Merge pull request #3 from CDK-R/master

latest updates
schymane · Nov 11, 2018 · 5d074e5031a2b04c99d58364b0a59ed20143f738 · 5d074e5
2 parents 6b01c3b + a9332c6
commit 5d074e5031a2b04c99d58364b0a59ed20143f738
diff --git a/README.md b/README.md
@@ -54,4 +54,4 @@ sudo R CMD javareconf
 install.packages('rJava', type="source")
 ```

-Further informaiton about R's use of Java can be [found here](https://cran.r-project.org/doc/manuals/r-release/R-admin.html#Java-support). 
+Further informaiton about R's use of Java can be [found here](https://cran.r-project.org/doc/manuals/r-release/R-admin.html#Java-support).   
diff --git a/rcdk/R/fingerprint.R b/rcdk/R/fingerprint.R
@@ -1,3 +1,56 @@
+#' Generate molecular fingerprints
+#' 
+#' `get.fingerprint` returns a `fingerprint` object representing molecular fingerprint of
+#' the input molecule.
+#' 
+#' @param molecule A \code{jobjRef} object to an \code{IAtomContaine}
+#' @param type The type of fingerprint. Possible values are:
+#'   \itemize{
+#' \item standard - Considers paths of a given length. The default is
+#' but can be changed. These are hashed fingerprints, with a
+#' default length of 1024
+#' \item extended - Similar to the standard type, but takes rings and
+#' atomic properties into account into account
+#' \item graph - Similar to the standard type by simply considers connectivity
+#' \item hybridization - Similar to the standard type, but only consider hybridization state
+#' \item maccs - The popular 166 bit MACCS keys described by MDL
+#' \item estate - 79 bit fingerprints corresponding to the E-State atom types described by Hall and Kier
+#' \item pubchem - 881 bit fingerprints defined by PubChem
+#' \item kr - 4860 bit fingerprint defined by Klekota and Roth
+#' \item shortestpath - A fingerprint based on the shortest paths between pairs of atoms and takes into account ring systems, charges etc.
+#' \item signature - A feature,count type of fingerprint, similar in nature to circular fingerprints, but based on the signature 
+#' descriptor
+#' \item circular - An implementation of the ECFP6 fingerprint
+#' }
+#' @param fp.mode The style of fingerprint. Specifying "`bit`" will return a binary fingerprint,
+#' "`raw`" returns the the original representation (usually sequence of integers) and 
+#' "`count`" returns the fingerprint as a sequence of counts.
+#' @param depth The search depth. This argument is ignored for the
+#' `pubchem`, `maccs`, `kr` and `estate` fingerprints
+#' @param size The final length of the fingerprint. 
+#' This argument is ignored for the `pubchem`, `maccs`, `kr`, `signature`, `circular` and 
+#' `estate` fingerprints
+#' @param verbose Verbose output if \code{TRUE}
+#' @return an S4 object of class \code{\link{fingerprint-class}} or \code{\link{featvec-class}}, 
+#' which can be manipulated with the fingerprint package.
+#' @export
+#' @author Rajarshi Guha (\email{rajarshi.guha@@gmail.com})
+#' @examples 
+#' ## get some molecules
+#' sp <- get.smiles.parser()
+#' smiles <- c('CCC', 'CCN', 'CCN(C)(C)', 'c1ccccc1Cc1ccccc1','C1CCC1CC(CN(C)(C))CC(=O)CC')
+#' mols <- parse.smiles(smiles)
+#' 
+#' ## get a single fingerprint using the standard
+#' ## (hashed, path based) fingerprinter
+#' fp <- get.fingerprint(mols[[1]])
+#' 
+#' ## get MACCS keys for all the molecules
+#' fps <- lapply(mols, get.fingerprint, type='maccs')
+#' 
+#' ## get Signature fingerprint
+#' ## feature, count fingerprinter
+#' fps <- lapply(mols, get.fingerprint, type='signature', fp.mode='raw')
 get.fingerprint <- function(molecule, type = 'standard', fp.mode = 'bit', depth=6, size=1024, verbose=FALSE) {
  if (is.null(attr(molecule, 'jclass'))) stop("Must supply an IAtomContainer or something coercable to it")
  if (attr(molecule, "jclass") != "org/openscience/cdk/interfaces/IAtomContainer") {
diff --git a/rcdk/R/frags.R b/rcdk/R/frags.R
@@ -1,3 +1,32 @@
+#' Generate Bemis-Murcko Fragments
+#' 
+#' Fragment the input molecule using the Bemis-Murcko scheme
+#' 
+#' A variety of methods for fragmenting molecules are available ranging from
+#' exhaustive, rings to more specific methods such as Murcko frameworks. Fragmenting a
+#' collection of molecules can be a useful for a variety of analyses. In addition
+#' fragment based analysis can be a useful and faster alternative to traditional 
+#' clustering of the whole collection, especially when it is large.
+#' 
+#' Note that exhaustive fragmentation of large molecules (with many single bonds) can become
+#' time consuming.
+#' 
+#' @param mols A list of `jobjRef` objects of Java class `IAtomContainer`
+#' @param min.frag.size The smallest fragment to consider (in terms of heavy atoms)
+#' @param as.smiles If `TRUE` return the fragments as SMILES strings. If not, then fragments
+#' are returned as `jobjRef` objects
+#' @param single.framework If `TRUE`, then a single framework (i.e., the framework consisting of the
+#' union of all ring systems and linkers) is returned for each molecule. Otherwise, all combinations
+#' of ring systems and linkers are returned
+#' @return Returns a list with each element being a list with two elements: `rings` and
+#' `frameworks`. Each of these elements is either a character vector of SMILES strings or a list of
+#' `IAtomContainer` objects.
+#' @author Rajarshi Guha (\email{rajarshi.guha@@gmail.com})
+#' @seealso [get.exhuastive.fragments()]
+#' @examples 
+#' mol <- parse.smiles('c1ccc(cc1)CN(c2cc(ccc2[N+](=O)[O-])c3c(nc(nc3CC)N)N)C')[[1]]
+#' mf1 <- get.murcko.fragments(mol, as.smiles=TRUE, single.framework=TRUE)
+#' mf1 <- get.murcko.fragments(mol, as.smiles=TRUE, single.framework=FALSE)
 get.murcko.fragments <- function(mols, min.frag.size = 6, as.smiles = TRUE, single.framework = FALSE) {
  if (!is.list(mols)) mols <- list(mols)
  klasses <- unlist(lapply(mols, function(x) attr(x, "jclass")))
@@ -22,6 +51,9 @@ get.murcko.fragments <- function(mols, min.frag.size = 6, as.smiles = TRUE, sing
  return(ret)
 }

+#' @inherit get.murcko.fragments 
+#' @return returns a list of length equal to the number of input molecules. Each
+#' element is a character vector of SMILES strings or a list of `jobjRef` objects.
 get.exhaustive.fragments <- function(mols, min.frag.size = 6, as.smiles = TRUE) {
  if (!is.list(mols)) mols <- list(mols)
  klasses <- unlist(lapply(mols, function(x) attr(x, "jclass")))
diff --git a/rcdk/man/frags.Rd b/rcdk/man/frags.Rd
diff --git a/rcdk/man/get.exhaustive.fragments.Rd b/rcdk/man/get.exhaustive.fragments.Rd
diff --git a/rcdk/man/get.fingerprint.Rd b/rcdk/man/get.fingerprint.Rd
diff --git a/rcdk/man/get.murcko.fragments.Rd b/rcdk/man/get.murcko.fragments.Rd