_count"}) { $$bmrb_hlist{"residue_count"} = scalar(@{$$bmrb_hlist{"name_array"}}); } # update shift ids across assigned chemical shifts frame and spectral peak list frames &update_shift_ids($bmrb_hlist); # loop through save_frames my $save_frame_types = {}; foreach my $save_frame (@{$$bmrb_hlist{"save_frames"}}) { my $text_lines; if (($$save_frame{"type"} eq "assigned_chemical_shifts") && exists $$save_frame{"sections"} && @{$$save_frame{"sections"}} && ! $$save_frame_types{$$save_frame{"type"}}) { $text_lines = &create_assigned_chemical_shifts_frame($save_frame, $bmrb_hlist, $write_options); $$save_frame_types{$$save_frame{"type"}}++; } elsif (($$save_frame{"type"} eq "monomeric_polymer") && exists $$save_frame{"sections"} && @{$$save_frame{"sections"}} && ! $$save_frame_types{$$save_frame{"type"}}) { $text_lines = &create_monomeric_polymer_frame($save_frame, $bmrb_hlist, $write_options); $$save_frame_types{$$save_frame{"type"}}++; } elsif (($$save_frame{"type"} eq "chemical_shift_reference") && exists $$save_frame{"sections"} && @{$$save_frame{"sections"}} && ! $$save_frame_types{$$save_frame{"type"}}) { $text_lines = &create_chemical_shift_reference_frame($save_frame, $bmrb_hlist); $$save_frame_types{$$save_frame{"type"}}++; } elsif (($$save_frame{"type"} eq "spectral_peak_list") && exists $$save_frame{"sections"} && @{$$save_frame{"sections"}}) { $text_lines = &create_spectral_peak_list_frame($save_frame, $bmrb_hlist); } elsif (($$save_frame{"type"} eq "coupling_constants") && exists $$save_frame{"sections"} && @{$$save_frame{"sections"}}) { $text_lines = &create_coupling_constants_frame($save_frame, $bmrb_hlist); } elsif (($$save_frame{"type"} eq "secondary_structure") && exists $$save_frame{"sections"} && @{$$save_frame{"sections"}}) { $text_lines = &create_secondary_structure_frame($save_frame, $bmrb_hlist); } elsif (exists $$save_frame{"text"} && @{$$save_frame{"text"}}) { $text_lines = $$save_frame{"text"}; } else # just in case something is not quite right { $text_lines = []; } if (@$text_lines) { print STARFILE "save_"; if (exists $$save_frame{"name"}) { print STARFILE $$save_frame{"name"}; } print STARFILE "\n"; print STARFILE " _Saveframe_category "; if (exists $$save_frame{"type"}) { print STARFILE $$save_frame{"type"}; } else { print STARFILE "."; } print STARFILE "\n"; foreach my $line (@$text_lines) { print STARFILE $line,"\n"; } print STARFILE "save_\n\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; } $$bmrb_hlist{"rlist"} = $rlist; } } # readBMRBasCMAP # Reads a bmrb file in a CMap naming scheme and returns a BMRB/CMap hash of records. # # Parameters: # $file - bmrb filename to read # $restriction_list - ref to list of atom names to restrict to (optional). sub readBMRBasCMAP { my $input_bmrb_filename = shift @_; my $user_shift_name_list = 0; if (@_ && @{$_[0]}) { my $shift_list = shift @_; $user_shift_name_list = {}; foreach my $shift_name (@$shift_list) { $$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{$_})); } @CMAP_shift_name_order ]; # unshift @{$$bmrb_hlist1{"parsedtokens"}}, "AA"; return $bmrb_hlist1; } # convertBMRBtoCMAP # Converts a bmrb hlist into a CMap naming scheme and returns a BMRB/CMap hash of records. # # Parameters: # $file - bmrb filename to read # $restriction_list - ref to list of atom names to restrict to (optional). sub convertBMRBtoCMap { my $bmrb_hlist1 = shift @_; my $user_shift_name_list = 0; if (@_ && @{$_[0]}) { my $shift_list = shift @_; $user_shift_name_list = {}; foreach my $shift_name (@$shift_list) { $$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{$_})); } @CMAP_shift_name_order ]; # unshift @{$$bmrb_hlist1{"parsedtokens"}}, "AA"; return $bmrb_hlist1; } ####################################### deMultiplicate ######################################## # Input : a bmrb_hlist type # # Output : a bmrb_hlist type # # Purpose : To return only the proper multiplicity of the bmrb_hlist # ############################################################################################### sub deMultiplicate { my $bmrb_hlist = shift @_; foreach my $residue_name (keys %{$$bmrb_hlist{"rlist"}}) { foreach my $shift_name_real (keys %{$$bmrb_hlist{"rlist"}{$residue_name}{"shifts"}}) { my $suffix = ""; my $shift_name = ($shift_name_real =~ /^(.*?)(\-1)?$/)[0]; $suffix = "-1" if ($shift_name ne $shift_name_real); if ( ($suffix ne "") && ( exists $$bmrb_hlist{"rlist"}{$residue_name}{"prev"}) && ( 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}); } } } } ################################# convertAtomNameBMRBtoCMap ################################### # Input : an amino acid and an BMRB atom name # # Output : a CMap atom name # # Purpose : To convert a BMRB atom name to its equivalent CMap atom name # ############################################################################################### sub convertAtomNameBMRBtoCMap { my $aa = shift @_; my $atom_name = shift @_; # print lc($aa_name_conversion2{uc($aa)}), ":", $atom_name, "\n"; return $cmap_shift_conversion{lc($aa_name_conversion2{uc($aa)})}{$atom_name}; } ################################# convertSSelemBMRBtoCMap ##################################### # Input : a BMRB secondary structure element code # # Output : a CMap secondary structure element code # # Purpose : To convert a BMRB SSE code to its equivalent CMap SSE code # ############################################################################################### sub convertSSelemBMRBtoCMap { my $bmrb_sse = shift @_; # print lc($aa_name_conversion2{uc($aa)}), ":", $atom_name, "\n"; return $cmap_sse_conversion{lc($bmrb_sse)}; } #################################### convertJBMRBtoCMap ####################################### # Input : a BMRB J coupling constant code # # Output : a CMap J coupling constant code # # Purpose : To convert a BMRB J code to its equivalent CMap J code # ############################################################################################### sub convertJBMRBtoCMap { my $bmrb_J = shift @_; # print lc($aa_name_conversion2{uc($aa)}), ":", $atom_name, "\n"; return $cmap_J_conversion{uc($bmrb_J)}; } # # # Routines for internal use only. # # # # # Routines for reading BMRB files # # # loop_contents # checks to see whether the loop_ fields contain the required and returns a hash of field name to field order. # # Parameters: # $line_array - reference to array of lines. # $start - starting position in array to test # $required_fields - array of elements to check against the array of lines sub loop_contents { my $line_array = shift @_; my $start = shift @_; my $required_fields = shift @_; my $columns = {}; my $required_count = 0; # Check all elements ... my $x=0; while (($start < @$line_array) && ($$line_array[$start] !~ /^\s*$/)) { # skip comment lines if ($$line_array[$start] =~ /^\s*\#/) { $start++; next; } my ($field_name) = ($$line_array[$start] =~ /^\s*([A-Za-z0-9_.]+)/); my @new_name = (grep { $field_name =~ /^$_$/i; } (@$required_fields)); if (@new_name) { $required_count++; $field_name = $new_name[0]; } $$columns{$field_name} = $x; $x++; $start++; } my @found_fields = (keys %$columns); if ($required_count != @$required_fields) # this test could be erroneous; however, it is very unlikely { return 0; } return $columns; } # process_assigned_chemical_shifts_frame # Processes the assigned chemical shift lines and puts them in the bmrb hash structure. # # Parameters: # $save_frame - save_frame hash # $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 process_assigned_chemical_shifts_frame { my $save_frame = shift @_; my $convert_aa_names = shift @_; my $convert_shift_names = shift @_; my $shift_conversion_hash = shift @_; my $bmrb_hlist = shift @_; my $sections = []; my @expected_chem_shift_fields = ("_Atom_shift_assign_ID", "_Residue_seq_code", "_Residue_label", "_Atom_name", "_Atom_type", "_Chem_shift_value", "_Chem_shift_value_error", "_Chem_shift_ambiguity_code"); my @required_chem_shift_fields = ("_Atom_shift_assign_ID", "_Residue_seq_code", "_Residue_label", "_Atom_name", "_Atom_type", "_Chem_shift_value"); my $orig_text = $$save_frame{"text"}; # foreach line in the file until stop_ for(my $x=0; $x < @$orig_text; $x++) { my $columns = 0; # process the chemical shifts if (($$orig_text[$x] =~ /^\s*loop_/) && ($columns = &loop_contents($orig_text,$x+1,\@required_chem_shift_fields))) { $x += 1 + scalar(keys %$columns); my @extra_tags = (grep {my $test = $_; (! grep {$test eq $_; } (@expected_chem_shift_fields)); } (keys %$columns)); $x = &process_chemical_shift_lines($orig_text,$x,$columns,$convert_aa_names, $convert_shift_names, $shift_conversion_hash, $bmrb_hlist, \@extra_tags); push @$sections, { "type" => "chemical_shifts_loop", "extra_tags" => [@extra_tags], "all_tags" => [ sort { $$columns{$a} <=> $$columns{$b}; } (keys %$columns) ] }; } # process the ambiguity list elsif(($$orig_text[$x] =~ /^\s*loop_/) && ($columns = &loop_contents($orig_text,$x+1,["_Atom_shift_assign_ID_ambiguity"]))) { $x += 1 + scalar(keys %$columns); $x = &process_chemical_shift_ambiguity($orig_text,$x,$columns,$bmrb_hlist); push @$sections, { "type" => "ambiguity_loop", "all_tags" => [ sort { $$columns{$a} <=> $$columns{$b}; } (keys %$columns) ] }; } else { if (! @$sections || ($$sections[$#{$sections}]{"type"} ne "text")) { push @$sections, { "type" => "text", "value" => [] }; } push @{$$sections[$#{$sections}]{"value"}}, $$orig_text[$x]; } } if (@$sections) { $$save_frame{"sections"} = $sections; delete $$save_frame{"text"}; } } # process_chemical_shift_ambiguity # Processes the assigned chemical shift ambiguity lines and puts them in the bmrb hash structure. # Returns the ending line index. # # Parameters: # $text_array - array of text lines to process # $start - starting index in the array. # $column_elements - hash of fields to column positions. # $bmrb_hlist - bmrb hash structure to fill. sub process_chemical_shift_ambiguity { my $text_array = shift @_; my $start = shift @_; my $column_elements = shift @_; my $bmrb_hlist = shift @_; $$bmrb_hlist{"ambiguity_lists"} = []; while($start < @$text_array) { # stop on the stop_ if ($$text_array[$start] =~ /^\s*stop_/) { $start++; last; } # skip comment or blank lines next if (($$text_array[$start] =~ /^\s*\#/) || ($$text_array[$start] =~ /^\s*$/)); # split and split it on spaces my @tokens = split(/\s+/, $$text_array[$start]); # get rid of the null element in the beginning caused by the spaces followed by characters while (@tokens && ($tokens[0] eq "")) { shift @tokens; } # skip lines which do not have enough columns. next if (scalar(@tokens) < scalar(keys %$column_elements)); push @{$$bmrb_hlist{"ambiguity_lists"}}, [ split(/,/, $tokens[$$column_elements{"_Atom_shift_assign_ID_ambiguity"}]) ]; } continue { $start++; } return $start; } # process_chemical_shift_lines # Processes the assigned chemical shift lines and puts them in the bmrb hash structure. # Returns the ending line index. # # Parameters: # $text_array - array of text lines to process # $start - starting index in the array. # $column_elements - hash of fields to column positions. # $convert_aa_names - converts single letter amino acid names to three letter representations if true. # $convert_shift_names - convert shift names to degenerate naming scheme. # $shift_conversion_hash - hash to use for converting shift names. # $bmrb_hlist - bmrb hash structure to fill. # $extra_tags - array of extra tags in the column_elements. sub process_chemical_shift_lines { my $text_array = shift @_; my $start = shift @_; my $column_elements = shift @_; my $convert_aa_names = shift @_; my $convert_shift_names = shift @_; my $shift_conversion_hash = shift @_; my $bmrb_hlist = shift @_; my $extra_tags = shift @_; while($start < @$text_array) { # stop on the stop_ if ($$text_array[$start] =~ /^\s*stop_/) { $start++; last; } # skip comment or blank lines next if (($$text_array[$start] =~ /^\s*\#/) || ($$text_array[$start] =~ /^\s*$/)); # split and split it on spaces my @tokens = split(/\s+/, $$text_array[$start]); # get rid of the null element in the beginning caused by the spaces followed by characters while (@tokens && ($tokens[0] eq "")) { shift @tokens; } # skip lines which do not have enough columns. next if (scalar(@tokens) < scalar(keys %$column_elements)); # as long as you have enough tokens to map to the column elements and the residue label is legitimate continue, otherwise next line. next if ((@tokens < scalar(keys %$column_elements)) || ((! exists $aa_name_conversion{lc($tokens[$$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 $$column_elements{"_Residue_author_seq_code"} && ($tokens[$$column_elements{"_Residue_author_seq_code"}] ne ".")); $$residue{"aa"} = $tokens[$$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[$$column_elements{"_Chem_shift_ambiguity_code"}] if ($tokens[$$column_elements{"_Chem_shift_ambiguity_code"}] ne "."); $$residue{"shifts"}{$tokens[$$column_elements{"_Atom_name"}]}{"list"} = []; $$residue{"shifts"}{$tokens[$$column_elements{"_Atom_name"}]}{"idlist"} = []; $$residue{"shifts"}{$tokens[$$column_elements{"_Atom_name"}]}{"error"} = $tokens[$$column_elements{"_Chem_shift_value_error"}] if ($tokens[$$column_elements{"_Chem_shift_value_error"}] ne "."); } # if the atom name is defined then push the chemical shift value and the extra_tags if ($tokens[$$column_elements{"_Atom_name"}] ne "") { push @{$$residue{"shifts"}{$tokens[$$column_elements{"_Atom_name"}]}{"list"}}, $tokens[$$column_elements{"_Chem_shift_value"}]; push @{$$residue{"shifts"}{$tokens[$$column_elements{"_Atom_name"}]}{"idlist"}}, $tokens[$$column_elements{"_Atom_shift_assign_ID"}]; foreach my $field (@$extra_tags) { $$residue{"shifts"}{$tokens[$$column_elements{"_Atom_name"}]}{"extra_tags"}{$field} = $tokens[$$column_elements{$field}] if ($tokens[$$column_elements{$field}] ne "."); } } } continue { $start++; } $start--; return $start; } # process_spectral_peak_list_frame # Processes a spectral peak list frame and creates an organized data hash structure. # # Parameters: # $save_frame - save_frame hash # sub process_spectral_peak_list_frame { my $save_frame = shift @_; my $bmrb_hlist = shift @_; my $sections = []; # required and expected fields for loops my @expected_dim_description_fields = ("_Spectral_dim.Entry_ID","_Spectral_dim.Spectral_peak_list_ID","_Spectral_dim.Spectral_dim_ID","_Spectral_dim.Atom_type","_Spectral_dim.Spectral_region","_Spectral_dim.Magnetization_linkage_ID","_Spectral_dim.Sweep_width","_Spectral_dim.Encoding_code","_Spectral_dim.Encoded_source_dimension_ID"); my @required_dim_description_fields = ("_Spectral_dim.Spectral_dim_ID","_Spectral_dim.Atom_type","_Spectral_dim.Spectral_region","_Spectral_dim.Magnetization_linkage_ID","_Spectral_dim.Sweep_width","_Spectral_dim.Encoding_code","_Spectral_dim.Encoded_source_dimension_ID"); my @expected_peak_fields = ("_Peak.Entry_ID","_Peak.Spectral_peak_list_ID","_Peak.Peak_ID","_Peak.Intensity_val","_Peak.Intensity_err","_Peak.Figure_of_merit","_Peak.Intensity_measurement_methods_ID","_Peak.Derivation_set_ID"); my @required_peak_fields = ("_Peak.Peak_ID","_Peak.Intensity_val","_Peak.Intensity_err","_Peak.Figure_of_merit","_Peak.Intensity_measurement_methods_ID","_Peak.Derivation_set_ID"); my @expected_peak_char_fields = ("_Peak_char.Entry_ID","_Peak_char.Spectral_peak_list_ID","_Peak_char.Peak_ID","_Peak_char.Spectral_dimension_ID","_Peak_char.Chem_shift_val","_Peak_char.Chem_shift_val_err","_Peak_char.Line_width_val","_Peak_char.Line_width_val_err","_Peak_char.Phase_val","_Peak_char.Phase_val_err","_Peak_char.Decay_rate_val","_Peak_char.Decay_rate_val_err","_Peak_char.Derivation_methods_ID"); my @required_peak_char_fields = ("_Peak_char.Peak_ID","_Peak_char.Spectral_dimension_ID","_Peak_char.Chem_shift_val","_Peak_char.Chem_shift_val_err","_Peak_char.Line_width_val","_Peak_char.Line_width_val_err","_Peak_char.Phase_val","_Peak_char.Phase_val_err","_Peak_char.Decay_rate_val","_Peak_char.Decay_rate_val_err","_Peak_char.Derivation_methods_ID"); my @expected_assignment_fields = ("_Assigned_peak_chem_shift.Entry_ID","_Assigned_peak_chem_shift.Spectral_peak_list_ID","_Assigned_peak_chem_shift.Peak_ID","_Assigned_peak_chem_shift.Set_ID","_Assigned_peak_chem_shift.Magnetization_linkage_ID","_Assigned_peak_chem_shift.Figure_of_merit","_Assigned_peak_chem_shift.Spectral_dimension_ID","_Assigned_peak_chem_shift.List_ID","_Assigned_peak_chem_shift.List_label","_Assigned_peak_chem_shift.Atom_chem_shift_ID"); my @required_assignment_fields = ("_Assigned_peak_chem_shift.Peak_ID","_Assigned_peak_chem_shift.Set_ID","_Assigned_peak_chem_shift.Magnetization_linkage_ID","_Assigned_peak_chem_shift.Figure_of_merit","_Assigned_peak_chem_shift.Spectral_dimension_ID","_Assigned_peak_chem_shift.List_ID","_Assigned_peak_chem_shift.List_label","_Assigned_peak_chem_shift.Atom_chem_shift_ID"); my $orig_text = $$save_frame{"text"}; # foreach line in the file until stop_ for(my $x=0; $x < @$orig_text; $x++) { my $columns = 0; # process details if($$orig_text[$x] =~ /^\s*_Spectral_peak_list\.Details/) { # skip spaces and comment lines while(($x < @$orig_text) && ($$orig_text[$x] !~ /^;/)) { $x++; } # skip the ";" $x++; # process to the ";" line while(($x < @$orig_text) && ($$orig_text[$x] !