CRAN 7.2 submission

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

@@ -26,6 +26,7 @@ jobs:
     env:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
       R_KEEP_PKG_SOURCE: yes
+      NOT_CRAN: true
 
     steps:
       - uses: actions/checkout@v3
@@ -43,7 +44,12 @@ jobs:
           extra-packages: |
             any::rcmdcheck
             any::covr
+            any::polyRAD
           needs: check
+
+      - name: Install VariantAnnotation (no Suggests)
+        run: pak::pkg_install("bioc::VariantAnnotation", dependencies = c("Depends", "Imports", "LinkingTo"))
+        shell: Rscript {0}
       - uses: r-lib/actions/check-r-package@v2
 
       - name: Generate test coverage report
@@ -57,4 +63,3 @@ jobs:
           token: ${{ secrets.CODECOV_TOKEN }}
           slug: Breeding-Insight/BIGr
           files: coverage.xml
-

.gitignore

@@ -3,3 +3,4 @@
 .RData
 .Ruserdata
 revdep/
+.DS_Store

BIGr.Rproj

@@ -1,4 +1,5 @@
 Version: 1.0
+ProjectId: 0eeaab63-2615-4da7-b10a-927160fc78a3
 
 RestoreWorkspace: No
 SaveWorkspace: No

CRAN-SUBMISSION

@@ -1,3 +1,3 @@
-Version: 0.6.2
-Date: 2025-09-18 12:16:11 UTC
-SHA: 142dc9524d88b47db88ddca2aa39cd729a8d5a0d
+Version: 0.7.2
+Date: 2026-05-17 23:05:53 UTC
+SHA: 0fd7d9c081cfb341c56dc58de4d77d283d7ce726

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: BIGr
 Title: Breeding Insight Genomics Functions for Polyploid and Diploid Species
-Version: 0.6.2
+Version: 0.7.2
 Authors@R: c(person(given='Alexander M.',
                     family='Sandercock',
                     email='sandercock.alex@gmail.com',
@@ -23,7 +23,7 @@ Authors@R: c(person(given='Alexander M.',
              person(given='Dongyan',
                     family='Zhao',
                     role='ctb'),
-             person('Cornell', 'University',
+             person('University', "of Florida",
                     role=c('cph'), 
                     comment = "Breeding Insight"))
 Maintainer: Alexander M. Sandercock <sandercock.alex@gmail.com>
@@ -44,7 +44,7 @@ URL: https://github.com/Breeding-Insight/BIGr
 BugReports: https://github.com/Breeding-Insight/BIGr/issues
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.2
+RoxygenNote: 7.3.3
 Depends: R (>= 4.4.0)
 biocViews:
 Imports: 
@@ -62,12 +62,15 @@ Imports:
     janitor,
     quadprog,
     tibble,
-    stringr
+    stringr,
+    data.table
 Suggests: 
     covr,
+    ggplot2,
     spelling,
     rmdformats,
     knitr (>= 1.10),
     rmarkdown,
+    polyRAD,
     testthat (>= 3.0.0)   
 RdMacros: Rdpack

