% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/preprocess.R
\name{seq_encoding_lm}
\alias{seq_encoding_lm}
\title{Encodes integer sequence for language model}
\usage{
seq_encoding_lm(
  sequence = NULL,
  maxlen,
  vocabulary,
  start_ind,
  ambiguous_nuc = "zero",
  nuc_dist = NULL,
  quality_vector = NULL,
  return_int = FALSE,
  target_len = 1,
  use_coverage = FALSE,
  max_cov = NULL,
  cov_vector = NULL,
  n_gram = NULL,
  n_gram_stride = 1,
  output_format = "target_right",
  char_sequence = NULL,
  adjust_start_ind = FALSE,
  tokenizer = NULL
)
}
\arguments{
\item{sequence}{Sequence of integers.}

\item{maxlen}{Length of predictor sequence.}

\item{vocabulary}{Vector of allowed characters. Characters outside vocabulary get encoded as specified in \code{ambiguous_nuc}.}

\item{start_ind}{Start positions of samples in \code{sequence}.}

\item{ambiguous_nuc}{How to handle nucleotides outside vocabulary, either \code{"zero"}, \code{"empirical"} or \code{"equal"}.
See \code{\link{train_model}}. Note that \code{"discard"} option is not available for this function.}

\item{nuc_dist}{Nucleotide distribution.}

\item{quality_vector}{Vector of quality probabilities.}

\item{return_int}{Whether to return integer encoding or one-hot encoding.}

\item{target_len}{Number of nucleotides to predict at once for language model.}

\item{use_coverage}{Integer or \code{NULL}. If not \code{NULL}, use coverage as encoding rather than one-hot encoding and normalize.
Coverage information must be contained in fasta header: there must be a string \code{"cov_n"} in the header, where \code{n} is some integer.}

\item{max_cov}{Biggest coverage value. Only applies if \code{use_coverage = TRUE}.}

\item{cov_vector}{Vector of coverage values associated to the input.}

\item{n_gram}{Integer, encode target not nucleotide wise but combine n nucleotides at once. For example for \verb{n=2, "AA" ->  (1, 0,..., 0),}
\verb{"AC" ->  (0, 1, 0,..., 0), "TT" -> (0,..., 0, 1)}, where the one-hot vectors have length \code{length(vocabulary)^n}.}

\item{n_gram_stride}{Step size for n-gram encoding. For AACCGGTT with \code{n_gram = 4} and \code{n_gram_stride = 2}, generator encodes
\verb{(AACC), (CCGG), (GGTT)}; for \code{n_gram_stride = 4} generator encodes \verb{(AACC), (GGTT)}.}

\item{output_format}{Determines shape of output tensor for language model.
Either \code{"target_right"}, \code{"target_middle_lstm"}, \code{"target_middle_cnn"} or \code{"wavenet"}.
Assume a sequence \code{"AACCGTA"}. Output correspond as follows
\itemize{
\item \verb{"target_right": X = "AACCGT", Y = "A"}
\item \verb{"target_middle_lstm": X = (X_1 = "AAC", X_2 = "ATG"), Y = "C"} (note reversed order of X_2)
\item \verb{"target_middle_cnn": X = "AACGTA", Y = "C"}
\item \verb{"wavenet": X = "AACCGT", Y = "ACCGTA"}
}}

\item{char_sequence}{A character string.}

\item{adjust_start_ind}{Whether to shift values in \code{start_ind} to start at 1: for example (5,11,25) becomes (1,7,21).}

\item{tokenizer}{A keras tokenizer.}
}
\value{
A list of 2 tensors.
}
\description{
Helper function for \code{\link{generator_fasta_lm}}.
Encodes integer sequence to input/target list according to \code{output_format} argument.
}
\examples{
\dontshow{if (reticulate::py_module_available("tensorflow")) (if (getRversion() >= "3.4") withAutoprint else force)(\{ # examplesIf}
# use integer sequence as input 

z <- seq_encoding_lm(sequence = c(1,0,5,1,3,4,3,1,4,1,2),
maxlen = 5,
vocabulary = c("a", "c", "g", "t"),
start_ind = c(1,3),
ambiguous_nuc = "equal",
target_len = 1,
output_format = "target_right")

x <- z[[1]]
y <- z[[2]]

x[1,,] # 1,0,5,1,3
y[1,] # 4

x[2,,] # 5,1,3,4,
y[2,] # 1

# use character string as input
z <- seq_encoding_lm(sequence = NULL,
maxlen = 5,
vocabulary = c("a", "c", "g", "t"),
start_ind = c(1,3),
ambiguous_nuc = "zero",
target_len = 1,
output_format = "target_right",
char_sequence = "ACTaaTNTNaZ")


x <- z[[1]]
y <- z[[2]]

x[1,,] # actaa
y[1,] # t

x[2,,] # taatn
y[2,] # t
\dontshow{\}) # examplesIf}
}