Merge pull request #7 from NBISweden/0.1.0

Update tests and documentation for 0.1.0 release

.Rbuildignore

@@ -4,3 +4,7 @@
 ^scripts$
 ^doc$
 ^Meta$
+^_pkgdown\.yml$
+^docs$
+^pkgdown$
+^tests/testthat.R$

.github/workflows/R-CMD-check.yaml

@@ -4,19 +4,18 @@ name: R-CMD-check
 
 jobs:
   R-CMD-check:
-    runs-on: macOS-latest
+    runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - uses: r-lib/actions/setup-r@master
-      - uses: r-lib/actions/setup-pandoc@master
-      - name: Install dependencies
-        run: |
-          install.packages(c("remotes", "rcmdcheck", "knitr"))
-          deps <- remotes::dev_package_deps(dependencies = TRUE)
-          install.packages(deps$package[!is.na(deps$available)])
-          if (!requireNamespace("BiocManager", quietly = TRUE)) {install.packages("BiocManager")}
-          BiocManager::install(deps$package[is.na(deps$available)])
-        shell: Rscript {0}
-      - name: Check
-        run: rcmdcheck::rcmdcheck(args = "--no-manual", error_on = "error")
-        shell: Rscript {0}
+      - uses: actions/checkout@v3
+      - uses: r-lib/actions/setup-r@v2
+      - uses: r-lib/actions/setup-pandoc@v2
+        with:
+          pandoc-version: '2.17.1'
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::rcmdcheck devtools
+          needs: check
+      - uses: r-lib/actions/check-r-package@v2
+        with:
+          args: 'c("--no-manual")'
+          error-on: '"error"'

.github/workflows/pkgdown.yaml

@@ -0,0 +1,48 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+    branches: [main, master]
+  release:
+    types: [published]
+  workflow_dispatch:
+
+name: pkgdown
+
+jobs:
+  pkgdown:
+    runs-on: ubuntu-latest
+    # Only restrict concurrency for non-PR jobs
+    concurrency:
+      group: pkgdown-${{ github.event_name != 'pull_request' || github.run_id }}
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v3
+
+      - uses: r-lib/actions/setup-pandoc@v2
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::pkgdown, local::.
+          needs: website
+
+      - name: Build site
+        run: pkgdown::build_site_github_pages(new_process = FALSE, install = FALSE)
+        shell: Rscript {0}
+
+      - name: Deploy to GitHub pages 🚀
+        if: github.event_name != 'pull_request'
+        uses: JamesIves/github-pages-deploy-action@v4.4.1
+        with:
+          clean: false
+          branch: gh-pages
+          folder: docs

.lintr

@@ -0,0 +1,2 @@
+linters: linters_with_defaults(
+    indentation_linter(hanging_indent_style="tidy"))

.pre-commit-config.yaml

@@ -0,0 +1,52 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: check-merge-conflict
+      - id: debug-statements
+      - id: mixed-line-ending
+      - id: detect-private-key
+      - id: check-case-conflict
+      - id: check-yaml
+      - id: trailing-whitespace
+  - repo: https://github.com/DavidAnson/markdownlint-cli2
+    rev: v0.11.0
+    hooks:
+      - id: markdownlint-cli2
+        files: \.(md|qmd)$
+        types: [file]
+        exclude: LICENSE.md
+      - id: markdownlint-cli2-fix
+        files: \.(md|qmd)$
+        types: [file]
+        exclude: LICENSE.md
+  - repo: https://github.com/lorenzwalthert/precommit
+    rev: v0.3.2.9027
+    hooks:
+      - id: style-files
+        name: style-files
+        description: style files with {styler}
+        entry: Rscript inst/hooks/exported/style-files.R
+        language: r
+        files: '(\.[rR]profile|\.[rR]|\.[rR]md|\.[rR]nw|\.[qQ]md)$'
+        exclude: |
+          (?x)^(
+          renv/activate\.R|
+          )$
+        minimum_pre_commit_version: "2.13.0"
+      - id: parsable-R
+        name: parsable-R
+        description: check if a .R file is parsable
+        entry: Rscript inst/hooks/exported/parsable-R.R
+        language: r
+        files: '\.[rR](md)?$'
+        minimum_pre_commit_version: "2.13.0"
+      - id: lintr
+        args: [--warn_only]
+        name: lintr
+        description: check if a `.R` file is lint free (using {lintr})
+        entry: Rscript inst/hooks/exported/lintr.R
+        language: r
+        files: '(\.[rR]profile|\.R|\.Rmd|\.Rnw|\.r|\.rmd|\.rnw)$'
+        exclude: 'renv/activate\.R'
+        minimum_pre_commit_version: "2.13.0"

