Skip to content

Commit

Permalink
Add functional groups and update documentation
Browse files Browse the repository at this point in the history
  • Loading branch information
Old-Shatterhand committed Nov 5, 2024
1 parent 4ce022a commit 6f2dcef
Show file tree
Hide file tree
Showing 7 changed files with 4,307 additions and 197 deletions.
3 changes: 3 additions & 0 deletions docs/howto/fgs.nblink
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
{
"path": "../../examples/fgs.ipynb"
}
1 change: 1 addition & 0 deletions docs/index.rst
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,7 @@ Welcome to the documentation of GlyLES!
howto/conversion
howto/visualization
howto/filtering
howto/fgs

.. toctree::
:glob:
Expand Down
4,036 changes: 4,036 additions & 0 deletions examples/fgs.ipynb

Large diffs are not rendered by default.

46 changes: 38 additions & 8 deletions glyles/glycans/mono/reactor.py
Original file line number Diff line number Diff line change
Expand Up @@ -24,11 +24,14 @@
"Am": "C(=N)C",
"Asp": "N[C@@H](CC(=O)O)C(=O)O",
"Br": "Br",
"Cbz": "C(=O)OCc2ccccc2",
"Cer": "OC[C@H](NC=O)C(O)/C=C/" + "C" * 13,
"Cho": "OCC[N+](C)(C)C",
"Cl": "Cl",
"ClAc": "C(=O)CCl",
"Cm": "NC(=O)",
"Cys": "N[C@@H](CS)C(=O)O",
"DCA": "C(=O)C(Cl)Cl",
"Etn": "OCCN",
"EtN": "OCCN",
"F": "F",
Expand All @@ -38,51 +41,78 @@
"I": "I",
"Lys": "NCCCC[C@H](N)C(=O)O",
"N": "N",
"N3": "N=[N+]=[N-]",
"NFo": "NC=O",
"Ns": "S(=O)(=O)c2ccccc2[N+](=O)[O-]",
"oNB": "Cc2ccccc2[N+](=O)[O-]",
"Orn": "NCCC[C@H](N)C(=O)O",
"P": "OP(=O)(O)O",
"PhNO2": "Oc2ccc([N+]([O-])=O)cc2",
"Pic": "CC2=CC=CC=N2",
"Pico": "C(=O)C2=CC=CC=N2",
"Pp": "OC(=O)CC",
"S": "S(=O)(=O)O",
"Pro": "N2CCCC2C(=O)O",
"Ser": "OC(=O)[C@H](N)CO",
"TBDPS": "[Si](C(C)(C)C)(c2ccccc2)c2ccccc2",
"TBS": "[Si](C)(C)C(C)(C)C",
"TCA": "C(=O)C(Cl)(Cl)Cl",
"TES": "[Si](CC)(CC)CC",
"Tf": "OS(=O)(=O)C(F)(F)F",
"TFA": "C(=O)C(F)(F)F",
"TIPS": "[Si](C(C)C)(C(C)C)C(C)C",
"TMS": "[Si](C)(C)C",
"Thr": "N[C@@H](C(=O)O)[C@@H](O)C",
"Troc": "C(=O)OCC(Cl)(Cl)Cl",
"Ts": "S(=O)(=O)c2ccc(C)cc2",
"Ulo": "OC(c2ccccc2)(c2ccccc2(Cl))CCN(C)C",

