bpforms/alphabet/protein.canonical.yml
id: canonical_protein
name: Canonical protein amino acids
description: The canonical protein amino acids
monomers:
A:
id: Ala
name: L-alanine
synonyms:
- 3-phenyl-L-alanine
- (S)-2-Amino-3-phenylpropionic acid
- (S)-alpha-Amino-beta-phenylpropionic acid
- β-phenyl-L-alanine
identifiers:
- ns: chebi
id: CHEBI:16977
- ns: pubchem.compound
id: '5950'
- ns: resid
id: AA0001
- ns: metacyc.compound
id: L-ALPHA-ALANINE
structure: C[C@H]([NH3+])C(=O)O
l_bond_atoms:
- molecule: Monomer
element: N
position: 4
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 4
charge: 1
- molecule: Monomer
element: H
position: 4
r_bond_atoms:
- molecule: Monomer
element: C
position: 8
r_displaced_atoms:
- molecule: Monomer
element: O
position: 10
- molecule: Monomer
element: H
position: 10
R:
id: Arg
name: L-arginine
synonyms:
- 3-phenyl-L-alanine
- (S)-2-Amino-3-phenylpropionic acid
- (S)-alpha-Amino-beta-phenylpropionic acid
- β-phenyl-L-alanine
identifiers:
- ns: pubchem.compound
id: '6322'
- ns: resid
id: AA0002
- ns: chebi
id: CHEBI:16467
- ns: metacyc.compound
id: ARG
structure: OC(=O)[C@H](CCCNC(=[NH2+])N)[NH3+]
l_bond_atoms:
- molecule: Monomer
element: N
position: 15
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 15
charge: 1
- molecule: Monomer
element: H
position: 15
r_bond_atoms:
- molecule: Monomer
element: C
position: 2
r_displaced_atoms:
- molecule: Monomer
element: O
position: 1
- molecule: Monomer
element: H
position: 1
N:
id: Asn
name: L-asparagine
synonyms:
- (S)-Asparagine
- L-aspartic acid beta-amide
- (S)-2-amino-3-carbamoylpropanoic acid
- (2S)-2-amino-3-carbamoylpropanoic acid
- 2-Aminosuccinamic acid
- (2S)-2,4-diamino-4-oxobutanoic acid
- L-Asparagine
- Aspartamic acid
- L-Asparagin
- L-2-aminosuccinamic acid
- alpha-aminosuccinamic acid
identifiers:
- ns: metacyc.compound
id: ASN
- ns: resid
id: AA0003
- ns: pubchem.compound
id: '6267'
- ns: chebi
id: CHEBI:17196
structure: NC(=O)C[C@@H](C(=O)O)[NH3+]
l_bond_atoms:
- molecule: Monomer
element: N
position: 10
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 10
charge: 1
- molecule: Monomer
element: H
position: 10
r_bond_atoms:
- molecule: Monomer
element: C
position: 7
r_displaced_atoms:
- molecule: Monomer
element: O
position: 9
- molecule: Monomer
element: H
position: 9
D:
id: Asp
name: L-aspartic acid
synonyms:
- (S)-2-aminosuccinic acid
- (S)-2-aminobutanedioic acid
- 2-Aminosuccinic acid
- L-Asparaginsaeure
identifiers:
- ns: chebi
id: CHEBI:17053
- ns: resid
id: AA0004
- ns: pubchem.compound
id: '5960'
- ns: metacyc.compound
id: ASP
structure: '[O-]C(=O)C[C@@H](C(=O)O)[NH3+]'
l_bond_atoms:
- molecule: Monomer
element: N
position: 10
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 10
charge: 1
- molecule: Monomer
element: H
position: 10
r_bond_atoms:
- molecule: Monomer
element: C
position: 7
r_displaced_atoms:
- molecule: Monomer
element: O
position: 9
- molecule: Monomer
element: H
position: 9
C:
id: Cys
name: L-cysteine
synonyms:
- E920
- E 920
- L-2-Amino-3-mercaptopropionic acid
- (2R)-2-amino-3-sulfanylpropanoic acid
- E-920
- (2R)-2-amino-3-mercaptopropanoic acid
- L-Zystein
- (R)-2-amino-3-mercaptopropanoic acid
identifiers:
- ns: chebi
id: CHEBI:17561
- ns: pubchem.compound
id: '5862'
- ns: resid
id: AA0005
- ns: metacyc.compound
id: CYS
structure: OC(=O)[C@@H]([NH3+])CS
l_bond_atoms:
- molecule: Monomer
element: N
position: 6
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 6
charge: 1
- molecule: Monomer
element: H
position: 6
r_bond_atoms:
- molecule: Monomer
element: C
position: 2
r_displaced_atoms:
- molecule: Monomer
