---
title: "chinf"
author: "Lubomír Prokeš"
date: "11/12/2020"
output:
  pdf_document: default
  word_document: default
  html_document: default
---


### R ###


Organic plant protection products in the river Jagst (Germany) in 2013
```{r, echo = FALSE}

library(webchem)
# jagst

```


```{r}

unique(jagst[,2])

```
SMILES
```{r}

library(webchem)

smile <- as.character(cir_query('Triclosan', 'smiles'))
is.smiles(smile, verbose = TRUE)
smile

```
SDF
```{r}

library(rJava)
library(rcdk)
library(webchem)

mol <- parse.smiles('c1ccccc1C(Cl)(Br)c1ccccc1')[[1]]

write.molecules(mol, filename='c:\\Users\\lubop\\Documents\\R a Python chemie\\R\\mymols2.sdf')

mols <- load.molecules("c:\\Users\\lubop\\Documents\\R a Python chemie\\R\\mymols.sdf")

## view molecule depictions
view.molecule.2d(mols) # nefunguje

## evaluate fingerprints
fps <- get.fingerprints(mols, type="maccs")

## generate descriptors
dnames <- get.desc.names("topological")
descs <- eval.desc(mols, dnames)

```


```{r}

library(rJava)
library(rcdk)

m <- parse.smiles(smile)[[1]]

formula <- get.mol2formula(m,charge=0)
formula@mass
formula@charge
formula@isotopes
formula@string

get.exact.mass(m)
get.natural.mass(m)
is.neutral(m)

get.atom.count(m)
get.bonds(m)


mol <- parse.smiles('CC(=O)CC(=O)NCN')[[1]]
convert.implicit.to.explicit(mol)
get.tpsa(mol)
get.xlogp(mol)
get.alogp(mol)

mol <- parse.smiles('c1ccccc1C(Cl)(Br)c1ccccc1')[[1]]
atoms <- get.atoms(mol)
bonds <- get.bonds(mol)
cat('No. of atoms =', length(atoms), '\n')
cat('No. of bonds =', length(bonds), '\n')

```

[Chemical Identifier Resolver(CIR)](https://cactus.nci.nih.gov/) 

```{r}
library(webchem)

cir_query("piperonyl butoxide", representation = "smiles", resolver = NULL, first = FALSE, verbose = TRUE)

# viz  Reference Manual
cir_query('DEET', 'cas', first = TRUE)
cir_query('Triclosan', 'cas')
cir_query('Triclosan', 'smiles')
cir_query('Triclosan', 'smiles')
cir_query('Aspirin', 'smiles')

# CAS
cir_query('Imidacloprid', representation = 'cas')

# SMILES
cir_query('Imidacloprid', representation = 'smiles')

# InChIKey
cir_query('Imidacloprid', representation = 'stdinchikey')

# Molecular weight
cir_query('Imidacloprid', representation = 'mw')

# number of rings
cir_query('Imidacloprid', representation = 'ring_count')



cir_query("51-03-6", representation = "smiles", resolver = NULL, first = FALSE, verbose = TRUE)

cir_query("3380-34-5", 'cas', first = TRUE)
cir_query("3380-34-5", 'cas', resolver = 'cas_number')
cir_query("3380-34-5", 'smiles')
cir_query("3380-34-5", 'formula')
cir_query("3380-34-5", 'names')
cir_query("3380-34-5", 'pubchem_sid')
cir_query("3380-34-5", 'chemnavigator_sid')


name = 'Triclosan'
cir_query(name, 'mw')
cir_query(name, 'formula')
cir_query(name, 'monoisotopic_mass')
cir_query(name, 'heteroatom_count')
cir_query(name, 'hydrogen_atom_count')


comp <- c('Triclosan', 'Aspirin')
cir_query(comp, 'cas')
cir_query(comp, 'cas', first = TRUE)
cir_query(comp, 'smiles')
cir_query(comp, 'mw')


