iqspr (version 1.1)

SmcChem-class: SMC chemical generator class

Description

SMILES generator with Sequence Monte Calro sampler

Fields

qsprpred

QSPRpred object

engram

ENgram object

m

numeric value representing the order of extended N-gram model

v_ESSth

numeric value representing the threshold which resample is done when ESS is less than 100 * v_ESSth

v_decay

numeric value decaying temparature for the target distribution in SMC sampler

Methods

get_hiscores(nsmi = 100, exsim = 0.8)

get chemical structures with high QSPR score from SmcChem object (same as get_hiscores function)

get_smiles()

get SMILES strings from the SmcChem object (same as get_smiles function)

initialize(smis = NULL, v_engram = NULL, v_qsprpred = NULL, v_m = NULL, temp = 1, ESSth = 0.5, lambda = 0, decay = 0.95, gentype = "ML", maxstock = 2000)

Initialize the SMC chemical generator with initial SMILES strings smis, ENgram class object v_engram and QSPRpred class object v_qsprpred

smcexec(niter, nsteps = 5, preorder = 0, nview = 0)

modify chemical structures with niter SMC updates

viewstr(idx)

view 2D structures from SMILES string vector with index idx (same as viewstr function)

Examples

# NOT RUN {
#sample data
data(qspr.data)
idx <- sample(nrow(qspr.data), 5000)
smis <- paste(qspr.data[idx,1])
y <- qspr.data[idx,c(2,5)]

#learning a pattern of chemical strings
data(trainedSMI)
data(engram_5k)  #same as run => engram <- ENgram$new(trainedSMI, order=10)

#learning QSPR model
data(qsprpred_EG_5k)
#same as run => qsprpred <- QSPRpred$new(smis=smis, y=as.matrix(y), v_fpnames="graph")

#set target range 
qsprpred_EG_5k$ymin <- c(200, 1.5)
qsprpred_EG_5k$ymax <- c(350, 2.5)

#getting chemical strings from the Inverse-QSPR model
smchem <- SmcChem$new(smis = rep("c1ccccc1O", 25), v_qsprpred=qsprpred_EG_5k,
                     v_engram=engram_5k,temp=3)
#-----arguments
#smis: initial SMILES strings in SMC sampler
#v_qsprpred: QSPRpred object 
#v_engram: ENgram object
#v_m: numeric value representing the order of modified N-gram model
#ESSth: numeric resampling threshold at 100 * v_ESSth
#temp: numeric, annealing parameter in SMC sampler
#lambda: numeric 
#decay: numeric, decaying rate for temparature 
#-----arguments
                
smchem$smcexec(niter=5, preorder=0, nview=4)
#if OpenBabel (>= 2.3.1) is installed, you can use reordering for better mixing as 
#smchem$smcexec(niter=100, preorder=0.2, nview=4)
#see http://openbabel.org

#check
smiles <- get_smiles(smchem)
predict(qsprpred_EG_5k, smiles[1:5])

# }