added spelling and updated docs

.Rbuildignore

@@ -1,2 +1,3 @@
 ^.*\.Rproj$
 ^\.Rproj\.user$
+docs

DESCRIPTION

@@ -39,17 +39,18 @@ Imports: pillar (>= 1.4.2),
          crayon (>= 1.3.4),
          Rcpp (>= 1.0.1),
          stringi (>= 1.4.3)
+Suggests: AmyloGram (>= 1.0),
+          testthat (>= 2.1.0),
+          ape (>= 5.3),
+          Biostrings (>= 2.52.0),
+          seqinr (>= 3.4-5),
+          spelling
 License: GPL (>= 2)
 URL: https://github.com/michbur/tidysq
 BugReports: https://github.com/michbur/tidysq/issues
 NeedsCompilation: no
 Repository: CRAN
 Encoding: UTF-8
+Language: en-US
 RoxygenNote: 6.1.1
 LinkingTo: Rcpp
-Suggests: AmyloGram (>= 1.0),
-          testthat (>= 2.1.0),
-          ape (>= 5.3),
-          Biostrings (>= 2.52.0),
-          seqinr (>= 3.4-5)
-

R/data.R

@@ -62,7 +62,7 @@ NULL
 #' @name BLOSUM50
 #' @docType data
 #' @format A data frame with with 20 rows and 20 columns.
-#' \describe{Contains an one-letter codes of amino acid as colums and rows names.
+#' \describe{Contains an one-letter codes of amino acid as columns and rows names.
 #' You can check three-letter codes and full names of the amino acids in
 #' \code{\link{aminoacids_df}}.
 #'  }
@@ -96,7 +96,7 @@ NULL
 #' @name BLOSUM62
 #' @docType data
 #' @format A data frame with with 20 rows and 20 columns.
-#' \describe{Contains an one-letter codes of amino acid as colums and rows names.
+#' \describe{Contains an one-letter codes of amino acid as columns and rows names.
 #' You can check three-letter codes and full names of the amino acids in
 #' \code{\link{aminoacids_df}}.
 #'  }
@@ -105,7 +105,7 @@ NULL
 #' BLOSUM matrices are actual percentage identity values of sequences selected for
 #' construction of the matrices. BLOSUM62 indicates that the sequences
 #' selected for constructing the matrix share an average identity value of 62\%.
-#' BLOSUM62 is miderange matrix between close and  distangly related proteins.
+#' BLOSUM62 is miderange matrix between close and  distantly related proteins.
 #' Matrix made by matblas from blosum62.iij
 #' BLOSUM Clustered Scoring Matrix in 1/2 Bit Units
 #' Cluster Percentage: >= 62
@@ -131,7 +131,7 @@ NULL
 #' @name BLOSUM50_enc
 #' @docType data
 #' @format A data frame with with 21 rows and 21 columns.
-#' \describe{Contains an one-letter codes of amino acid as colums and rows names
+#' \describe{Contains an one-letter codes of amino acid as columns and rows names
 #' and also row and column zero vectors representing 'X' (any amino acid).
 #' You can check three-letter codes and full names of the amino acids in
 #' \code{\link{aminoacids_df}}.
@@ -166,7 +166,7 @@ NULL
 #' @name BLOSUM62_enc
 #' @docType data
 #' @format A data frame with with 21 rows and 21 columns.
-#' \describe{Contains an one-letter codes of amino acid as colums and rows names
+#' \describe{Contains an one-letter codes of amino acid as columns and rows names
 #' and also row and column zero vectors representing 'X' (any amino acid).
 #' You can check three-letter codes and full names of the amino acids in
 #' \code{\link{aminoacids_df}}.
@@ -176,7 +176,7 @@ NULL
 #' BLOSUM matrices are actual percentage identity values of sequences selected for
 #' construction of the matrices. BLOSUM62 indicates that the sequences
 #' selected for constructing the matrix share an average identity value of 62\%.
-#' BLOSUM62 is miderange matrix between close and  distangly related proteins.
+#' BLOSUM62 is miderange matrix between close and  distantly related proteins.
 #' Matrix made by matblas from blosum62.iij
 #' BLOSUM Clustered Scoring Matrix in 1/2 Bit Units
 #' Cluster Percentage: >= 62
@@ -208,7 +208,7 @@ NULL
 #' \code{\link{aminoacids_df}}.
 #'  }
 #' @details
-#' The BLOSUM50_pca matrix enables PCA calculation on proteins sequences aligments.
+#' The BLOSUM50_pca matrix enables PCA calculation on proteins sequences alignments.
 #' Components are generated by an eigenvector decomposition of the matrix formed
 #' from pairwise similarity scores between each pair of sequences. The similarity score model
 #' used for creating BLOSUM50_pca matrix is the \code{\link{BLOSUM50}}. 
@@ -240,7 +240,7 @@ NULL
 #' \code{\link{aminoacids_df}}.
 #'  }
 #' @details
-#' The BLOSUM62_pca matrix enables PCA calculation on proteins sequences aligments.
+#' The BLOSUM62_pca matrix enables PCA calculation on proteins sequences alignments.
 #' Components are generated by an eigenvector decomposition of the matrix formed
 #' from pairwise similarity scores between each pair of sequences. The similarity score model
 #' used for creating BLOSUM62_pca matrix is the \code{\link{BLOSUM62}}. 
@@ -427,13 +427,13 @@ NULL
 #'  \item{FAUJ880112}{Negative charge (Fauchere et al., 1988)}
 #'  \item{FAUJ880113}{pK-a(RCOOH) (Fauchere et al., 1988)}
 #'  \item{FINA770101}{Helix-coil equilibrium constant (Finkelstein-Ptitsyn, 1977)}
-#'  \item{FINA910101}{Helix initiation parameter at posision i-1 (Finkelstein et
+#'  \item{FINA910101}{Helix initiation parameter at position i-1 (Finkelstein et
 #'  al., 1991)}
-#'  \item{FINA910102}{Helix initiation parameter at posision i,i+1,i+2 (Finkelstein
+#'  \item{FINA910102}{Helix initiation parameter at position i,i+1,i+2 (Finkelstein
 #'  et al., 1991)}
-#'  \item{FINA910103}{Helix termination parameter at posision j-2,j-1,j
+#'  \item{FINA910103}{Helix termination parameter at position j-2,j-1,j
 #'  (Finkelstein et al., 1991)}
-#'  \item{FINA910104}{Helix termination parameter at posision j+1 (Finkelstein et
+#'  \item{FINA910104}{Helix termination parameter at position j+1 (Finkelstein et
 #'  al., 1991)}
 #'  \item{GARJ730101}{Partition coefficient (Garel et al., 1973)}
 #'  \item{GEIM800101}{Alpha-helix indices (Geisow-Roberts, 1980)}

