GAMA version 0.2.8

Author: JLewis-dev

CITATION.cff

@@ -1,8 +1,8 @@
 cff-version: 1.2.0
 message: 'If you use GAMA in your research, please cite it as below.'
 title: 'GAMA: Genomic Availability & Metadata Analysis Tool'
-version: 0.2.7
-date-released: 2026-04-23
+version: 0.2.8
+date-released: 2026-05-08
 authors:
   - family-names: Lewis
     given-names: James

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: GAMA
 Title: Genomic Availability & Metadata Analysis Tool
-Version: 0.2.7
+Version: 0.2.8
 Authors@R:
     person('James', 'Lewis',
            email = 'James.Lewis-2022@outlook.com',

NEWS.md

@@ -1,3 +1,21 @@
+# GAMA 0.2.8
+
+## Reliability
+- Patched SRA modality subclass capitalisation so `other` and `unknown` are treated consistently as lower-case labels
+- Added clearer error messaging for invalid `class`, `subclass`, and `unit` argument parameters, including suggestion logic
+
+## API changes
+- Removed the `classes` argument from `plot_sra_geo()`
+- `plot_sra_geo()` now uses a fixed GEO-oriented modality display set
+
+## Documentation
+- Updated roxygen documentation and the GAMA user guide accordingly
+
+## Testing
+- Tested canonical, normalised, fuzzy, and unmatched parameter inputs using real `query_species()` workflows
+
+---
+
 # GAMA 0.2.7
 
 ## Reliability

R/Availability_Analysis.R

@@ -371,7 +371,7 @@ include_geo = FALSE) {
 #'
 #' Retrieves and structures assembly metadata for one or more species using the
 #' Assembly identifiers stored in the output of [query_species()]. Metadata are
-#' returned in a tidy tibble and optionally reduced to a single 'best' assembly
+#' returned in a tidy tibble and optionally reduced to a single best assembly
 #' per species.
 #'
 #' When `best = TRUE`, the best assembly is selected using structural-weighting
@@ -501,6 +501,7 @@ extract_assembly_metadata <- function(results, species = NULL, best = FALSE) {
 #' `SELEX`}
 #' \item{`chromatin`}{`3C-based`, `ChIA-PET`, `Hi-C`, `TCC`}
 #' \item{`other`}{`other`}
+#' \item{`unknown`}{`unknown`}
 #' }
 #'
 #' @param results A list returned by [query_species()], containing SRA IDs.
@@ -540,6 +541,13 @@ only_geo = FALSE) {
     if (length(missing) > 0L) .gama_warn('Requested species not found in `results`: ', paste(missing, collapse = ', '), '. Dropping.')
     species <- species[species %in% names(results)]
   }
+  valid_class <- c(names(.ONTOLOGY), 'unknown')
+  valid_subclass <- c(
+    unique(unlist(lapply(.ONTOLOGY, names), use.names = FALSE)),
+    'unknown'
+  )
+  class <- .gama_validate_choices(class, 'class', valid_class)
+  subclass <- .gama_validate_choices(subclass, 'subclass', valid_subclass)
   if (!is.null(species) && !length(species)) {
     META <- tibble::tibble(
     species       = character(),
@@ -617,9 +625,9 @@ only_geo = FALSE) {
 summarise_sra_skew <- function(x, species = NULL, unit = c('bioproject', 'biosample'), class = NULL) {
   x <- .gama_require_output(x, 'summarise_sra_availability')
   if (missing(unit)) unit <- 'bioproject'
-  if (length(unit) != 1L) .gama_stop('`unit` must be a single value: \'bioproject\' or \'biosample\'.')
-  unit <- match.arg(unit)
-  if (!is.null(class) && length(class) != 1L) .gama_stop('`class` must be a single modality class (or NULL). Use one class per call.')
+  unit <- .gama_validate_choices(unit, 'unit', c('bioproject', 'biosample'), multiple = FALSE, allow_null = FALSE)
+  valid_class <- c(names(.ONTOLOGY), 'unknown')
+  class <- .gama_validate_choices(class, 'class', valid_class, multiple = FALSE)
   prof <- .gama_require_cache(
     x,
     attr_name = 'sra_profile',

