johrpan/ubigen
1
0
Fork 0
mirror of https://github.com/johrpan/ubigen.git synced 2025-10-26 19:57:24 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

Introduce more variation measures

Browse source
This commit is contained in:
Elias Projahn 2022-09-25 19:02:13 +02:00
parent 2eec3285f9
commit 76f81ab6a7
3 changed files with 22 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

21
scripts/analyze.R
View file

@ -33,6 +33,15 @@ results <- data[, .(
above_95 = mean(expression > expression_95)
), by = "gene"]
results[, `:=`(
qcv_expression = iqr_expression / median_expression,
qcv_expression_normalized =
iqr_expression_normalized / median_expression_normalized,
cv_expression = sd_expression / mean_expression,
cv_expression_normalized =
sd_expression_normalized / mean_expression_normalized
)]
# Normalize values to the range of 0.0 to 1.0.
results[, `:=`(
median_expression_normalized =
@ -45,6 +54,11 @@ results[, `:=`(
min(iqr_expression_normalized, na.rm = TRUE)) /
(max(iqr_expression_normalized, na.rm = TRUE) -
min(iqr_expression_normalized, na.rm = TRUE)),
qcv_expression_normalized =
(qcv_expression_normalized -
min(qcv_expression_normalized, na.rm = TRUE)) /
(max(qcv_expression_normalized, na.rm = TRUE) -
min(qcv_expression_normalized, na.rm = TRUE)),
mean_expression_normalized =
(mean_expression_normalized -
min(mean_expression_normalized, na.rm = TRUE)) /
@ -54,7 +68,12 @@ results[, `:=`(
(sd_expression_normalized -
min(sd_expression_normalized, na.rm = TRUE)) /
(max(sd_expression_normalized, na.rm = TRUE) -
min(sd_expression_normalized, na.rm = TRUE))
min(sd_expression_normalized, na.rm = TRUE)),
cv_expression_normalized =
(cv_expression_normalized -
min(cv_expression_normalized, na.rm = TRUE)) /
(max(cv_expression_normalized, na.rm = TRUE) -
min(cv_expression_normalized, na.rm = TRUE))
)]
fwrite(results, file = here("scripts", "output", "results.csv"))

4
scripts/ranking.R
View file

@ -10,8 +10,8 @@ genes <- fread(here("scripts", "input", "genes.csv"))
data <- fread(here("scripts", "output", "results.csv"))
data[, score := 0.5 * above_95 +
0.25 * mean_expression_normalized +
-0.25 * sd_expression_normalized]
0.25 * median_expression_normalized +
-0.25 * qcv_expression_normalized]
# Normalize scores to be between 0.0 and 1.0.
data[, score := (score - min(score, na.rm = TRUE)) /