taxdump

README

taxdump

This package provides querying manipulations from NCBI Taxonomy taxdump files.

History

This package was originally maintained in unikmer.

Documentation

Index

• Variables
• type Taxonomy
  • func NewTaxonomy(file string, childColumn int, parentColumn int) (*Taxonomy, error)
  • func NewTaxonomyFromNCBI(file string) (*Taxonomy, error)
  • func NewTaxonomyWithRank(file string, childColumn int, parentColumn int, rankColumn int) (*Taxonomy, error)
  • func NewTaxonomyWithRankFromNCBI(file string) (*Taxonomy, error)
  • func (t *Taxonomy) AtOrBelowRank(taxid uint32, rank string) bool
  • func (t *Taxonomy) CacheLCA()
  • func (t *Taxonomy) LCA(a uint32, b uint32) uint32
  • func (t *Taxonomy) LineageNames(taxid uint32) []string
  • func (t *Taxonomy) LineageTaxIds(taxid uint32) []uint32
  • func (t *Taxonomy) LoadDeletedNodes(file string, column int) error
  • func (t *Taxonomy) LoadDeletedNodesFromNCBI(file string) error
  • func (t *Taxonomy) LoadMergedNodes(file string, oldColumn int, newColumn int) error
  • func (t *Taxonomy) LoadMergedNodesFromNCBI(file string) error
  • func (t *Taxonomy) LoadNames(file string, taxidColumn int, nameColumn int, typeColumn int, _type string) error
  • func (t *Taxonomy) LoadNamesFromNCBI(file string) error
  • func (t *Taxonomy) MaxTaxid() uint32
  • func (t *Taxonomy) Name(taxid uint32) string
  • func (t *Taxonomy) Rank(taxid uint32) string
  • func (t *Taxonomy) TaxId(taxid uint32) (uint32, bool)

Variables

var ErrIllegalColumnIndex = errors.New("taxdump: illegal column index, positive integer needed")

ErrIllegalColumnIndex means column index is 0 or negative.

var ErrNamesNotLoaded = errors.New("taxdump: taxonomy names not loaded, please call: LoadNames")

ErrNamesNotLoaded means you should call LoadNames before using taxonomy names.

var ErrRankNotLoaded = errors.New("taxdump: taxonomic ranks not loaded, please call: NewTaxonomyWithRank")

ErrRankNotLoaded means you should reate load Taxonomy with NewTaxonomyWithRank before calling some methods.

var ErrTooManyRanks = errors.New("taxdump: number of ranks exceed limit of 255")

ErrTooManyRanks means number of ranks exceed limit of 255

var ErrUnkownRank = errors.New("taxdump: unknown rank")

ErrUnkownRank indicate an unknown rank

Types

type Taxonomy

type Taxonomy struct {
	Nodes      map[uint32]uint32 // child -> parent
	DelNodes   map[uint32]struct{}
	MergeNodes map[uint32]uint32 // from -> to
	Names      map[uint32]string

	Ranks map[string]interface{}
	// contains filtered or unexported fields
}

Taxonomy holds relationship of taxon in a taxonomy.

func NewTaxonomy

func NewTaxonomy(file string, childColumn int, parentColumn int) (*Taxonomy, error)

NewTaxonomy only loads nodes from nodes.dmp file.

func NewTaxonomyFromNCBI

func NewTaxonomyFromNCBI(file string) (*Taxonomy, error)

NewTaxonomyFromNCBI parses nodes relationship from nodes.dmp from ftp://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz .

func NewTaxonomyWithRank

func NewTaxonomyWithRank(file string, childColumn int, parentColumn int, rankColumn int) (*Taxonomy, error)

NewTaxonomyWithRank loads nodes and ranks from nodes.dmp file.

func NewTaxonomyWithRankFromNCBI

func NewTaxonomyWithRankFromNCBI(file string) (*Taxonomy, error)

NewTaxonomyWithRankFromNCBI parses Taxonomy from nodes.dmp from ftp://ftp.ncbi.nih.gov/pub/taxonomy/taxdump.tar.gz .

func (*Taxonomy) AtOrBelowRank

func (t *Taxonomy) AtOrBelowRank(taxid uint32, rank string) bool

AtOrBelowRank returns whether a taxid is at or below one rank.

func (*Taxonomy) CacheLCA

func (t *Taxonomy) CacheLCA()

CacheLCA tells to cache every LCA query result

func (*Taxonomy) LCA

func (t *Taxonomy) LCA(a uint32, b uint32) uint32

LCA returns the Lowest Common Ancestor of two nodes, 0 for unknown taxid.

func (*Taxonomy) LineageNames

func (t *Taxonomy) LineageNames(taxid uint32) []string

LineageNames returns nodes' names of the the complete lineage.

func (*Taxonomy) LineageTaxIds

func (t *Taxonomy) LineageTaxIds(taxid uint32) []uint32

LineageTaxIds returns nodes' taxid of the the complete lineage.

func (*Taxonomy) LoadDeletedNodes

func (t *Taxonomy) LoadDeletedNodes(file string, column int) error

LoadDeletedNodes loads deleted nodes.

func (*Taxonomy) LoadDeletedNodesFromNCBI

func (t *Taxonomy) LoadDeletedNodesFromNCBI(file string) error

LoadDeletedNodesFromNCBI loads deleted nodes from NCBI delnodes.dmp.

func (*Taxonomy) LoadMergedNodes

func (t *Taxonomy) LoadMergedNodes(file string, oldColumn int, newColumn int) error

LoadMergedNodes loads merged nodes.

func (*Taxonomy) LoadMergedNodesFromNCBI

func (t *Taxonomy) LoadMergedNodesFromNCBI(file string) error

LoadMergedNodesFromNCBI loads merged nodes from NCBI merged.dmp.

func (*Taxonomy) LoadNames

func (t *Taxonomy) LoadNames(file string, taxidColumn int, nameColumn int, typeColumn int, _type string) error

LoadNames loads names.

func (*Taxonomy) LoadNamesFromNCBI

func (t *Taxonomy) LoadNamesFromNCBI(file string) error

LoadNamesFromNCBI loads scientific names from NCBI names.dmp

func (*Taxonomy) MaxTaxid

func (t *Taxonomy) MaxTaxid() uint32

MaxTaxid returns maximum taxid

func (*Taxonomy) Name

func (t *Taxonomy) Name(taxid uint32) string

Name returns the name of a TaxId. If being merged, the name of the new TaxId will be returned. If the TaxId is not found or deleted, empty will be returned.

func (*Taxonomy) Rank

func (t *Taxonomy) Rank(taxid uint32) string

Rank returns the rank of a taxid. If being merged, the rank of the new TaxId will be returned. If the TaxId is not found or deleted, empty will be returned.

func (*Taxonomy) TaxId

func (t *Taxonomy) TaxId(taxid uint32) (uint32, bool)

TaxId checks if a TaxId is valid in the database. If being merged, the new TaxId will be returned. If the TaxId is not found or deleted, false will be returned.