johrpan/geposan
1
0
Fork 0
mirror of https://github.com/johrpan/geposan.git synced 2025-10-26 10:47:25 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

neural: Reimplement merging positions and distances

Browse source
This commit is contained in:
Elias Projahn 2021-11-21 23:55:56 +01:00
parent 5a58f457a4
commit 61422a6a06
4 changed files with 146 additions and 129 deletions
Download patch file Download diff file Expand all files Collapse all files

2
DESCRIPTION
View file

@ -22,7 +22,7 @@ Depends:
R (>= 2.10)
Imports:
data.table,
neuralnet,
keras,
rlang
Suggests:
biomaRt,

3
R/analyze.R
View file

@ -40,9 +40,6 @@ analyze <- function(preset, progress = NULL) {
correlation(..., use_positions = TRUE)
},
"neural" = neural,
"neural_positions" = function(...) {
neural(..., use_positions = TRUE)
},
"proximity" = proximity
)

163
R/neural.R
View file

@ -1,18 +1,10 @@
# Find genes by training a neural network on reference position data.
#
# @param seed A seed to get reproducible results.
neural <- function(preset,
use_positions = FALSE,
progress = NULL,
seed = 448077) {
# Find genes by training and applying a neural network.
neural <- function(preset, progress = NULL, seed = 49641) {
species_ids <- preset$species_ids
gene_ids <- preset$gene_ids
reference_gene_ids <- preset$reference_gene_ids
cached(
"neural",
c(species_ids, gene_ids, reference_gene_ids, use_positions),
{ # nolint
cached("neural", c(species_ids, gene_ids, reference_gene_ids), {
set.seed(seed)
gene_count <- length(gene_ids)
@ -24,31 +16,24 @@ neural <- function(preset,
# variables.
data <- data.table(gene = gene_ids)
# Buffer to keep track of species included in the computation.
# Species from `species_ids` may be excluded if they don't have
# enough data.
species_ids_included <- NULL
# Buffer to keep track of the names of the input variables.
input_vars <- NULL
# Make a column containing positions for each species.
# Make a columns containing positions and distances for each
# species.
for (species_id in species_ids) {
species_data <- if (use_positions) {
setnames(distances[
species_data <- distances[
species == species_id,
.(gene, position)
], "position", "distance")
} else {
distances[
species == species_id,
.(gene, distance)
.(gene, position, distance)
]
}
# Only include species with at least 25% known values.
# Only include species with at least 25% known values. As
# positions and distances always coexist, we don't loose any
# data here.
species_data <- stats::na.omit(species_data)
if (nrow(species_data) >= 0.25 * gene_count) {
species_ids_included <- c(species_ids_included, species_id)
data <- merge(data, species_data, all.x = TRUE)
# Replace missing data with mean values. The neural network
@ -58,18 +43,33 @@ neural <- function(preset,
# 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]
# Name the new column after the species.
setnames(data, "distance", species_id)
data[is.na(distance), `:=`(
position = mean_position,
distance = mean_distance
)]
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)
}
}
# Extract the reference genes.
reference_data <- data[gene %chin% reference_gene_ids]
reference_data[, neural := 1.0]
reference_data[, score := 1.0]
# Take out random samples from the remaining genes. This is another
# compromise with a negative impact on significance. Because there
@ -86,61 +86,82 @@ neural <- function(preset,
)
]
reference_samples[, neural := 0.0]
reference_samples[, score := 0.0]
# Merge training data. The training data includes all reference
# genes as well as an equal number of random sample genes.
training_data <- rbindlist(list(reference_data, reference_samples))
# Construct and train the neural network.
# Layers for the neural network.
input_layer <- length(input_vars)
layer1 <- input_layer
layer2 <- 0.5 * input_layer
layer3 <- 0.5 * layer2
nn_formula <- stats::as.formula(sprintf(
"neural~%s",
paste(species_ids_included, collapse = "+")
))
# Train the model using the specified subset of the training data and
# apply it for predicting the genes.
apply_network <- function(training_gene_ids, gene_ids) {
# Create a new model for each training session, because the model
# would keep its state across training sessions otherwise.
model <- keras::keras_model_sequential() |>
keras::layer_dense(
units = layer1,
activation = "relu",
input_shape = input_layer,
) |>
keras::layer_dense(
units = layer2,
activation = "relu",
kernel_regularizer = keras::regularizer_l2()
) |>
keras::layer_dense(
units = layer3,
activation = "relu",
kernel_regularizer = keras::regularizer_l2()
) |>
keras::layer_dense(
units = 1,
activation = "sigmoid"
) |>
keras::compile(loss = "binary_crossentropy")
layer1 <- length(species_ids) * 0.66
layer2 <- layer1 * 0.66
layer3 <- layer2 * 0.66
# Prepare training data by filtering it to the given genes and
# converting it to a matrix.
training_data <- training_data[gene %chin% training_gene_ids]
training_matrix <- as.matrix(training_data[, ..input_vars])
colnames(training_matrix) <- NULL
training_matrix <- keras::normalize(training_matrix)
nn <- neuralnet::neuralnet(
nn_formula,
training_data,
hidden = c(layer1, layer2, layer3),
linear.output = FALSE
keras::fit(
model,
x = training_matrix,
y = training_data$score,
epochs = 300,
verbose = FALSE
)
if (!is.null(progress)) {
progress(0.33)
# Convert the input data to a matrix.
data_matrix <- as.matrix(data[gene %chin% gene_ids, ..input_vars])
colnames(data_matrix) <- NULL
data_matrix <- keras::normalize(data_matrix)
data[gene %chin% gene_ids, score := predict(model, data_matrix)]
}
# Apply the neural network.
data[, score := neuralnet::compute(nn, data)$net.result]
# Reconstruct and run the neural network for each training gene
# by training it without the respective gene.
for (gene_id in training_data$gene) {
nn <- neuralnet::neuralnet(
nn_formula,
training_data[gene != gene_id],
hidden = c(layer1, layer2, layer3),
linear.output = FALSE
# Apply the network to all non-training genes first.
apply_network(
training_data$gene,
gene_ids[!gene_ids %chin% training_data$gene]
)
data[
gene == gene_id,
score := neuralnet::compute(
nn,
training_data[gene == gene_id]
)$net.result
]
}
if (!is.null(progress)) {
progress(1.0)
# Apply the network to the training genes leaving out the gene itself.
for (training_gene_id in training_data$gene) {
apply_network(
training_data[gene != training_gene_id, gene],
training_gene_id
)
}
data[, .(gene, score)]
}
)
})
}

1
R/preset.R
View file

@ -43,7 +43,6 @@ preset <- function(methods = c(
"correlation",
"correlation_positions",
"neural",
"neural_positions",
"proximity"
),
species_ids = NULL,