R/Core_Logic.R

@@ -174,7 +174,7 @@
 
 .classify_strategy <- function(term, ontology) {
   if (is.na(term) || !nzchar(term) || .is_unknown(term)) {
-    return(list(class = 'unknown', subclass = 'Unknown'))
+    return(list(class = 'unknown', subclass = 'unknown'))
   }
   for (class in names(ontology)) {
     for (subclass in names(ontology[[class]])) {
@@ -183,7 +183,7 @@
       }
     }
   }
-  list(class = 'other', subclass = 'Other')
+  list(class = 'other', subclass = 'other')
 }
 
 .classify_strategy_fallback <- function(strategy_raw,
@@ -192,7 +192,7 @@ source_raw,
 selection_raw,
 title_raw = NA_character_) {
   if (!.is_unknown(strategy_raw) && !.is_unknown(strategy_norm) && !.is_other_strategy(strategy_norm)) {
-    return(list(class = 'other', subclass = 'Other'))
+    return(list(class = 'other', subclass = 'other'))
   }
   src <- .normalise_strategy(source_raw)
   sel <- .normalise_strategy(selection_raw)
@@ -211,7 +211,7 @@ title_raw = NA_character_) {
       return(list(class = 'transcriptomic', subclass = 'small-RNA'))
     }
     if (!is.na(ttl) && grepl('\\biso\\s*seq\\b|\\bisoseq\\b|\\bdirect rna\\b', ttl)) {
-      return(list(class = 'transcriptomic', subclass = 'Long-read'))
+      return(list(class = 'transcriptomic', subclass = 'long-read'))
     }
     return(list(class = 'transcriptomic', subclass = 'RNA-seq'))
   }
@@ -226,8 +226,8 @@ title_raw = NA_character_) {
     if (!is.na(ttl) && grepl('\\bfaire\\b', ttl)) return(list(class = 'epigenomic', subclass = 'FAIRE-seq'))
     if (!is.na(ttl) && grepl('\\bmnase\\b', ttl)) return(list(class = 'epigenomic', subclass = 'MNase-seq'))
     if (!is.na(ttl) && grepl('\\bchip\\b', ttl)) return(list(class = 'epigenomic', subclass = 'ChIP-seq'))
-    if (!is.na(ttl) && grepl('\\bbisulfite\\b|\\bwgbs\\b|\\brrbs\\b|\\bmethyl\\b', ttl)) return(list(class = 'epigenomic', subclass = 'Bisulfite-seq'))
-    return(list(class = 'epigenomic', subclass = 'Other'))
+    if (!is.na(ttl) && grepl('\\bbisulfite\\b|\\bwgbs\\b|\\brrbs\\b|\\bmethyl\\b', ttl)) return(list(class = 'epigenomic', subclass = 'bisulfite-seq'))
+    return(list(class = 'epigenomic', subclass = 'other'))
   }
   if (!is.na(ttl) && grepl('\\batac\\b|\\bdnase\\b|\\bfaire\\b|\\bmnase\\b|\\bchip\\b|\\bcut tag\\b|\\bcutandtag\\b|\\bcut run\\b|\\bcutandrun\\b', ttl)) {
     if (grepl('\\bcut tag\\b|\\bcutandtag\\b', ttl)) return(list(class = 'epigenomic', subclass = 'CUT&Tag'))
@@ -239,14 +239,14 @@ title_raw = NA_character_) {
     if (grepl('\\bchip\\b', ttl)) return(list(class = 'epigenomic', subclass = 'ChIP-seq'))
   }
   if (!is.na(ttl) && grepl('\\bbisulfite\\b|\\bwgbs\\b|\\brrbs\\b|\\bmethyl\\b', ttl)) {
-    return(list(class = 'epigenomic', subclass = 'Bisulfite-seq'))
+    return(list(class = 'epigenomic', subclass = 'bisulfite-seq'))
   }
   if (!is.na(src) && grepl('\\bchromatin\\b|\\bchromosome conformation\\b|\\bconformation\\b', src)) {
     if (!is.na(ttl) && grepl('\\bhi c\\b|\\bhic\\b', ttl)) return(list(class = 'chromatin', subclass = 'Hi-C'))
     if (!is.na(ttl) && grepl('\\bchia pet\\b', ttl)) return(list(class = 'chromatin', subclass = 'ChIA-PET'))
     if (!is.na(ttl) && grepl('\\btcc\\b', ttl)) return(list(class = 'chromatin', subclass = 'TCC'))
     if (!is.na(ttl) && grepl('\\b3c\\b|\\b4c\\b|\\b5c\\b|\\bcapture c\\b|\\bpromoter capture\\b|\\bhichip\\b|\\bplac\\b', ttl)) return(list(class = 'chromatin', subclass = '3C-based'))
-    return(list(class = 'chromatin', subclass = 'Other'))
+    return(list(class = 'chromatin', subclass = 'other'))
   }
   if (!is.na(ttl) && grepl('\\bhi c\\b|\\bhic\\b|\\bchia pet\\b|\\btcc\\b|\\b3c\\b|\\b4c\\b|\\b5c\\b|\\bcapture c\\b|\\bhichip\\b|\\bplac\\b|\\bpromoter capture\\b', ttl)) {
     if (grepl('\\bhi c\\b|\\bhic\\b', ttl)) return(list(class = 'chromatin', subclass = 'Hi-C'))
@@ -255,9 +255,9 @@ title_raw = NA_character_) {
     return(list(class = 'chromatin', subclass = '3C-based'))
   }
   if (.is_unknown(strategy_raw) || .is_unknown(strategy_norm) || .is_other_strategy(strategy_norm)) {
-    return(list(class = 'unknown', subclass = 'Unknown'))
+    return(list(class = 'unknown', subclass = 'unknown'))
   }
-  list(class = 'other', subclass = 'Other')
+  list(class = 'other', subclass = 'other')
 }
 
