Properly access distance data

R/analyze.R

@@ -45,9 +45,8 @@ analyze <- function(preset, progress = NULL) {
     #
     # A method describes a way to perform a computation on gene distance data
     # that results in a single score per gene. The function should accept the
-    # distances data, the preset to apply (see [preset()]) and an optional
+    # preset to apply (see [preset()]) and an optional progress function (that
-    # progress function (that may be called with a number between 0.0 and 1.0)
+    # may be called with a number between 0.0 and 1.0) as its parameters.
-    # as its parameters.
     #
     # The function should return a [data.table] with the following columns:
     #
@@ -62,19 +61,14 @@ analyze <- function(preset, progress = NULL) {
 
     total_progress <- 0.0
     method_count <- length(preset$method_ids)
-    results <- data.table(gene = genes$id)
+    results <- data.table(gene = preset$gene_ids)
 
     for (method_id in preset$method_ids) {
         method_progress <- if (!is.null(progress)) function(p) {
             progress(total_progress + p / method_count)
         }
 
-        method_results <- methods[[method_id]](
+        method_results <- methods[[method_id]](preset, method_progress)
-            distances,
-            preset,
-            method_progress
-        )
-
         setnames(method_results, "score", method_id)
 
         results <- merge(

R/clusteriness.R

@@ -36,11 +36,11 @@ clusteriness_priv <- function(data, height = 1000000) {
 }
 
 # Process genes clustering their distance to telomeres.
-clusteriness <- function(distances, preset, progress = NULL) {
+clusteriness <- function(preset, progress = NULL) {
     results <- data.table(gene = preset$gene_ids)
 
     # Prefilter the input data by species.
-    distances <- distances[species %chin% preset$species_ids]
+    distances <- geposan::distances[species %chin% preset$species_ids]
 
     # Add an index for quickly accessing data per gene.
     setkey(distances, gene)

R/correlation.R

@@ -1,12 +1,12 @@
 # Compute the mean correlation coefficient comparing gene distances with a set
 # of reference genes.
-correlation <- function(distances, preset, progress = NULL) {
+correlation <- function(preset, progress = NULL) {
     species_ids <- preset$species_ids
     gene_ids <- preset$gene_ids
     reference_gene_ids <- preset$reference_gene_ids
 
     # Prefilter distances by species.
-    distances <- distances[species %chin% species_ids]
+    distances <- geposan::distances[species %chin% species_ids]
 
     # Tranform data to get species as rows and genes as columns. We construct
     # columns per species, because it requires fewer iterations, and transpose

R/neural.R

@@ -1,7 +1,7 @@
 # Find genes by training a neural network on reference position data.
 #
 # @param seed A seed to get reproducible results.
-neural <- function(distances, preset, progress = NULL, seed = 448077) {
+neural <- function(preset, progress = NULL, seed = 448077) {
     species_ids <- preset$species_ids
     reference_gene_ids <- preset$reference_gene_ids
 
@@ -9,7 +9,7 @@ neural <- function(distances, preset, progress = NULL, seed = 448077) {
     gene_count <- length(preset$gene_ids)
 
     # Prefilter distances by species.
-    distances <- distances[species %chin% species_ids]
+    distances <- geposan::distances[species %chin% species_ids]
 
     # Input data for the network. This contains the gene ID as an identifier
     # as well as the per-species gene distances as input variables.

R/proximity.R

@@ -2,9 +2,9 @@
 #
 # A score will be given to each gene such that 0.0 corresponds to the maximal
 # mean distance across all genes and 1.0 corresponds to a distance of 0.
-proximity <- function(distances, preset, progress = NULL) {
+proximity <- function(preset, progress = NULL) {
     # Prefilter distances by species and gene.
-    distances <- distances[
+    distances <- geposan::distances[
         species %chin% preset$species_ids & gene %chin% preset$gene_ids
     ]