util

package
v0.1.0 Latest Latest
Warning

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

 Go to latest Published: May 5, 2026 License: MIT Imports: 19 Imported by: 0

Documentation

Index

Constants

View Source 
const (
	STOP = 0
	DIAG = 1 // Diagonal move (match/mismatch)
	UP   = 2 // Up move (gap in sequence B)
	LEFT = 3 // Left move (gap in sequence A)
)
View Source 
const BAI1_int = 0x01494142 // 'BAI\1' in Intel CPUs
View Source 
const CODE_STAT_MOUSE_EVENT = 1

Variables

This section is empty.

Functions

func AbsInt 

func AbsInt(i int) int

func AffineGlobalAlignment 

func AffineGlobalAlignment(query, reference string, params ScoringParams) (cigar string, score int)

AffineGlobalAlignment performs global alignment (End-to-End) so no base is left unmapped.

func AsciiColorStr 

func AsciiColorStr(clr int) string

func CalcOverlap 

func CalcOverlap(fe GeneFeature, sec MappedSection) int

func ChoiceInt 

func ChoiceInt(ints []int) int

func ChoiceStr 

func ChoiceStr(strs []string) string

func ChoiceStrExcept 

func ChoiceStrExcept(strs []string, exc string) string

func ChroPos2Linear 

func ChroPos2Linear(chro string, pos int) (rpos int64, err error)

func Cigar14To13 

func Cigar14To13(cigar string) string

func CigarChroLen 

func CigarChroLen(opts []CigarOpt) int

func CigarIndelLen 

func CigarIndelLen(opts []CigarOpt) int

func CigarMappedLen 

func CigarMappedLen(opts []CigarOpt, incI bool) int

func CigarReadLen 

func CigarReadLen(opts []CigarOpt) int

func CompressCigar 

func CompressCigar(cigar string) string

func ContainStr 

func ContainStr(sli []string, target string) bool

func CropCigarOnChro 

func CropCigarOnChro(cigar string, first_base_loc, wanted_first_chro_base, wanted_last_chro_base int, add_S_before_after bool) (ret string, new_mapped_loc_after_S, skipped_rbases int)

func CropCigarOnRead 

func CropCigarOnRead(cigar string, chro_pos_after_S, wanted_first_read_base_0based, wanted_last_read_base_0based int, add_S_before_after bool) (ret string, new_first_base_chro_loc, skipped_chrobases int)

func DelTempFile 

func DelTempFile(fn string)

func ExIntTag 

func ExIntTag(extra_columns []SAMAppendix, key string) int

func ExecStream 

func ExecStream(cmdstr string) (return_code int, stdout io.ReadCloser)

func ExtraTagInt 

func ExtraTagInt(extra []SAMAppendix, tagname string) (found bool, tagvalue int)

func FixSoftClipping 

func FixSoftClipping(pos int, cigar string) (newpos int, newcigar string)

func GetBlockInfo 

func GetBlockInfo(voff uint64) (bam_offset uint64, inblock_offset uint32)

func GetIntTag 

func GetIntTag(fl, tag string) int

func GlobalAlignmentCIGAR 

func GlobalAlignmentCIGAR(query_seq, reference_seq string, matchScore, mismatchPenalty, gapOpenPenalty, gapExtendPenalty int) (string, int)

Scores and Penalties are all positive.

func HammingDistance 

func HammingDistance(a, b string) (dist int, err error)

func HashCode 

func HashCode(str string) uint

func IfElseInt 

func IfElseInt(con bool, i1, i2 int) int

func IfElseStr 

func IfElseStr(con bool, i1, i2 string) string

func IntersectInt 

func IntersectInt(s1, s2 []int) []int

func IntersectStr 

func IntersectStr(s1, s2 []string) []string

func IsFile 

func IsFile(fname string) bool

func IsFusionRead 

func IsFusionRead(sections []MappedSection, max_intron int) bool

func IsOverlapping 

func IsOverlapping(As, Ae, Bs, Be, min_hanging_len int) bool

A and B should have at least min_hanging_len bases overlapping

func IsWellContaining 

func IsWellContaining(As, Ae, Bs, Be, min_hanging_len int) bool

A should contain B; A should be much longer than B

func JoinInt 

func JoinInt(split string, ints []int) string

func JoinStr 

func JoinStr(split string, strs []string) string

func ListDir 

func ListDir(path string) (files []string, err error)

func LoadJuncsInTranscripts 

func LoadJuncsInTranscripts(GTF_fname string, gtf_gene_id, gtf_transcript_id string) (lookup_table map[string]int, err error)

