uniprot

package
v0.11.2 Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Jul 13, 2021 License: MIT Imports: 8 Imported by: 0

Documentation

Index

Examples

Constants

This section is empty.

Variables

This section is empty.

Functions

func Parse 

func Parse(r io.Reader, entries chan<- Entry, errors chan<- error)

Parse parses Uniprot entries into a channel.

Example 
xmlFile, _ := os.Open("data/uniprot_sprot_mini.xml.gz")
unzippedBytes, _ := gzip.NewReader(xmlFile)

entries := make(chan Entry, 100) // if you don't have a buffered channel, nothing will be read in loops on the channel.
decoderErrors := make(chan error, 100)

go Parse(unzippedBytes, entries, decoderErrors)

var entry Entry
for singleEntry := range entries {
	entry = singleEntry
}
fmt.Println(entry.Accession[0])

Output:

O55723

func Read 

func Read(path string) (chan Entry, chan error, error)

Read reads a gzipped Uniprot XML dump. Failing to open the XML dump gives a single error, while errors encountered while decoding the XML dump are added to the errors channel.

Example 
entries, _, _ := Read("data/uniprot_sprot_mini.xml.gz")

var entry Entry
for singleEntry := range entries {
	entry = singleEntry
}
fmt.Println(entry.Accession[0])

Output:

O55723

Types

type Absorption 

type Absorption struct {
	Max  EvidencedStringType   `xml:"http://uniprot.org/uniprot max,omitempty"`
	Text []EvidencedStringType `xml:"http://uniprot.org/uniprot text,omitempty"`
}

type AlternativeName 

type AlternativeName struct {
	FullName  EvidencedStringType   `xml:"http://uniprot.org/uniprot fullName,omitempty"`
	ShortName []EvidencedStringType `xml:"http://uniprot.org/uniprot shortName,omitempty"`
	EcNumber  []EvidencedStringType `xml:"http://uniprot.org/uniprot ecNumber,omitempty"`
}

type Anon6 

type Anon6 struct {
	Type Type `xml:"type,attr"`
}

type CitationType 

type CitationType struct {
	Title       string            `xml:"http://uniprot.org/uniprot title,omitempty"`
	EditorList  NameListType      `xml:"http://uniprot.org/uniprot editorList,omitempty"`
	AuthorList  NameListType      `xml:"http://uniprot.org/uniprot authorList,omitempty"`
	Locator     string            `xml:"http://uniprot.org/uniprot locator,omitempty"`
	DbReference []DbReferenceType `xml:"http://uniprot.org/uniprot dbReference,omitempty"`
	Type        Type              `xml:"type,attr"`
	Date        Date              `xml:"date,attr,omitempty"`
	Name        string            `xml:"name,attr,omitempty"`
	Volume      string            `xml:"volume,attr,omitempty"`
	First       string            `xml:"first,attr,omitempty"`
	Last        string            `xml:"last,attr,omitempty"`
	Publisher   string            `xml:"publisher,attr,omitempty"`
	City        string            `xml:"city,attr,omitempty"`
	Db          string            `xml:"db,attr,omitempty"`
	Number      string            `xml:"number,attr,omitempty"`
	Institute   string            `xml:"institute,attr,omitempty"`
	Country     string            `xml:"country,attr,omitempty"`
}

Describes different types of citations. Equivalent to the flat file RX-, RG-, RA-, RT- and RL-lines.

type CofactorType 

type CofactorType struct {
	Name        string          `xml:"http://uniprot.org/uniprot name"`
	DbReference DbReferenceType `xml:"http://uniprot.org/uniprot dbReference"`
	Evidence    IntListType     `xml:"evidence,attr,omitempty"`
}

Describes a cofactor.