 .ONTOLOGY <- list(
@@ -276,7 +276,7 @@ title_raw = NA_character_) {
       'genome sequencing',
       'genomic sequencing'
     ),
-    `Amplicon-seq` = c(
+    `amplicon-seq` = c(
       'amplicon',
       'amplicon seq',
       'amplicon sequencing',
@@ -304,7 +304,7 @@ title_raw = NA_character_) {
       'genotyping by sequencing',
       'genotyping by seq'
     ),
-    `Targeted-Capture` = c(
+    `targeted-capture` = c(
       'targeted capture',
       'targeted sequencing',
       'targeted seq',
@@ -320,7 +320,7 @@ title_raw = NA_character_) {
       'panel sequencing',
       'gene panel'
     ),
-    `Clone-based` = c(
+    `clone-based` = c(
       'clone',
       'cloneend',
       'poolclone',
@@ -391,7 +391,7 @@ title_raw = NA_character_) {
       'sirna seq',
       'pirna seq'
     ),
-    `Long-read` = c(
+    `long-read` = c(
       'iso seq',
       'isoseq',
       'direct rna seq',
@@ -402,7 +402,7 @@ title_raw = NA_character_) {
     )
   ),
   epigenomic = list(
-    `Bisulfite-seq` = c(
+    `bisulfite-seq` = c(
       'bisulfite seq',
       'mbd seq',
       'medip seq',
@@ -524,7 +524,7 @@ title_raw = NA_character_) {
     )
   ),
   other = list(
-    `Other` = c(
+    `other` = c(
       'custom',
       'custom sequencing',
       'custom protocol',
@@ -624,12 +624,12 @@ title_raw = NA_character_) {
           if (!is.null(rescue$class) && rescue$class %in% c('genomic', 'transcriptomic', 'epigenomic', 'chromatin')) {
             cls <- rescue
           } else if (.is_unknown(strategy_raw) || .is_unknown(strategy_norm) || .is_other_strategy(strategy_norm)) {
-            cls <- list(class = 'unknown', subclass = 'Unknown')
+            cls <- list(class = 'unknown', subclass = 'unknown')
           }
         }
       }
       if (cls$class == 'other' && (.is_unknown(strategy_raw) || .is_unknown(strategy_norm))) {
-        cls <- list(class = 'unknown', subclass = 'Unknown')
+        cls <- list(class = 'unknown', subclass = 'unknown')
       }
       sra_ids <- .extract_sra_ids(x)
       geo <- .extract_geo_accessions(x$expxml)