NAMESPACE

@@ -4,27 +4,30 @@ export(allele_freq_poly)
 export(calculate_Het)
 export(calculate_MAF)
 export(check_homozygous_trios)
+export(check_madc_sanity)
 export(check_ped)
 export(check_replicates)
 export(dosage2vcf)
 export(dosage_ratios)
 export(filterMADC)
 export(filterVCF)
+export(find_parentage)
 export(flip_dosage)
 export(get_countsMADC)
 export(imputation_concordance)
 export(madc2gmat)
 export(madc2vcf_all)
+export(madc2vcf_multi)
 export(madc2vcf_targets)
 export(merge_MADCs)
 export(solve_composition_poly)
 export(thinSNP)
 export(updog2vcf)
+export(validate_pedigree)
 import(dplyr)
 import(janitor)
 import(parallel)
 import(quadprog)
-import(rlang)
 import(stringr)
 import(tibble)
 import(tidyr)
@@ -33,13 +36,36 @@ importFrom(Biostrings,DNAString)
 importFrom(Biostrings,reverseComplement)
 importFrom(Rdpack,reprompt)
 importFrom(Rsamtools,bgzip)
+importFrom(data.table,CJ)
+importFrom(data.table,as.data.table)
+importFrom(data.table,copy)
+importFrom(data.table,data.table)
+importFrom(data.table,fread)
+importFrom(data.table,fwrite)
+importFrom(data.table,rbindlist)
+importFrom(data.table,set)
+importFrom(dplyr,"%>%")
+importFrom(dplyr,across)
+importFrom(dplyr,arrange)
+importFrom(dplyr,case_when)
+importFrom(dplyr,filter)
+importFrom(dplyr,group_by)
+importFrom(dplyr,group_modify)
+importFrom(dplyr,mutate)
+importFrom(dplyr,select)
+importFrom(dplyr,summarise)
+importFrom(dplyr,ungroup)
+importFrom(dplyr,where)
 importFrom(pwalign,nucleotideSubstitutionMatrix)
 importFrom(pwalign,pairwiseAlignment)
 importFrom(readr,read_csv)
 importFrom(reshape2,dcast)
 importFrom(reshape2,melt)
+importFrom(rlang,sym)
 importFrom(stats,cor)
+importFrom(stats,reorder)
 importFrom(stats,setNames)
+importFrom(tibble,as_tibble)
 importFrom(utils,packageVersion)
 importFrom(utils,read.csv)
 importFrom(utils,read.table)

