File: smi_canonicalise

package info (click to toggle)
smiles-scripts 0.3.0%2Bsvn878%2Bbranch%2Bsystem%2Bdeps-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 3,860 kB
  • sloc: perl: 1,889; java: 1,218; sh: 1,092; makefile: 246
file content (280 lines) | stat: -rwxr-xr-x 9,559 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
#!/usr/bin/perl

use strict;
use warnings;

use Chemistry::OpenSMILES qw(
    is_cis_trans_bond
    is_double_bond
    is_single_bond
    valence
);
use Chemistry::OpenSMILES::Aromaticity qw( aromatise kekulise );
use Chemistry::OpenSMILES::Parser;
use Chemistry::OpenSMILES::Stereo qw(
    chirality_to_pseudograph
    cis_trans_to_pseudoedges
    mark_all_double_bonds
);
use Chemistry::OpenSMILES::Writer qw( write_SMILES );
use File::Basename qw( basename );
use Getopt::Long::Descriptive;
use Graph::Nauty qw( canonical_order );
use List::Util qw( any first shuffle );

$Graph::Nauty::worksize = 25600;

my $basename = basename $0;
my( $opt, $usage ) = describe_options( <<"END" . 'OPTIONS',
USAGE
    $basename [<args>] [<files>]

DESCRIPTION
    $basename reads in files with SMILES descriptors and outputs them
    according to stable atom ordering established by Graph::Nauty.
    Moieties, if more than one, are ordered in lexicographic order.

END
    [ raw => hidden => {
        one_of => [
            [ 'infer-hydrogens' =>
                'infer hydrogen atom counts according to valency rules [default]' ],
            [ 'no-infer-hydrogens' =>
                'do not infer hydrogen atom counts' ]
        ],
        default => 'infer_hydrogens'
      }
    ],
    [],
    [ aroma => hidden => {
        one_of => [
            [ 'aromatise' => 'aromatise Kekule structures ' .
                             '(experimental)' ],
            [ 'no-aromatise' => 'do not attempt to aromatise [default]' ]
        ],
        default => 'no-aromatise'
      }
    ],
    [ kekul => hidden => {
        one_of => [
            [ 'kekulise' => 'kekulise simple aromatic structures ' .
                            '(experimental)' ],
            [ 'no-kekulise' => 'do not attempt to kekulise [default]' ]
        ],
        default => 'no-kekulise'
      }
    ],
    [],
    [ haloanions => hidden => {
        one_of => [
            [ 'canonicalise-haloanions'    => 'canonicalise the representation of haloanions [default]' ],
            [ 'no-canonicalise-haloanions' => 'retain input representation of haloanions' ],
        ],
        default => 'canonicalise_haloanions'
      }
    ],
    [ nitro_groups => hidden => {
        one_of => [
            [ 'canonicalise-nitro-groups', 'canonicalise the representation of nitro groups by converting them from *-[N+]([O-])=O to *-N(=O)=O' ],
            [ 'no-canonicalise-nitro-groups', 'retain input representation of nitro groups [default]' ],
        ],
        default => 'no_canonicalise_nitro_groups'
      }
    ],
    [],
    [ 'ignore-class',
      'ignore SMILES atom class in canonicalisation (useful for testing)' ],
    [ 'random-order',
      'instead of canonical, output SMILES in random order (useful for testing)' ],
    [],
    [ 'help', 'print usage message and exit', { shortcircuit => 1 } ],
);

if( $opt->help ) {
    print $usage->text;
    exit;
}

my $errors = 0;
while (<>) {
    chomp;
    my $additional_position = '';
    if( s/\t([^\t]*)$// ) {
        $additional_position = ' ' . $1;
    }

    local $SIG{__WARN__} = sub {
        print STDERR "$basename: $ARGV($.)$additional_position: $_[0]";
    };

    my $parser = Chemistry::OpenSMILES::Parser->new;
    my @moieties;
    eval {
        @moieties = $parser->parse( $_, { raw => $opt->raw eq 'no_infer_hydrogens' } );
    };
    if( $@ ) {
        $@ =~ s/^[^:]+:\s*// if !index( $@, $0 );
        print STDERR "$basename: $ARGV($.)$additional_position: $@";
        $errors++;
    }

    my @smiles_parts;
    for my $moiety (@moieties) {
        aromatise( $moiety ) if $opt->aroma eq 'aromatise';
        canonicalise_haloanions( $moiety )
                    if $opt->haloanions eq 'canonicalise_haloanions';
        canonicalise_nitro_groups( $moiety )
                    if $opt->nitro_groups eq 'canonicalise_nitro_groups';

        my @order;
        if( !$opt->random_order ) {
            # copy() makes a shallow copy without edge attributes, thus they
            # have to be added later:
            my $copy = $moiety->copy;
            for my $bond ($moiety->edges) {
                next unless $moiety->has_edge_attribute( @$bond, 'bond' );
                $copy->set_edge_attribute( @$bond,
                                           'bond',
                                           $moiety->get_edge_attribute( @$bond, 'bond' ) );
            }
            cis_trans_to_pseudoedges( $copy );
            chirality_to_pseudograph( $copy );