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: genecovr
 Title: Gene body coverage analysis to evaluate genome assemblies
-Version: 0.0.0.9013
-Authors@R: 
+Version: 0.1.0
+Authors@R:
     person(given = "Per",
            family = "Unneberg",
            role = c("aut", "cre"),
@@ -14,9 +14,7 @@ License: GPL-3
 Encoding: UTF-8
 LazyData: true
 Imports:
-	BiocGenerics,
 	BiocParallel,
-	Biostrings,
 	GenomeInfoDb,
 	GenomicRanges (>= 1.32.0),
 	IRanges,
@@ -36,4 +34,5 @@ Suggests:
 VignetteBuilder:
 	knitr
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.1.2
+RoxygenNote: 7.2.3
+URL: https://nbisweden.github.io/genecovr/

README.Rmd

@@ -19,21 +19,30 @@ knitr::opts_chunk$set(
 [![R build status](https://github.com/NBISweden/genecovr/workflows/R-CMD-check/badge.svg)](https://github.com/NBISweden/genecovr/actions)
 <!-- badges: end -->
 
-Perform gene body coverage analyses in R to evaluate genome assembly
-quality.
+`genecovr` is an `R` package that provides plotting functions that
+summarize gene transcript to genome alignments. The main purpose is to
+assess the effect of polishing and scaffolding operations has on the
+quality of a genome assembly. The gene transcript set is a large
+sequence set consisting of assembled transcripts from RNA-seq data
+generated in relation to a genome assembly project. Therefore,
+`genecovr` serves as a complement to software such as
+[BUSCO](https://busco.ezlab.org/), which evaluates genome assembly
+quality using a smaller set of well-defined single-copy orthologs.
 
 ## Installation
 
 You can install the released version of genecovr from [NBIS
 GitHub](https://github.com/nbis) with:
 
 ``` r
+# If necessary, uncomment to install devtools
 # install.packages("devtools")
 devtools::install_github("NBISweden/genecovr")
 ```
 