type CommentType 

type CommentType struct {
	Molecule              string                      `xml:"http://uniprot.org/uniprot molecule,omitempty"`
	Absorption            Absorption                  `xml:"http://uniprot.org/uniprot absorption,omitempty"`
	Kinetics              Kinetics                    `xml:"http://uniprot.org/uniprot kinetics,omitempty"`
	PhDependence          PhDependence                `xml:"http://uniprot.org/uniprot phDependence,omitempty"`
	RedoxPotential        RedoxPotential              `xml:"http://uniprot.org/uniprot redoxPotential,omitempty"`
	TemperatureDependence TemperatureDependence       `xml:"http://uniprot.org/uniprot temperatureDependence,omitempty"`
	Reaction              ReactionType                `xml:"http://uniprot.org/uniprot reaction,omitempty"`
	PhysiologicalReaction []PhysiologicalReactionType `xml:"http://uniprot.org/uniprot physiologicalReaction,omitempty"`
	Cofactor              []CofactorType              `xml:"http://uniprot.org/uniprot cofactor,omitempty"`
	SubcellularLocation   []SubcellularLocationType   `xml:"http://uniprot.org/uniprot subcellularLocation,omitempty"`
	Conflict              Conflict                    `xml:"http://uniprot.org/uniprot conflict,omitempty"`
	Link                  []Link                      `xml:"http://uniprot.org/uniprot link,omitempty"`
	Event                 []EventType                 `xml:"http://uniprot.org/uniprot event,omitempty"`
	Isoform               []IsoformType               `xml:"http://uniprot.org/uniprot isoform,omitempty"`
	Interactant           []InteractantType           `xml:"http://uniprot.org/uniprot interactant,omitempty"`
	OrganismsDiffer       bool                        `xml:"http://uniprot.org/uniprot organismsDiffer,omitempty"`
	Experiments           int                         `xml:"http://uniprot.org/uniprot experiments,omitempty"`
	Disease               Disease                     `xml:"http://uniprot.org/uniprot disease,omitempty"`
	Location              []LocationType              `xml:"http://uniprot.org/uniprot location,omitempty"`
	Text                  []EvidencedStringType       `xml:"http://uniprot.org/uniprot text,omitempty"`
	Type                  Type                        `xml:"type,attr"`
	LocationType          string                      `xml:"locationType,attr,omitempty"`
	Name                  string                      `xml:"name,attr,omitempty"`
	Mass                  float32                     `xml:"mass,attr,omitempty"`
	Error                 string                      `xml:"error,attr,omitempty"`
	Method                string                      `xml:"method,attr,omitempty"`
	Evidence              IntListType                 `xml:"evidence,attr,omitempty"`
}

Describes different types of general annotations. Equivalent to the flat file CC-line.

func (*CommentType) UnmarshalXML 

func (t *CommentType) UnmarshalXML(d *xml.Decoder, start xml.StartElement) error

type Component 

type Component struct {
	RecommendedName RecommendedName       `xml:"http://uniprot.org/uniprot recommendedName,omitempty"`
	AlternativeName []AlternativeName     `xml:"http://uniprot.org/uniprot alternativeName,omitempty"`
	SubmittedName   []SubmittedName       `xml:"http://uniprot.org/uniprot submittedName,omitempty"`
	AllergenName    EvidencedStringType   `xml:"http://uniprot.org/uniprot allergenName,omitempty"`
	BiotechName     EvidencedStringType   `xml:"http://uniprot.org/uniprot biotechName,omitempty"`
	CdAntigenName   []EvidencedStringType `xml:"http://uniprot.org/uniprot cdAntigenName,omitempty"`
	InnName         []EvidencedStringType `xml:"http://uniprot.org/uniprot innName,omitempty"`
}

type Conflict 

type Conflict struct {
	Sequence Sequence `xml:"http://uniprot.org/uniprot sequence,omitempty"`
	Type     Type     `xml:"type,attr"`
}

type ConsortiumType 

type ConsortiumType struct {
	Name string `xml:"name,attr"`
}

Describes the authors of a citation when these are represented by a consortium. Equivalent to the flat file RG-line.

type Dataset 

type Dataset string

May be one of Swiss-Prot, TrEMBL

type Date 

type Date string

type DbReferenceType 

type DbReferenceType struct {
	Molecule string         `xml:"http://uniprot.org/uniprot molecule,omitempty"`
	Property []PropertyType `xml:"http://uniprot.org/uniprot property,omitempty"`
	Type     string         `xml:"type,attr"`
	Evidence IntListType    `xml:"evidence,attr,omitempty"`
}

