--- a
+++ b/man/predict_model.Rd
@@ -0,0 +1,139 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/predict.R
+\name{predict_model}
+\alias{predict_model}
+\title{Make prediction for nucleotide sequence or entries in fasta/fastq file}
+\usage{
+predict_model(
+  model,
+  output_format = "one_seq",
+  layer_name = NULL,
+  sequence = NULL,
+  path_input = NULL,
+  round_digits = NULL,
+  filename = "states.h5",
+  step = 1,
+  vocabulary = c("a", "c", "g", "t"),
+  batch_size = 256,
+  verbose = TRUE,
+  return_states = FALSE,
+  output_type = "h5",
+  padding = "none",
+  use_quality = FALSE,
+  quality_string = NULL,
+  mode = "label",
+  lm_format = "target_right",
+  output_dir = NULL,
+  format = "fasta",
+  include_seq = FALSE,
+  reverse_complement_encoding = FALSE,
+  ambiguous_nuc = "zero",
+  ...
+)
+}
+\arguments{
+\item{model}{A keras model.}
+
+\item{output_format}{Either \code{"one_seq"}, \code{"by_entry"}, \code{"by_entry_one_file"}, \code{"one_pred_per_entry"}.}
+
+\item{layer_name}{Name of layer to get output from. If \code{NULL}, will use the last layer.}
+
+\item{sequence}{Character string, ignores path_input if argument given.}
+
+\item{path_input}{Path to fasta file.}
+
+\item{round_digits}{Number of decimal places.}
+
+\item{filename}{Filename to store states in. No file output if argument is \code{NULL}.
+If \code{output_format = "by_entry"}, adds "\emph{nr}" + "i" after name, where i is entry number.}
+
+\item{step}{Frequency of sampling steps.}
+
+\item{vocabulary}{Vector of allowed characters. Characters outside vocabulary get encoded as specified in \code{ambiguous_nuc}.}
+
+\item{batch_size}{Number of samples used for one network update.}
+
+\item{verbose}{Boolean.}
+
+\item{return_states}{Return predictions as data frame. Only supported for output_format \code{"one_seq"}.}
+
+\item{output_type}{\code{"h5"} or \code{"csv"}. If \verb{output_format`` is }"by_entries_one_file", "one_pred_per_entry"\verb{can only be}"h5"`.}
+
+\item{padding}{Either \code{"none"}, \code{"maxlen"}, \code{"standard"} or \code{"self"}.
+\itemize{
+\item If \code{"none"}, apply no padding and skip sequences that are too short.
+\item If \code{"maxlen"}, pad with maxlen number of zeros vectors.
+\item If \code{"standard"}, pad with zero vectors only if sequence is shorter than maxlen. Pads to minimum size required for one prediction.
+\item If \code{"self"}, concatenate sequence with itself until sequence is long enough for one prediction.
+Example: if sequence is "ACGT" and maxlen is 10, make prediction for "ACGTACGTAC".
+Only applied if sequence is shorter than maxlen.
+}}
+
+\item{use_quality}{Whether to use quality scores.}
+
+\item{quality_string}{String for encoding with quality scores (as used in fastq format).}
+
+\item{mode}{Either \code{"lm"} for language model or \code{"label"} for label classification.}
+
+\item{lm_format}{Either \code{"target_right"}, \code{"target_middle_lstm"}, \code{"target_middle_cnn"} or \code{"wavenet"}.}
+
+\item{output_dir}{Directory for file output.}
+
+\item{format}{File format, \code{"fasta"}, \code{"fastq"}, \code{"rds"} or \code{"fasta.tar.gz"}, \code{"fastq.tar.gz"} for \code{tar.gz} files.}
+
+\item{include_seq}{Whether to include input sequence in h5 file.}
+
+\item{reverse_complement_encoding}{Whether to use both original sequence and reverse complement as two input sequences.}
+
+\item{ambiguous_nuc}{How to handle nucleotides outside vocabulary, either \code{"zero"}, \code{"discard"}, \code{"empirical"} or \code{"equal"}.
+\itemize{
+\item If \code{"zero"}, input gets encoded as zero vector.
+\item If \code{"equal"}, input is repetition of \code{1/length(vocabulary)}.
+\item If \code{"discard"}, samples containing nucleotides outside vocabulary get discarded.
+\item If \code{"empirical"}, use nucleotide distribution of current file.
+}}
+
+\item{...}{Further arguments for sequence encoding with \code{\link{seq_encoding_label}}.}
+}
+\value{
+If \code{return_states = TRUE} returns a list of model predictions and position of corresponding sequences.
+If additionally \code{include_seq = TRUE}, list contains sequence strings.
+If \code{return_states = FALSE} returns nothing, just writes output to file(s).
+}
+\description{
+Removes layers (optional) from pretrained model and calculates states of fasta/fastq file or nucleotide sequence.
+Writes states to h5 or csv file (access content of h5 output with \code{\link{load_prediction}} function).
+There are several options on how to process an input file:
+\itemize{
+\item If \code{"one_seq"}, computes prediction for sequence argument or fasta/fastq file.
+Combines fasta entries in file to one sequence. This means predictor sequences can contain elements from more than one fasta entry.
+\item If \code{"by_entry"}, will output a separate file for each fasta/fastq entry.
+Names of output files are: \code{output_dir} + "Nr" + i + \code{filename} + \code{output_type}, where i is the number of the fasta entry.
+\item If \code{"by_entry_one_file"}, will store prediction for all fasta entries in one h5 file.
+\item If \code{"one_pred_per_entry"}, will make one prediction for each entry by either picking random sample for long sequences
+or pad sequence for short sequences.
+}
+}
+\examples{
+\dontshow{if (reticulate::py_module_available("tensorflow")) (if (getRversion() >= "3.4") withAutoprint else force)(\{ # examplesIf}
+# make prediction for single sequence and write to h5 file
+model <- create_model_lstm_cnn(maxlen = 20, layer_lstm = 8, layer_dense = 2, verbose = FALSE)
+vocabulary <- c("a", "c", "g", "t")
+sequence <- paste(sample(vocabulary, 200, replace = TRUE), collapse = "")
+output_file <- tempfile(fileext = ".h5")
+predict_model(output_format = "one_seq", model = model, step = 10,
+             sequence = sequence, filename = output_file, mode = "label")
+
+# make prediction for fasta file with multiple entries, write output to separate h5 files
+fasta_path <- tempfile(fileext = ".fasta")
+create_dummy_data(file_path = fasta_path, num_files = 1,
+                 num_seq = 5, seq_length = 100,
+                 write_to_file_path = TRUE)
+model <- create_model_lstm_cnn(maxlen = 20, layer_lstm = 8, layer_dense = 2, verbose = FALSE)
+output_dir <- tempfile()
+dir.create(output_dir)
+predict_model(output_format = "by_entry", model = model, step = 10, verbose = FALSE,
+               output_dir = output_dir, mode = "label", path_input = fasta_path)
+list.files(output_dir)
+\dontshow{\}) # examplesIf}
+}