element: O
position: 1
- molecule: Monomer
element: H
position: 1
Q:
id: Gln
name: L-glutamine
synonyms:
- L-Glutaminsaeure-5-amid
- L-(+)-glutamine
- L-2-Aminoglutaramic acid
- Glutamic acid amide
- (S)-2,5-diamino-5-oxopentanoic acid
- (2S)-2-amino-4-carbamoylbutanoic acid
- L-glutamic acid gamma-amide
- Levoglutamide
- (2S)-2,5-diamino-5-oxopentanoic acid
- L-2-aminoglutaramic acid
- Glutamic acid 5-amide
identifiers:
- ns: metacyc.compound
id: GLN
- ns: chebi
id: CHEBI:18050
- ns: resid
id: AA0007
- ns: pubchem.compound
id: '5961'
structure: NC(=O)CC[C@@H](C(=O)O)[NH3+]
l_bond_atoms:
- molecule: Monomer
element: N
position: 11
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 11
charge: 1
- molecule: Monomer
element: H
position: 11
r_bond_atoms:
- molecule: Monomer
element: C
position: 8
r_displaced_atoms:
- molecule: Monomer
element: O
position: 10
- molecule: Monomer
element: H
position: 10
E:
id: Glu
name: L-glutamic acid
synonyms:
- L-Glutaminsaeure
- (S)-2-aminopentanedioic acid
- Glutamate
- (S)-glutamic acid
- L-Glutaminic acid
identifiers:
- ns: resid
id: AA0006
- ns: chebi
id: CHEBI:16015
- ns: metacyc.compound
id: GLU
- ns: pubchem.compound
id: '33032'
structure: '[O-]C(=O)CC[C@@H](C(=O)O)[NH3+]'
l_bond_atoms:
- molecule: Monomer
element: N
position: 11
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 11
charge: 1
- molecule: Monomer
element: H
position: 11
r_bond_atoms:
- molecule: Monomer
element: C
position: 8
r_displaced_atoms:
- molecule: Monomer
element: O
position: 10
- molecule: Monomer
element: H
position: 10
G:
id: Gly
name: glycine
synonyms:
- Aminoacetic acid
- aminoethanoic acid
identifiers:
- ns: pubchem.compound
id: '750'
- ns: metacyc.compound
id: GLY
- ns: chebi
id: CHEBI:15428
- ns: resid
id: AA0008
structure: OC(=O)C[NH3+]
l_bond_atoms:
- molecule: Monomer
element: N
position: 5
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 5
charge: 1
- molecule: Monomer
element: H
position: 5
r_bond_atoms:
- molecule: Monomer
element: C
position: 2
r_displaced_atoms:
- molecule: Monomer
element: O
position: 1
- molecule: Monomer
element: H
position: 1
H:
id: His
name: L-histidine
synonyms:
- (S)-4-(2-Amino-2-carboxyethyl)imidazole
- (S)-alpha-amino-1H-Imidazole-4-propanoic acid
- L-(-)-histidine
- (S)-alpha-Amino-1H-imidazole-4-propionic acid
identifiers:
- ns: resid
id: AA0009
- ns: metacyc.compound
id: HIS
- ns: pubchem.compound
id: '33032'
- ns: chebi
id: CHEBI:15971
structure: OC(=O)[C@@H]([NH3+])Cc1c[nH]cn1
l_bond_atoms:
- molecule: Monomer
element: N
position: 6
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 6
charge: 1
- molecule: Monomer
element: H
position: 6
r_bond_atoms:
- molecule: Monomer
element: C
position: 2
r_displaced_atoms:
- molecule: Monomer
element: O
position: 1
- molecule: Monomer
element: H
position: 1
I:
id: Ile
name: L-isoleucine
synonyms:
- (2S,3S)-2-amino-3-methylpentanoic acid
- alpha-amino-beta-methylvaleric acid
- 2-Amino-3-methylvaleric acid
identifiers:
- ns: resid
id: AA0010
- ns: metacyc.compound
id: ILE
- ns: chebi
id: CHEBI:17191
- ns: pubchem.compound
id: '6306'
structure: CC[C@@H]([C@@H](C(=O)O)[NH3+])C
l_bond_atoms:
- molecule: Monomer
element: N
position: 10
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 10
charge: 1
- molecule: Monomer
element: H
position: 10
r_bond_atoms:
- molecule: Monomer
element: C
position: 7
r_displaced_atoms:
- molecule: Monomer
element: O
position: 9
- molecule: Monomer
element: H
position: 9
L:
id: Leu
name: L-leucine
synonyms:
- (S)-leucine
- 2-Amino-4-methylvaleric acid
- (2S)-2-amino-4-methylpentanoic acid