Describes a database cross-reference. Equivalent to the flat file DR-line.

type Direction 

type Direction string

May be one of left-to-right, right-to-left

type Disease 

type Disease struct {
	Name        string          `xml:"http://uniprot.org/uniprot name"`
	Acronym     string          `xml:"http://uniprot.org/uniprot acronym"`
	Description string          `xml:"http://uniprot.org/uniprot description"`
	DbReference DbReferenceType `xml:"http://uniprot.org/uniprot dbReference"`
}

type Domain 

type Domain struct {
	RecommendedName RecommendedName       `xml:"http://uniprot.org/uniprot recommendedName,omitempty"`
	AlternativeName []AlternativeName     `xml:"http://uniprot.org/uniprot alternativeName,omitempty"`
	SubmittedName   []SubmittedName       `xml:"http://uniprot.org/uniprot submittedName,omitempty"`
	AllergenName    EvidencedStringType   `xml:"http://uniprot.org/uniprot allergenName,omitempty"`
	BiotechName     EvidencedStringType   `xml:"http://uniprot.org/uniprot biotechName,omitempty"`
	CdAntigenName   []EvidencedStringType `xml:"http://uniprot.org/uniprot cdAntigenName,omitempty"`
	InnName         []EvidencedStringType `xml:"http://uniprot.org/uniprot innName,omitempty"`
}

type Entry 

type Entry struct {
	Accession        []string             `xml:"http://uniprot.org/uniprot accession"`
	Name             []string             `xml:"http://uniprot.org/uniprot name"`
	Protein          ProteinType          `xml:"http://uniprot.org/uniprot protein"`
	Gene             []GeneType           `xml:"http://uniprot.org/uniprot gene,omitempty"`
	Organism         OrganismType         `xml:"http://uniprot.org/uniprot organism"`
	OrganismHost     []OrganismType       `xml:"http://uniprot.org/uniprot organismHost,omitempty"`
	GeneLocation     []GeneLocationType   `xml:"http://uniprot.org/uniprot geneLocation,omitempty"`
	Reference        []ReferenceType      `xml:"http://uniprot.org/uniprot reference"`
	Comment          []CommentType        `xml:"http://uniprot.org/uniprot comment,omitempty"`
	DbReference      []DbReferenceType    `xml:"http://uniprot.org/uniprot dbReference,omitempty"`
	ProteinExistence ProteinExistenceType `xml:"http://uniprot.org/uniprot proteinExistence"`
	Keyword          []KeywordType        `xml:"http://uniprot.org/uniprot keyword,omitempty"`
	Feature          []FeatureType        `xml:"http://uniprot.org/uniprot feature,omitempty"`
	Evidence         []EvidenceType       `xml:"http://uniprot.org/uniprot evidence,omitempty"`
	Sequence         SequenceType         `xml:"http://uniprot.org/uniprot sequence"`
	Dataset          Dataset              `xml:"dataset,attr"`
	Created          time.Time            `xml:"created,attr"`
	Modified         time.Time            `xml:"modified,attr"`
	Version          int                  `xml:"version,attr"`
}

func (*Entry) UnmarshalXML 

func (t *Entry) UnmarshalXML(d *xml.Decoder, start xml.StartElement) error

type EventType 

type EventType struct {
	Type Type `xml:"type,attr"`
}

Describes the type of events that cause alternative products.

type EvidenceType 

type EvidenceType struct {
	Source       SourceType       `xml:"http://uniprot.org/uniprot source,omitempty"`
	ImportedFrom ImportedFromType `xml:"http://uniprot.org/uniprot importedFrom,omitempty"`
	Type         string           `xml:"type,attr"`
	Key          int              `xml:"key,attr"`
}

Describes the evidence for an annotation. No flat file equivalent.

type EvidencedStringType 

type EvidencedStringType struct {
	Value    string      `xml:",chardata"`
	Evidence IntListType `xml:"evidence,attr,omitempty"`
}

type FeatureType 

type FeatureType struct {
	Original    string       `xml:"http://uniprot.org/uniprot original,omitempty"`
	Variation   []string     `xml:"http://uniprot.org/uniprot variation,omitempty"`
	Location    LocationType `xml:"http://uniprot.org/uniprot location"`
	Type        Type         `xml:"type,attr"`
	Description string       `xml:"description,attr,omitempty"`
	Evidence    IntListType  `xml:"evidence,attr,omitempty"`
}

