#/**********************************************************************
#Copyright (C) 2000-2005, 2010 by OpenEye Scientific Software, Inc.
#***********************************************************************/
#This file defines the rules for filtering multi-structure files based on 
#properties and substructure patterns.
MIN_MOLWT      200         "Minimum molecular weight"
MAX_MOLWT      600         "Maximum molecular weight"

MIN_NUM_HVY   15         "Minimum number of heavy atoms"
MAX_NUM_HVY   35         "Maximum number of heavy atoms"

MIN_RING_SYS    0      "Minumum number of ring systems"
MAX_RING_SYS    5      "Maximum number of ring systems"

MIN_RING_SIZE    0      "Minimum atoms in any ring system"
MAX_RING_SIZE    20      "Maximum atoms in any ring system"

MIN_CON_NON_RING    0      "Minimum number of connected non-ring atoms"
MAX_CON_NON_RING    15     "Maximum number of connected non-ring atoms"

MIN_FCNGRP       0      "Minimum number of functional groups"
MAX_FCNGRP       18      "Maximum number of functional groups"

MIN_UNBRANCHED   0      "Minimum number of connected unbranched non-ring atoms"
MAX_UNBRANCHED   6      "Maximum number of connected unbranched non-ring atoms"

MIN_CARBONS      7      "Minimum number of carbons"
MAX_CARBONS      35      "Maximum number of carbons"

MIN_HETEROATOMS    2      "Minimum number of heteroatoms"
MAX_HETEROATOMS    20      "Maximum number of heteroatoms"

MIN_Het_C_Ratio    0.10    "Minimum heteroatom to carbon ratio"
MAX_Het_C_Ratio    1.0      "Maximum heteroatom to carbon ratio"      

MIN_HALIDE_FRACTION      0.0      "Minimum Halide Fraction"
MAX_HALIDE_FRACTION      0.5      "Maximum Halide Fraction"

#count ring degrees of freedom = (#BondsInRing) - 4 - (RigidBondsInRing) - (BondsSharedWithOtherRings)
#must be >= 0, from JCAMD 14:251-265,2000.
ADJUST_ROT_FOR_RING     true      "BOOLEAN for whether to estimate degrees of freedom in rings"

MIN_ROT_BONDS    0      "Minimum number of rotatable bonds"
MAX_ROT_BONDS    20      "Maximum number of rotatable bonds"

MIN_RIGID_BONDS    0      "Minimum number of rigid bonds"
MAX_RIGID_BONDS    35      "Maximum number of rigid bonds"

MIN_HBOND_DONORS  0      "Minimum number of hydrogen-bond donors"    
MAX_HBOND_DONORS  6      "Maximum number of hydrogen-bond donors"    

MIN_HBOND_ACCEPTORS  0      "Minimum number of hydrogen-bond acceptors"    
MAX_HBOND_ACCEPTORS  8      "Maximum number of hydrogen-bond acceptors"    

MIN_LIPINSKI_DONORS  0      "Minimum number of hydrogens on O & N atoms"
MAX_LIPINSKI_DONORS  5      "Maximum number of hydrogens on O & N atoms"

MIN_LIPINSKI_ACCEPTORS  0      "Minimum number of oxygen & nitrogen atoms"
MAX_LIPINSKI_ACCEPTORS  10      "Maximum number of oxygen & nitrogen atoms"

MIN_COUNT_FORMAL_CRG    0      "Minimum number formal charges"
MAX_COUNT_FORMAL_CRG    3      "Maximum number of formal charges"

MIN_SUM_FORMAL_CRG   -2      "Minimum sum of formal charges"
MAX_SUM_FORMAL_CRG    2      "Maximum sum of formal charges"

MIN_CHIRAL_CENTERS   0   "Minimum chiral centers"
MAX_CHIRAL_CENTERS   4   "Maximum chiral centers"

MIN_XLOGP      -5.0      "Minimum XLogP"
MAX_XLOGP       6.0      "Maximum XLogP"

#choices are insoluble<poorly<moderately<soluble<very<highly
MIN_SOLUBILITY      moderately      "Minimum solubility"

PSA_USE_SandP   false    "Count S and P as polar atoms"
MIN_2D_PSA      0.0      "Minimum 2-Dimensional (SMILES) Polar Surface Area"
MAX_2D_PSA      150.0    "Maximum 2-Dimensional (SMILES) Polar Surface Area"

AGGREGATORS    true      "Eliminate known aggregators"
PRED_AGG       true      "Eliminate predicted aggregators"

#secondary filters (based on multiple primary filters)
GSK_VEBER      true      "PSA>140 or >10 rot bonds"
MAX_LIPINSKI   1         "Maximum number of Lipinski violations"
MIN_ABS 0.5              "Minimum probability F>10% in rats"
PHARMACOPIA    true      "LogP > 5.88 or PSA > 131.6"

ALLOWED_ELEMENTS  H,C,N,O,F,S,Cl,Br
ELIMINATE_METALS Sc,Ti,V,Cr,Mn,Fe,Co,Ni,Cu,Zn,Y,Zr,Nb,Mo,Tc,Ru,Rh,Pd,Ag,Cd

