Chem-Structure-Parser
view release on metacpan or search on metacpan
t/data/generate.pl view on Meta::CPAN
cols(1,6,'SEQRES', 8,3,1,'R', 12,1,'B', 14,4,4,'R',
20,51,join('', map { sprintf('%3s ', $_) } qw(DA DC DG DT))),
# MODRES: idCode 8-11, resName 13-15, chain 17, seqNum 19-22,
# stdRes 25-27, comment 30-70
cols(1,6,'MODRES', 8,4,'9XYZ', 13,3,'MSE', 17,1,'A', 19,4,7,'R',
25,3,'MET', 30,41,'SELENOMETHIONINE'),
# HET: hetID 8-10, chain 13, seqNum 14-17, iCode 18, numHetAtoms 21-25
cols(1,6,'HET', 8,3,'NAG','R', 13,1,'A', 14,4,201,'R', 21,5,14,'R'),
cols(1,6,'HET', 8,3,'ZN', 'R', 13,1,'A', 14,4,202,'R', 21,5,1, 'R'),
# HETNAM: continuation 9-10, hetID 12-14, text 16-70
cols(1,6,'HETNAM', 12,3,'NAG','R', 16,55,'2-ACETAMIDO-2-DEOXY-BETA-D-GLUCOPYRANOSE'),
cols(1,6,'HETNAM', 12,3,'ZN', 'R', 16,55,'ZINC ION'),
# FORMUL: compNum 9-10, hetID 13-15, continuation 17-18, asterisk 19, text 20-70
cols(1,6,'FORMUL', 9,2,3,'R', 13,3,'NAG','R', 20,51,'C8 H15 N O6'),
cols(1,6,'FORMUL', 9,2,4,'R', 13,3,'ZN', 'R', 20,51,'ZN 2+'),
cols(1,6,'FORMUL', 9,2,5,'R', 13,3,'HOH','R', 19,1,'*', 20,51,'2(H2 O)'),
# HELIX: serNum 8-10, helixID 12-14, initResName 16-18, initChain 20,
# initSeqNum 22-25, endResName 28-30, endChain 32, endSeqNum 34-37,
# helixClass 39-40, length 72-76
cols(1,6,'HELIX', 8,3,1,'R', 12,3,'AA1', 16,3,'MET', 20,1,'A', 22,4,1,'R',
28,3,'GLY', 32,1,'A', 34,4,3,'R', 39,2,1,'R', 72,5,3,'R'),
t/data/generate.pl view on Meta::CPAN
cif_loop('citation_author', [qw(citation_id name ordinal)],
[ 'primary', 'Condon, D.E.', 1 ], [ 'primary', 'Other, A.N.', 2 ]), '#',
cif_pairs('cell', entry_id => '9XYZ',
length_a => '40.100', length_b => '50.200', length_c => '60.300',
angle_alpha => '90.00', angle_beta => '95.50', angle_gamma => '90.00',
'Z_PDB' => 4), '#',
cif_pairs('symmetry', entry_id => '9XYZ', 'space_group_name_H-M' => 'P 1 21 1'), '#',
cif_loop('entity', [qw(id type src_method pdbx_description pdbx_ec pdbx_fragment)],
[ 1, 'polymer', 'man', 'TEST PROTEIN', '3.4.21.5', 'CATALYTIC DOMAIN' ],
[ 2, 'polymer', 'syn', 'TEST DNA', undef, undef ],
[ 3, 'non-polymer', 'syn', '2-ACETAMIDO-2-DEOXY-BETA-D-GLUCOPYRANOSE', undef, undef ],
[ 4, 'non-polymer', 'syn', 'ZINC ION', undef, undef ],
[ 5, 'water', 'nat', 'water', undef, undef ]), '#',
cif_loop('entity_poly', [qw(entity_id type pdbx_seq_one_letter_code_can pdbx_strand_id)],
[ 1, 'polypeptide(L)', 'MAGLKCMHHSC', 'A' ],
[ 2, 'polydeoxyribonucleotide', 'ACGT', 'B' ]), '#',
cif_loop('entity_poly_seq', [qw(entity_id num mon_id hetero)],
(map { [ 1, $_->[0], $_->[1], 'n' ] }
map { [ $_ + 1, (qw(MET ALA GLY LEU LYS CYS MSE HIS HIS SER CYS))[$_] ] } 0 .. 10),
(map { [ 2, $_->[0], $_->[1], 'n' ] }
map { [ $_ + 1, (qw(DA DC DG DT))[$_] ] } 0 .. 3)), '#',
t/data/generate.pl view on Meta::CPAN
entity_id => 1,
pdbx_gene_src_scientific_name => 'HOMO SAPIENS',
pdbx_gene_src_ncbi_taxonomy_id => 9606,
pdbx_host_org_scientific_name => 'ESCHERICHIA COLI'), '#',
cif_pairs('pdbx_entity_src_syn',
entity_id => 2,
organism_scientific => 'SYNTHETIC CONSTRUCT',
ncbi_taxonomy_id => 32630), '#',
cif_loop('chem_comp', [qw(id name formula type)],
[ 'MSE', 'SELENOMETHIONINE', 'C5 H11 N O2 Se', 'L-peptide linking' ],
[ 'NAG', '2-ACETAMIDO-2-DEOXY-BETA-D-GLUCOPYRANOSE', 'C8 H15 N O6', 'D-saccharide' ],
[ 'ZN', 'ZINC ION', 'ZN 2+', 'non-polymer' ],
[ 'HOH', 'WATER', 'H2 O', 'water' ]), '#',
cif_loop('pdbx_nonpoly_scheme',
[qw(asym_id entity_id mon_id pdb_strand_id pdb_seq_num pdb_ins_code)],
[ 'C', 3, 'NAG', 'A', 201, '.' ],
[ 'D', 4, 'ZN', 'A', 202, '.' ],
[ 'E', 5, 'HOH', 'A', 301, '.' ],
[ 'E', 5, 'HOH', 'A', 302, '.' ]), '#',
cif_loop('pdbx_struct_mod_residue',
[qw(id label_comp_id auth_comp_id auth_asym_id auth_seq_id parent_comp_id details)],
t/data/mini.cif view on Meta::CPAN
#
loop_
_entity.id
_entity.type
_entity.src_method
_entity.pdbx_description
_entity.pdbx_ec
_entity.pdbx_fragment
1 polymer man 'TEST PROTEIN' 3.4.21.5 'CATALYTIC DOMAIN'
2 polymer syn 'TEST DNA' ? ?