Describes different types of sequence annotations. Equivalent to the flat file FT-line.

type Fragment 

type Fragment string

May be one of single, multiple

type GeneLocationType 

type GeneLocationType struct {
	Name     []StatusType `xml:"http://uniprot.org/uniprot name,omitempty"`
	Type     Type         `xml:"type,attr"`
	Evidence IntListType  `xml:"evidence,attr,omitempty"`
}

Describes non-nuclear gene locations (organelles and plasmids). Equivalent to the flat file OG-line.

type GeneNameType 

type GeneNameType struct {
	Value    string      `xml:",chardata"`
	Evidence IntListType `xml:"evidence,attr,omitempty"`
	Type     Type        `xml:"type,attr"`
}

Describes different types of gene designations. Equivalent to the flat file GN-line.

type GeneType 

type GeneType struct {
	Name []GeneNameType `xml:"http://uniprot.org/uniprot name"`
}

Describes a gene. Equivalent to the flat file GN-line.

type ImportedFromType 

type ImportedFromType struct {
	DbReference DbReferenceType `xml:"http://uniprot.org/uniprot dbReference"`
}

Describes the source of the evidence, when it is not assigned by UniProt, but imported from an external database.

type IntListType 

type IntListType []int

func (*IntListType) UnmarshalText 

func (x *IntListType) UnmarshalText(text []byte) error

type InteractantType 

type InteractantType struct {
	Id          string          `xml:"http://uniprot.org/uniprot id"`
	Label       string          `xml:"http://uniprot.org/uniprot label,omitempty"`
	DbReference DbReferenceType `xml:"http://uniprot.org/uniprot dbReference,omitempty"`
	IntactId    string          `xml:"intactId,attr"`
}

type IsoformType 

type IsoformType struct {
	Id       []string              `xml:"http://uniprot.org/uniprot id"`
	Name     []Name                `xml:"http://uniprot.org/uniprot name"`
	Sequence Anon6                 `xml:"http://uniprot.org/uniprot sequence"`
	Text     []EvidencedStringType `xml:"http://uniprot.org/uniprot text,omitempty"`
}

Describes isoforms in 'alternative products' annotations.

type KeywordType 

type KeywordType struct {
	Value    string      `xml:",chardata"`
	Evidence IntListType `xml:"evidence,attr,omitempty"`
}

type Kinetics 

type Kinetics struct {
	KM   []EvidencedStringType `xml:"http://uniprot.org/uniprot KM,omitempty"`
	Vmax []EvidencedStringType `xml:"http://uniprot.org/uniprot Vmax,omitempty"`
	Text []EvidencedStringType `xml:"http://uniprot.org/uniprot text,omitempty"`
}

type Lineage 

type Lineage struct {
	Taxon []string `xml:"http://uniprot.org/uniprot taxon"`
}
type Link struct {
	Uri string `xml:"uri,attr"`
}

type LocationType 

type LocationType struct {
	Begin    PositionType `xml:"http://uniprot.org/uniprot begin,omitempty"`
	End      PositionType `xml:"http://uniprot.org/uniprot end,omitempty"`
	Position PositionType `xml:"http://uniprot.org/uniprot position,omitempty"`
	Sequence string       `xml:"sequence,attr,omitempty"`
}

Describes a sequence location as either a range with a begin and end or as a position. The 'sequence' attribute is only used when the location is not on the canonical sequence displayed in the current entry.

type Name 

type Name struct {
	Value    string      `xml:",chardata"`
	Evidence IntListType `xml:"evidence,attr,omitempty"`
}

type NameListType 

type NameListType struct {
	Consortium ConsortiumType `xml:"http://uniprot.org/uniprot consortium,omitempty"`
	Person     PersonType     `xml:"http://uniprot.org/uniprot person,omitempty"`
}

type OrganismNameType 

type OrganismNameType struct {
	Value string `xml:",chardata"`
	Type  Type   `xml:"type,attr"`
}

