From 599f09a52ff386bc0c76685d77daefffade71d75 Mon Sep 17 00:00:00 2001
From: Elias Projahn <elias@johrpan.de>
Date: Mon, 22 Nov 2021 15:16:05 +0100
Subject: [PATCH] Remove position analysis

---
 R/analyze.R      |  6 ------
 R/clusteriness.R | 11 +++--------
 R/correlation.R  | 21 ++++++---------------
 R/neural.R       | 27 ++++++---------------------
 R/preset.R       |  2 --
 5 files changed, 15 insertions(+), 52 deletions(-)

diff --git a/R/analyze.R b/R/analyze.R
index 6db623b..e443ca0 100644
--- a/R/analyze.R
+++ b/R/analyze.R
@@ -32,13 +32,7 @@ analyze <- function(preset, progress = NULL) {
     #  - `score` Score for the gene between 0.0 and 1.0.
     methods <- list(
         "clusteriness" = clusteriness,
-        "clusteriness_positions" = function(...) {
-            clusteriness(..., use_positions = TRUE)
-        },
         "correlation" = correlation,
-        "correlation_positions" = function(...) {
-            correlation(..., use_positions = TRUE)
-        },
         "neural" = neural,
         "proximity" = proximity
     )
diff --git a/R/clusteriness.R b/R/clusteriness.R
index f2490a1..d884000 100644
--- a/R/clusteriness.R
+++ b/R/clusteriness.R
@@ -36,11 +36,11 @@ clusteriness_priv <- function(data, height = 1000000) {
 }
 
 # Process genes clustering their distance to telomeres.
-clusteriness <- function(preset, use_positions = FALSE, progress = NULL) {
+clusteriness <- function(preset, progress = NULL) {
     species_ids <- preset$species_ids
     gene_ids <- preset$gene_ids
 
-    cached("clusteriness", c(species_ids, gene_ids, use_positions), {
+    cached("clusteriness", c(species_ids, gene_ids), {
         results <- data.table(gene = gene_ids)
 
         # Prefilter the input data by species.
@@ -54,12 +54,7 @@ clusteriness <- function(preset, use_positions = FALSE, progress = NULL) {
 
         # Perform the cluster analysis for one gene.
         compute <- function(gene_id) {
-            data <- if (use_positions) {
-                distances[gene_id, position]
-            } else {
-                distances[gene_id, distance]
-            }
-
+            data <- distances[gene_id, distance]
             score <- clusteriness_priv(data)
 
             if (!is.null(progress)) {
diff --git a/R/correlation.R b/R/correlation.R
index e0057a8..60831a1 100644
--- a/R/correlation.R
+++ b/R/correlation.R
@@ -1,14 +1,12 @@
 # Compute the mean correlation coefficient comparing gene distances with a set
 # of reference genes.
-correlation <- function(preset, use_positions = FALSE, progress = NULL) {
+correlation <- function(preset, progress = NULL) {
     species_ids <- preset$species_ids
     gene_ids <- preset$gene_ids
     reference_gene_ids <- preset$reference_gene_ids
 
     cached(
-        "correlation",
-        c(species_ids, gene_ids, reference_gene_ids, use_positions),
-        { # nolint
+        "correlation", c(species_ids, gene_ids, reference_gene_ids), {
             # Prefilter distances by species.
             distances <- geposan::distances[species %chin% species_ids]
 
@@ -20,17 +18,10 @@ correlation <- function(preset, use_positions = FALSE, progress = NULL) {
 
             # Make a column containing distance data for each species.
             for (species_id in species_ids) {
-                species_data <- if (use_positions) {
-                    setnames(distances[
-                        species == species_id,
-                        .(gene, position)
-                    ], "position", "distance")
-                } else {
-                    distances[
-                        species == species_id,
-                        .(gene, distance)
-                    ]
-                }
+                species_data <- distances[
+                    species == species_id,
+                    .(gene, distance)
+                ]
 
                 data <- merge(data, species_data, all.x = TRUE)
                 setnames(data, "distance", species_id)
diff --git a/R/neural.R b/R/neural.R
index 91f332c..c36bc98 100644
--- a/R/neural.R
+++ b/R/neural.R
@@ -25,10 +25,7 @@ neural <- function(preset, progress = NULL, seed = 49641) {
         # Make a columns containing positions and distances for each
         # species.
         for (species_id in species_ids) {
-            species_data <- distances[
-                species == species_id,
-                .(gene, position, distance)
-            ]
+            species_data <- distances[species == species_id, .(gene, distance)]
 
             # Only include species with at least 25% known values. As
             # positions and distances always coexist, we don't loose any
@@ -46,26 +43,14 @@ neural <- function(preset, progress = NULL, seed = 49641) {
                 # However, this will of course lessen the significance of
                 # the results.
 
-                mean_position <- round(species_data[, mean(position)])
                 mean_distance <- round(species_data[, mean(distance)])
+                data[is.na(distance), `:=`(distance = mean_distance)]
 
-                data[is.na(distance), `:=`(
-                    position = mean_position,
-                    distance = mean_distance
-                )]
+                # Name the new column after the species.
+                setnames(data, "distance", species_id)
 
-                input_position <- sprintf("%s_position", species_id)
-                input_distance <- sprintf("%s_distance", species_id)
-
-                # Name the new columns after the species.
-                setnames(
-                    data,
-                    c("position", "distance"),
-                    c(input_position, input_distance)
-                )
-
-                # Add the input variables to the buffer.
-                input_vars <- c(input_vars, input_position, input_distance)
+                # Add the input variable to the buffer.
+                input_vars <- c(input_vars, species_id)
             }
         }
 
diff --git a/R/preset.R b/R/preset.R
index cc21615..e3b0edd 100644
--- a/R/preset.R
+++ b/R/preset.R
@@ -40,9 +40,7 @@
 #' @export
 preset <- function(methods = c(
                        "clusteriness",
-                       "clusteriness_positions",
                        "correlation",
-                       "correlation_positions",
                        "neural",
                        "proximity"
                    ),