+## Usage
 
-## Quick usage
+### genecovr script quick start
 
 There is a helper script for generating basic plots located in
 PACKAGE_DIR/bin/genecovr. Create a data input csv-delimited file with
@@ -52,8 +61,67 @@ script to generate plots:
 PACKAGE_DIR/bin/genecovr indata.csv
 ```
 
-## Vignette
+#### Example
 
-Alternatively, import the library as usual in an R script and use the
-package functions. See the vignette for a minimum working example.
+There are example files located in PACKAGE_DIR/inst/extdata consisting
+of two psl alignment files containing gmap alignments and fasta
+indices for the transcript sequences and two for different assembly
+versions:
 
+- nonpolished.fai - fasta index for raw assembly
+- polished.fai - fasta index for polished assembly
+- transcripts.fai - fasta index for transcript sequences
+- transcripts2nonpolished.psl - gmap alignments, transcripts to raw assembly
+- transcripts2polished.psl - gmap alignments, transcripts to polished
+  assembly
+
+Using these files and the labels `non` and `pol` for the different
+assemblies, a `genecovr` input file (called e.g., `assemblies.csv`)
+would look as follows:
+
+```
+nonpol,transcripts2nonpolished.psl,nonpolished.fai,transcripts.fai
+pol,transcripts2polished.psl,polished.fai,transcripts.fai
+```
+
+and the command to run would be:
+
+```
+genecovr assemblies.csv
+```
+
+#### genecovr options
+
+To list genecovr script options, type 'genecovr -h`:
+
+```
+usage: genecovr [-h] [-v] [-p number]
+                             [-d OUTPUT_DIRECTORY] [--height HEIGHT]
+                             [--width WIDTH]
+                             csvfile
+
+positional arguments:
+  csvfile               csv-delimited file with columns
+                            1. data label
+                            2. mapping file (supported formats: psl)
+                            3. assembly file (fasta or fasta index)
+                            4. transcript file (fasta or fasta index)
+
+optional arguments:
+  -h, --help            show this help message and exit
+  -v, --verbose         print extra output
+  -p number, --cpus number
+                        number of cpus [default 1]
+  -d OUTPUT_DIRECTORY, --output-directory OUTPUT_DIRECTORY
+                        output directory
+  --height HEIGHT       figure height in inches [default 6.0]
+  --width WIDTH         figure width in inches [default 6.0]
+```
+
+
+
+### R package vignette
+
+Alternatively, import the library in an R script and use the package
+functions. See [Get started](articles/genecovr.html) or run
+`vignette("genecovr")` for a minimum working example.

_pkgdown.yml

@@ -0,0 +1,9 @@
+url: https://nbisweden.github.io/genecovr/
+template:
+  bootstrap: 5
+
+reference:
+  - title: genecovr
+  - contents:
+      - matches(".*")
+

inst/bin/genecovr

@@ -131,6 +131,7 @@ apl <- AlignmentPairsList(
                 seqinfo.query=transcripts.sinfo[[x]])
     }, BPPARAM=bpparam)
 )
+
 names(apl) <- names(psl.fn)
 
 ##------------------------------
@@ -183,8 +184,9 @@ save_plot(p, outfile)
 
 
 ## FIXME: number of levels should be parametrized via option
+suppressPackageStartupMessages(library(dplyr))
 outfile <- file.path(outdir, "qnuminsert")
-x <- insertionSummary(apl, reduce=FALSE)
+x <- dplyr::tibble(insertionSummary(apl, reduce=FALSE))
 p <- ggplot(x, aes(id)) +
     geom_bar(aes(fill=cuts)) +
     scale_fill_viridis_d(name="qNumInsert", begin=1, end=0)
@@ -199,9 +201,8 @@ message("saving ", outfile)
 write.csv(x, file=gzfile(outfile), row.names=FALSE)
 
 ## Also make plot based on gbc
-suppressPackageStartupMessages(library(dplyr))
 outfile <- file.path(outdir, "qnuminsert.gbc")
-x <- insertionSummary(apl)
+x <- dplyr::tibble(insertionSummary(apl))
 p <- ggplot(x, aes(id)) +
     geom_bar(aes(fill=cuts)) +
     scale_fill_viridis_d(name="qNumInsert", begin=1, end=0)
@@ -211,6 +212,10 @@ save_plot(p, outfile)
 ##--------------------
 ## Save gbc data
 ##--------------------
+x$revmap <- as.character(x$revmap)
+x$hitCoverage <- as.character(x$hitCoverage)
+x$hitStart <- as.character(x$hitStart)
+x$hitEnd <- as.character(x$hitEnd)
 outfile <- file.path(outdir, "gbcdata.tsv.gz")
 message("saving ", outfile)
 write.table(x, file=gzfile(outfile), row.names=FALSE, sep="\t")
@@ -313,11 +318,13 @@ p <- ggplot(data=subset(data, n.subjects>1),
 outfile <- file.path(outdir, paste0("depth_breadth_seqlengths.mm", mm))
 save_plot(p, outfile)
 
-
+data$revmap <- as.character(data$revmap)
+data$hitCoverage <- as.character(data$hitCoverage)
+data$hitStart <- as.character(data$hitStart)
+data$hitEnd <- as.character(data$hitEnd)
 outfile <- file.path(outdir, "gene_body_coverage.csv.gz")
 message("saving ", outfile)
-write.csv(data, gzfile(outfile), row.names=FALSE)
-
+write.csv(dplyr::tibble(data), gzfile(outfile), row.names=FALSE)
 
 ##############################
 ## Save Rdata of analysis