- (2S)-alpha-Leucine
- (S)-(+)-leucine
- (2S)-alpha-2-Amino-4-methylvaleric acid
identifiers:
- ns: resid
id: AA0011
- ns: pubchem.compound
id: '6106'
- ns: chebi
id: CHEBI:15603
- ns: metacyc.compound
id: LEU
structure: '[NH3+][C@H](C(=O)O)CC(C)C'
l_bond_atoms:
- molecule: Monomer
element: N
position: 1
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 1
charge: 1
- molecule: Monomer
element: H
position: 1
r_bond_atoms:
- molecule: Monomer
element: C
position: 7
r_displaced_atoms:
- molecule: Monomer
element: O
position: 9
- molecule: Monomer
element: H
position: 9
K:
id: Lys
name: L-lysine
identifiers:
- ns: chebi
id: CHEBI:18019
- ns: pubchem.compound
id: '5962'
- ns: resid
id: AA0012
- ns: metacyc.compound
id: LYS
structure: '[NH3+]CCCC[C@@H](C(=O)O)[NH3+]'
l_bond_atoms:
- molecule: Monomer
element: N
position: 14
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 14
charge: 1
- molecule: Monomer
element: H
position: 14
r_bond_atoms:
- molecule: Monomer
element: C
position: 11
r_displaced_atoms:
- molecule: Monomer
element: O
position: 13
- molecule: Monomer
element: H
position: 13
M:
id: Met
name: L-methionine
synonyms:
- (2S)-2-amino-4-(methylsulfanyl)butanoic acid
- (S)-2-amino-4-(methylthio)butanoic acid
- (S)-methionine
- L-alpha-amino-gamma-methylmercaptobutyric acid
- L-(-)-methionine
- (S)-2-amino-4-(methylthio)butyric acid
identifiers:
- ns: metacyc.compound
id: MET
- ns: chebi
id: CHEBI:16643
- ns: pubchem.compound
id: '6137'
- ns: resid
id: AA0013
structure: CSCC[C@H]([NH3+])C(=O)O
l_bond_atoms:
- molecule: Monomer
element: N
position: 7
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 7
charge: 1
- molecule: Monomer
element: H
position: 7
r_bond_atoms:
- molecule: Monomer
element: C
position: 11
r_displaced_atoms:
- molecule: Monomer
element: O
position: 13
- molecule: Monomer
element: H
position: 13
F:
id: Phe
name: L-phenylalanine
synonyms:
- 3-phenyl-L-alanine
- (S)-2-Amino-3-phenylpropionic acid
- (S)-alpha-Amino-beta-phenylpropionic acid
- β-phenyl-L-alanine
identifiers:
- ns: pubchem.compound
id: '22848660'
- ns: metacyc.compound
id: PHE
- ns: resid
id: AA0014
- ns: chebi
id: CHEBI:17295
structure: '[NH3+][C@H](C(=O)O)Cc1ccccc1'
l_bond_atoms:
- molecule: Monomer
element: N
position: 1
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 1
charge: 1
- molecule: Monomer
element: H
position: 1
r_bond_atoms:
- molecule: Monomer
element: C
position: 7
r_displaced_atoms:
- molecule: Monomer
element: O
position: 9
- molecule: Monomer
element: H
position: 9
P:
id: Pro
name: L-proline
synonyms:
- L-(-)-proline
- (2S)-pyrrolidine-2-carboxylic acid
- 2-Pyrrolidinecarboxylic acid
- (-)-proline
- L-pyrrolidine-2-carboxylic acid
- (S)-2-carboxypyrrolidine
- (S)-pyrrolidine-2-carboxylic acid
- (S)-2-pyrrolidinecarboxylic acid
- (-)-2-pyrrolidinecarboxylic acid
- L-alpha-pyrrolidinecarboxylic acid
- (-)-(S)-proline
identifiers:
- ns: pubchem.compound
id: '145742'
- ns: resid
id: AA0015
- ns: metacyc.compound
id: PRO
- ns: chebi
id: CHEBI:17203
structure: OC(=O)[C@@H]1CCC[NH2+]1
l_bond_atoms:
- molecule: Monomer
element: N
position: 9
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 9
charge: 1
- molecule: Monomer
element: H
position: 9
r_bond_atoms:
- molecule: Monomer
element: C
position: 2
r_displaced_atoms:
- molecule: Monomer
element: O
position: 1
- molecule: Monomer
element: H
position: 1
S:
id: Ser
name: L-serine
synonyms:
- (S)-serine
- beta-Hydroxy-L-alanine
- (S)-alpha-Amino-beta-hydroxypropionic acid
- L-2-Amino-3-hydroxypropionic acid
- L-3-Hydroxy-alanine
- (S)-(-)-serine
- (2S)-2-amino-3-hydroxypropanoic acid