3 non-polymer syn 2-ACETAMIDO-2-DEOXY-BETA-D-GLUCOPYRANOSE ? ?
4 non-polymer syn 'ZINC ION' ? ?
5 water nat water ? ?
#
loop_
_entity_poly.entity_id
_entity_poly.type
_entity_poly.pdbx_seq_one_letter_code_can
_entity_poly.pdbx_strand_id
1 polypeptide(L) MAGLKCMHHSC A
2 polydeoxyribonucleotide ACGT B
t/data/mini.cif view on Meta::CPAN
_pdbx_entity_src_syn.entity_id 2
_pdbx_entity_src_syn.organism_scientific 'SYNTHETIC CONSTRUCT'
_pdbx_entity_src_syn.ncbi_taxonomy_id 32630
#
loop_
_chem_comp.id
_chem_comp.name
_chem_comp.formula
_chem_comp.type
MSE SELENOMETHIONINE 'C5 H11 N O2 Se' 'L-peptide linking'
NAG 2-ACETAMIDO-2-DEOXY-BETA-D-GLUCOPYRANOSE 'C8 H15 N O6' D-saccharide
ZN 'ZINC ION' 'ZN 2+' non-polymer
HOH WATER 'H2 O' water
#
loop_
_pdbx_nonpoly_scheme.asym_id
_pdbx_nonpoly_scheme.entity_id
_pdbx_nonpoly_scheme.mon_id
_pdbx_nonpoly_scheme.pdb_strand_id
_pdbx_nonpoly_scheme.pdb_seq_num
_pdbx_nonpoly_scheme.pdb_ins_code
t/data/mini.pdb view on Meta::CPAN
REMARK 465 MISSING RESIDUES
DBREF 9XYZ A 1 11 UNP P12345 TEST_HUMAN 1 11
DBREF1 9XYZ B 1 4 GB TEST_SEQUENCE_LONG
DBREF2 9XYZ B AB0123456789 101 104
SEQADV 9XYZ MSE A 7 UNP P12345 MET 7 MODIFIED RESIDUE
SEQRES 1 A 11 MET ALA GLY LEU LYS CYS MSE HIS HIS SER CYS
SEQRES 1 B 4 DA DC DG DT
MODRES 9XYZ MSE A 7 MET SELENOMETHIONINE
HET NAG A 201 14
HET ZN A 202 1
HETNAM NAG 2-ACETAMIDO-2-DEOXY-BETA-D-GLUCOPYRANOSE
HETNAM ZN ZINC ION
FORMUL 3 NAG C8 H15 N O6
FORMUL 4 ZN ZN 2+
FORMUL 5 HOH *2(H2 O)
HELIX 1 AA1 MET A 1 GLY A 3 1 3
SHEET 1 AA1 2 CYS A 6 HIS A 8 0
SHEET 2 AA1 2 SER A 9 CYS A 10 -1
SSBOND 1 CYS A 6 CYS A 10 1555 1555 2.03
LINK ZN ZN A 202 SG CYS A 6 2.31
CISPEP 1 GLY A 3 CYS A 6 0 -0.42
db_begin => '101', db_end => '104',
} ], 'DBREF1/DBREF2: a reference too long for DBREF is read off the pair');
is($i->{seqadv}[0]{resname}, 'MSE', 'SEQADV: the residue that differs');
is($i->{seqadv}[0]{database}, 'UNP', 'SEQADV: the database it differs from');
is($i->{seqadv}[0]{comment}, 'MODIFIED RESIDUE', 'SEQADV: why');
is($i->{modres}{MSE}{standard}, 'MET', 'MODRES: what the modified residue stands for');
#--------
# heterogens
#--------
is($i->{het}{NAG}{name}, '2-ACETAMIDO-2-DEOXY-BETA-D-GLUCOPYRANOSE', 'HETNAM');
is($i->{het}{NAG}{formula}, 'C8 H15 N O6', 'FORMUL');
is($i->{het}{NAG}{instances}[0]{chain}, 'A', 'HET: which chain the heterogen is in');
is($i->{het}{NAG}{instances}[0]{natoms}, '14', 'HET: how many atoms it should have');
is($i->{het}{ZN}{name}, 'ZINC ION', 'HETNAM for a two-letter het id');
is($i->{het}{HOH}{water}, 1, 'FORMUL: the asterisk marks the water');
#--------
# secondary structure and bonds
#--------
is($i->{helix}[0]{init_resname}, 'MET', 'HELIX: first residue');
( run in 0.915 second using v1.01-cache-2.11-cpan-1bcd28dbaf1 )