```



```{r, echo = FALSE}

library(rJava)
library(rcdk)
library(webchem)

todepict <- function(mol,pathsd){
  result = tryCatch({
    factory <- .jnew("org.openscience.cdk.depict.DepictionGenerator")$withAtomColors()
    factory$withSize(1000,1000)#$getStyle("cow")
    temp1 <- paste0(pathsd)
    result<-factory$depict(mol)$writeTo(temp1)
  }, warning = function(w) {
    result=NULL
  }, error = function(e) {
    result=NULL
  })
# return(result)
}
```

```{r, echo = FALSE}
name = "permethrin"
smile <- as.character(cir_query(name, 'smiles'))
molv<-parse.smiles(smile, kekulise=TRUE)[[1]]
todepict(molv,paste("c:\\Users\\lubop\\OneDrive\\Dokumenty\\",name,".png",sep=""))

library(imager)
im <- load.image(paste("c:\\Users\\lubop\\OneDrive\\Dokumenty\\",name,".png",sep=""))
```

Název sloučeniny:  `r name `

```{r, echo = FALSE}

plot(im, axes = FALSE)

```

Název sloučeniny:  `r name `

![]("c:\\Users\\lubop\\OneDrive\\Dokumenty\\permethrin.png")


```{r}
library(rcellminer)
tmp <- parse.smiles("C1=CN(C(=O)N=C1N)C2C(C(C(O2)CO)O)(F)F")
#rcdkplot(tmp[[1]], width=300, height=300, main="Gemcitabine")

```


```{r}
library(rJava)
library(rcdk)
library(webchem)

name = "permethrin"

rcdkplot2 = function(molecule){
  par(mar=c(0,0,0,0)) # set margins to zero since this isn't a real plot
  temp1 = view.image.2d(molecule, depictor = NULL) # get Java representation into an image matrix. set number of pixels you want horizontal and vertical
  plot(NA,NA,xlim=c(1,14),ylim=c(1,10),xaxt='n',yaxt='n',xlab='',ylab='') # create an empty plot
  rasterImage(temp1,2,1,12,10) # boundaries of raster: xmin, ymin, xmax, ymax. here i set them equal to plot boundaries
}
smile <- as.character(cir_query(name, 'smiles'))
# is.smiles(smile, verbose = TRUE)
# smile
m <- parse.smiles(smile)[[1]]
rcdkplot2(m)


library(rJava)
library(rcdk)
library(webchem)

mol <- parse.smiles(as.character(cir_query(name, 'smiles')))[[1]]

write.molecules(mol, filename = paste("c:\\Users\\lubop\\OneDrive\\Dokumenty\\",name,".sdf",sep=""))

mols <- load.molecules( paste("c:\\Users\\lubop\\OneDrive\\Dokumenty\\",name,".sdf",sep=""))



```


[Alan Woods Compendium of Pesticide Common Names](http://www.alanwood.net/pesticides)  

```{r}
library(webchem)

# name
aw_query(name, from = 'name', verbose = TRUE)
#aw_query("fluazinam", from = 'name', verbose = TRUE)$fluazinam$formula[1]

# cas
aw_query("51-03-6", from = 'cas', verbose = TRUE)

```



### PYTHON ###


```{r setup, include=FALSE}  
library(knitr)  
library(reticulate)  
knitr::knit_engines$set(python = reticulate::eng_python)  

Sys.setenv(RETICULATE_PYTHON = "c:/Users/lubop/AppData/Local/r-miniconda")


```


 
```{python}

import pubchempy as pcp

c = pcp.Compound.from_cid(5090)

print(c.molecular_formula)
print(c.molecular_weight)
print(c.isomeric_smiles)
print(c.xlogp)
print(c.iupac_name)
print(c.synonyms)

```

```{python}

import pubchempy as pcp
from pubchempy import Compound, get_compounds

c = Compound.from_cid(1423)
cs = get_compounds('Aspirin', 'name')

results = pcp.get_compounds('Glucose', 'name')
print(results)

```


```{python}

import cirpy
cirpy.resolve('Aspirin', 'smiles')
cirpy.resolve('Aspirin', 'formula')
cirpy.resolve('Aspirin', 'iupac_name')
cirpy.resolve('Aspirin', 'cas')
cirpy.resolve('Aspirin', 'inchi')
cirpy.resolve('Aspirin', 'stdinchi')
cirpy.resolve('Aspirin', 'stdinchikey')

cirpy.resolve('coumarin 343', 'mw')
cirpy.resolve('coumarin 343', 'ring_count')
cirpy.resolve('coumarin 343', 'ringsys_count')
cirpy.resolve('coumarin 343', 'h_bond_donor_count')
cirpy.resolve('coumarin 343', 'h_bond_acceptor_count')
cirpy.resolve('coumarin 343', 'h_bond_center_count')
cirpy.resolve('coumarin 343', 'rule_of_5_violation_count')
cirpy.resolve('coumarin 343', 'rotor_count')
cirpy.resolve('coumarin 343', 'effective_rotor_count')

