\name{fit.xyz} \alias{fit.xyz} \alias{rot.lsq} \title{ Coordinate Superposition } \description{ Coordinate superposition with the Kabsch algorithm. } \usage{ fit.xyz(fixed, mobile, fixed.inds = NULL, mobile.inds = NULL, verbose=FALSE, prefix= "", pdbext = "", outpath = "fitlsq", full.pdbs=FALSE, ncore = 1, nseg.scale = 1, ...) rot.lsq(xx, yy, xfit = rep(TRUE, length(xx)), yfit = xfit, verbose = FALSE) } \arguments{ \item{fixed }{ numeric vector of xyz coordinates.} \item{mobile}{ numeric vector, numeric matrix, or an object with an \code{xyz} component containing one or more coordinate sets. } \item{fixed.inds}{ a vector of indices that selects the elements of \code{fixed} upon which fitting should be based.} \item{mobile.inds}{ a vector of indices that selects the elements of \code{mobile} upon which fitting should be based.} \item{full.pdbs}{ logical, if TRUE \dQuote{full} coordinate files (i.e. all atoms) are written to the location specified by \code{outpath}. } \item{prefix}{ prefix to mobile$id to locate \dQuote{full} input PDB files. Only required if \code{full.pdbs} is TRUE. } \item{pdbext}{ the file name extension of the input PDB files. } \item{outpath}{ character string specifing the output directory when \code{full.pdbs} is TRUE. } \item{xx}{ numeric vector corresponding to the moving \sQuote{subject} coordinate set. } \item{yy}{ numeric vector corresponding to the fixed \sQuote{target} coordinate set. } \item{xfit}{ logical vector with the same length as \code{xx}, with TRUE elements corresponding to the subset of positions upon which fitting is to be performed. } \item{yfit}{ logical vector with the same length as \code{yy}, with TRUE elements corresponding to the subset of positions upon which fitting is to be performed. } \item{verbose}{ logical, if TRUE more details are printed. } \item{\dots}{ other parameters for \code{\link{read.pdb}}. } \item{ncore }{ number of CPU cores used to do the calculation. \code{ncore>1} requires package \sQuote{parallel} installed. } \item{nseg.scale }{ split input data into specified number of segments prior to running multiple core calculation. } } \details{ The function \code{fit.xyz} is a wrapper for the function \code{rot.lsq}, which performs the actual coordinate superposition. The function \code{rot.lsq} is an implementation of the Kabsch algorithm (Kabsch, 1978) and evaluates the optimal rotation matrix to minimize the RMSD between two structures. Since the Kabsch algorithm assumes that the number of points are the same in the two input structures, care should be taken to ensure that consistent atom sets are selected with \code{fixed.inds} and \code{mobile.inds}. Optionally, \dQuote{full} PDB file superposition and output can be accomplished by setting \cr \code{full.pdbs=TRUE}. In that case, the input (\code{mobile}) passed to \code{fit.xyz} should be a list object obtained with the function \code{\link{read.fasta.pdb}}, since the components \code{id}, \code{resno} and \code{xyz} are required to establish correspondences. See the examples below. In dealing with large vector and matrix, running on multiple cores, especially when \code{ncore>>1}, may ask for a large portion of system memory. To avoid the overuse of memory, input data is first split into segments (for xyz matrix, the splitting is along the row). The number of data segments is equal to \code{nseg.scale*nseg.base}, where \code{nseg.base } is an integer determined by the dimension of the data. } \value{ Returns moved coordinates. } \references{ Grant, B.J. et al. (2006) \emph{Bioinformatics} \bold{22}, 2695--2696. Kabsch \emph{Acta Cryst} (1978) \bold{A34}, 827--828. } \author{ Barry Grant with \code{rot.lsq} contributions from Leo Caves } \seealso{ \code{\link{rmsd}}, \code{\link{read.pdb}}, \code{\link{read.fasta.pdb}}, \code{\link{read.dcd}} } \examples{ \donttest{ # PDB server connection required - testing excluded try({ ##--- Read an alignment & Fit aligned structures aln <- read.fasta(system.file("examples/kif1a.fa",package="bio3d")) pdbs <- read.fasta.pdb(aln) gaps <- gap.inspect(pdbs$xyz) xyz <- fit.xyz( fixed = pdbs$xyz[1,], mobile = pdbs$xyz, fixed.inds = gaps$f.inds, mobile.inds = gaps$f.inds ) #rmsd( xyz[, gaps$f.inds] ) #rmsd( pdbs$xyz[, gaps$f.inds] ) }, silent=TRUE) if(inherits(.Last.value, "try-error")) { message("Need internet to run the example") } } \dontrun{ ##-- Superpose again this time outputing PDBs xyz <- fit.xyz( fixed = pdbs$xyz[1,], mobile = pdbs, fixed.inds = gaps$f.inds, mobile.inds = gaps$f.inds, outpath = "rough_fit", full.pdbs = TRUE) } \donttest{ try({ ##--- Fit two PDBs A <- read.pdb("1bg2") A.ind <- atom.select(A, resno=c(256:269), elety='CA') B <- read.pdb("2kin") B.ind <- atom.select(B, resno=c(257:270), elety='CA') xyz <- fit.xyz(fixed=A$xyz, mobile=B$xyz, fixed.inds=A.ind$xyz, mobile.inds=B.ind$xyz) }, silent=TRUE) if(inherits(.Last.value, "try-error")) { message("Need internet to run the example") } } \dontrun{ # Write out moved PDB C <- B; C$xyz = xyz write.pdb(pdb=C, file = "moved.pdb") } } \keyword{ utilities }