lookup_table: chro:pos1 <TAB> pos2. pos1 and pos2 are both 1-base coordinates, both included in the exons. pos1 < pos2. value: 1 if positive; 2 if negative; bitwise-or

func LoadTab 

func LoadTab(fn string, oldmap *map[string]string) map[string]string

func Map2Slice 

func Map2Slice(m map[string]bool) []string

func MatchPrefix 

func MatchPrefix(onestr string, prefix_pool []string) (prefix string, found bool)

func MaxFloat64 

func MaxFloat64(i, j float64) float64

func MaxInt 

func MaxInt(i, j int) int

func MaxStr 

func MaxStr(a, b string) string

func MergedGaps 

func MergedGaps(gaps [][2]int) [][2]int

func MinInt 

func MinInt(i, j int) int

func MinStr 

func MinStr(a, b string) string

func Mv 

func Mv(o, n string)

func OverlapGaps 

func OverlapGaps(gapA [][2]int, gapB [][2]int) [][2]int

Gaps are open gaps. Close gap of [1, 99] is [1, 100) in input. Output is also open gaps. gapA and gapB MUST be sorted by coordinates and non-overlapping.

func Phred64_to_33 

func Phred64_to_33(s string) string

func Random4Bases 

func Random4Bases(length int) string

func RandomBases 

func RandomBases(length int) string

func RandomString 

func RandomString(length int) string

func ReadFastA 

func ReadFastA(fname string) (seqlist []string, seqmap map[string]string, err error)

func ReadOnerowFastA 

func ReadOnerowFastA(fname string) (rname, seq string, err error)

func ReadUInt16LittleEndianFp 

func ReadUInt16LittleEndianFp(fp *os.File) (ret uint16, err error)

func ReadUInt32LittleEndianFp 

func ReadUInt32LittleEndianFp(fp *os.File) (ret uint32, err error)

func ReadUInt64LittleEndianFp 

func ReadUInt64LittleEndianFp(fp *os.File) (ret uint64, err error)

func ReverseRead 

func ReverseRead(bases, qual string) (rbases, rqual string)

func SelectQualString 

func SelectQualString(rlen int, reflib string) (rqual string, floats []float64)

func SequenceErrorByQualityString 

func SequenceErrorByQualityString(read, qstr string, error_scalling float64) (newread string, seq_error []bool)

func SequenceErrorByRandomQualityString 

func SequenceErrorByRandomQualityString(read string, error_scalling float64) (newread, qual string, seq_error []bool)

func SequenceErrorByRandomQualityStringEx 

func SequenceErrorByRandomQualityStringEx(read string, error_scalling float64, refqual string) (newread, qual string, seq_error []bool)

func SetTtyCanonical 

func SetTtyCanonical(is_canon, has_echo bool)

func System 

func System(cmd string) (return_code int, stdout string)

func TempFileName 

func TempFileName() string

func TestTty 

func TestTty()

func ULID 

func ULID() string

func UUID 

func UUID() string

func UXID 

func UXID() string

func UnionInt 

func UnionInt(s1, s2 []int) []int

func UnionStr 

func UnionStr(s1, s2 []string) []string

func UniqueFeatureLength 

func UniqueFeatureLength(mas []FeatureReadMatching) int

func UniqueInt 

func UniqueInt(strs []int) []int

func UniqueStr 

func UniqueStr(strs []string) []string

func WriteFastA 

func WriteFastA(fp io.Writer, name, seq string)

func WriteFastAEx 

func WriteFastAEx(fp io.Writer, name, seq string, fasta_line_width int)

Types

type AlignmentResult 

type AlignmentResult struct {
	Score     int
	SequenceA string
	SequenceB string
	StartA    int // Start index in the original Sequence A
	StartB    int // Start index in the original Sequence B
}

AlignmentResult holds the results of the Smith-Waterman alignment.

func SmithWaterman 

func SmithWaterman(seqA, seqB string, matchScore, mismatchScore, gapCreationPenalty, gapExtensionPenalty int) AlignmentResult

SmithWaterman performs local sequence alignment using a traceback matrix for correctness.

func SmithWaterman3P 

func SmithWaterman3P(seqA, seqB string, matchScore, mismatchScore, gapPenalty int) AlignmentResult

SmithWaterman performs local sequence alignment using a traceback matrix for correctness.

