align

Documentation

Index

• Constants
• func AlphabetFromString(alphabet string) int
• func DetectAlphabet(seq string) int
• func NewAlign(alphabet int) *align
• func NewSeqBag(alphabet int) *seqbag
• func NewSequence(name string, sequence []rune, comment string) *seq
• func RandomSequence(alphabet, length int) ([]rune, error)
• type AlignChannel
• type Alignment
  • func RandomAlignment(alphabet, length, nbseq int) (Alignment, error)
• type SeqBag
• type Sequence

Constants

const (
	AMINOACIDS = 0 // Amino acid sequence alphabet
	NUCLEOTIDS = 1 // Nucleotid sequence alphabet
	UNKNOWN    = 2 // Unkown alphabet

	GAP   = '-'
	POINT = '.'
	OTHER = '*'

	PSSM_NORM_NONE = 0 // No normalization
	PSSM_NORM_FREQ = 1 // Normalization by freq in the site
	PSSM_NORM_DATA = 2 // Normalization by aa/nt frequency in data
	PSSM_NORM_UNIF = 3 // Normalization by uniform frequency
	PSSM_NORM_LOGO = 4 // Normalization like LOGO : v(site)=freq*(log2(alphabet)-H(site)-pseudocount

	FORMAT_FASTA   = 0
	FORMAT_PHYLIP  = 1
	FORMAT_NEXUS   = 2
	FORMAT_CLUSTAL = 3

	POSITION_IDENTICAL      = 0 // All characters in a position are the same
	POSITION_CONSERVED      = 1 // Same strong group
	POSITION_SEMI_CONSERVED = 2 // Same weak group
	POSITION_NOT_CONSERVED  = 3 // None of the above values
)

Functions

func AlphabetFromString

func AlphabetFromString(alphabet string) int

func DetectAlphabet

func DetectAlphabet(seq string) int

func NewAlign

func NewAlign(alphabet int) *align

func NewSeqBag

func NewSeqBag(alphabet int) *seqbag

func NewSequence

func NewSequence(name string, sequence []rune, comment string) *seq

func RandomSequence

func RandomSequence(alphabet, length int) ([]rune, error)

Types

type AlignChannel

type AlignChannel struct {
	Achan chan Alignment
	Err   error
}

type Alignment

type Alignment interface {
	SeqBag
	AddGaps(rate, lenprop float64)
	AvgAllelesPerSite() float64
	BuildBootstrap() Alignment
	CharStatsSite(site int) (map[rune]int, error)
	Clone() (Alignment, error)
	CodonAlign(ntseqs SeqBag) (codonAl *align, err error)
	Concat(Alignment) error // concatenates the given alignment with this alignment
	Deduplicate() (Alignment, error)
	Entropy(site int, removegaps bool) (float64, error) // Entropy of the given site
	Length() int                                        // Length of the alignment
	MaxCharStats() ([]rune, []int)
	Mutate(rate float64)                                                                        // Adds uniform substitutions in the alignment (~sequencing errors)
	NbVariableSites() int                                                                       // Nb of variable sites
	Pssm(log bool, pseudocount float64, normalization int) (pssm map[rune][]float64, err error) // Normalization: PSSM_NORM_NONE, PSSM_NORM_UNIF, PSSM_NORM_DATA
	Rarefy(nb int, counts map[string]int) (Alignment, error)                                    // Take a new rarefied sample taking into accounts weights
	RandSubAlign(length int) (Alignment, error)                                                 // Extract a random subalignment with given length from this alignment
	Recombine(rate float64, lenprop float64)
	RemoveGapSeqs(cutoff float64)     // Removes sequences having >= cutoff gaps
	RemoveGapSites(cutoff float64)    // Removes sites having >= cutoff gaps
	Sample(nb int) (Alignment, error) // generate a sub sample of the sequences
	ShuffleSites(rate float64, roguerate float64, randroguefirst bool) []string
	SimulateRogue(prop float64, proplen float64) ([]string, []string) // add "rogue" sequences
	SiteConservation(position int) (int, error)                       // If the site is conserved:
	SubAlign(start, length int) (Alignment, error)                    // Extract a subalignment from this alignment
	Swap(rate float64)
	Translate(phase int) (transAl *align, err error) // Translates nt sequence if possible
	TrimSequences(trimsize int, fromStart bool) error
}

func RandomAlignment

func RandomAlignment(alphabet, length, nbseq int) (Alignment, error)

type SeqBag

type SeqBag interface {
	AddSequence(name string, sequence string, comment string) error
	AddSequenceChar(name string, sequence []rune, comment string) error
	AppendSeqIdentifier(identifier string, right bool)
	Alphabet() int
	AlphabetStr() string
	AlphabetCharacters() []rune
	AutoAlphabet() // detects and sets alphabet automatically for all the sequences
	CharStats() map[rune]int64
	CleanNames()                            // Clean sequence names (newick special char)
	GetSequence(name string) (string, bool) // Get a sequence by names
	GetSequenceById(ith int) (string, bool)
	GetSequenceChar(name string) ([]rune, bool)
	GetSequenceCharById(ith int) ([]rune, bool)
	GetSequenceNameById(ith int) (string, bool)
	SetSequenceChar(ithAlign, ithSite int, char rune) error
	Identical(SeqBag) bool
	Iterate(it func(name string, sequence string))
	IterateChar(it func(name string, sequence []rune))
	IterateAll(it func(name string, sequence []rune, comment string))
	NbSequences() int
	Rename(namemap map[string]string)
	RenameRegexp(regex, replace string, namemap map[string]string) error
	ShuffleSequences() // Shuffle sequence order
	TrimNames(namemap map[string]string, size int) error
	TrimNamesAuto(namemap map[string]string, curid *int) error
	Sort() // Sorts the sequences by name
}

type Sequence

type Sequence interface {
	Sequence() string
	SequenceChar() []rune
	Name() string
	Comment() string
	Length() int
}