R/Helpers.R

@@ -1,6 +1,6 @@
 # HELPERS =====================================================================
 
-.GAMA_VERSION <- '0.2.7'
+.GAMA_VERSION <- '0.2.8'
 
 # NCBI configuration
 
@@ -372,7 +372,93 @@ utils::globalVariables(c(
   stop(.gama_prefix(), paste0(..., collapse = ''), call. = call.)
 }
 
-# Object identity and validation
+# Argument validation
+
+.gama_choice_key <- function(x) {
+  x <- trimws(as.character(x))
+  x <- tolower(x)
+  gsub('[^a-z0-9]+', '', x)
+}
+
+.gama_format_values <- function(x) {
+  paste0("'", x, "'", collapse = ', ')
+}
+
+.gama_suggest_choice <- function(x, choices) {
+  choices <- unique(as.character(choices))
+  x_key <- .gama_choice_key(x)
+  choice_keys <- .gama_choice_key(choices)
+  normalised_match <- choices[choice_keys == x_key]
+  if (length(normalised_match) == 1L) return(normalised_match)
+  d <- as.integer(utils::adist(x_key, choice_keys))
+  best <- min(d)
+  if (best > 2L) return(NA_character_)
+  fuzzy_match <- choices[d == best]
+  if (length(fuzzy_match) == 1L) fuzzy_match else NA_character_
+}
+
+.gama_format_suggestions <- function(invalid, suggestions, pairs = length(invalid) > 1L) {
+  suggestions <- unname(suggestions)
+  if (!isTRUE(pairs)) return(.gama_format_values(suggestions))
+  paste0("'", invalid, "' -> '", suggestions, "'", collapse = '; ')
+}
+
+.gama_validate_choices <- function(x, arg, choices, multiple = TRUE, allow_null = TRUE) {
+  if (is.null(x)) {
+    if (isTRUE(allow_null)) return(invisible(NULL))
+    .gama_stop('`', arg, '` must be a single value.')
+  }
+  if (!is.character(x)) .gama_stop('`', arg, '` must be a character vector or NULL.')
+  if (!multiple && length(x) != 1L) .gama_stop('`', arg, '` must be a single value or NULL.')
+  if (any(is.na(x) | !nzchar(trimws(x)))) .gama_stop('`', arg, '` cannot contain missing or empty values.')
+  choices <- unique(as.character(choices))
+  invalid <- setdiff(unique(x), choices)
+  if (!length(invalid)) return(x)
+  suggestions <- vapply(
+    invalid,
+    .gama_suggest_choice,
+    choices = choices,
+    FUN.VALUE = character(1)
+  )
+  has_suggestion <- !is.na(suggestions) & nzchar(suggestions)
+  if (all(has_suggestion)) {
+    msg <- paste0(
+      'Invalid `',
+      arg,
+      '` parameter',
+      if (length(invalid) > 1L) 's' else '',
+      ': ',
+      .gama_format_values(invalid),
+      '. Did you mean ',
+      .gama_format_suggestions(invalid, suggestions),
+      '?'
+    )
+    .gama_stop(msg)
+  }
+  no_suggestion <- invalid[!has_suggestion]
+  msg <- paste0(
+    'Invalid `',
+    arg,
+    '` parameter',
+    if (length(no_suggestion) > 1L) 's' else '',
+    ': ',
+    .gama_format_values(no_suggestion),
+    '. Accepted values are: ',
+    .gama_format_values(choices),
+    '.'
+  )
+  if (any(has_suggestion)) {
+    msg <- paste0(
+      msg,
+      ' Did you mean ',
+      .gama_format_suggestions(invalid[has_suggestion], suggestions[has_suggestion], pairs = TRUE),
+      '?'
+    )
+  }
+  .gama_stop(msg)
+}
+
+# Object validation
 
 .set_gama_object <- function(x, object_name) {
   attr(x, 'gama_object') <- object_name