--- a
+++ b/man/get_start_ind.Rd
@@ -0,0 +1,50 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/preprocess.R
+\name{get_start_ind}
+\alias{get_start_ind}
+\title{Computes start position of samples}
+\usage{
+get_start_ind(
+  seq_vector,
+  length_vector,
+  maxlen,
+  step,
+  train_mode = "label",
+  discard_amb_nuc = FALSE,
+  vocabulary = c("A", "C", "G", "T")
+)
+}
+\arguments{
+\item{seq_vector}{Vector of character sequences.}
+
+\item{length_vector}{Length of sequences in \code{seq_vector}.}
+
+\item{maxlen}{Length of one predictor sequence.}
+
+\item{step}{Distance between samples from one entry in \code{seq_vector}.}
+
+\item{train_mode}{Either \code{"lm"} for language model or \code{"label"} for label classification.}
+
+\item{discard_amb_nuc}{Whether to discard all samples that contain characters outside vocabulary.}
+
+\item{vocabulary}{Vector of allowed characters. Characters outside vocabulary get encoded as specified in \code{ambiguous_nuc}.}
+}
+\value{
+A numeric vector.
+}
+\description{
+Helper function for data generators.
+Computes start positions in sequence where samples can be extracted, given maxlen, step size and ambiguous nucleotide constraints.
+}
+\examples{
+seq_vector <- c("AAACCCNNNGGGTTT")
+get_start_ind(
+  seq_vector = seq_vector,
+  length_vector = nchar(seq_vector),
+  maxlen = 4,
+  step = 2,
+  train_mode = "label",
+  discard_amb_nuc = TRUE,
+  vocabulary = c("A", "C", "G", "T"))
+  
+}