~ /^;/)) { push @{$$save_frame{"data"}{"details"}}, $$orig_text[$x]; $x++; } push @$sections, { "type" => "details" }; } # process entry ID elsif($$orig_text[$x] =~ /^\s*_Spectral_peak_list\.Entry_ID/) { ($$save_frame{"data"}{"entry_id"}) = ($$orig_text[$x] =~ /\s*_Spectral_peak_list\.Entry_ID\s*(\w+)\s*/); push @$sections, { "type" => "entry_id" }; } # process spectral peak list ID elsif($$orig_text[$x] =~ /^\s*_Spectral_peak_list\.Spectral_peak_list_ID/) { ($$save_frame{"data"}{"peak_list_id"}) = ($$orig_text[$x] =~ /\s*_Spectral_peak_list\.Spectral_peak_list_ID\s*(\w+)\s*/); push @$sections, { "type" => "peak_list_id" }; } # process Number of Spectral Dimensions elsif($$orig_text[$x] =~ /^\s*_Spectral_peak_list\.Number_of_spectral_dimensions/) { ($$save_frame{"data"}{"num_dimensions"}) = ($$orig_text[$x] =~ /\s*_Spectral_peak_list\.Number_of_spectral_dimensions\s*(\w+)\s*/); push @$sections, { "type" => "num_dimensions" }; } # process Experiment label elsif($$orig_text[$x] =~ /^\s*_Spectral_peak_list\.Experiment_label/) { ($$save_frame{"data"}{"experiment_label"}) = ($$orig_text[$x] =~ /\s*_Spectral_peak_list\.Experiment_label\s*(\w+)\s*/); push @$sections, { "type" => "experiment_label" }; } # process the dimension description loop elsif (($$orig_text[$x] =~ /^\s*loop_/) && ($columns = &loop_contents($orig_text,$x+1,\@required_dim_description_fields))) { $x += 1 + scalar(keys %$columns); my @extra_tags = (grep {my $test = $_; (! grep {$test eq $_; } (@expected_dim_description_fields)); } (keys %$columns)); $x = &process_dimension_description_lines($orig_text,$x,$columns,$save_frame,\@extra_tags); push @$sections, { "type" => "dimension_descriptions", "extra_tags" => [@extra_tags], "all_tags" => [ sort { $$columns{$a} <=> $$columns{$b}; } (keys %$columns) ] }; } # process the peak loop elsif (($$orig_text[$x] =~ /^\s*loop_/) && ($columns = &loop_contents($orig_text,$x+1,\@required_peak_fields))) { $x += 1 + scalar(keys %$columns); my @extra_tags = (grep {my $test = $_; (! grep {$test eq $_; } (@expected_peak_fields)); } (keys %$columns)); $x = &process_peak_lines($orig_text,$x,$columns,$save_frame,\@extra_tags); push @$sections, { "type" => "peaks", "extra_tags" => [@extra_tags], "all_tags" => [ sort { $$columns{$a} <=> $$columns{$b}; } (keys %$columns) ] }; } # process the peak characteristics loop elsif (($$orig_text[$x] =~ /^\s*loop_/) && ($columns = &loop_contents($orig_text,$x+1,\@required_peak_char_fields))) { $x += 1 + scalar(keys %$columns); my @extra_tags = (grep {my $test = $_; (! grep {$test eq $_; } (@expected_peak_char_fields)); } (keys %$columns)); $x = &process_peak_characteristics_lines($orig_text,$x,$columns,$save_frame,\@extra_tags); push @$sections, { "type" => "peak_characteristics", "extra_tags" => [@extra_tags], "all_tags" => [ sort { $$columns{$a} <=> $$columns{$b}; } (keys %$columns) ] }; } # process the assignment loop elsif (($$orig_text[$x] =~ /^\s*loop_/) && ($columns = &loop_contents($orig_text,$x+1,\@required_assignment_fields))) { $x += 1 + scalar(keys %$columns); my @extra_tags = (grep {my $test = $_; (! grep {$test eq $_; } (@expected_assignment_fields)); } (keys %$columns)); $x = &process_peak_assignment_lines($orig_text,$x,$columns,$save_frame,\@extra_tags); push @$sections, { "type" => "peak_assignments", "extra_tags" => [@extra_tags], "all_tags" => [ sort { $$columns{$a} <=> $$columns{$b}; } (keys %$columns) ] }; } else { if (! @$sections || ($$sections[$#{$sections}]{"type"} ne "text")) { push @$sections, { "type" => "text", "value" => [] }; } push @{$$sections[$#{$sections}]{"value"}}, $$orig_text[$x]; } } if (@$sections) { $$save_frame{"sections"} = $sections; delete $$save_frame{"text"}; } } # update_spectral_peak_list_frames # Processes the dimension description lines and add them to the save_frame data subhash # Returns the ending line index. # # Parameters: # $text_array - array of text lines to process # $start - starting index in the array. # $column_elements - hash of fields to column positions. # $save_frame - save frame hash # $extra_tags - array of extra tags in the column_elements. sub update_spectral_peak_list_frames { my $bmrb_hlist = shift @_; my $peak_list_frames = shift @_; #build shift id list my $shift_id_hash = {}; foreach my $residue (values %{$$bmrb_hlist{"rlist"}}) { foreach my $atom_name (keys %{$$residue{"shifts"}}) { foreach my $id (@{$$residue{"shifts"}{$atom_name}{"idlist"}}) { $$shift_id_hash{$id} = [ $residue, $atom_name ]; } } } #update spectral_peak_list save frames. foreach my $save_frame (@$peak_list_frames) { foreach my $peak (values %{$$save_frame{"data"}{"plist"}}) { foreach my $dimension (values %{$$peak{"dimensions"}}) { if (exists $$dimension{"assignments"}) { foreach my $assignment (@{$$dimension{"assignments"}}) { $$assignment{"aa"} = $$shift_id_hash{$$assignment{"shift_id"}}[0]{"aa"}; $$assignment{"index"} = $$shift_id_hash{$$assignment{"shift_id"}}[0]{"index"}; $$assignment{"atom_name"} = $$shift_id_hash{$$assignment{"shift_id"}}[1]; } } } } } } # process_dimension_description_lines # Processes the dimension description lines and add them to the save_frame data subhash # Returns the ending line index. # # Parameters: # $text_array - array of text lines to process # $start - starting index in the array. # $column_elements - hash of fields to column positions. # $save_frame - save frame hash # $extra_tags - array of extra tags in the column_elements. sub process_dimension_description_lines { my $text_array = shift @_; my $start = shift @_; my $column_elements = shift @_; my $save_frame = shift @_; my $extra_tags = shift @_; $$save_frame{"data"}{"dimension_descriptions"} = []; while($start < @$text_array) { # stop on the stop_ if ($$text_array[$start] =~ /^\s*stop_/) { $start++; last; } # skip comment or blank lines next if (($$text_array[$start] =~ /^\s*\#/) || ($$text_array[$start] =~ /^\s*$/)); # split and split it on spaces my @tokens = split(/\s+/, $$text_array[$start]); # get rid of the null element in the beginning caused by the spaces followed by characters while (@tokens && ($tokens[0] eq "")) { shift @tokens; } # skip lines which do not have enough columns. next if (scalar(@tokens) < scalar(keys %$column_elements)); my $dimension_description = {}; $$dimension_description{"dim_id"} = $tokens[$$column_elements{"_Spectral_dim.Spectral_dim_ID"}]; $$dimension_description{"atom_type"} = $tokens[$$column_elements{"_Spectral_dim.Atom_type"}] if ($tokens[$$column_elements{"_Spectral_dim.Atom_type"}] ne "."); $$dimension_description{"spectral_region"} = $tokens[$$column_elements{"_Spectral_dim.Spectral_region"}] if ($tokens[$$column_elements{"_Spectral_dim.Spectral_region"}] ne "."); $$dimension_description{"magnetization_linkage"} = $tokens[$$column_elements{"_Spectral_dim.Magnetization_linkage_ID"}] if ($tokens[$$column_elements{"_Spectral_dim.Magnetization_linkage_ID"}] ne "."); $$dimension_description{"sweep_width"} = $tokens[$$column_elements{"_Spectral_dim.Sweep_width"}] if ($tokens[$$column_elements{"_Spectral_dim.Sweep_width"}] ne "."); $$dimension_description{"encoding"} = $tokens[$$column_elements{"_Spectral_dim.Encoding_code"}] if ($tokens[$$column_elements{"_Spectral_dim.Encoding_code"}] ne "."); $$dimension_description{"encoding_dimension"} = $tokens[$$column_elements{"_Spectral_dim.Encoded_source_dimension_ID"}] if ($tokens[$$column_elements{"_Spectral_dim.Encoded_source_dimension_ID"}] ne "."); foreach my $field (@$extra_tags) { if ($tokens[$$column_elements{$field}] ne ".") { $$dimension_description{"extra_tags"}{$field} = $tokens[$$column_elements{$field}]; } } push @{$$save_frame{"data"}{"dimension_descriptions"}}, $dimension_description; } continue { $start++; } $start--; return $start; } # process_peak_lines # Processes the peak lines and add them to the save_frame data subhash # Returns the ending line index. # # Parameters: # $text_array - array of text lines to process # $start - starting index in the array. # $column_elements - hash of fields to column positions. # $save_frame - save frame hash # $extra_tags - array of extra tags in the column_elements. sub process_peak_lines { my $text_array = shift @_; my $start = shift @_; my $column_elements = shift @_; my $save_frame = shift @_; my $extra_tags = shift @_; $$save_frame{"data"}{"plist"} = {}; $$save_frame{"data"}{"index_array"} = []; while($start < @$text_array) { # stop on the stop_ if ($$text_array[$start] =~ /^\s*stop_/) { $start++; last; } # skip comment or blank lines next if (($$text_array[$start] =~ /^\s*\#/) || ($$text_array[$start] =~ /^\s*$/)); # split and split it on spaces my @tokens = split(/\s+/, $$text_array[$start]); # get rid of the null element in the beginning caused by the spaces followed by characters while (@tokens && ($tokens[0] eq "")) { shift @tokens; } # skip lines which do not have enough columns. next if (scalar(@tokens) < scalar(keys %$column_elements)); my $peak = {}; $$peak{"index"} = $tokens[$$column_elements{"_Peak.Peak_ID"}]; $$peak{"intensity"} = $tokens[$$column_elements{"_Peak.Intensity_val"}] if ($tokens[$$column_elements{"_Peak.Intensity_val"}] ne "."); $$peak{"intensity_error"} = $tokens[$$column_elements{"_Peak.Intensity_err"}] if ($tokens[$$column_elements{"_Peak.Intensity_err"}] ne "."); $$peak{"figure_of_merit"} = $tokens[$$column_elements{"_Peak.Figure_of_merit"}] if ($tokens[$$column_elements{"_Peak.Figure_of_merit"}] ne "."); $$peak{"measurement_method"} = $tokens[$$column_elements{"_Peak.Intensity_measurement_methods_ID"}] if ($tokens[$$column_elements{"_Peak.Intensity_measurement_methods_ID"}] ne "."); $$peak{"derivation_set"} = $tokens[$$column_elements{"_Peak.Derivation_set_ID"}] if ($tokens[$$column_elements{"_Peak.Derivation_set_ID"}] ne "."); foreach my $field (@$extra_tags) { if ($tokens[$$column_elements{$field}] ne ".") { $$peak{"extra_tags"}{$field} = $tokens[$$column_elements{$field}]; } } push @{$$save_frame{"data"}{"index_array"}}, $$peak{"index"}; $$save_frame{"data"}{"plist"}{$$peak{"index"}} = $peak; } continue { $start++; } $start--; return $start; } # process_peak_characteristics_lines # Processes the peak characteristic lines and add them to the save_frame data subhash # Returns the ending line index. # # Parameters: # $text_array - array of text lines to process # $start - starting index in the array. # $column_elements - hash of fields to column positions. # $save_frame - save frame hash # $extra_tags - array of extra tags in the column_elements. sub process_peak_characteristics_lines { my $text_array = shift @_; my $start = shift @_; my $column_elements = shift @_; my $save_frame = shift @_; my $extra_tags = shift @_; while($start < @$text_array) { # stop on the stop_ if ($$text_array[$start] =~ /^\s*stop_/) { $start++; last; } # skip comment or blank lines next if (($$text_array[$start] =~ /^\s*\#/) || ($$text_array[$start] =~ /^\s*$/)); # split and split it on spaces my @tokens = split(/\s+/, $$text_array[$start]); # get rid of the null element in the beginning caused by the spaces followed by characters while (@tokens && ($tokens[0] eq "")) { shift @tokens; } # skip lines which do not have enough columns. next if (scalar(@tokens) < scalar(keys %$column_elements)); my $dimension = {}; my $peak_index = $tokens[$$column_elements{"_Peak_char.Peak_ID"}]; $$dimension{"dim_id"} = $tokens[$$column_elements{"_Peak_char.Spectral_dimension_ID"}]; $$dimension{"shift"} = $tokens[$$column_elements{"_Peak_char.Chem_shift_val"}]; $$dimension{"shift_error"} = $tokens[$$column_elements{"_Peak_char.Chem_shift_val_err"}] if ($tokens[$$column_elements{"_Peak_char.Chem_shift_val_err"}] ne "."); $$dimension{"width"} = $tokens[$$column_elements{"_Peak_char.Line_width_val"}] if ($tokens[$$column_elements{"_Peak_char.Line_width_val"}] ne "."); $$dimension{"width_error"} = $tokens[$$column_elements{"_Peak_char.Line_width_val_err"}] if ($tokens[$$column_elements{"_Peak_char.Line_width_val_err"}] ne "."); $$dimension{"phase"} = $tokens[$$column_elements{"_Peak_char.Phase_val"}] if ($tokens[$$column_elements{"_Peak_char.Phase_val"}] ne "."); $$dimension{"phase_error"} = $tokens[$$column_elements{"_Peak_char.Phase_val_err"}] if ($tokens[$$column_elements{"_Peak_char.Phase_val_err"}] ne "."); $$dimension{"decay"} = $tokens[$$column_elements{"_Peak_char.Decay_rate_val"}] if ($tokens[$$column_elements{"_Peak_char.Decay_rate_val"}] ne "."); $$dimension{"decay_error"} = $tokens[$$column_elements{"_Peak_char.Decay_rate_val_err"}] if ($tokens[$$column_elements{"_Peak_char.Decay_rate_val_err"}] ne "."); $$dimension{"derivation_method"} = $tokens[$$column_elements{"_Peak_char.Derivation_methods_ID"}] if ($tokens[$$column_elements{"_Peak_char.Derivation_methods_ID"}] ne "."); foreach my $field (@$extra_tags) { if ($tokens[$$column_elements{$field}] ne ".") { $$dimension{"extra_tags"}{$field} = $tokens[$$column_elements{$field}]; } } $$save_frame{"data"}{"plist"}{$peak_index}{"dimensions"}{$$dimension{"dim_id"}} = $dimension; } continue { $start++; } $start--; return $start; } # process_peak_assignment_lines # Processes the peak assignment lines and add them to the save_frame data subhash # Returns the ending line index. # # Parameters: # $text_array - array of text lines to process # $start - starting index in the array. # $column_elements - hash of fields to column positions. # $save_frame - save frame hash # $extra_tags - array of extra tags in the column_elements. sub process_peak_assignment_lines { my $text_array = shift @_; my $start = shift @_; my $column_elements = shift @_; my $save_frame = shift @_; my $extra_tags = shift @_; while($start < @$text_array) { # stop on the stop_ if ($$text_array[$start] =~ /^\s*stop_/) { $start++; last; } # skip comment or blank lines next if (($$text_array[$start] =~ /^\s*\#/) || ($$text_array[$start] =~ /^\s*$/)); # split and split it on spaces my @tokens = split(/\s+/, $$text_array[$start]); # get rid of the null element in the beginning caused by the spaces followed by characters while (@tokens && ($tokens[0] eq "")) { shift @tokens; } # skip lines which do not have enough columns. next if (scalar(@tokens) < scalar(keys %$column_elements)); my $assignment = {}; my $peak_index = $tokens[$$column_elements{"_Assigned_peak_chem_shift.Peak_ID"}]; my $dimension_id = $tokens[$$column_elements{"_Assigned_peak_chem_shift.Spectral_dimension_ID"}]; $$assignment{"set_id"} = $tokens[$$column_elements{"_Assigned_peak_chem_shift.Set_ID"}] if ($tokens[$$column_elements{"_Assigned_peak_chem_shift.Set_ID"}] ne "."); $$assignment{"magnetization_linkage"} = $tokens[$$column_elements{"_Assigned_peak_chem_shift.Magnetization_linkage_ID"}] if ($tokens[$$column_elements{"_Assigned_peak_chem_shift.Magnetization_linkage_ID"}] ne "."); $$assignment{"figure_of_merit"} = $tokens[$$column_elements{"_Assigned_peak_chem_shift.Figure_of_merit"}] if ($tokens[$$column_elements{"_Assigned_peak_chem_shift.Figure_of_merit"}] ne "."); $$assignment{"list_id"} = $tokens[$$column_elements{"_Assigned_peak_chem_shift.List_ID"}] if ($tokens[$$column_elements{"_Assigned_peak_chem_shift.List_ID"}] ne "."); $$assignment{"list_label"} = $tokens[$$column_elements{"_Assigned_peak_chem_shift.List_label"}] if ($tokens[$$column_elements{"_Assigned_peak_chem_shift.List_label"}] ne "."); $$assignment{"shift_id"} = $tokens[$$column_elements{"_Assigned_peak_chem_shift.Atom_chem_shift_ID"}]; foreach my $field (@$extra_tags) { if ($tokens[$$column_elements{$field}] ne ".") { $$assignment{"extra_tags"}{$field} = $tokens[$$column_elements{$field}]; } } push @{$$save_frame{"data"}{"plist"}{$peak_index}{"dimensions"}{$dimension_id}{"assignments"}}, $assignment; } continue { $start++; } $start--; return $start; } # process_monomeric_polymer_frame # Reads the residue list from a monomeric polymer frame and puts them in the bmrb hash. # # Parameters: # $save_frame - save_frame hash # $convert_aa_names - converts single letter amino acid names to three letter representations if true. # $bmrb_hlist - bmrb hash structure to fill. # $save_frame_count - count of save frames of this type # sub process_monomeric_polymer_frame { my $save_frame = shift @_; my $convert_aa_names = shift @_; my $bmrb_hlist = shift @_; my $save_frame_count = shift @_; if ($save_frame_count > 1) { return 1; } # if you do not have a name array then make it a reference to an array. if (! exists $$bmrb_hlist{"name_array"}) { $$bmrb_hlist{"name_array"} = []; } my $sections = []; my @required_sequence_fields = ("_Residue_seq_code", "_Residue_label"); my @expected_sequence_fields = ("_Residue_seq_code", "_Residue_label", "_Residue_author_seq_code", "_Insertion_code", "_Segment_definition_code"); my $orig_text = $$save_frame{"text"}; # foreach line in the file until stop_ for(my $x=0; $x < @$orig_text; $x++) { my $columns = 0; # process the chemical shifts if (($$orig_text[$x] =~ /^\s*loop_/) && ($columns = &loop_contents($orig_text,$x+1,\@required_sequence_fields))) { $x += 1 + scalar(keys %$columns); my @extra_tags = (grep {my $test = $_; (! grep {$test eq $_; } (@expected_sequence_fields)); } (keys %$columns)); $x = &process_sequence_loop_lines($orig_text,$x,$columns,$convert_aa_names, $bmrb_hlist, \@extra_tags); push @$sections, { "type" => "sequence_loop", "extra_tags" => [@extra_tags], "all_tags" => [ sort { $$columns{$a} <=> $$columns{$b}; } (keys %$columns) ] }; } elsif($$orig_text[$x] =~ /^\s*_Residue_count/) { my ($value) = ($$orig_text[$x] =~ /\s*_Residue_count\s*(\d+)\s*/); if (($value ne ".") && ($value ne "")) { $$bmrb_hlist{"residue_count"} = $value; } push @$sections, { "type" => "residue_count" }; } elsif($$orig_text[$x] =~ /^\s*_Mol_type/) { my ($value) = ($$orig_text[$x] =~ /\s*_Mol_type\s*(\w+)\s*/); if (($value ne ".") && ($value ne "")) { $$bmrb_hlist{"molecule_type"} = $value; } push @$sections, { "type" => "molecule_type" }; } elsif($$orig_text[$x] =~ /^\s*_Mol_polymer_class/) { my ($value) = ($$orig_text[$x] =~ /\s*_Mol_polymer_class\s*(\w+)\s*/); if ($value ne "protein") { @$sections = (); } else { if (($value ne ".") && ($value ne "")) { $$bmrb_hlist{"polymer_class"} = $value; } push @$sections, { "type" => "polymer_class" }; } } elsif($$orig_text[$x] =~ /^\s*_Name_common/) { my ($value) = ($$orig_text[$x] =~ /\s*_Name_common\s*\"(.*)\"\s*/); if ($value eq "") { ($value) = ($$orig_text[$x] =~ /\s*_Name_common\s*\'(.