Initial commit

This commit is contained in:
Elias Projahn 2021-10-19 13:39:55 +02:00
commit c52d42c2b6
24 changed files with 1350 additions and 0 deletions

19
man/analyze.Rd Normal file
View file

@ -0,0 +1,19 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/analyze.R
\name{analyze}
\alias{analyze}
\title{Analyze by applying the specified preset.}
\usage{
analyze(preset)
}
\arguments{
\item{preset}{The preset to use which can be created using \code{\link[=preset]{preset()}}.}
}
\value{
A \link{data.table} with one row for each gene identified by it's ID
(\code{gene} column). The additional columns contain the resulting scores per
method and are named after the method IDs.
}
\description{
Analyze by applying the specified preset.
}

22
man/distances.Rd Normal file
View file

@ -0,0 +1,22 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/data.R
\docType{data}
\name{distances}
\alias{distances}
\title{Information on gene positions across species.}
\format{
A \link{data.table} with 1390730 rows and 3 variables:
\describe{
\item{species}{Species ID}
\item{gene}{Gene ID}
\item{distance}{Distance to nearest telomere}
}
}
\usage{
distances
}
\description{
This dataset contains each known value for a gene's distance to the telomeres
per species. The data is sourced from Ensembl.
}
\keyword{datasets}

23
man/genes.Rd Normal file
View file

@ -0,0 +1,23 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/data.R
\docType{data}
\name{genes}
\alias{genes}
\title{Information on human genes within the Ensembl database.}
\format{
A \link{data.table} with 60568 rows and 3 variables:
\describe{
\item{id}{Ensembl gene ID}
\item{name}{The gene's HGNC name}
\item{chrosome}{The human chromosome the gene is located on}
\item{n_species}{Number of known species with the gene.}
}
}
\usage{
genes
}
\description{
This includes only genes on the primary suggested assembly of the human
nuclear DNA.
}
\keyword{datasets}

22
man/optimize_weights.Rd Normal file
View file

@ -0,0 +1,22 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/ranking.R
\name{optimize_weights}
\alias{optimize_weights}
\title{Find the best weights to rank the results.}
\usage{
optimize_weights(results, methods, reference_gene_ids)
}
\arguments{
\item{results}{Results from \code{\link[=analyze]{analyze()}} or \code{\link[=ranking]{ranking()}}.}
\item{methods}{Methods to include in the score.}
\item{reference_gene_ids}{IDs of the reference genes.}
}
\value{
Named list pairing method names with their optimal weights.
}
\description{
This function finds the optimal parameters to \code{\link[=ranking]{ranking()}} that result in the
reference genes ranking particulary high.
}

34
man/preset.Rd Normal file
View file

@ -0,0 +1,34 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/analyze.R
\name{preset}
\alias{preset}
\title{Create a new preset.}
\usage{
preset(methods, species, genes, reference_genes)
}
\arguments{
\item{methods}{IDs of methods to apply.}
\item{species}{IDs of species to include.}
\item{genes}{IDs of genes to screen.}
\item{reference_genes}{IDs of reference genes to compare to.}
}
\value{
The preset to use with \code{\link[=analyze]{analyze()}}.
}
\description{
A preset is used to specify which methods and inputs should be used for an
analysis. Note that the genes to process should normally include the
reference genes to be able to assess the results later.
}
\details{
Available methods are:
\itemize{
\item \code{clusteriness} How much the gene distances cluster across species.
\item \code{correlation} The mean correlation with the reference genes.
\item \code{proximity} Mean proximity to telomeres.
\item \code{neural} Assessment by neural network.
}
}

17
man/ranking.Rd Normal file
View file

@ -0,0 +1,17 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/ranking.R
\name{ranking}
\alias{ranking}
\title{Rank the results by computing a score.}
\usage{
ranking(results, weights)
}
\arguments{
\item{results}{Results from \code{\link[=analyze]{analyze()}}.}
\item{weights}{Named list pairing method names with weighting factors.}
}
\description{
This function takes the result from \code{\link[=analyze]{analyze()}} and creates a score by
computing a weighted mean across the different methods' results.
}

20
man/species.Rd Normal file
View file

@ -0,0 +1,20 @@
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/data.R
\docType{data}
\name{species}
\alias{species}
\title{Information on included species from the Ensembl database.}
\format{
A \link{data.table} with 91 rows and 2 variables:
\describe{
\item{id}{Unique species ID}
\item{name}{Human readable species name}
}
}
\usage{
species
}
\description{
Information on included species from the Ensembl database.
}
\keyword{datasets}