- L-3-Hydroxy-2-aminopropionic acid
- (S)-2-amino-3-hydroxypropanoic acid
- L-(-)-serine; beta-Hydroxyalanine
identifiers:
- ns: resid
id: AA0016
- ns: metacyc.compound
id: SER
- ns: chebi
id: CHEBI:17115
- ns: pubchem.compound
id: '5951'
structure: OC[C@@H](C(=O)O)[NH3+]
l_bond_atoms:
- molecule: Monomer
element: N
position: 8
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 8
charge: 1
- molecule: Monomer
element: H
position: 8
r_bond_atoms:
- molecule: Monomer
element: C
position: 5
r_displaced_atoms:
- molecule: Monomer
element: O
position: 7
- molecule: Monomer
element: H
position: 7
T:
id: Thr
name: L-threonine
synonyms:
- 2-Amino-3-hydroxybutyric acid
- (2S,3R)-2-amino-3-hydroxybutanoic acid
- L-alpha-amino-beta-hydroxybutyric acid
- (2S)-threonine
- (2S,3R)-(-)-Threonine
- L-2-Amino-3-hydroxybutyric acid
- L-(-)-Threonine
identifiers:
- ns: resid
id: AA0017
- ns: metacyc.compound
id: THR
- ns: chebi
id: CHEBI:16857
- ns: pubchem.compound
id: '6288'
structure: C[C@H]([C@@H](C(=O)O)[NH3+])O
l_bond_atoms:
- molecule: Monomer
element: N
position: 9
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 9
charge: 1
- molecule: Monomer
element: H
position: 9
r_bond_atoms:
- molecule: Monomer
element: C
position: 6
r_displaced_atoms:
- molecule: Monomer
element: O
position: 8
- molecule: Monomer
element: H
position: 8
W:
id: Trp
name: L-tryptophan
synonyms:
- (S)-α-amino-1H-indole-3-propanoic acid
- (S)-alpha-Amino-beta-(3-indolyl)-propionic acid
- L-β-3-indolylalanine
- (S)-tryptophan
- (2S)-2-amino-3-(1H-indol-3-yl)propanoic acid
- L-(−)-tryptophan
identifiers:
- ns: chebi
id: CHEBI:16828
- ns: metacyc.compound
id: TRP
- ns: pubchem.compound
id: '6305'
- ns: resid
id: AA0018
structure: OC(=O)[C@H](Cc1c[nH]c2c1cccc2)[NH3+]
l_bond_atoms:
- molecule: Monomer
element: N
position: 17
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 17
charge: 1
- molecule: Monomer
element: H
position: 17
r_bond_atoms:
- molecule: Monomer
element: C
position: 2
r_displaced_atoms:
- molecule: Monomer
element: O
position: 1
- molecule: Monomer
element: H
position: 1
Y:
id: Tyr
name: L-tyrosine
synonyms:
- (S)-alpha-amino-4-hydroxybenzenepropanoic acid
- (S)-(-)-Tyrosine
- 4-hydroxy-L-phenylalanine
- (2S)-2-amino-3-(4-hydroxyphenyl)propanoic acid
- (S)-Tyrosine
- (S)-3-(p-Hydroxyphenyl)alanine
- (S)-2-Amino-3-(p-hydroxyphenyl)propionic acid
- (-)-alpha-amino-p-hydroxyhydrocinnamic acid
identifiers:
- ns: metacyc.compound
id: TYR
- ns: chebi
id: CHEBI:17895
- ns: resid
id: AA0019
- ns: pubchem.compound
id: '6057'
structure: OC(=O)[C@H](Cc1ccc(cc1)O)[NH3+]
l_bond_atoms:
- molecule: Monomer
element: N
position: 14
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 14
charge: 1
- molecule: Monomer
element: H
position: 14
r_bond_atoms:
- molecule: Monomer
element: C
position: 2
r_displaced_atoms:
- molecule: Monomer
element: O
position: 1
- molecule: Monomer
element: H
position: 1
V:
id: Val
name: L-valine
synonyms:
- L-alpha-Amino-beta-methylbutyric acid
- (S)-valine
- 2-Amino-3-methylbutyric acid
- L-(+)-alpha-Aminoisovaleric acid
- (2S)-2-amino-3-methylbutanoic acid
identifiers:
- ns: resid
id: AA0020
- ns: pubchem.compound
id: '6287'
- ns: metacyc.compound
id: VAL
- ns: chebi
id: CHEBI:16414
structure: '[NH3+]C(C(=O)O)C(C)C'
l_bond_atoms:
- molecule: Monomer
element: N
position: 1
charge: -1
l_displaced_atoms:
- molecule: Monomer
element: H
position: 1
charge: 1
- molecule: Monomer
element: H
position: 1
r_bond_atoms:
- molecule: Monomer
element: C
position: 6
r_displaced_atoms:
- molecule: Monomer
element: O
position: 8
- molecule: Monomer
element: H
position: 8