R/encode.R

@@ -24,7 +24,7 @@
 #' in \code{\link{sq}}), which represents encoded sequences.
 #' 
 #' The named vector (ex. \code{c(G = 1, K = 2, P = 2)}) should have all letters 
-#' assigned, otherwise unasigned letters will be shown as \code{NA}. If any letter that
+#' assigned, otherwise unassigned letters will be shown as \code{NA}. If any letter that
 #' appears in alphabet appears in at least one of sequences, user will be informed about it.
 #' Default action is a warning printed in the console, but it can be changed via setting
 #' "tidysq_encode_no_given_action" (see details at \code{\link{tidysq-options}}).

R/encsq_to_list.R

@@ -9,7 +9,7 @@
 #' In a new object you can check what value is assigned to each letter.
 #' 
 #' @return A list with named numeric vectors. Each vector represents values assigned to
-#' according sequnence with \code{\link{encode}} function. Vectors are named and their names
+#' according sequence with \code{\link{encode}} function. Vectors are named and their names
 #' are letters of original sequences.
 #' 
 #' @details Function is used to transform an \code{\link{sq}} object with 

R/fasta.R

@@ -66,7 +66,7 @@ read_fasta <- function(file, type = NULL, is_clean = NULL, non_standard = NULL)
 #' @param sq a \code{\link{sq}} object.
 #' @param name a \code{\link{character}} vector of length equal to \code{sq} length.
 #' @param file a \code{\link{character}} string indicating path to file to write into.
-#' @param nchar a posiitive \code{\link{integer}} value informing about maximum number of 
+#' @param nchar a positive \code{\link{integer}} value informing about maximum number of 
 #' characters to put in each line of file.
 #' @export
 write_fasta <- function(sq, name, file, nchar = 80) {