            @order = canonical_order( $copy, \&represent_vertex );
            my %order;
            for (0..$#order) {
                $order{$order[$_]} = $_;
            }

            # Collect cis/trans bonds for marking them up
            my @cis_trans_bonds;
            for my $bond ($moiety->edges) {
                next unless is_double_bond( $moiety, @$bond );

                my $subgraph = $copy->subgraph( [ $moiety->neighbours( $bond->[0] ),
                                                  $moiety->neighbours( $bond->[1] ) ] );
                my $cis_trans_bond = first { $copy->has_edge_attribute( @$_, 'pseudo' ) }
                                           $subgraph->edges;
                next unless $cis_trans_bond;

                @$cis_trans_bond = reverse @$cis_trans_bond unless $subgraph->has_edge( $bond->[0], $cis_trans_bond->[0] );
                push @cis_trans_bonds, [ $cis_trans_bond->[0],
                                         $bond->[0],
                                         $bond->[1],
                                         $cis_trans_bond->[1],
                                         $copy->get_edge_attribute( @$cis_trans_bond, 'pseudo' ) ];
            }

            # Drop cis/trans markers from the input graph and mark them
            # anew.
            for my $bond ($moiety->edges) {
                next unless is_cis_trans_bond( $moiety, @$bond );
                $moiety->delete_edge_attribute( @$bond, 'bond' );
            }
            mark_all_double_bonds( $moiety,
                                   \@cis_trans_bonds,
                                   sub { $order{$_[0]} } );
        } else {
            @order = shuffle $moiety->vertices;
        }
        my %order;
        for (0..$#order) {
            $order{$order[$_]} = $_;
        }

        kekulise( $moiety, sub { $order{$_[0]} } ) if $opt->kekul eq 'kekulise';

        eval {
            my $part =
                 write_SMILES( $moiety,
                               {
                                    order_sub =>
                                        sub {
                                            my @sorted = sort { $order{$a} <=> $order{$b} }
                                                              keys %{$_[0]};
                                            return $_[0]->{shift @sorted};
                                        },
                                    raw => $opt->raw eq 'no_infer_hydrogens',
                               } );

            # In a SMILES descriptor, one can substitute all '/' with '\'
            # and vice versa, retaining correct cis/trans settings.
            # Similar rule is explained in O'Boyle (2012), Rule H.
            if( $part =~ /([\/\\])/ && $1 eq '\\' ) {
                $part =~ tr/\/\\/\\\//;
            }
            push @smiles_parts, $part;
        };
        if( $@ ) {
            print STDERR "$basename: $ARGV($.)$additional_position: $@";
            $errors++;
        }
    }

    $additional_position =~ s/^ /\t/;
    print join( '.', sort @smiles_parts ), $additional_position, "\n";
}

exit( $errors > 0 );

sub represent_vertex
{
    my( $vertex ) = @_;

    return '' unless %$vertex;

    my %atom = %$vertex;
    delete $atom{chirality};
    delete $atom{class} if $opt->ignore_class;
    return write_SMILES( \%atom );
}

# See https://projects.ibt.lt/repositories/issues/1622 for rationale and algorithm
sub canonicalise_haloanions
{
    my( $moiety ) = @_;

    return if ( $moiety->vertices < 5 || $moiety->vertices > 7 );

    my @anions = grep  { $moiety->degree($_) == 1 } $moiety->vertices;
    my $center = first { $moiety->degree($_)  > 3 } $moiety->vertices;

    return unless $center;
    return unless @anions == $moiety->vertices - 1;
    return unless $center->{symbol} =~ /^(As|Se|Si|[BPS])$/;
    return if any { $_->{symbol} !~ /^(At|Br|Cl|[FI])$/ } @anions;

    return unless any { $_->{charge} } @anions;
    return if any { $_->{charge} && $_->{charge} > 0 } @anions;

    for (@anions) {
        next unless exists $_->{charge};
        $center->{charge} += $_->{charge};
        delete $_->{charge};
    }
}

sub canonicalise_nitro_groups
{
    my( $moiety ) = @_;

    my @N = grep { $_->{symbol} eq 'N' &&
                   $_->{charge} &&
                   $_->{charge} == 1 &&
                   $moiety->degree( $_  ) == 3 &&
                   valence( $moiety, $_ ) == 4 } $moiety->vertices;
    for my $N (@N) {
        my @O = grep { $_->{symbol} eq 'O' && $moiety->degree( $_ ) == 1 }
                     $moiety->neighbours( $N );
        next unless @O >= 2;
        my $ketone = first { is_double_bond( $moiety, $N, $_ ) } @O;
        my $O      = first { is_single_bond( $moiety, $N, $_ ) &&
                             $_->{charge} &&
                             $_->{charge} == -1 } @O;
        next unless $ketone && $O;

        delete $N->{charge};
        delete $O->{charge};
        $moiety->set_edge_attribute( $N, $O, 'bond', '=' );
    }
}