*)\'\s*/); } if ($value eq "") { ($value) = ($$orig_text[$x] =~ /\s*_Name_common\s*(\w+)\s*/); } if (($value ne ".") && ($value ne "")) { $$bmrb_hlist{"common_name"} = $value; } push @$sections, { "type" => "common_name" }; } elsif($$orig_text[$x] =~ /^\s*_Mol_residue_sequence/) { # skip spaces and comment lines while(($x < @$orig_text) && ($$orig_text[$x] !~ /^;/)) { $x++; } # skip the ";" $x++; # process to the ";" line while(($x < @$orig_text) && ($$orig_text[$x] !~ /^;/)) { my ($sequence_part) = ($$orig_text[$x] =~ /^\s*(\w+)\s*/); $$bmrb_hlist{"sequence"} .= $sequence_part; $x++; } push @$sections, { "type" => "sequence" }; } else { if (! @$sections || ($$sections[$#{$sections}]{"type"} ne "text")) { push @$sections, { "type" => "text", "value" => [] }; } push @{$$sections[$#{$sections}]{"value"}}, $$orig_text[$x]; } } if (@$sections) { $$save_frame{"sections"} = $sections; delete $$save_frame{"text"}; return 1; } return 0; } # process_sequence_loop_lines # Processes the assigned chemical shift lines and puts them in the bmrb hash structure. # Returns the ending line index. # # Parameters: # $text_array - array of text lines to process # $start - starting index in the array. # $column_elements - hash of fields to column positions. # $convert_aa_names - converts single letter amino acid names to three letter representations if true. # $bmrb_hlist - bmrb hash structure to fill. sub process_sequence_loop_lines { my $text_array = shift @_; my $start = shift @_; my $column_elements = shift @_; my $convert_aa_names = shift @_; my $bmrb_hlist = shift @_; my $extra_tags = shift @_; while($start < @$text_array) { # stop on the stop_ if ($$text_array[$start] =~ /^\s*stop_/) { $start++; last; } # skip comment or blank lines next if (($$text_array[$start] =~ /^\s*\#/) || ($$text_array[$start] =~ /^\s*$/)); # split and split it on spaces my @tokens = split(/\s+/, $$text_array[$start]); # get rid of the null element in the beginning caused by the spaces followed by characters while (@tokens && ($tokens[0] eq "")) { shift @tokens; } while (scalar(@tokens) >= scalar(keys %$column_elements)) { # as long as you have enough tokens to map to the column elements and the residue label is legitimate continue, otherwise next line. next if ((@tokens < scalar(keys %$column_elements)) || ((! exists $aa_name_conversion{lc($tokens[$$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[$$column_elements{"_Residue_author_seq_code"}]; # print STDERR "YO >> ",$residue_name, "\n"; my $residue; # if this has already been defined, then skip next if (grep { $_ eq $residue_name; } @{$$bmrb_hlist{"name_array"}}); 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"} && ($tokens[$$column_elements{"_Residue_author_seq_code"}] ne ".")); $$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 (exists $$column_elements{"_Insertion_code"} && ($$column_elements{"_Insertion_code"} ne ".")) { $$residue{"insertion_code"} = $tokens[$$column_elements{"_Insertion_code"}]; } if (exists $$column_elements{"_Segment_definition_code"} && ($$column_elements{"_Segment_definition_code"} ne ".")) { $$residue{"segment_definition_code"} = $tokens[$$column_elements{"_Segment_definition_code"}]; } foreach my $field (@$extra_tags) { if ($tokens[$$column_elements{$field}] ne ".") { $$residue{"extra_tags"}{$field} = $tokens[$$column_elements{$field}]; } } # add the residue name to the name array. push @{$$bmrb_hlist{"name_array"}}, $residue_name; } continue { foreach my $junk (keys %$column_elements) { shift @tokens; } } } continue { $start++; } $start--; return $start; } # process_chemical_shift_reference_frame # Reads the chemical shift reference from a bmrb file and puts them in the bmrb hash structure. # # Parameters: # $save_frame - save_frame hash # $bmrb_hlist - bmrb hash structure to fill. # sub process_chemical_shift_reference_frame { my $save_frame = shift @_; my $bmrb_hlist = shift @_; my $sections = []; my @required_chem_shift_fields = ("_Atom_type", "_Chem_shift_value"); my $orig_text = $$save_frame{"text"}; # foreach line in the file until stop_ for(my $x=0; $x < @$orig_text; $x++) { my $columns = 0; # process the chemical shifts if (($$orig_text[$x] =~ /^\s*loop_/) && ($columns = &loop_contents($orig_text,$x+1,\@required_chem_shift_fields))) { $x += 1 + scalar(keys %$columns); $x = &process_reference_lines($orig_text,$x,$columns,$bmrb_hlist); push @$sections, { "type" => "reference_loop", "all_tags" => [ sort { $$columns{$a} <=> $$columns{$b}; } (keys %$columns) ] }; } else { if (! @$sections || ($$sections[$#{$sections}]{"type"} ne "text")) { push @$sections, { "type" => "text", "value" => [] }; } push @{$$sections[$#{$sections}]{"value"}}, $$orig_text[$x]; } } if (@$sections) { $$save_frame{"sections"} = $sections; delete $$save_frame{"text"}; } } # process_reference_lines # Processes the assigned chemical shift reference lines and puts them in the bmrb hash structure. # Returns the ending line index. # # Parameters: # $text_array - array of text lines to process # $start - starting index in the array. # $column_elements - hash of fields to column positions. # $bmrb_hlist - bmrb hash structure to fill. sub process_reference_lines { my $text_array = shift @_; my $start = shift @_; my $column_elements = shift @_; my $bmrb_hlist = shift @_; $$bmrb_hlist{"reference_fields"} = [ sort { $$column_elements{$a} <=> $$column_elements{$b}; } (keys %$column_elements) ]; my @junk = grep { $$bmrb_hlist{"reference_fields"}[$_] =~ /_[Cc]hem_[Ss]hift_[Vv]alue/; } (0..$#{$$bmrb_hlist{"reference_fields"}}); if (@junk) { $$bmrb_hlist{"reference_shift_index"} = pop @junk; } while($start < @$text_array) { # stop on the stop_ if ($$text_array[$start] =~ /^\s*stop_/) { $start++; last; } # skip comment or blank lines next if (($$text_array[$start] =~ /^\s*\#/) || ($$text_array[$start] =~ /^\s*$/)); # split on spaces my @tokens = grep { (defined $_) && ($_ ne "") ; } (split(/\s+|(\'.*\')/, $$text_array[$start])); # get rid of the null element in the beginning caused by the spaces followed by characters while (@tokens && ($tokens[0] eq "")) { shift @tokens; } # strip away single quote marks foreach my $token (@tokens) { $token =~ tr/\'//d; } # skip lines which do not have enough columns. next if (scalar(@tokens) < scalar(keys %$column_elements)); $$bmrb_hlist{"reference"}{$tokens[$$column_elements{"_Atom_type"}]} = [@tokens]; } continue { $start++; } $start--; return $start; } # process_coupling_constants_frame # Reads the coupling constants from a bmrb file and puts them in the bmrb hash structure. # # Parameters: # $save_frame - save_frame hash # $bmrb_hlist - bmrb hash structure to fill. # sub process_coupling_constants_frame { my $save_frame = shift @_; my $bmrb_hlist = shift @_; my $sections = []; my @coupling_constants_fields_hlist = (values %$coupling_constants_saveframe); my @required_coupling_constants_fields = grep {if ($$_{"required"}) { $_ = $$_{"bmrbFieldName"}}} @coupling_constants_fields_hlist; undef @coupling_constants_fields_hlist; my $orig_text = $$save_frame{"text"}; # foreach line in the file until stop_ for(my $x=0; $x < @$orig_text; $x++) { my $columns = 0; # process the chemical shifts if (($$orig_text[$x] =~ /^\s*loop_/) && ($columns = &loop_contents($orig_text,$x+1,\@required_coupling_constants_fields))) { $x += 1 + scalar(keys %$columns); $x = &process_coupling_constants_lines($orig_text,$x,$columns,$save_frame); push @$sections, { "type" => "coupling_constants", "all_tags" => [ sort { $$columns{$a} <=> $$columns{$b}; } (keys %$columns) ] }; } else { if (! @$sections || ($$sections[$#{$sections}]{"type"} ne "text")) { push @$sections, { "type" => "text", "value" => [] }; } push @{$$sections[$#{$sections}]{"value"}}, $$orig_text[$x]; } } if (@$sections) { $$save_frame{"sections"} = $sections; delete $$save_frame{"text"}; } } # process_coupling_constants_lines # Processes the coupling constants lines and puts them in the bmrb hash structure. # Returns the ending line index. # # Parameters: # $text_array - array of text lines to process # $start - starting index in the array. # $column_elements - hash of fields to column positions. # $bmrb_hlist - bmrb hash structure to fill. sub process_coupling_constants_lines { my $text_array = shift @_; my $start = shift @_; my $column_elements = shift @_; my $save_frame = shift @_; while($start < @$text_array) { # stop on the stop_ last if ($$text_array[$start] =~ /^\s*stop_/); # skip comment or blank lines next if (($$text_array[$start] =~ /^\s*\#/) || ($$text_array[$start] =~ /^\s*$/)); # split on spaces my @tokens = grep { (defined $_) && ($_ ne ""); } (split(/\s+|(\'.