R/methods_sq.R

@@ -113,7 +113,7 @@ c.sq <- function(...) {
 
 #' Convert an object to sq
 #' 
-#' This generic funciton takes an object of arbitrary type and returns a \code{\link{sq}} object 
+#' This generic function takes an object of arbitrary type and returns a \code{\link{sq}} object 
 #' as an output. Default implementation of the method throws an error - there needs to be 
 #' implemented a method for specified class in order for function to work.
 #' 
@@ -163,7 +163,7 @@ as.sq.character <- function(x, type = NULL, is_clean = NULL, non_standard = NULL
 #' 
 #' @details This method for class \code{\link{sq}} allows converting sequences from
 #' the sq object into a character vector of length equal to the length 
-#' of sq. Each element of resulting vector is a seperate sequence. 
+#' of sq. Each element of resulting vector is a separate sequence. 
 #' All attributes of the input sq are lost during the conversion to 
 #' character vector.
 #' 
@@ -197,11 +197,11 @@ as.character.sq <- function(x, ...) {
 #' is \strong{enc}).
 #' 
 #' @details This method for class \code{sq} allows converting sequences from
-#' the sq object into a matrix. Each row corresponds to the seperate sequence
+#' the sq object into a matrix. Each row corresponds to the separate sequence
 #' from the sq object, whereas each column indicates a single position within 
 #' a sequence. Dimensions of matrix are determined by the number of sequences 
 #' (rows) and the length of the longest sequence (columns). If a length of
-#' sequence is smaller than the lenght of the longest sequence, the remaining
+#' sequence is smaller than the length of the longest sequence, the remaining
 #' columns will be filled with \code{\link{NA}}. All attributes of the input \code{sq} are lost 
 #' during the conversion to matrix.
 #' 
@@ -242,7 +242,7 @@ as.matrix.encsq <- function(x, ...) {
 
 #' Check if object has specified type
 #' 
-#' Function to checks if object is a \code{\link{sq}} object without specyfying type or
+#' Function to checks if object is a \code{\link{sq}} object without specifying type or
 #' if it is a \code{\link{sq}} object with specific type.
 #' @param x an object to be checked.
 #' @return A \code{\link{logical}} value - \code{TRUE} if \code{x} has given type, \code{FALSE}
@@ -325,7 +325,7 @@ is.encsq <- function(x) {
 #' Compare sq object 
 #' @description Compares input \code{\link{sq}} object with another given.
 #'   
-#' @details \code{`==`} converts left hand side of comparision (\code{x1}) to chracters 
+#' @details \code{`==`} converts left hand side of comparison (\code{x1}) to characters 
 #' vector using \code{\link{as.character}} and checks whether given on the right side 
 #' object can be compared with \code{\link{sq}} object. Function also check 
 #' the type of \code{\link{sq}} object with which given object will be compared.
@@ -334,12 +334,12 @@ is.encsq <- function(x) {
 #' with usage \code{\link{toupper}}. If right hand side object (\code{x2}) is \code{\link{sq}}
 #' it is converted to character vector using also \code{\link{as.character}} function.
 #' 
-#' When both objects are already converted to character vectors, comparision is done 
+#' When both objects are already converted to character vectors, comparison is done 
 #' elementwise with standard R rules, (e.g. recycling is used). You can check details 
 #' \code{\link[base:Comparison]{here}}.
 #' 
 #' Comparing sequences as characters vectors cause that various types of sequences
-#' can be compared for example aminoacids with nucleotides sequences so attention 
+#' can be compared for example amino acids with nucleotides sequences so attention 
 #' should be paid which sequences types are compared. 
 #' 
 #' @param x1 a \code{\link{sq}} object.

