Merge pull request #50 from ShawHahnLab/release-0.3.0

Release 0.3.0

.Rbuildignore

@@ -2,11 +2,8 @@
 ^\.Rproj\.user$
 ^\.travis.yml$
 .utils
-environment.yml
-install_linux_conda.sh
 install_linux.sh
 install_windows.cmd
-install_windows.R
 install_mac.command
 README.md
 GUIDE.Rmd

.travis.yml

@@ -1,14 +1,29 @@
+# https://docs.travis-ci.com/user/multi-os/
+os:
+  - linux
+  - osx
 # https://docs.travis-ci.com/user/languages/r
 language: r
-bioc_packages: msa
 r:
   - oldrel
   - release
   - devel
   - bioc-release
+  - bioc-devel
+# Mac OS R devel build URL is out of date, currently.
+# https://travis-ci.community/t/672
+matrix:
+  exclude:
+    - r: devel
+      os: osx
 cache: packages
 script:
   - R CMD build .
   - R CMD check *tar.gz
-  - ./inst/bin/demo.sh
-  - ./inst/bin/demo_empty.sh
+  - ./exec/demo.sh
+  - ./exec/demo_empty.sh
+  - ./tools/travis_install_test.sh
+# Don't cache the installed chiimp R package itself.  We want to start without
+# it installed for each test.
+before_cache:
+  - rm -rf $HOME/R/Library/chiimp

DESCRIPTION

@@ -1,16 +1,20 @@
 Package: chiimp
 Title: Computational, High-throughput Individual Identification through Microsatellite Profiling
-Version: 0.2.3
+Version: 0.3.0
 Authors@R: person("Jesse", "Connell", email = "[email protected]", role = c("aut", "cre"))
 Description: An R package to analyze microsatellites in high-throughput sequencing datasets.
 Depends: R (>= 3.2.3)
 License: file LICENSE
 Encoding: UTF-8
 LazyData: true
+Language: en-US
+biocViews:
 Imports:
   argparser (>= 0.4),
+  Biostrings (>= 2.38.4),
   dnaplotr (>= 0.1),
   dnar (>= 0.1),
+  devtools (>= 1.13.5),
   graphics (>= 3.2.3),
   grDevices (>= 3.2.3),
   kableExtra (>= 0.2.1.9000),
@@ -29,7 +33,7 @@ Imports:
 Remotes:
   github::sherrillmix/dnar,
   github::sherrillmix/dnaplotr
-RoxygenNote: 6.0.1
+RoxygenNote: 6.1.1
 Suggests:
   testthat,
   roxygen2

GUIDE.Rmd

@@ -4,7 +4,7 @@
 
 title: "CHIIMP User Guide"
 author: "Jesse Connell"
-date: "2018/11/07"
+date: "2019/07/10"
 output:
   pdf_document:
     toc: true
@@ -34,8 +34,12 @@ package documentation.
 
 ## Installation
 
-Most dependencies are provided by installation of [R] and [RStudio].  Once these
-are installed, follow the specific instructions below for your operating system.
+Most dependencies are provided by installation of [R] and [RStudio].  Once
+these are installed, follow the specific instructions below for your operating
+system.  In all three cases CHIIMP performs an anlysis when a configuration
+file is dragged and dropped onto the desktop icon; there is no interactive
+interface via the icon, though the R package can be used interactively.  See
+the Usage section for more information.
 
 ### Windows
 
@@ -51,6 +55,10 @@ right-click (control+click) and select "Open" in the menu that appears.
 Apple has specific instructions [here](https://support.apple.com/kb/PH25088?locale=en_US)
 about these security setings.
 
+If a window appears recommending installation of the Mac OS command-line
+developer tools, go ahead and install them.  After that you'll probably need to
+re-run the CHIIMP installer again to finish the install.
+
 ### Linux
 
 On Linux, run the `install_linux.sh` shell script to automatically install the 

NAMESPACE

@@ -14,6 +14,7 @@ export(full_analysis)
 export(histogram)
 export(load_allele_names)
 export(load_config)
+export(load_csv)
 export(load_dataset)
 export(load_genotypes)
 export(load_locus_attrs)
@@ -39,6 +40,7 @@ export(sample_summary_funcs)
 export(save_alignment_images)
 export(save_alignments)
 export(save_allele_seqs)
+export(save_csv)
 export(save_dataset)
 export(save_dist_mat)
 export(save_histograms)

NEWS.md

@@ -1,3 +1,24 @@
+# chiimp 0.3.0
+
+ * Improved icon setup on Mac OS ([#48]).
+ * Added support for use of reverse primers in locus-matching ([#47]).
+ * Made read count ratio thresholds for PCR stutter and artifact sequence
+   flagging customizable ([#46]).
+ * Added drag-and-drop usage message when desktop icon is opened directly
+   ([#44]).
+ * Added `load_csv` and `save_csv` functions to centralize loading and saving
+   tabular data ([#43]).
+ * Reorganized installer and wrapper scripts ([#38]).
+ * Added support for demo scripts and integration testing in Mac OS ([#32]).
+
+[#48]: https://github.com/ShawHahnLab/chiimp/pull/48
+[#47]: https://github.com/ShawHahnLab/chiimp/pull/47
+[#46]: https://github.com/ShawHahnLab/chiimp/pull/46
+[#44]: https://github.com/ShawHahnLab/chiimp/pull/44
+[#43]: https://github.com/ShawHahnLab/chiimp/pull/43
+[#38]: https://github.com/ShawHahnLab/chiimp/pull/38
+[#32]: https://github.com/ShawHahnLab/chiimp/pull/32
+
 # chiimp 0.2.3
 
  * Fixed package checks and testing on latest R development releases ([#27]).