```
 
 
 
```{python}

import openbabel

mol = openbabel.OBMol()
print('Should print 0 (atoms)')
print(mol.NumAtoms())

a = mol.NewAtom()
a.SetAtomicNum(6)   # carbon atom
a.SetVector(0.0, 1.0, 2.0) # coordinates

b = mol.NewAtom()
mol.AddBond(1, 2, 1)   # atoms indexed from 1
print('Should print 2 (atoms)')
print(mol.NumAtoms())
print('Should print 1 (bond)')
print(mol.NumBonds())

mol.Clear()

#####

obConversion = openbabel.OBConversion()
obConversion.SetInAndOutFormats("smi", "mdl")

mol = openbabel.OBMol()
obConversion.ReadString(mol, "C1=CC=CS1")

print('Should print 5 (atoms)')
print(mol.NumAtoms())

mol.AddHydrogens()
print('Should print 9 (atoms) after adding hydrogens')
print(mol.NumAtoms())

outMDL = obConversion.WriteString(mol)

#####

obConversion = openbabel.OBConversion()
obConversion.SetInAndOutFormats("pdb", "mol2")

mol = openbabel.OBMol()
#    obConversion.ReadFile(mol, "1ABC.pdb.gz")   # Open Babel will uncompress automatically

mol.AddHydrogens()

print(mol.NumAtoms())
print(mol.NumBonds())
print(mol.NumResidues())

obConversion.WriteFile(mol, '1abc.mol2')

######

for obatom in openbabel.OBMolAtomIter(mol):
    print(obatom.GetAtomicMass())
    

```


```{python}

from matplotlib import style
style.use('ggplot')

from rdkit import Chem
from rdkit.Chem import Draw

size = (120, 120)  # Smaller figures than the default.

m = Chem.MolFromSmiles('[Na+].[Cl-]')
fig = Draw.MolToMPL(m, size=size)

m = Chem.MolFromSmiles('c1ccccc1')
fig = Draw.MolToMPL(m, size=size)

m = Chem.MolFromSmiles('C1=C2C(=CC(=C1Cl)Cl)OC3=CC(=C(C=C3O2)Cl)Cl')
fig = Draw.MolToMPL(m, size=size)

m = Chem.MolFromSmiles('Cn1cnc2c1c(=O)n(c(=O)n2C)C')
fig = Draw.MolToMPL(m, size=size)

m = Chem.MolFromSmiles('CC1([C@@H](N2[C@H](S1)[C@@H](C2=O)NC(=O)Cc3ccccc3)C(=O)O)C')
fig = Draw.MolToMPL(m, size=size)
# fig = Draw.MolToMPL(m, size=(200, 200))

```



```{python}

from rdkit import Chem
from rdkit.Chem import Draw

m = Chem.MolFromSmiles('[Na+].[Cl-]')
Draw.MolToFile(m,'molx.png')

m0 = Chem.MolFromSmiles('c1ccccc1')
Draw.MolToFile(m0,'molx0.png')

m1 = Chem.MolFromSmiles('C1=C2C(=CC(=C1Cl)Cl)OC3=CC(=C(C=C3O2)Cl)Cl')
Draw.MolToFile(m1,'molx1.png')

m2 = Chem.MolFromSmiles('Cn1cnc2c1c(=O)n(c(=O)n2C)C')
Draw.MolToFile(m2,'molx2.png')

m3 = Chem.MolFromSmiles('CC1([C@@H](N2[C@H](S1)[C@@H](C2=O)NC(=O)Cc3ccccc3)C(=O)O)C')
Draw.MolToFile(m3,'molx3.png')

```

```{r, echo=FALSE}

knitr::include_graphics("molx.png")
knitr::include_graphics("molx0.png")
knitr::include_graphics("molx1.png")
knitr::include_graphics("molx2.png")
knitr::include_graphics("molx3.png")

```