# COH land
"A": "OC(=O)C",
"Al": "CCC=C",
"Allyl": "CC=C",
"Ac": "C(=O)C",
"Ang": "OC(=O)C/(C)=C\\C",
"Bz": "C(=O)c2ccccc2",
"Ang": "OC(=O)/C(C)=C\\C",
"Bn": "Cc2ccccc2",
"Boc": "C(=O)OC(C)(C)C",
"Bz": "C(=O)c2ccccc2",
"cdPam": "OC(=O)CCCCCCC/C=C\\CCCCCC",
"Cet": "CCC(=O)O",
"cHx": "C2CCCCC2",
"Cin": "OC(=O)/C=C/c2ccccc2",
"Coum": "OC(=O)/C=C/c1ccc(O)ccc1",
"Coum": "OC(=O)/C=C/c2cc(O)ccc2",
"Dce": "OC(=O)CCCCCCCC=C",
"Dhp": "OC(=O)C(O)(O)CCC",
"Dhpa": "OC(=O)C(O)(O)CCC",
"DMT": "C(c2ccc(OC)cc2)(c2ccccc2)c2ccccc2",
"Etg": "OCCO",
"Fer": "OC(=O)/C=C/c2ccc(O)c(OC)c2",
"Fmoc": "C(=O)OCC2c3ccccc3c4c2cccc4",
"Fo": "OC(=O)",
"Gc": "C(=O)CO",
"Gly": "OCC(O)CO",
"Gro": "OCC(O)CO",
"He": "C(O)C",
"Lac": "OC(=O)C(O)C",
"Lev": "C(=O)CCC(=O)C",
"Lin": "OC(=O)CCCCCCC/C=C\\C/C=C\\CCCCC",
"Mal": "O[C@H](C(=O)O)CC(=O)O",
"MMT": "C(c2ccccc2)(c2ccccc2)c2ccc(OC)cc2",
"MOM": "COC",
"NAP": "CCc2cc3ccccc3cc2",
"Ole": "OC(=O)CCCCCCC/C=C\\CCCCCCCC",
"Ph": "c2ccccc2",
"Phyt": "OCCC(C)CCCC(C)CCCC(C)CCCC(C)C",
"Piv": "C(=O)C(C)(C)C",
"PMB": "Cc2ccc(OC)cc2",
"PMP": "Cc2ccccc2O",
"Poc": "C(=O)OCC#C",
"Pyr": "OC(=O)C(=O)C",
"Sin": "OC(=O)/C=C/c2cc(OC)c(O)c(OC)c2",
"Suc": "OC(=O)CCC(=O)O",
"Tig": "OC(=O)C/(C)=C/C",
"Tr": "C(c2ccccc2)(c3ccccc3)c4ccccc4",
"Ts": "OS(=O)(=O)c2ccc(C)cc2",
"THP": "C2CCCCO2",
"Tig": "OC(=O)/C(C)=C/C",
"Tr": "C(c2ccccc2)(c2ccccc2)c2ccccc2",
"Vac": "OC(=O)CCCCCCCCCC=CCCCCCC",

# Sugar rings
Expand Down Expand Up @@ -157,7 +187,7 @@

# list of functional groups that start with an N and might be confused with a nitrogen-bridge
n_conflict = [
"Ner", "Nno", "Non", "Nn"
"NAP", "Ner", "Nno", "Non", "Nn"
]

# list of functional groups that start with an O and might be confused with an oxygen-bridge
Expand All @@ -167,7 +197,7 @@

# list of functional groups that start with a P and might be confused with a phosphate-bridge
p_conflict = [
"Psyllic", "Prop", "Pam", "Pro", "Pyr", "Pe", "Ph", "Pr", "Pp"
"PMB", "PMP", "Pic", "Pico", "Psyllic", "Prop", "Pam", "Pro", "Pyr", "Pe", "Ph", "Pr", "Pp"
]

# list of functional groups that start with a C and might be confused with a carbon-bridge
Expand Down
21 changes: 10 additions & 11 deletions glyles/grammar/Glycan.g4
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
grammar Glycan;