*\')/, $$text_array[$start])); # get rid of the null element in the beginning caused by the spaces followed by characters while (@tokens && ($tokens[0] eq "")) { shift @tokens; } # strip away single quote marks foreach my $token (@tokens) { $token =~ tr/\'//d; } # skip lines which do not have enough columns. next if (scalar(@tokens) < scalar(keys %$column_elements)); my $count = 0; # print "YO >> ", join(":", @tokens), "\n"; # $dumper->dumpValue($column_elements); # print "YO \n"; if (exists $$save_frame{"data"}{"cclist"}) { $count = @{$$save_frame{"data"}{"cclist"}}; } foreach my $key (keys %$coupling_constants_saveframe) { my $bmrbFieldName = $$coupling_constants_saveframe{$key}{"bmrbFieldName"}; if ((exists $$column_elements{$bmrbFieldName}) && (@tokens > $$column_elements{$bmrbFieldName}) && ($tokens[$$column_elements{$bmrbFieldName}] ne ".")) { $ {$$save_frame{"data"}{"cclist"}}[$count]{$key} = $tokens[$$column_elements{$bmrbFieldName}]; } } # my $cc_elem = $ {$$save_frame{"data"}{"cclist"}}[$count]; # $dumper->dumpValue($cc_elem); } continue { $start++; } $start--; return $start; } # process_secondary_structure_frame # Reads the secondary structure from a bmrb file and puts them in the bmrb hash structure. # # Parameters: # $save_frame - save_frame hash # $bmrb_hlist - bmrb hash structure to fill. # sub process_secondary_structure_frame { my $save_frame = shift @_; my $bmrb_hlist = shift @_; my $sections = []; my @secondary_structure_fields_hlist = (values %$secondary_structure_saveframe); my @required_secondary_structure_fields = grep {if ($$_{"required"}) { $_ = $$_{"bmrbFieldName"}}} @secondary_structure_fields_hlist; undef @secondary_structure_fields_hlist; my $orig_text = $$save_frame{"text"}; # foreach line in the file until stop_ for(my $x=0; $x < @$orig_text; $x++) { my $columns = 0; # process the chemical shifts if (($$orig_text[$x] =~ /^\s*loop_/) && ($columns = &loop_contents($orig_text,$x+1,\@required_secondary_structure_fields))) { $x += 1 + scalar(keys %$columns); $x = &process_secondary_structure_lines($orig_text,$x,$columns,$save_frame); push @$sections, { "type" => "secondary_structure", "all_tags" => [ sort { $$columns{$a} <=> $$columns{$b}; } (keys %$columns) ] }; } else { if (! @$sections || ($$sections[$#{$sections}]{"type"} ne "text")) { push @$sections, { "type" => "text", "value" => [] }; } push @{$$sections[$#{$sections}]{"value"}}, $$orig_text[$x]; } } if (@$sections) { $$save_frame{"sections"} = $sections; delete $$save_frame{"text"}; } } # process_secondary_structure_lines # Processes the secondary structure lines and puts them in the bmrb hash structure. # Returns the ending line index. # # Parameters: # $text_array - array of text lines to process # $start - starting index in the array. # $column_elements - hash of fields to column positions. # $bmrb_hlist - bmrb hash structure to fill. sub process_secondary_structure_lines { my $text_array = shift @_; my $start = shift @_; my $column_elements = shift @_; my $save_frame = shift @_; while($start < @$text_array) { # stop on the stop_ last if ($$text_array[$start] =~ /^\s*stop_/); # skip comment or blank lines next if (($$text_array[$start] =~ /^\s*\#/) || ($$text_array[$start] =~ /^\s*$/)); # split on spaces my @tokens = grep { (defined $_) && ($_ ne ""); } (split(/\s+|(\'.*\')/, $$text_array[$start])); # get rid of the null element in the beginning caused by the spaces followed by characters while (@tokens && ($tokens[0] eq "")) { shift @tokens; } # strip away single quote marks foreach my $token (@tokens) { $token =~ tr/\'//d; } # skip lines which do not have enough columns. next if (scalar(@tokens) < scalar(keys %$column_elements)); my $count = 0; # print "YO >> ", join(":", @tokens), "\n"; # $dumper->dumpValue($column_elements); # print "YO \n"; if (exists $$save_frame{"data"}{"sslist"}) {$count = @{$$save_frame{"data"}{"sslist"}};} foreach my $key (keys %$secondary_structure_saveframe) { my $bmrbFieldName = $$secondary_structure_saveframe{$key}{"bmrbFieldName"}; if ((exists $$column_elements{$bmrbFieldName}) && (@tokens > $$column_elements{$bmrbFieldName}) && ($tokens[$$column_elements{$bmrbFieldName}] ne ".")) { $ {$$save_frame{"data"}{"sslist"}}[$count]{$key} = $tokens[$$column_elements{$bmrbFieldName}]; } } } continue { $start++; } $start--; return $start; } #################################### residueNameofIndex ####################################### # Input : a bmrb_hlist type and an index # # Output : the residue name of the residue with that index # # Purpose : To return the residue name of the residue with the inputted index # ############################################################################################### sub residueNameofIndex { my $bmrb_hlist = shift @_; my $index = shift @_; foreach my $residue_name (@{$$bmrb_hlist{"name_array"}}) { $residue_name =~ /^([A-Za-z]+)(\d+)$/; if ($2 == $index) { return $residue_name; } } return ""; } # # # Routines for writing BMRB files # # # has_shifts # Returns true if the given bmrb hash structure has any shifts # # Parameters: # $bmrb_hlist - reference to bmrb hash structure. sub has_shifts { my $bmrb_hlist = shift @_; if (exists $$bmrb_hlist{"rlist"}) { foreach my $residue (values %{$$bmrb_hlist{"rlist"}}) { if (exists $$residue{"shifts"}) { foreach my $shift (values %{$$residue{"shifts"}}) { if (exists $$shift{"list"} && @{$$shift{"list"}}) { return 1; } } } } } return 0; } # update_shift_ids # updates the shift ids in the bmrb hash structure. # # Parameters: # $bmrb_hlist - ref to bmrb hash structure. # sub update_shift_ids { my $bmrb_hlist = shift @_; if (&has_shifts($bmrb_hlist)) { my $id_conversion_hash = {}; my $shift_id = 1; # update assigned chemical shifts foreach my $residue_name (@{$$bmrb_hlist{"name_array"}}) { my $residue = $$bmrb_hlist{"rlist"}{$residue_name}; foreach my $shift_name (sort { $BMRB_shift_name_ordering{$a} <=> $BMRB_shift_name_ordering{$b}; } (keys %{$$residue{"shifts"}})) { if (exists $$residue{"shifts"}{$shift_name}{"list"}) { for(my $x=0; $x < @{$$residue{"shifts"}{$shift_name}{"list"}}; $x++) { if (! exists $$residue{"shifts"}{$shift_name}{"idlist"} || (ref $$residue{"shifts"}{$shift_name}{"idlist"} ne "ARRAY")) { $$residue{"shifts"}{$shift_name}{"idlist"} = []; } if ($x < @{$$residue{"shifts"}{$shift_name}{"idlist"}}) { $$id_conversion_hash{$$residue{"shifts"}{$shift_name}{"idlist"}[$x]} = $shift_id; } $$residue{"shifts"}{$shift_name}{"idlist"}[$x] = $shift_id; $shift_id++; } } } } # update ambiguous settings if (exists $$bmrb_hlist{"ambiguity_lists"} && @{$$bmrb_hlist{"ambiguity_lists"}}) { foreach my $ambiguity_list (@{$$bmrb_hlist{"ambiguity_lists"}}) { foreach my $shift_id (@$ambiguity_list) { if (exists $$id_conversion_hash{$shift_id}) { $shift_id = $$id_conversion_hash{$shift_id}; } } } } # update peak assignments if (exists $$bmrb_hlist{"save_frames"} && (ref $$bmrb_hlist{"save_frames"} eq "ARRAY")) { foreach my $save_frame (grep {$$_{"type"} eq "spectral_peak_list"; } (@{$$bmrb_hlist{"save_frames"}})) { if (exists $$save_frame{"data"} && $$save_frame{"data"}{"plist"}) { foreach my $peak (values %{$$save_frame{"data"}{"plist"}}) { foreach my $dimension (values %{$$peak{"dimensions"}}) { if (exists $$dimension{"assignments"}) { foreach my $assignment (@{$$dimension{"assignments"}}) { if (exists $$assignment{"shift_id"} && exists $$id_conversion_hash{$$assignment{"shift_id"}}) { $$assignment{"shift_id"} = $$id_conversion_hash{$$assignment{"shift_id"}}; } } } } } } } } } } # create_assigned_chemical_shifts_frame # Returns an array of text_lines given the description of the save_frame and the bmrb hash structure. # # Parameters: # $save_frame - ref to save_frame hash structure. # $bmrb_hlist - ref to bmrb hash structure. # $write_options - ref to write options hash # sub create_assigned_chemical_shifts_frame { my $save_frame = shift @_; my $bmrb_hlist = shift @_; my $write_options = shift @_; my $text_lines = []; foreach my $section (@{$$save_frame{"sections"}}) { if ($$section{"type"} eq "text") { push @$text_lines, (@{$$section{"value"}}); } elsif ($$section{"type"} eq "chemical_shifts_loop") { push @$text_lines, " loop_"; foreach my $tag ("_Atom_shift_assign_ID", "_Residue_seq_code", "_Residue_label", "_Atom_name", "_Atom_type", "_Chem_shift_value", "_Chem_shift_value_error", "_Chem_shift_ambiguity_code") { push @$text_lines, " " . $tag; } if (exists $$section{"extra_tags"} && @{$$section{"extra_tags"}}) { foreach my $tag (@{$$section{"extra_tags"}}) { push @$text_lines, " " . $tag; } } push @$text_lines, ""; foreach my $residue_name (@{$$bmrb_hlist{"name_array"}}) { my $residue = $$bmrb_hlist{"rlist"}{$residue_name}; foreach my $shift_name (sort { $BMRB_shift_name_ordering{$a} <=> $BMRB_shift_name_ordering{$b}; } (keys %{$$residue{"shifts"}})) { if (exists $$residue{"shifts"}{$shift_name}{"list"}) { for(my $x=0; $x < @{$$residue{"shifts"}{$shift_name}{"list"}}; $x++) { # build shift line my $shift_line = $$residue{"shifts"}{$shift_name}{"idlist"}[$x] . " " . $$residue{"index"} . " " . $aa_name_conversion2{uc($$residue{"aa"})} . " " . $shift_name . " " . $$residue{"shifts"}{$shift_name}{"atom_type"} . " " . $$residue{"shifts"}{$shift_name}{"list"}[$x] ; if (exists $$residue{"shifts"}{$shift_name}{"error"}) { $shift_line .