R/analyze_dataset.R

@@ -20,6 +20,15 @@
 #'   \code{\link{load_locus_attrs}}.
 #' @param nrepeats number of repeats of each locus' motif to require for a
 #'   match (see \code{\link{analyze_seqs}}).
+#' @param stutter.count.ratio_max highest ratio of read counts for second most
+#'   frequent sequence to the most frequent where the second will be
+#'   considered stutter (see \code{\link{analyze_seqs}}).
+#' @param artifact.count.ratio_max as for \code{stutter.count.ratio_max} but for
+#'   non-stutter artifact sequences.
+#' @param use_reverse_primers consider the ReversePrimer column from the locus
+#'   attributes for locus-matching?
+#' @param reverse_primer_r1 Is each reverse primer given in its orientation on
+#'   the forward read?  (See \code{\link{analyze_seqs}})
 #' @param ncores integer number of CPU cores to use in parallel for sample
 #'   analysis.  Defaults to one less than half the number of detected cores with
 #'   a minimum of 1.  If 1, the function will run without using the
@@ -44,16 +53,25 @@
 #'   per-sample data frames.
 #'
 #' @export
-analyze_dataset <- function(dataset,
-                            locus_attrs,
-                            nrepeats,
-                            ncores = 0,
-                            analysis_opts,
-                            summary_opts,
-                            analysis_function=analyze_sample,
-                            summary_function=summarize_sample,
-                            known_alleles=NULL,
-                            name_args=list()) {
+analyze_dataset <- function(
+  dataset,
+  locus_attrs,
+  nrepeats,
+  stutter.count.ratio_max = config.defaults$seq_analysis$
+    stutter.count.ratio_max,
+  artifact.count.ratio_max = config.defaults$seq_analysis$
+    artifact.count.ratio_max,
+  use_reverse_primers = config.defaults$seq_analysis$
+    use_reverse_primers,
+  reverse_primer_r1 = config.defaults$seq_analysis$
+    reverse_primer_r1,
+  ncores = 0,
+  analysis_opts,
+  summary_opts,
+  analysis_function=analyze_sample,
+  summary_function=summarize_sample,
+  known_alleles=NULL,
+  name_args=list()) {
   if (! all(dataset$Locus %in% locus_attrs$Locus)) {
     rogue_loci <- unique(dataset$Locus[! dataset$Locus %in% locus_attrs$Locus])
     msg <- paste("ERROR: Locus names in dataset not in attributes table:",
@@ -63,9 +81,15 @@ analyze_dataset <- function(dataset,
   if (ncores == 0) {
     ncores <- max(1, as.integer(parallel::detectCores() / 2) - 1)
   }
-  analyze.file <- function(fp, locus_attrs, nrepeats) {
+  analyze.file <- function(fp, locus_attrs, nrepeats,
+                           stutter.count.ratio_max, artifact.count.ratio_max,
+                           use_reverse_primers,
+                           reverse_primer_r1) {
     seqs <- load_seqs(fp)
-    analyze_seqs(seqs, locus_attrs, nrepeats)
+    analyze_seqs(seqs, locus_attrs, nrepeats,
+                 stutter.count.ratio_max, artifact.count.ratio_max,
+                 use_reverse_primers,
+                 reverse_primer_r1)
   }
   analyze.entry <- function(entry, analysis_opts, summary_opts,
                             analysis_function, summary_function,
@@ -114,7 +138,11 @@ analyze_dataset <- function(dataset,
       fps <- unique(dataset$Filename)
       analyzed_files <- parallel::parLapply(cluster, fps, analyze.file,
                                             locus_attrs = locus_attrs,
-                                            nrepeats = nrepeats)
+                                            nrepeats = nrepeats,
+                                            stutter.count.ratio_max,
+                                            artifact.count.ratio_max,
+                                            use_reverse_primers,
+                                            reverse_primer_r1)
       names(analyzed_files) <- fps
       raw.results <- parallel::parApply(cluster, dataset, 1, analyze.entry,
                                         analysis_opts = analysis_opts,
@@ -130,7 +158,11 @@ analyze_dataset <- function(dataset,
     fps <- unique(dataset$Filename)
     analyzed_files <- lapply(fps, analyze.file,
                              locus_attrs = locus_attrs,
-                             nrepeats = nrepeats)
+                             nrepeats = nrepeats,
+                             stutter.count.ratio_max,
+                             artifact.count.ratio_max,
+                             use_reverse_primers,
+                             reverse_primer_r1)
     names(analyzed_files) <- fps
     raw.results <- apply(dataset, 1, analyze.entry,
                          analysis_opts = analysis_opts,