Describes different types of source organism names.

type OrganismType 

type OrganismType struct {
	Name        []OrganismNameType `xml:"http://uniprot.org/uniprot name"`
	DbReference []DbReferenceType  `xml:"http://uniprot.org/uniprot dbReference"`
	Lineage     Lineage            `xml:"http://uniprot.org/uniprot lineage,omitempty"`
	Evidence    IntListType        `xml:"evidence,attr,omitempty"`
}

Describes the source organism.

type PersonType 

type PersonType struct {
	Name string `xml:"name,attr"`
}

type PhDependence 

type PhDependence struct {
	Text []EvidencedStringType `xml:"http://uniprot.org/uniprot text"`
}

type PhysiologicalReactionType 

type PhysiologicalReactionType struct {
	DbReference DbReferenceType `xml:"http://uniprot.org/uniprot dbReference"`
	Direction   Direction       `xml:"direction,attr"`
	Evidence    IntListType     `xml:"evidence,attr,omitempty"`
}

Describes a physiological reaction.

type Plasmid 

type Plasmid struct {
	Value    string      `xml:",chardata"`
	Evidence IntListType `xml:"evidence,attr,omitempty"`
}

type PositionType 

type PositionType struct {
	Position uint64      `xml:"position,attr,omitempty"`
	Status   Status      `xml:"status,attr,omitempty"`
	Evidence IntListType `xml:"evidence,attr,omitempty"`
}

func (*PositionType) UnmarshalXML 

func (t *PositionType) UnmarshalXML(d *xml.Decoder, start xml.StartElement) error

type PropertyType 

type PropertyType struct {
	Type  string `xml:"type,attr"`
	Value string `xml:"value,attr"`
}

type ProteinExistenceType 

type ProteinExistenceType struct {
	Type Type `xml:"type,attr"`
}

Describes the evidence for the protein's existence. Equivalent to the flat file PE-line.

type ProteinType 

type ProteinType struct {
	RecommendedName RecommendedName       `xml:"http://uniprot.org/uniprot recommendedName,omitempty"`
	AlternativeName []AlternativeName     `xml:"http://uniprot.org/uniprot alternativeName,omitempty"`
	SubmittedName   []SubmittedName       `xml:"http://uniprot.org/uniprot submittedName,omitempty"`
	AllergenName    EvidencedStringType   `xml:"http://uniprot.org/uniprot allergenName,omitempty"`
	BiotechName     EvidencedStringType   `xml:"http://uniprot.org/uniprot biotechName,omitempty"`
	CdAntigenName   []EvidencedStringType `xml:"http://uniprot.org/uniprot cdAntigenName,omitempty"`
	InnName         []EvidencedStringType `xml:"http://uniprot.org/uniprot innName,omitempty"`
	Domain          []Domain              `xml:"http://uniprot.org/uniprot domain,omitempty"`
	Component       []Component           `xml:"http://uniprot.org/uniprot component,omitempty"`
}

Describes the names for the protein and parts thereof. Equivalent to the flat file DE-line.

type ReactionType 

type ReactionType struct {
	Text        string            `xml:"http://uniprot.org/uniprot text"`
	DbReference []DbReferenceType `xml:"http://uniprot.org/uniprot dbReference"`
	Evidence    IntListType       `xml:"evidence,attr,omitempty"`
}

Describes a chemical reaction.

type RecommendedName 

type RecommendedName struct {
	FullName  EvidencedStringType   `xml:"http://uniprot.org/uniprot fullName"`
	ShortName []EvidencedStringType `xml:"http://uniprot.org/uniprot shortName,omitempty"`
	EcNumber  []EvidencedStringType `xml:"http://uniprot.org/uniprot ecNumber,omitempty"`
}

type RedoxPotential 

type RedoxPotential struct {
	Text []EvidencedStringType `xml:"http://uniprot.org/uniprot text"`
}

type ReferenceType 

type ReferenceType struct {
	Citation CitationType   `xml:"http://uniprot.org/uniprot citation"`
	Scope    []string       `xml:"http://uniprot.org/uniprot scope"`
	Source   SourceDataType `xml:"http://uniprot.org/uniprot source,omitempty"`
	Evidence IntListType    `xml:"evidence,attr,omitempty"`
	Key      string         `xml:"key,attr"`
}