R/random_sq.R

@@ -1,11 +1,11 @@
 #' Generate random sequences
 #' 
-#' Generates a \code{\link{sq}} object with specified number of sequences of given lenght 
+#' Generates a \code{\link{sq}} object with specified number of sequences of given length 
 #' and given type.
 #' 
 #' @param n a positive \code{\link{integer}} value - number of sequences to generate.
 #' @param len a positive \code{\link{integer}} value - length of each sequence if \code{sd} not 
-#' specified and mean length of sequences if \code{sd} spedified.
+#' specified and mean length of sequences if \code{sd} specified
 #' @param type a type of generated sq object; possible values are "ami" and "nuc" (see section
 #' \emph{sq types} in \code{\link{sq}} documentation for details).
 #' @param is_clean a \code{\link{logical}} value - if \code{TRUE}, letters will be drawn from

R/sq.R

@@ -105,7 +105,7 @@
 #' fact that although there is a standard for format of \emph{fasta} files, sometimes 
 #' there are other types of symbols which do not fit the standard. Thanks to these types, 
 #' tidysq can import files with customized alphabets can be imported. Moreover, an user 
-#' may want to group amino acids with simillar properties (e.g. for machine learning) 
+#' may want to group amino acids with similar properties (e.g. for machine learning) 
 #' and replace the longer alphabet with symbols of groups. To check details, see 
 #' \code{\link{read_fasta}}, \code{\link{construct_sq}} and \code{\link{substitute_letters}}.
 #'
@@ -127,7 +127,7 @@
 #' \strong{ami} or \strong{nuc} object.
 #' 
 #' \strong{Important note:} maximum length of an alphabet is \strong{30 letters}. You are
-#' not allowed to read fasta files or construct from character vectros that have more
+#' not allowed to read fasta files or construct from character vectors that have more
 #' than 30 distinct characters in sequences (with exception of reading or constructing
 #' \strong{ami} or \strong{nuc} objects - during their construction lowercase letters
 #' are automatically converted to uppercase).
@@ -180,16 +180,16 @@
 #' and subset them using \code{\link[=sq-extract]{extract operator}}. Alphabet is kept
 #' as an attribute of the object. 
 #' 
-#' Raw vectors are the most efficient way of storage - each letter of sequece has asigned
+#' Raw vectors are the most efficient way of storage - each letter of the sequence has assigned
 #' an integer (its index in alphabet of \code{sq} object). Those integers in binary format
 #' fit in less than 8 bits, but normally are stored on 16 bits. However, thanks to bit
 #' packing it is possible to remove unused bits and store numbers more tightly. This 
 #' operations result in a little time overhead in all operations, because most of them 
-#' require unpacking and repacking sequences, but this cost is relatively low in comparision
+#' require unpacking and repacking sequences, but this cost is relatively low in comparison
 #' to amount of saved memory.
 #' 
 #' For example - \strong{nuc} \strong{cln} alphabet consist of 6 values: ACGTU-. They are 
-#' asigned numbers 1 to 6 respectively. Those numbers in binary format take form: \code{001},
+#' assigned numbers 1 to 6 respectively. Those numbers in binary format take form: \code{001},
 #' \code{010}, \code{011}, \code{100}, \code{101}, \code{110}. Each of the letters can 
 #' be coded with just 3 bits instead of 8 which is demanded by \code{char} - this allows
 #' us to save more than 60\% of memory spent on storage of nucleotides sequences.
@@ -294,7 +294,7 @@ NULL
 #' \item If you specify \code{type} as "unt" and won't neither \code{is_clean} nor 
 #' \code{non_standard}, type will be set to \strong{unt}. Letters won't be converted to uppercase, 
 #' alphabet will consist of all letters found in sequences. 
-#' \item If you do not sepcify neither \code{type} nor \code{is_clean} and specify 
+#' \item If you do not specify neither \code{type} nor \code{is_clean} and specify 
 #' \code{non_standard} parameter, which should be character vector where each element is at least 
 #' two characters long, all strings as specified will be detected in sequences and treated as 
 #' letters in constructed \strong{atp} \code{sq}.

R/sqapply.R

@@ -11,7 +11,7 @@
 #' @param paste_char a \code{\link{logical}} value indicating in which form sequences should be
 #' passed to the function \code{fun}; if \code{FALSE} (default), they will be treated as character
 #' vectors, if \code{TRUE}, they will be pasted into a single string.
-#' @param use_na_char a \code{\link{logical}} value indicating whether to use printing characater
+#' @param use_na_char a \code{\link{logical}} value indicating whether to use a printing character
 #' to represent \code{\link{NA}} values; if \code{TRUE}, letter from option "tidysq_na_print_char"
 #' will be used instead of \code{NA} values (default value for this option is "!", for details
 #' see \code{\link{tidysq-options}}), otherwise just \code{NA} values will be used; default value

