johrpan/geposanui
1
0
Fork 0
mirror of https://github.com/johrpan/geposanui.git synced 2025-10-26 11:17:24 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

Enhance progress information

Browse source
This commit is contained in:
Elias Projahn 2021-09-21 16:47:13 +02:00
parent 8e54dacd3d
commit ba7c624705
3 changed files with 49 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

22
clustering.R
View file

@ -1,4 +1,5 @@
library(data.table)
library(progress)
library(rlog)
#' Process genes clustering their distance to telomeres.
@ -17,14 +18,21 @@ process_clustering <- function(distances, species_ids, gene_ids) {
results <- data.table(gene = gene_ids)
gene_count <- length(gene_ids)
for (i in 1:gene_count) {
gene_id <- gene_ids[i]
log_info(sprintf(
"Clustering %i genes from %i species",
gene_count,
length(species_ids)
))
log_info(sprintf(
"[%3i%%] Processing gene \"%s\"",
round(i / gene_count * 100),
gene_id
))
progress <- progress_bar$new(
total = gene_count,
format = "Clustering genes [:bar] :percent (ETA :eta)"
)
for (i in 1:gene_count) {
progress$tick()
gene_id <- gene_ids[i]
data <- distances[
species %chin% species_ids & gene == gene_id,

24
correlation.R
View file

@ -1,4 +1,5 @@
library(data.table)
library(progress)
library(rlog)
#' Compute the mean correlation coefficient comparing gene distances with a set
@ -15,24 +16,29 @@ library(rlog)
#' @param reference_gene_ids Genes to compare to.
process_correlation <- function(distances, species_ids, gene_ids,
reference_gene_ids) {
log_info("Processing genes for correlation")
results <- data.table(gene = gene_ids)
gene_count <- length(gene_ids)
reference_count <- length(reference_gene_ids)
log_info(sprintf(
"Correlating %i genes from %i species with %i reference genes",
gene_count,
length(species_ids),
reference_count
))
progress <- progress_bar$new(
total = gene_count,
format = "Correlating genes [:bar] :percent (ETA :eta)"
)
# Prefilter distances by species.
distances <- distances[species %chin% species_ids]
for (i in 1:gene_count) {
progress$tick()
gene_id <- gene_ids[i]
log_info(sprintf(
"[%3i%%] Processing gene \"%s\"",
round(i / gene_count * 100),
gene_id
))
gene_distances <- distances[gene == gene_id]
if (nrow(gene_distances) < 12) {

29
input.R
View file

@ -1,5 +1,6 @@
library(biomaRt)
library(data.table)
library(progress)
library(rlog)
library(stringr)
@ -115,6 +116,23 @@ retrieve_genes <- function() {
#' - `gene` Ensembl gene ID.
#' - `distance` Distance to nearest telomere in base pairs.
retrieve_distances <- function(species_ids, gene_ids) {
# Exclude the human from the species, in case it is present there.
species_ids <- species_ids[species_ids != "hsapiens"]
species_count <- length(species_ids)
gene_count <- length(gene_ids)
log_info(sprintf(
"Retrieving distance data for %i genes from %i species",
gene_count,
species_count
))
progress <- progress_bar$new(
total = gene_count,
format = "Retrieving distance data [:bar] :percent (ETA :eta)"
)
# Special case the human species and retrieve all available distance
# information.
@ -148,19 +166,10 @@ retrieve_distances <- function(species_ids, gene_ids) {
)
]
# Exclude the human from the species, in case it is present there.
species_ids <- species_ids[species_ids != "hsapiens"]
species_count <- length(species_ids)
for (i in 1:species_count) {
species_id <- species_ids[i]
log_info(sprintf(
"[%3i%%] Loading species \"%s\"",
round(i / species_count * 100),
species_id
))
progress$tick()
ensembl <- useDataset(
sprintf("%s_gene_ensembl", species_id),