Refactoring to a proper package

.gitignore

@@ -1,11 +1 @@
-# History files
-.Rhistory
-
-# Example code in package build process
-*-Ex.R
-
-# R data files from past sessions
-.Rdata
-
-# RStudio files
-.Rproj.user/
+inst/doc

DESCRIPTION

@@ -0,0 +1,17 @@
+Package: Romulus
+Title: Robust Multi-State Identification of Transcription Factor Binding Sites
+Version: 1.0.0.9000
+Authors@R: person("Aleksander", "Jankowski", email = "ajank@mimuw.edu.pl", role = c("aut", "cre"))
+Description: Romulus is a computational method to accurately identify individual
+    transcription factor binding sites from genome sequence information and
+    cell-type--specific experimental data, such as DNase-seq. It combines the
+    strengths of its predecessors, CENTIPEDE and Wellington, while keeping
+    the number of free parameters in the model robustly low. The method is
+    unique in allowing for multiple binding states for a single transcription
+    factor, differing in their cut profile and overall number of DNase I cuts.
+URL: http://github.com/ajank/Romulus
+Depends: R (>= 2.10)
+License: GPL-3
+LazyData: true
+Suggests: knitr
+VignetteBuilder: knitr

NAMESPACE

@@ -0,0 +1 @@
+exportPattern("^[^\\.]")

R/data.R

@@ -0,0 +1,33 @@
+#' Annotations of 4,828 NRSF (REST) motif instances.
+#'
+#' A dataset containing the annotations of 4,828 NRSF (REST) motif instances in the human genome (hg19 assembly).
+#'
+#' @format A data frame with 4828 rows and 6 variables:
+#' \describe{
+#'   \item{chrom}{chromosome}
+#'   \item{start}{starting base pair (1-based, inclusive)}
+#'   \item{end}{ending base pair}
+#'   \item{strand}{strand (\code{"-"} or \code{"+"})}
+#'   \item{score}{Position Weight Matrix score (log-likelihood)}
+#'   \item{signalValue}{ChIP-seq signal value in K562 cells}
+#' }
+#' @source Motif instances are downloaded from \url{http://homer.salk.edu/homer/} (HOMER Known Motifs track).
+#'
+#' ChIP-seq signal value was extracted from \url{http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeAwgTfbsUniform/wgEncodeAwgTfbsHaibK562NrsfV0416102UniPk.narrowPeak.gz}.
+"NRSF.anno"
+
+#' DNase I cuts around 4,828 NRSF (REST) motif instances.
+#'
+#' A dataset containing the exact numbers of DNase I cuts around 4,828 NRSF (REST) motif instances, split into forward and reverse strand cuts.
+#'
+#' @format An integer matrix with 4828 rows and 838 columns. Columns 1-419 correspond to forward strand cuts (200 bp upstream + 19 bp motif site + 200 bp downstream), while columns 420-838 correspond to reverse strand cuts at the same positions.
+#'
+#' @source Extracted from \url{http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeOpenChromDnase/wgEncodeOpenChromDnaseK562AlnRep1V2.bam}.
+"NRSF.cuts"
+
+#' Number of base pairs of margin for \code{NRSF.cuts}.
+#'
+#' Number of base pairs of upstream and downstream margin for \code{NRSF.cuts}.
+#'
+#' @format Integer, equal to 200 (base pairs).
+"NRSF.margin"