NEWS.md

@@ -1,3 +1,107 @@
+# BIGr 0.7.2
+
+- Fixed manual text errors
+
+# BIGr 0.7.1
+
+- Updated `check_ped()` to return corrected pedigree data in the result list instead of assigning objects to the global environment
+- Skipped long remote `madc2vcf_all` integration tests on CRAN while keeping them enabled in GitHub Actions
+
+# BIGr 0.7.0
+
+## Updates on `dosage2vcf`
+
+- Added support for DArT SNP/INDEL 1-row and 2-row report formats
+- `dosage2vcf` now validates marker and sample sets between report and counts files, then aligns counts to the report order before writing VCF genotypes
+- VCF `CHROM` and `POS` are derived from `Chrom`/`ChromPos` when present, otherwise from `MarkerName`; `MarkerName` is retained in the VCF `ID` field
+- Missing SNP/INDEL genotype calls (`-`/`NA`) are written as diploid missing genotypes (`./.`)
+
+## New function `madc2vcf_multi`
+
+- New function `madc2vcf_multi` to convert a DArTag MADC file to a VCF using the polyRAD pipeline for multiallelic genotyping
+- Runs `check_madc_sanity` before loading the data and stops with informative errors if:
+    - Required columns are missing
+    - IUPAC (non-ATCG) codes are present in AlleleSequence
+    - Ref/Alt sequences are unpaired (`RefAltSeqs = FALSE`)
+    - Allele IDs have not been fixed by HapApp (`FixAlleleIDs = FALSE`)
+    - CloneIDs do not follow `Chr_Pos` format and no `markers_info` is provided
+- New argument `markers_info`: optional path or URL to a CSV with `CloneID`/`BI_markerID`, `Chr`, and `Pos` columns; required when CloneIDs do not follow the `Chr_Pos` format
+- Runs `check_botloci` to validate and reconcile CloneIDs between the MADC and botloci file, automatically fixing padding mismatches
+- A corrected temp file is written and passed to `readDArTag` only when needed (all-NA rows/columns detected, CloneIDs remapped by `check_botloci`, or botloci IDs remapped)
+- Accepts paths or URLs for `madc_file`, `botloci_file`, and `markers_info`
+- Estimates overdispersion with `polyRAD::TestOverdispersion`, iterates priors with `polyRAD::IterateHWE`, and exports the result with `polyRAD::RADdata2VCF`
+- `polyRAD` is a soft dependency (listed under `Suggests`); an informative error is raised if it is not installed
+
+# BIGr 0.6.6
+
+## Updates on `madc2vcf_all`
+
+- New arguments for controlling processing of `Other` alleles:
+    - `add_others`: if `TRUE` (default), alleles labeled "Other" in the MADC are included in off-target SNP extraction
+    - `others_max_snps`: discards Other alleles with more than this many SNP differences relative to the Ref sequence (default: 5)
+    - `others_rm_with_indels`: discards Other alleles containing insertions or deletions relative to the Ref sequence (default: `TRUE`)
+- Others alleles that carry a different base at the target SNP position are now reported as a 3rd allele in the VCF instead of being silently dropped
+- Target position is now correctly removed from Others alignments, preventing duplicate VCF positions and marker IDs
+- Fixed a bug where Others alleles with "Ref_" or "Alt_" in their AlleleID would corrupt the target SNP REF/ALT fields and read depth counts in `merge_counts`
+- Improved verbose messages throughout: counts of Other alleles found, kept, and discarded (by indel filter and by max SNP filter) are now reported; multiallelic target SNPs with a 3rd allele from Others are counted and reported
+- Debug-level message (level 3) listing each Other allele added and its genomic position
+
+# BIGr 0.6.5
+
+## Updates on madc2vcf functions
+Details:
+
+- both functions targets and all (targets + off-targets) markers now have `check_madc_sanity` function implemented. It tests:
+    - [Columns] If MADC has the expected columns
+    - [allNArow | allNAcol] Presence of columns and rows with all NA (happens often when people open the MADC in excel before loading in R)
+    - [IUPACcodes] Presence of IUPAC codes on AlleleSequence
+    - [LowerCase] Presence of lower case bases on AlleleSequence
+    - [Indels] Presence of Indels
+    - [ChromPos] If CloneID follows the format Chr_Pos
+    - [RefAltSeqs] If all Ref Allele has corresponding Alt and vice-versa
+    - [OtherAlleles] If "Other" exists in the MADC AlleleID
+
+- Better messages if `verbose = TRUE` in `madc2vcf_all`
+- `madc2vcf_all` support for Indels - markers_info with Indels position is required; only the target indel is extracted, off-targets are ignored for the tag
+- `madc2vcf_targets` doesn’t run if: 
+    - MADC Column names are not correct
+    - Ignore Other alleles - but inform the user if they exist or not and direct them to `madc2vcf_all` in case they want to extract them as well
+- See the table for madc2vcf_targets requirements accordingly to MADC content:
+
+  | check status | get_REF_ALT | Requires
+-- | -- | -- | --
+IUPAC | TRUE | TRUE | markers_info REF/ALT
+  | TRUE | FALSE | -
+  | FALSE | TRUE | botloci or markers_info REF/ALT
+  | FALSE | FALSE | -
+Indels | TRUE | TRUE | markers_info REF/ALT
+  | TRUE | FALSE | -
+  | FALSE | TRUE | botloci or markers_info REF/ALT
+  | FALSE | FALSE | -
+ChromPos | TRUE | TRUE | botloci or markers_info REF/ALT
+  | TRUE | FALSE | -
+  | FALSE | TRUE | markers_info CHR/POS/REF/ALT or markers_info CHR/POS/ + botloci
+  | FALSE | FALSE | markers_info CHR/POS
+FixAlleleIDs | TRUE | TRUE | botloci or markers_info REF/ALT
+  | TRUE | FALSE | -
+  | FALSE | TRUE | markers_info REF/ALT
+  | FALSE | FALSE | -
+
+# BIGr 0.6.4
+
+- Add function `vmsg` to organize messages printed on the console
+- Add metadata to VCF header from madc2vcf_targets
+- Add argument `madc_object` to `get_countsMADC` to avoid reading the MADC file twice and to get directly the MADC fixed padding output from `check_botloci`
+- Organize messages from `madc2vcf_targets` checks
+- Add argument `collapse_matches_counts` and `verbose` to `madc2vcf_targets` function
+
+# BIGr 0.6.3
+
+- New function to check MADC files: `check_madc_sanity`. Currently, it checks for the presence of required columns, whether fixed allele IDs were assigned, the presence of IUPAC codes, lowercase sequence bases, indels, and chromosome and position information.
+- Added new argument `markers_info`, which allows users to provide a CSV file with marker information such as CHROM, POS, marker type, and position of indels. For BI species, this information is available from [PanelHub](https://github.com/Breeding-Insight/BIGapp-PanelHub).
+- Checked inputs for `madc2vcf_all`.
+- Updated affiliation in `DESCRIPTION`.
+
 # BIGr 0.6.2
 
 - Fixed the doi and name list in the CITATION file
@@ -51,4 +155,3 @@
 -   updog2vcf function option to output compressed VCF (.vcf.gz) - set as default
 -   remove need for defining ploidy
 -   add metadata at the VCF header
-