add strelka, minimap2, freebayes

DESCRIPTION

@@ -34,6 +34,6 @@ Suggests:
 Config/testthat/edition: 3
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.2
+RoxygenNote: 7.3.3
 URL: https://github.com/WangLabCSU/blit, https://wanglabcsu.github.io/blit/
 BugReports: https://github.com/WangLabCSU/blit/issues

NAMESPACE

@@ -30,17 +30,20 @@ export(exec)
 export(fastp)
 export(fastq_pair)
 export(fastq_read_pair)
+export(freebayes)
 export(gistic2)
 export(install_appmamba)
 export(kraken2)
 export(kraken_tools)
 export(make_command)
+export(minimap2)
 export(perl)
 export(pyscenic)
 export(python)
 export(samtools)
 export(seqkit)
 export(snpEff)
+export(strelka)
 export(trust4)
 export(trust4_gene_names)
 export(trust4_imgt_annot)

NEWS.md

@@ -16,6 +16,10 @@
 
 * new command `bedtools`
 
+* new command `strelka`
+
+* new command `minimap2`
+
 # blit 0.2.0
 
 ## New features

R/cmd-freebayes.R

@@ -0,0 +1,53 @@
+#' Run freebayes
+#'
+#'freebayes is a Bayesian genetic variant detector designed to find small polymorphisms, 
+#'specifically SNPs (single-nucleotide polymorphisms), indels (insertions and deletions), 
+#'MNPs (multi-nucleotide polymorphisms), and complex events (composite insertion and substitution events) 
+#'smaller than the length of a short-read sequencing alignment.
+#' @param ref A string of reference file path.
+#' @param input A string of path to the input bam file.
+#' @param ofile A string of path to the output vcf file.
+#' @param ... `r rd_dots("freebayes")`.
+#' @param freebayes `r rd_cmd("freebayes")`.
+#' @family command
+#' @inherit exec return
+#' @seealso
+#' - <https://github.com/freebayes/freebayes>
+#'
+#' `r rd_seealso()`
+#' @export
+freebayes <- make_command(
+  "freebayes",
+  function(
+    ref,
+    input,
+    ofile,
+    ...,
+    freebayes = NULL
+  ){
+    assert_string(freebayes, allow_empty = FALSE, allow_null = TRUE)
+    Freebayes$new(
+      cmd = freebayes,
+      ...,
+      ref = ref,
+      input = input,
+      ofile = ofile,
+    )
+  }
+)
+
+Freebayes <- R6Class(
+  "Freebayes",
+  inherit = Command,
+  private = list(
+    alias = function() "freebayes",
+    setup_help_params = function() "--help",
+    setup_command_params = function(ref, input, ofile){
+      c(
+        arg0("-f", ref),
+        arg0("-b", input),
+        arg0("-v", ofile)
+      )
+    }
+  )
+)

R/cmd-minimap2.R

@@ -0,0 +1,70 @@
+#' Run minimap2
+#'
+#' Minimap2 is a versatile sequence alignment program that aligns DNA or mRNA sequences against a large reference database. 
+#' Typical use cases include: 
+#' (1) mapping PacBio or Oxford Nanopore genomic reads to the human genome; 
+#' (2) finding overlaps between long reads with error rate up to ~15%; 
+#' (3) splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA reads against a reference genome; 
+#' (4) aligning Illumina single- or paired-end reads; 
+#' (5) assembly-to-assembly alignment; 
+#' (6) full-genome alignment between two closely related species with divergence below ~15%.
+#' 
+#' @param method Mapping preset: "map-ont" (single-end long reads) or "sr" (paired-end short reads).
+#' @param ref Path to the reference genome FASTA file.
+#' @param reads A character vector of FASTQ files used as input to minimap2.
+#' @param ofile A string of path to the output SAM file.
+#' @param ... `r rd_dots("minimap2")`.
+#' @param minimap2 `r rd_cmd("minimap2")`.
+#' @family command
+#' @inherit exec return
+#' @seealso
+#' - <https://github.com/lh3/minimap2>
+#'
+#' `r rd_seealso()`
+#' @export
+minimap2 <- make_command(
+  "minimap2",
+  function(
+    method,
+    ref,
+    reads,
+    ofile,
+    ...,
+    minimap2 = NULL
+  ){
+    assert_string(minimap2, allow_empty = FALSE, allow_null = TRUE)
+    Minimap2$new(
+      cmd = minimap2,
+      ...,
+      method = method,
+      ref = ref,
+      reads = reads,
+      ofile = ofile
+    )
+  }
+)
+
+Minimap2 <- R6Class(
+  "Minimap2",
+  inherit = Command,
+  private = list(
+    alias = function() "minimap2",
+    setup_help_params = function() "--help",
+    setup_command_params = function(method, ref, reads, ofile){
+      c(
+        if (!method %in% c("map-ont", "sr")){
+          cli::cli_abort("{.arg method} must be map-ont or sr!")
+        } else { arg0("-ax", method) },
+        ref,
+        if (length(reads) == 1L){
+          reads
+        } else if (length(reads) == 2L){
+          reads
+        } else {
+          cli::cli_abort("{.arg reads} must be of length 1 or 2")
+        },
+        arg0(">", ofile)
+      )
+    }
+  )
+)

R/cmd-strelka.R

@@ -0,0 +1,50 @@
+#' Run strelka
+#' 
+#' Strelka is a fast and accurate small variant caller optimized for analysis of germline variation 
+#' in small cohorts and somatic variation in tumor/normal sample pairs. 
+#'
+#' @param script Name of the Strelka script. One of
+#' `r oxford_comma(code_quote(StrelkaScripts))`.
+#' @param ... `r rd_dots("strelka")`.
+#' @param strelka `r rd_cmd("strelka")`.
+#' @seealso 
+#' - <https://github.com/Illumina/strelka>
+#' 
+#' `r rd_seealso()`
+#' @inherit exec return
+#' @family command
+#' @export
+strelka <- make_command(
+  "strelka",
+  function(script, ...) {
+    script <- rlang::arg_match0(script, StrelkaScripts)
+    Strelka$new(
+      script = script,
+      ...
+      )
+  }
+)
+
+Strelka <- R6::R6Class(
+  "Strelka",
+  inherit = Command,
+  private = list(
+    alias = function() "strelka",
+    command_locate = function() {
+      py2 <- Sys.which("python2")
+      if (py2 == "") {
+        stop("Cannot locate python2. Please install it or activate a Conda environment with Python2.")
+      }else{py2}
+    },
+    setup_help_params = function() "--help",
+    setup_command_params = function(script) {
+      script_path <- pkg_extdata("strelka", paste0(script, ".py"))
+      file_executable(script_path)
+      c(script_path, super$combine_params())
+    }
+  )
+)
+
+StrelkaScripts <- c(
+  "configureStrelkaGermlineWorkflow", "configureStrelkaSomaticWorkflow", "runWorkflow"
+)

_pkgdown.yml

@@ -52,6 +52,9 @@ reference:
     - varscan
     - snpEff
     - gistic2
+    - strelka
+    - minimap2
+    - freebayes
 
   - title: "Transcriptomic tools"
     desc: "Wrappers for transcriptome sequencing data processing and analysis tools."