Describes a citation and a summary of its content. Equivalent to the flat file RN-, RP-, RC-, RX-, RG-, RA-, RT- and RL-lines.

type Resource 

type Resource string

May be one of EMBL-CDS, EMBL

type Sequence 

type Sequence struct {
	Resource Resource `xml:"resource,attr"`
	Version  int      `xml:"version,attr,omitempty"`
}

type SequenceType 

type SequenceType struct {
	Value     string    `xml:",chardata"`
	Length    int       `xml:"length,attr"`
	Mass      int       `xml:"mass,attr"`
	Checksum  string    `xml:"checksum,attr"`
	Modified  time.Time `xml:"modified,attr"`
	Version   int       `xml:"version,attr"`
	Precursor bool      `xml:"precursor,attr,omitempty"`
	Fragment  Fragment  `xml:"fragment,attr,omitempty"`
}

func (*SequenceType) UnmarshalXML 

func (t *SequenceType) UnmarshalXML(d *xml.Decoder, start xml.StartElement) error

type SourceDataType 

type SourceDataType struct {
	Strain     Strain     `xml:"http://uniprot.org/uniprot strain,omitempty"`
	Plasmid    Plasmid    `xml:"http://uniprot.org/uniprot plasmid,omitempty"`
	Transposon Transposon `xml:"http://uniprot.org/uniprot transposon,omitempty"`
	Tissue     Tissue     `xml:"http://uniprot.org/uniprot tissue,omitempty"`
}

Describes the source of the sequence according to the citation. Equivalent to the flat file RC-line.

type SourceType 

type SourceType struct {
	DbReference DbReferenceType `xml:"http://uniprot.org/uniprot dbReference,omitempty"`
}

Describes the source of the data using a database cross-reference (or a 'ref' attribute when the source cannot be found in a public data source, such as PubMed, and is cited only within the UniProtKB entry).

type Status 

type Status string

May be one of certain, uncertain, less than, greater than, unknown

type StatusType 

type StatusType struct {
	Value  string `xml:",chardata"`
	Status Status `xml:"status,attr,omitempty"`
}

Indicates whether the name of a plasmid is known or unknown.

type Strain 

type Strain struct {
	Value    string      `xml:",chardata"`
	Evidence IntListType `xml:"evidence,attr,omitempty"`
}

type SubcellularLocationType 

type SubcellularLocationType struct {
	Location    []EvidencedStringType `xml:"http://uniprot.org/uniprot location"`
	Topology    []EvidencedStringType `xml:"http://uniprot.org/uniprot topology,omitempty"`
	Orientation []EvidencedStringType `xml:"http://uniprot.org/uniprot orientation,omitempty"`
}

Describes the subcellular location and optionally the topology and orientation of a molecule.

type SubmittedName 

type SubmittedName struct {
	FullName EvidencedStringType   `xml:"http://uniprot.org/uniprot fullName"`
	EcNumber []EvidencedStringType `xml:"http://uniprot.org/uniprot ecNumber,omitempty"`
}

type TemperatureDependence 

type TemperatureDependence struct {
	Text []EvidencedStringType `xml:"http://uniprot.org/uniprot text"`
}

type Tissue 

type Tissue struct {
	Value    string      `xml:",chardata"`
	Evidence IntListType `xml:"evidence,attr,omitempty"`
}

type Transposon 

type Transposon struct {
	Value    string      `xml:",chardata"`
	Evidence IntListType `xml:"evidence,attr,omitempty"`
}

type Type 

type Type string

May be one of apicoplast, chloroplast, organellar chromatophore, cyanelle, hydrogenosome, mitochondrion, non-photosynthetic plastid, nucleomorph, plasmid, plastid

type Uniprot 

type Uniprot struct {
	Entry     []string `xml:"http://uniprot.org/uniprot entry"`
	Copyright string   `xml:"http://uniprot.org/uniprot copyright,omitempty"`
}

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.