type AsGap 

type AsGap [][2]int

func (AsGap) Len 

func (a AsGap) Len() int

func (AsGap) Less 

func (a AsGap) Less(i, j int) bool

func (AsGap) Swap 

func (a AsGap) Swap(i, j int)

type BamReader 

type BamReader struct {
	// contains filtered or unexported fields
}

func BAMopen 

func BAMopen(fname string) (br *BamReader, err error)

func (*BamReader) Array 

func (qf *BamReader) Array() (strarr []string, err error)

func (*BamReader) BamHeader 

func (qf *BamReader) BamHeader() string

func (*BamReader) Close 

func (br *BamReader) Close()

func (*BamReader) GetChromosomeInfo 

func (qf *BamReader) GetChromosomeInfo(chro_name string) *ChromosomeInfo

func (*BamReader) Line 

func (br *BamReader) Line() (st string, err error)

func (*BamReader) ReloadLine 

func (br *BamReader) ReloadLine()

func (*BamReader) SAMRecord 

func (qf *BamReader) SAMRecord() (read_name string, flags int, chro string, pos, mapq int, cigar, mate_chro string, mate_pos, tlen int, seq, qual string, err error)

func (*BamReader) SAMRecordEx 

func (qf *BamReader) SAMRecordEx() (read_name string, flags int, chro string, pos, mapq int, cigar, mate_chro string, mate_pos, tlen int, seq, qual string, extra_columns []SAMAppendix, err error)

type BucketedTable 

type BucketedTable struct {
	// contains filtered or unexported fields
}

func CreateBucketedTable 

func CreateBucketedTable(granularity int) *BucketedTable

granularity must be longer than the longest read length

func (*BucketedTable) Append 

func (who *BucketedTable) Append(chroname string, pos int, value string)

func (*BucketedTable) Lookup 

func (who *BucketedTable) Lookup(chroname string, read_start_pos, read_len int) (ret []string, found bool)

this will lookup all events in the read, given that the reat starts at read_start_pos, and is shorter than granularity.

type ChromosomeInfo 

type ChromosomeInfo struct {
	Name   string
	Length int
}

type CigarOpt 

type CigarOpt struct {
	OptType byte
	OptLen  int
}

func ParseCigar 

func ParseCigar(cigar string) []CigarOpt

func ParseCigar14 

func ParseCigar14(cigar string) []CigarOpt

type Exon 

type Exon struct {
	Chro        string
	Start, Stop int //Both are 1-base coordinates. Both inclusive in this exon. The same as in GTF format.
	IsNegative  bool
}

type FeatureIndex 

type FeatureIndex struct {
	RawFeatures []*GeneFeature
	// contains filtered or unexported fields
}

func CreateFeatureIndex 

func CreateFeatureIndex() *FeatureIndex

func LoadFeatureTable 

func LoadFeatureTable(fname string, include_intron bool) (FeatureIndex *FeatureIndex, err error)

func (*FeatureIndex) Append 

func (self *FeatureIndex) Append(chro string, start, end int, feat *GeneFeature)

func (*FeatureIndex) Features 

func (self *FeatureIndex) Features(sec MappedSection) []*GeneFeature

func (*FeatureIndex) GetGeneCount 

func (self *FeatureIndex) GetGeneCount() int

func (*FeatureIndex) IsGeneNeighbours 

func (self *FeatureIndex) IsGeneNeighbours(id1, id2 string) bool

func (*FeatureIndex) IsNeighbourFeatures 

func (self *FeatureIndex) IsNeighbourFeatures(f1, f2 GeneFeature) bool

func (*FeatureIndex) Lookup 

func (self *FeatureIndex) Lookup(chro string, start, stop int) []*GeneFeature

type FeatureReadMatching 

type FeatureReadMatching struct {
	Feature                                 GeneFeature
	ChroStart, ChroStop, ReadStart, ReadLen int // ChroStop is inclusive (len = Stop - Start + 1)
}

type FusionEvent 

type FusionEvent struct {
	Chro1, Chro2                          string
	Pos1, Pos2                            int
	Cross, ExtendToSmall1, ExtendToSmall2 bool
	ExtensionLength1, ExtensionLength2    int
	EventType                             string
	NSup                                  int
}

func ExtractFusionEvents 

func ExtractFusionEvents(sections []MappedSection, read_on_negative bool) []FusionEvent

func LoadFusions 

func LoadFusions(ff string) (fusions []FusionEvent, err error)

func LoadReportedJunctions 

func LoadReportedJunctions(JuncOut_file string) (junctions []FusionEvent, err error)