#acceptable molecules must have <= instances of each of the patterns below

#specific, undesirable functional groups

RULE  0  quinone
RULE  0  pentafluorophenyl_esters
RULE  0  paranitrophenyl_esters
RULE  0  HOBT_esters
RULE  0  triflates
RULE  0  lawesson_s_reagent
RULE  0  phosphoramides
RULE  0  beta_carbonyl_quat_nitrogen
RULE  0  acylhydrazide
RULE  0  cation_C_Cl_I_P_or_S
RULE  0  phosphoryl
RULE  0  alkyl_phosphate
RULE  0  phosphinic_acid
RULE  0  phosphanes
RULE  0  phosphoranes
RULE  0  imidoyl_chlorides
RULE  0  nitroso
RULE  0  N_P_S_Halides
RULE  0  carbodiimide
RULE  0  isonitrile
RULE  0  triacyloxime
RULE  0  cyanohydrins
RULE  0  acyl_cyanides
RULE  0  sulfonylnitrile
RULE  0  phosphonylnitrile
RULE  0  azocyanamides
RULE  0  beta_azo_carbonyl
RULE  0  polyenes
RULE  0  saponin_derivatives
RULE  1  cytochalasin_derivatives
RULE  4  cycloheximide_derivatives
RULE  1  monensin_derivatives
RULE  1  squalestatin_derivatives

#functional groups which often eliminate compounds from consideration

RULE  0  acid_halide
RULE  0  aldehyde
RULE  0  alkyl_halide
RULE  0  anhydride
RULE  0  azide
RULE  0  azo
RULE  0  di_peptide
RULE  0  michael_acceptor
RULE  0  beta_halo_carbonyl
RULE  0  nitro
RULE  0  oxygen_cation
RULE  0  peroxide
RULE  0  phosphonic_acid
RULE  0  phosphonic_ester
RULE  0  phosphoric_acid
RULE  0  phosphoric_ester
RULE  0  sulfonic_acid
RULE  0  sulfonic_ester
RULE  0  tricarbo_phosphene
RULE  0  epoxide
RULE  0  sulfonyl_halide
RULE  0  halopyrimidine
RULE  0  perhalo_ketone
RULE  0  aziridine
RULE  1  oxalyl
RULE  0  alphahalo_amine 
RULE  0  halo_amine 
RULE  0  halo_alkene
RULE  0  acyclic_NCN
RULE  0  acyclic_NS
RULE  0  SCN2
RULE  0  terminal_vinyl
RULE  0  hetero_hetero
RULE  0  hydrazine
RULE  0  N_methoyl
RULE  0  NS_beta_halothyl
RULE  0  propiolactones
RULE  0  iodoso
RULE  0  iodoxy
RULE  0  noxide


#groups of molecules

RULE  0  dye
  
#functional groups which are allowed, but may not be wanted in high quantities
#common functional groups

RULE  6  alcohol
RULE  4  alkene
RULE  4  amide
RULE  4  amino_acid
RULE  2  amine
RULE  4  primary_amine
RULE  4  secondary_amine
RULE  4  tertiary_amine
RULE  2  carboxylic_acid
RULE  6  halide
RULE  0  iodine
RULE  2  ketone
RULE  4  phenol
RULE  1  imine
RULE  1  methyl_ketone
RULE  1  alkylaniline
RULE  4  sulfonamide 
RULE  1  sulfonylurea 
RULE  0  phosphonamide 
RULE  0  alphahalo_ketone
RULE  0  oxaziridine
RULE  1  cyclopropyl
RULE  2  guanidine
RULE  0  sulfonimine
RULE  0  sulfinimine
RULE  1  hydroxamic_acid
RULE  0  sulfinylthio
RULE  0  disulfide
RULE  0  enol_ether
RULE  0  enamine
RULE  0  organometallic
RULE  0  dithioacetal
RULE  1  oxime
RULE  0  isothiocyanate
RULE  0  isocyanate
RULE  3  lactone
RULE  3  lactam
RULE  1  thioester
RULE  1  carbonate
RULE  0  carbamic_acid
RULE  1  thiocarbamate
RULE  0  triazine
RULE  1  malonic

#other functional groups

RULE  2  alkyne
RULE  4  aniline
RULE  4  aryl_halide
RULE  2  carbamate
RULE  3  ester
RULE  5  ether
RULE  1  hydrazone
RULE  0  nonacylhydrazone
RULE  1  hydroxylamine
RULE  2  nitrile
RULE  2  sulfide
RULE  2  sulfone
RULE  2  sulfoxide
RULE  0  thiourea
RULE  1  thioamide
RULE  1  thiol
RULE  2  urea

RULE  0  hemiketal 
RULE  0  hemiacetal
RULE  0  ketal
RULE  1  acetal
RULE  0  aminal
RULE  0  hemiaminal

#protecting groups

RULE  0  benzyloxycarbonyl_CBZ
RULE  0  t_butoxycarbonyl_tBOC
RULE  0  fluorenylmethoxycarbonyl_Fmoc
RULE  1  dioxolane_5MR
RULE  1  dioxane_6MR
RULE  1  tetrahydropyran_THP
RULE  1  methoxyethoxymethyl_MEM
RULE  2  benzyl_ether
RULE  2  t_butyl_ether
RULE  0  trimethylsilyl_TMS
RULE  0  t_butyldimethylsilyl_TBDMS
RULE  0  triisopropylsilyl_TIPS
RULE  0  t_butyldiphenylsilyl_TBDPS
RULE  1  phthalimides_PHT
RULE  2  arenesulfonyl