R/substitute_letters.R

@@ -1,6 +1,6 @@
 #' Substitute letters in a sequence
 #' 
-#' @description 1) Replace ambigous/extraordinary letters in nucleic or 
+#' @description 1) Replace ambiguous/extraordinary letters in nucleic or 
 #' amino acid sequence, stored in \code{\link{sq}} object, with the ones 
 #' that are compliant with the IUPAC standard, ones that are user-defined 
 #' or with \code{NA} values.
@@ -21,7 +21,7 @@
 #' @return a \code{\link{sq}} object with \strong{atp} type with replaced alphabet, 
 #' defined by user.
 #' 
-#' @details \code{substitute_letters} allows to replace ambigous/extraordinary 
+#' @details \code{substitute_letters} allows to replace ambiguous/extraordinary 
 #' letters in nucleic or amino acid sequence with user-defined or IUPAC 
 #' symbols. Letters can also be replaced with \code{\link{NA}} values, so that they 
 #' can be later removed, from the sequence, by \code{\link{clean}} function.
@@ -144,7 +144,7 @@ substitute_letters <- function(sq, encoding) {
     inds_fun[s]
   }, new_alph)
   if (.is_cleaned(sq)) {
-    .handle_opt_txt("tidysq_subsitute_letters_cln",
+    .handle_opt_txt("tidysq_substitute_letters_cln",
                     "'sq' object passed to substitute_letters had 'cln' subtype, output doesn't have it")
   }
 

R/support_funs.R

@@ -195,8 +195,8 @@ is_null_sq <- function(sq) {
 #' a \code{\link{sq}} object to amino acid or nucleotide alphabet. Output list has number of
 #' elements equal to length of \code{sq} object and each element is a character vector 
 #' of elements that appear in according sequence that does not fit destination type. This 
-#' function might be used to find specificly which sequences have which letters - user
-#' may want to use this information for example to check input sequeces.
+#' function might be used to find specifically which sequences have which letters - user
+#' may want to use this information for example to check input sequences.
 #' 
 #' You can check which letters are valid for specified type in \code{\link{sq}} class 
 #' documentation.

R/tidysq_options.R

@@ -2,17 +2,17 @@
 #' 
 #' You can get value of an option by calling \code{getOptions(option_name)} and set its value
 #' by calling \code{options(option_name = value)}, where \code{option_name} is an option name 
-#' (full list of this package included below) and \code{value} is a value to assing to an option.
+#' (full list of this package included below) and \code{value} is a value to assign to an option.
 #' 
 #' @details 
 #' You can change default behaviour of package using one of following options:
 #' \itemize{
 #' \item tidysq_bite_na_action (default "warning") - a \code{\link{character}} string specifying 
 #' in which way to inform user about biting sequences out of the range when using 
 #' \code{\link{bite}}; possible values: "error", "warning", "message", "none",
-#' \item tidysq_subsitute_letters_cln (default "warning") - a \code{\link{character}} string 
+#' \item tidysq_substitute_letters_cln (default "warning") - a \code{\link{character}} string 
 #' specifying in which way to inform user
-#' about droping \code{cln} subtype of \code{sq} while using \code{\link{substitute_letters}}; 
+#' about dropping \code{cln} subtype of \code{sq} while using \code{\link{substitute_letters}}; 
 #' possible values: "error", "warning", "message", "none",
 #' \item tidysq_typify_small_cap_let (default "warning") - a \code{\link{character}} string 
 #' specifying in which way to inform user
@@ -22,9 +22,9 @@
 #' specifying in which way to inform user
 #' about encoding unspecified letters as \code{\link{NA}} if they do appear in sequences in
 #' \code{\link{encode}}; possible values: "error", "warning", "message", "none",
-#' \item tidysq_max_pillar_sq_width (default 15) - an \code{\link{integer}} value specyfying 
+#' \item tidysq_max_pillar_sq_width (default 15) - an \code{\link{integer}} value specifying 
 #' pillar_shaft_sq width
-#' \item tidysq_max_print_sequences (default 10) - an \code{\link{integer}} value specyfying 
+#' \item tidysq_max_print_sequences (default 10) - an \code{\link{integer}} value specifying 
 #' maximum number of printed sequences
 #' in \code{\link[=print.sq]{print sq}},
 #' \item tidysq_colorful_sq_print (default \code{TRUE}) - a \code{\link{logical}} value if to