start:
'#' (LBRACK branch RBRACK)* begin '#';
begin:
Expand Down Expand Up @@ -60,16 +59,16 @@ OXYGEN:
PHOSPHOR:
'P';
FG:
'Ceroplastic' | 'Lacceroic' | '3oxoMyr' | 'Psyllic' | 'Geddic' | 'Allyl' | 'Phthi'
| 'aLnn' | 'gLnn' | 'eSte' | 'Coum' | 'HSer' | 'Prop'
| 'Ach' | 'Aep' | 'Ala' | 'Ang' | 'Asp' | 'Beh' | 'But' | 'Cct' | 'Cer' | 'Cet' | 'Cho' | 'Cin' | 'Crt' | 'Cys'
| 'Dce' | 'Dco' | 'Dec' | 'Dhp' | 'Dod' | 'Etg' | 'EtN' | 'Etn' | 'Fer' | 'Gro' | 'Glu' | 'Gly' | 'Hpo' | 'Hse'
| 'Hxo' | 'Lac' | 'Lau' | 'Leu' | 'Lin' | 'Lys' | 'Mal' | 'Mar' | 'Mel' | 'Mon' | 'Myr' | 'Ner' | 'Nno' | 'Non'
| 'Oco' | 'Ole' | 'Orn' | 'Pam' | 'Pro' | 'Pyr' | 'Ser' | 'Sin' | 'Ste' | 'tBu' | 'Thr' | 'Tig' | 'Und' | 'Vac'
| 'Udo' | 'Ulo' | 'ulo'
| 'Ac' | 'Am' | 'Bn' | 'Br' | 'Bu' | 'Bz' | 'Cl' | 'Cm' | 'DD' | 'DL' | 'Et' | 'Fo' | 'Gc' | 'Hp' | 'Hx'
| 'LD' | 'LL' | 'Me' | 'Nn' | 'Oc' | 'Pe' | 'Ph' | 'Pr' | 'Pp' | 'Tf' | 'Tr' | 'Ts' | 'Vl' | 'en'
| 'A' | 'F' | 'I' | 'S';
'3oxoMyr' | 'A' | 'Ac' | 'Ach' | 'Aep' | 'Al' | 'Ala' | 'Alloc' | 'Allyl' | 'aLnn' | 'Am' | 'Ang' | 'Asp' | 'Beh'
| 'Bn' | 'Boc' | 'Br' | 'Bu' | 'But' | 'Bz' | 'Cbz' | 'Cct' | 'Cer' | 'Ceroplastic' | 'Cet' | 'Cho' | 'cHx' | 'Cin'
| 'Cl' | 'ClAc' | 'Cm' | 'Coum' | 'Crt' | 'Cys' | 'DCA' | 'Dce' | 'Dco' | 'DD' | 'Dec' | 'Dhp' | 'DL' | 'DMT'
| 'Dod' | 'en' | 'eSte' | 'Et' | 'Etg' | 'EtN' | 'Etn' | 'F' | 'Fer' | 'Fmoc' | 'Fo' | 'Gc' | 'Geddic' | 'gLnn'
| 'Glu' | 'Gly' | 'Gro' | 'Hp' | 'Hpo' | 'Hse' | 'HSer' | 'Hx' | 'Hxo' | 'I' | 'Lac' | 'Lacceroic' | 'Lau' | 'LD'
| 'Leu' | 'Lev' | 'Lin' | 'LL' | 'Lys' | 'Mal' | 'Mar' | 'Me' | 'Mel' | 'MMT' | 'MOM' | 'Mon' | 'Myr' | 'N3'
| 'NAP' | 'Ner' | 'Nn' | 'Nno' | 'Non' | 'Ns' | 'Oc' | 'Oco' | 'Ole' | 'oNB' | 'Orn' | 'Pam' | 'Pe' | 'Ph'
| 'Phthi' | 'Pic' | 'Pico' | 'Piv' | 'PMB' | 'PMP' | 'Poc' | 'Pp' | 'Pr' | 'Pro' | 'Prop' | 'Psyllic' | 'Pyr'
| 'S' | 'Ser' | 'Sin' | 'Ste' | 'TBDPS' | 'TBS' | 'tBu' | 'TCA' | 'TES' | 'Tf' | 'TFA' | 'THP' | 'Thr' | 'Tig'
| 'TIPS' | 'TMS' | 'Tr' | 'Troc' | 'Ts' | 'Udo' | 'Ulo' | 'ulo' | 'Und' | 'Vac' | 'Vl';
ANHYDRO:
'Anhydro';
HEAD:
Expand Down
2 changes: 1 addition & 1 deletion glyles/grammar/GlycanLexer.interp

Large diffs are not rendered by default.

Loading

0 comments on commit 6f2dcef

Please sign in to comment.