prepare_training_data_indels: Prepare Training Data with Indel Information

In JakobPedersenLab/dreams: Deep Read-level Error Model for Sequencing data

Prepare Training Data with Indel Information

Description

This function processes training data by selecting specific features and the observed values (obs) for genomic data, including nucleotide bases and indels (insertions 'I' and deletions 'D'). It then prepares this data for use in machine learning models, particularly those that require categorical data to be converted into a one-hot encoded format.

Usage

prepare_training_data_indels(training_data, model_features)

Arguments

training_data	A data frame containing the training data.
model_features	A vector of selected feature names to be used in the model.

Value

A list with two elements: features containing the selected features of the training data, and labels containing the one-hot encoded labels.

JakobPedersenLab/dreams documentation built on Feb. 2, 2024, 3:14 p.m.