= " " . $$residue{"shifts"}{$shift_name}{"error"}; } else { $shift_line .= " ."; } if (exists $$residue{"shifts"}{$shift_name}{"ambiguity_code"} && $$residue{"shifts"}{$shift_name}{"ambiguity_code"}) { $shift_line .= " " . $$residue{"shifts"}{$shift_name}{"ambiguity_code"}; } else { $shift_line .= " 1"; } # add extra tags if they exist my @extra_tags; if (exists $$section{"extra_tags"} && @{$$section{"extra_tags"}}) { @extra_tags = @{$$section{"extra_tags"}}; } if (exists $$write_options{"extra_tags"} && exists $$write_options{"extra_tags"}{"shifts"}) { @extra_tags = @{$$write_options{"extra_tags"}{"shifts"}}; } if (@extra_tags) { foreach my $tag (@extra_tags) { if (exists $$residue{"shifts"}{$shift_name}{"extra_tags"} && exists $$residue{"shifts"}{$shift_name}{"extra_tags"}{$tag}) { $shift_line .= " " . $$residue{"shifts"}{$shift_name}{"extra_tags"}{$tag}; } else { $shift_line .= " ."; } } } # add shift line push @$text_lines, $shift_line; } } } } push @$text_lines, ""," stop_"; } elsif ($$section{"type"} eq "ambiguity_loop") { if (exists $$bmrb_hlist{"ambiguity_lists"} && @{$$bmrb_hlist{"ambiguity_lists"}}) { push @$text_lines, " loop_", " _Atom_shift_assign_ID_ambiguity", ""; foreach my $ambiguity_list (@{$$bmrb_hlist{"ambiguity_lists"}}) { my $ambiguity = ""; foreach my $id (@$ambiguity_list) { if ($ambiguity eq "") { $ambiguity = $id; } else { $ambiguity .= "," . $id; } } if ($ambiguity ne "") { push @$text_lines, $ambiguity; } } push @$text_lines, ""," stop_"; } } } return $text_lines; } # create_monomeric_polymer_frame # Returns an array of text_lines given the description of the save_frame and the bmrb hash structure. # # Parameters: # $save_frame - ref to save_frame hash structure. # $bmrb_hlist - ref to bmrb hash structure. # sub create_monomeric_polymer_frame { my $save_frame = shift @_; my $bmrb_hlist = shift @_; my $text_lines = []; foreach my $section (@{$$save_frame{"sections"}}) { if ($$section{"type"} eq "text") { push @$text_lines, (@{$$section{"value"}}); } elsif ($$section{"type"} eq "molecule_type") { if (exists $$bmrb_hlist{"molecule_type"} && ($$bmrb_hlist{"molecule_type"} ne "")) { push @$text_lines, " _Mol_type " . $$bmrb_hlist{"molecule_type"}; } else { push @$text_lines, " _Mol_type ."; } } elsif ($$section{"type"} eq "polymer_class") { if (exists $$bmrb_hlist{"polymer_class"} && ($$bmrb_hlist{"polymer_class"} ne "")) { push @$text_lines, " _Mol_polymer_class " . $$bmrb_hlist{"polymer_class"}; } else { push @$text_lines, " _Mol_polymer_class ."; } } elsif ($$section{"type"} eq "common_name" ) { if (exists $$bmrb_hlist{"common_name"} && ($$bmrb_hlist{"common_name"} ne "")) { if ($$bmrb_hlist{"common_name"} =~ /\s+/) { push @$text_lines, " _Name_common \'" . $$bmrb_hlist{"common_name"} . "\'"; } else { push @$text_lines, " _Name_common " . $$bmrb_hlist{"common_name"}; } } else { push @$text_lines, " _Name_common ."; } } elsif ($$section{"type"} eq "residue_count") { if (exists $$bmrb_hlist{"residue_count"} && ($$bmrb_hlist{"residue_count"} ne "")) { push @$text_lines, " _Residue_count " . $$bmrb_hlist{"residue_count"}; } else { push @$text_lines, " _Residue_count ."; } } elsif ($$section{"type"} eq "sequence") { push @$text_lines, " _Mol_residue_sequence", ";"; if (exists $$bmrb_hlist{"sequence"} && ($$bmrb_hlist{"sequence"} ne "")) { for(my $x=0; $x < length($$bmrb_hlist{"sequence"}); $x += 10) { if (($x + 10) > length($$bmrb_hlist{"sequence"})) { push @$text_lines, substr($$bmrb_hlist{"sequence"}, $x); } else { push @$text_lines, substr($$bmrb_hlist{"sequence"}, $x, 10); } } } else { push @$text_lines, "."; } push @$text_lines, ";"; } elsif ($$section{"type"} eq "sequence_loop") { push @$text_lines, " loop_"; foreach my $tag (@{$$section{"all_tags"}}) { push @$text_lines, " " . $tag; } push @$text_lines, ""; foreach my $residue_name (@{$$bmrb_hlist{"name_array"}}) { my $residue = $$bmrb_hlist{"rlist"}{$residue_name}; my $residue_line = ""; foreach my $tag (@{$$section{"all_tags"}}) { if ($tag eq "_Residue_seq_code") { if (exists $$residue{"index"}) { $residue_line .= " " . $$residue{"index"}; } else { $residue_line .= " ."; } } elsif ($tag eq "_Residue_author_seq_code") { if (exists $$residue{"author_index"}) { $residue_line .= " " . $$residue{"author_index"}; } else { $residue_line .= " ."; } } elsif ($tag eq "_Insertion_code") { if (exists $$residue{"insertion_code"}) { $residue_line .= " " . $$residue{"insertion_code"}; } else { $residue_line .= " ."; } } elsif ($tag eq "_Residue_label") { if (exists $$residue{"aa"}) { $residue_line .= " " . $aa_name_conversion2{uc($$residue{"aa"})}; } else { $residue_line .= " ."; } } elsif ($tag eq "_Segment_definition_code") { if (exists $$residue{"segment_definition_code"}) { $residue_line .= " " . $$residue{"segment_definition_code"}; } else { $residue_line .= " ."; } } else { if (exists $$residue{"extra_tags"} && exists $$residue{"extra_tags"}{$tag}) { $residue_line .= " " . $$residue{"extra_tags"}{$tag}; } else { $residue_line .= " ."; } } } push @$text_lines, $residue_line; } push @$text_lines, ""," stop_"; } } return $text_lines; } # create_spectral_peak_list_frame # Returns an array of text_lines given the description of the save_frame and the bmrb hash structure. # # Parameters: # $save_frame - ref to save_frame hash structure. # $bmrb_hlist - ref to bmrb hash structure. # sub create_spectral_peak_list_frame { my $save_frame = shift @_; my $bmrb_hlist = shift @_; my $dimension_descriptions_tag_converter = {"_Spectral_dim.Spectral_dim_ID" => "dim_id", "_Spectral_dim.Atom_type" => "atom_type", "_Spectral_dim.Spectral_region" => "spectral_region", "_Spectral_dim.Magnetization_linkage_ID" => "magnetization_linkage", "_Spectral_dim.Sweep_width" => "sweep_width", "_Spectral_dim.Encoding_code" => "encoding", "_Spectral_dim.Encoded_source_dimension_ID" => "encoding_dimension"}; my $peak_tag_converter = { "_Peak.Peak_ID" => "index", "_Peak.Intensity_val" => "intensity", "_Peak.Intensity_err" => "intensity_error", "_Peak.Figure_of_merit" => "figure_of_merit", "_Peak.Intensity_measurement_methods_ID" => "measurement_method", "_Peak.Derivation_set_ID" => "derivation_set" }; my $peak_characteristics_tag_converter = { "_Peak_char.Spectral_dimension_ID" => "dim_id", "_Peak_char.Chem_shift_val" => "shift", "_Peak_char.Chem_shift_val_err" => "shift_error", "_Peak_char.Line_width_val" => "width", "_Peak_char.Line_width_val_err" => "width_error", "_Peak_char.Phase_val" => "phase", "_Peak_char.Phase_val_err" => "phase_error", "_Peak_char.Decay_rate_val" => "decay", "_Peak_char.Decay_rate_val_err" => "decay_error", "_Peak_char.Derivation_methods_ID" => "derivation_method" }; my $peak_assignments_tag_converter = { "_Assigned_peak_chem_shift.Set_ID" => "set_id", "_Assigned_peak_chem_shift.Magnetization_linkage_ID" => "magnetization_linkage", "_Assigned_peak_chem_shift.Figure_of_merit" => "figure_of_merit", "_Assigned_peak_chem_shift.List_ID" => "list_id", "_Assigned_peak_chem_shift.List_label" => "list_label", "_Assigned_peak_chem_shift.Atom_chem_shift_ID" => "shift_id" }; my $text_lines = []; foreach my $section (@{$$save_frame{"sections"}}) { if ($$section{"type"} eq "text") { push @$text_lines, (@{$$section{"value"}}); } elsif ($$section{"type"} eq "details") { push @$text_lines, " _Spectral_peak_list.Details", ";"; if (exists $$save_frame{"data"}{"details"} && ($$save_frame{"data"}{"details"} ne "")) { push @$text_lines, @{$$save_frame{"data"}{"details"}}; } push @$text_lines, ";"; } elsif ($$section{"type"} eq "entry_id") { if (exists $$save_frame{"data"}{"entry_id"} && ($$save_frame{"data"}{"entry_id"} ne "")) { push @$text_lines, " _Spectral_peak_list.Entry_ID " . $$save_frame{"data"}{"entry_id"}; } else { push @$text_lines, " _Spectral_peak_list.Entry_ID ."; } } elsif ($$section{"type"} eq "peak_list_id" ) { if (exists $$save_frame{"data"}{"peak_list_id"} && ($$save_frame{"data"}{"peak_list_id"} ne "")) { push @$text_lines, " _Spectral_peak_list.Spectral_peak_list_ID " . $$save_frame{"data"}{"peak_list_id"}; } else { push @$text_lines, " _Spectral_peak_list.Spectral_peak_list_ID ."; } } elsif ($$section{"type"} eq "num_dimensions") { if (exists $$save_frame{"data"}{"num_dimensions"} && ($$save_frame{"data"}{"num_dimensions"} ne "")) { push @$text_lines, " _Spectral_peak_list.Number_of_spectral_dimensions " . $$save_frame{"data"}{"num_dimensions"}; } else { push @$text_lines, " _Spectral_peak_list.Number_of_spectral_dimensions ."; } } elsif ($$section{"type"} eq "experiment_label") { if (exists $$save_frame{"data"}{"experiment_label"} && ($$save_frame{"data"}{"experiment_label"} ne "")) { push @$text_lines, " _Spectral_peak_list.Experiment_label " . $$save_frame{"data"}{"experiment_label"}; } else { push @$text_lines, " _Spectral_peak_list.Experiment_label ."; } } elsif ($$section{"type"} eq "dimension_descriptions") { push @$text_lines, " loop_"; foreach my $tag (@{$$section{"all_tags"}}) { push @$text_lines, " " . $tag; } push @$text_lines, ""; # create direct name-pair hash my $value_hash = {}; if (exists $$save_frame{"data"}{"entry_id"} && ($$save_frame{"data"}{"entry_id"} ne "")) { $$value_hash{"_Spectral_dim.Entry_ID"} = $$save_frame{"data"}{"entry_id"}; } else { $$value_hash{"_Spectral_dim.Entry_ID"} = "."; } if (exists $$save_frame{"data"}{"peak_list_id"} && ($$save_frame{"data"}{"peak_list_id"} ne "")) { $$value_hash{"_Spectral_dim.Spectral_peak_list_ID"} = $$save_frame{"data"}{"peak_list_id"}; } else { $$value_hash{"_Spectral_dim.Spectral_peak_list_ID"} = "."; } foreach my $dim_description (@{$$save_frame{"data"}{"dimension_descriptions"}}) { push @$text_lines, &create_loop_line($$section{"all_tags"},$value_hash,$dimension_descriptions_tag_converter,$dim_description); } push @$text_lines, ""," stop_"; } elsif ($$section{"type"} eq "peaks") { push @$text_lines, " loop_"; foreach my $tag (@{$$section{"all_tags"}}) { push @$text_lines, " " . $tag; } push @$text_lines, ""; # create direct name-pair hash my $value_hash = {}; if (exists $$save_frame{"data"}{"entry_id"} && ($$save_frame{"data"}{"entry_id"} ne "")) { $$value_hash{"_Peak.Entry_ID"} = $$save_frame{"data"}{"entry_id"}; } else { $$value_hash{"_Peak.Entry_ID"} = "."; } if (exists $$save_frame{"data"}{"peak_list_id"} && ($$save_frame{"data"}{"peak_list_id"} ne "")) { $$value_hash{"_Peak.Spectral_peak_list_ID"} = $$save_frame{"data"}{"peak_list_id"}; } else { $$value_hash{"_Peak.Spectral_peak_list_ID"} = "."; } foreach my $peak_index (@{$$save_frame{"data"}{"index_array"}}) { push @$text_lines, &create_loop_line($$section{"all_tags"},$value_hash,$peak_tag_converter,$$save_frame{"data"}{"plist"}{$peak_index}); } push @$text_lines, ""," stop_"; } elsif ($$section{"type"} eq "peak_characteristics") { push @$text_lines, " loop_"; foreach my $tag (@{$$section{"all_tags"}}) { push @$text_lines, " " . $tag; } push @$text_lines, ""; # create direct name-pair hash my $value_hash = {}; if (exists $$save_frame{"data"}{"entry_id"} && ($$save_frame{"data"}{"entry_id"} ne "")) { $$value_hash{"_Peak_char.Entry_ID"} = $$save_frame{"data"}{"entry_id"}; } else { $$value_hash{"_Peak_char.Entry_ID"} = "."; } if (exists $$save_frame{"data"}{"peak_list_id"} && ($$save_frame{"data"}{"peak_list_id"} ne "")) { $$value_hash{"_Peak_char.Spectral_peak_list_ID"} = $$save_frame{"data"}{"peak_list_id"}; } else { $$value_hash{"_Peak_char.Spectral_peak_list_ID"} = "."; } foreach my $peak_index (@{$$save_frame{"data"}{"index_array"}}) { my $peak = $$save_frame{"data"}{"plist"}{$peak_index}; $$value_hash{"_Peak_char.Peak_ID"} = $$peak{"index"}; foreach my $dimension (values %{$$peak{"dimensions"}}) { push @$text_lines, &create_loop_line($$section{"all_tags"},$value_hash,$peak_characteristics_tag_converter,$dimension); } push @$text_lines, "#"; } push @$text_lines, ""," stop_"; } elsif ($$section{"type"} eq "peak_assignments") { push @$text_lines, " loop_"; foreach my $tag (@{$$section{"all_tags"}}) { push @$text_lines, " " . $tag; } push @$text_lines, ""; # create direct name-pair hash my $value_hash = {}; if (exists $$save_frame{"data"}{"entry_id"} && ($$save_frame{"data"}{"entry_id"} ne "")) { $$value_hash{"_Assigned_peak_chem_shift.Entry_ID"} = $$save_frame{"data"}{"entry_id"}; } else { $$value_hash{"_Assigned_peak_chem_shift.Entry_ID"} = "."; } if (exists $$save_frame{"data"}{"peak_list_id"} && ($$save_frame{"data"}{"peak_list_id"} ne "")) { $$value_hash{"_Assigned_peak_chem_shift.Spectral_peak_list_ID"} = $$save_frame{"data"}{"peak_list_id"}; } else { $$value_hash{"_Assigned_peak_chem_shift.Spectral_peak_list_ID"} = "."; } foreach my $peak_index (@{$$save_frame{"data"}{"index_array"}}) { my $peak = $$save_frame{"data"}{"plist"}{$peak_index}; $$value_hash{"_Assigned_peak_chem_shift.Peak_ID"} = $$peak{"index"}; foreach my $dim_id (sort { $a <=> $b; } (keys %{$$peak{"dimensions"}})) { my $dimension = $$peak{"dimensions"}{$dim_id}; $$value_hash{"_Assigned_peak_chem_shift.Spectral_dimension_ID"} = $$dimension{"dim_id"}; foreach my $assignment (@{$$dimension{"assignments"}}) { push @$text_lines, &create_loop_line($$section{"all_tags"},$value_hash,$peak_assignments_tag_converter,$assignment); } } push @$text_lines, "#"; } push @$text_lines, ""," stop_"; } } return $text_lines; } # create_loop_line # Returns new loop line created from list of tags and direct and indirect name-value hashes. # # Parameters: # $tag_list - array of tags in the line. # $value_hash - hash of direct name-value pairs. # $tag_converter - hash converter of tags to usable names. # $indirect_value_hash - hash of indirect name-value pairs. # sub create_loop_line { my $tag_list = shift @_; my $value_hash = shift @_; my $tag_converter = shift @_; my $indirect_value_hash = shift @_; my $line = ""; foreach my $tag (@$tag_list) { if (exists $$value_hash{$tag}) { $line .= " " . $$value_hash{$tag}; } elsif (exists $$tag_converter{$tag}) { if (exists $$indirect_value_hash{$$tag_converter{$tag}} && ($$indirect_value_hash{$$tag_converter{$tag}} ne "")) { $line .= " " . $$indirect_value_hash{$$tag_converter{$tag}}; } else { $line .= " ."; } } elsif (exists $$indirect_value_hash{"extra_tags"} && exists $$indirect_value_hash{"extra_tags"}{$tag} && ($$indirect_value_hash{"extra_tags"}{$tag} ne "")) { $line .= " " . $$indirect_value_hash{"extra_tags"}{$tag}; } else { $line .= " ."; } } return $line; } # create_chemical_shift_reference_frame # Returns an array of text_lines given the description of the save_frame and the bmrb hash structure. # # Parameters: # $save_frame - ref to save_frame hash structure. # $bmrb_hlist - ref to bmrb hash structure. # sub create_chemical_shift_reference_frame { my $save_frame = shift @_; my $bmrb_hlist = shift @_; my $text_lines = []; foreach my $section (@{$$save_frame{"sections"}}) { if ($$section{"type"} eq "text") { push @$text_lines, (@{$$section{"value"}}); } elsif($$section{"type"} eq "reference_loop") { push @$text_lines, " loop_"; foreach my $tag (@{$$bmrb_hlist{"reference_fields"}}) { push @$text_lines, " " . $tag; } push @$text_lines, ""; foreach my $reference (values %{$$bmrb_hlist{"reference"}}) { my $ref_line = ""; foreach my $ref_field (@$reference) { if ($ref_field =~ /\s+/) { $ref_line .= " \'" . $ref_field . "\'"; } else { $ref_line .= " " . $ref_field; } } push @$text_lines, $ref_line; } push @$text_lines, ""," stop_"; } } return $text_lines; } # create_coupling_constants_frame # Returns an array of text_lines given the description of the save_frame and the bmrb hash structure. # # Parameters: # $save_frame - ref to save_frame hash structure. # $bmrb_hlist - ref to bmrb hash structure. # sub create_coupling_constants_frame { my $save_frame = shift @_; my $bmrb_hlist = shift @_; my $text_lines = []; foreach my $section (@{$$save_frame{"sections"}}) { if ($$section{"type"} eq "text") { push @$text_lines, (@{$$section{"value"}}); } elsif($$section{"type"} eq "coupling_constants") { push @$text_lines, " loop_"; foreach my $tag (@{$$section{"all_tags"}}) { push @$text_lines, " " . $tag; } push @$text_lines, ""; foreach my $cc_elem (@{$$save_frame{"data"}{"cclist"}}) { # $dumper->dumpValue($cc_elem); my $cc_line = ""; foreach my $tag (@{$$section{"all_tags"}}) { my $data_tag = (grep {($$coupling_constants_saveframe{$_}{"bmrbFieldName"} eq $tag)} keys %$coupling_constants_saveframe) [0]; if (exists $$cc_elem{$data_tag}) {$cc_line .= " " . $$cc_elem{$data_tag};} else {$cc_line .= " .";} } push @$text_lines, $cc_line; } push @$text_lines, ""," stop_"; } } return $text_lines; } # create_secondary_structure_frame # Returns an array of text_lines given the description of the save_frame and the bmrb hash structure. # # Parameters: # $save_frame - ref to save_frame hash structure. # $bmrb_hlist - ref to bmrb hash structure. # sub create_secondary_structure_frame { my $save_frame = shift @_; my $bmrb_hlist = shift @_; my $text_lines = []; foreach my $section (@{$$save_frame{"sections"}}) { if ($$section{"type"} eq "text") { push @$text_lines, (@{$$section{"value"}}); } elsif($$section{"type"} eq "secondary_structure") { push @$text_lines, " loop_"; foreach my $tag (@{$$section{"all_tags"}}) { push @$text_lines, " " . $tag; } push @$text_lines, ""; foreach my $ss_elem (@{$$save_frame{"data"}{"sslist"}}) { my $ss_line = ""; foreach my $tag (@{$$section{"all_tags"}}) { my $data_tag = (grep {($$secondary_structure_saveframe{$_}{"bmrbFieldName"} eq $tag);} keys %$secondary_structure_saveframe) [0]; if (exists $$ss_elem{$data_tag}) {$ss_line .= " " . $$ss_elem{$data_tag};} else {$ss_line .= " .";} } push @$text_lines, $ss_line; } push @$text_lines, ""," stop_"; } } return $text_lines; } # module must return true return 1;