func (FusionEvent) Key 

func (self FusionEvent) Key() string

type GeneFeature 

type GeneFeature struct {
	Chro             string
	Start, Stop      int // Stop is inclusive (len = Stop - Start + 1)
	GeneID           string
	IsNegativeStrand bool
	ExonID           int
	FeatureIndex     int
}

func LoadFeatures 

func LoadFeatures(fname string, include_intron bool) (features []*GeneFeature, neighbour_gene_table map[string]bool, err error)

func LoadFeaturesEx 

func LoadFeaturesEx(fname string, include_intron bool, gtf_gene_id string) (features []*GeneFeature, neighbour_gene_table map[string]bool, err error)

func MergeSortFeatures 

func MergeSortFeatures(gfs []*GeneFeature) []*GeneFeature

func (*GeneFeature) Key 

func (self *GeneFeature) Key() string

type MappedSection 

type MappedSection struct {
	Chro                string
	Pos                 int
	Cigar               string
	ReadLength          int
	IsNegative          bool
	IsMainAlignment     bool
	IsCoordinateGoingUp bool

	ConnectToLeft  bool
	ConnectToRight bool

	ReadPosition     int
	ChromosomeLength int
}

func ParseCigarSections 

func ParseCigarSections(chro string, pos int, cigar string, flags int) []MappedSection

func ParseFusionSections 

func ParseFusionSections(chro string, pos int, cigar string, flags int, appendix []SAMAppendix) []MappedSection

type MappingCoverage 

type MappingCoverage struct {
	// contains filtered or unexported fields
}

func LoadCoverage 

func LoadCoverage(prefix string) (mc *MappingCoverage, err error)

func (*MappingCoverage) Coverage 

func (mc *MappingCoverage) Coverage(chro string, pos int) (coverage int, err error)

func (*MappingCoverage) MeanCoverage 

func (mc *MappingCoverage) MeanCoverage(chro string, pos, bases int) (meancoverage int, err error)

type MatrixCell 

type MatrixCell struct {
	// contains filtered or unexported fields
}

MatrixCell holds scores for the three affine states.

type MyError 

type MyError struct {
	// contains filtered or unexported fields
}

func NewError 

func NewError(msg string) *MyError

func (*MyError) Error 

func (self *MyError) Error() string

type Qfile 

type Qfile struct {
	// contains filtered or unexported fields
}

func Qopen 

func Qopen(filename string) (qfp *Qfile, err error)

func QopenGz 

func QopenGz(gzfile string) (qfp *Qfile, err error)

func Qstream 

func Qstream(raw_reader *io.ReadCloser) (qfp *Qfile, err error)

func (*Qfile) Array 

func (qf *Qfile) Array() (strarr []string, err error)

func (*Qfile) Close 

func (qf *Qfile) Close() (err error)

func (*Qfile) GetChromosomeInfo 

func (qf *Qfile) GetChromosomeInfo(chro_name string) *ChromosomeInfo

func (*Qfile) Line 

func (qf *Qfile) Line() (str string, err error)

func (*Qfile) ReloadLine 

func (qf *Qfile) ReloadLine()

func (*Qfile) Rewind 

func (qf *Qfile) Rewind()

func (*Qfile) SAMRecord 

func (qf *Qfile) SAMRecord() (read_name string, flags int, chro string, pos, mapq int, cigar, mate_chro string, mate_pos, tlen int, seq, qual string, err error)

func (*Qfile) SAMRecordEx 

func (qf *Qfile) SAMRecordEx() (read_name string, flags int, chro string, pos, mapq int, cigar, mate_chro string, mate_pos, tlen int, seq, qual string, extra_columns []SAMAppendix, err error)

func (*Qfile) SetFileInfo 

func (qf *Qfile) SetFileInfo(info string)

func (*Qfile) Split 

func (qf *Qfile) Split(sep string) (strarr []string, err error)

func (*Qfile) TrimLine 

func (qf *Qfile) TrimLine() (str string, err error)

type RawBAIChromosome 

type RawBAIChromosome struct {
	BinNumbers   []int
	ChunksInBins [][][2]uint64
}

func GetAllChromosomesBAI 

func GetAllChromosomesBAI(fname string) (chroinfo []RawBAIChromosome, window16offsets [][]uint64, err error)

type RawBamChroInfo 

type RawBamChroInfo struct {
	ChroName   string
	ChroLength int32
}

type RawBamFile 

type RawBamFile struct {
	Chro_Info   []RawBamChroInfo
	Read_Groups []ReadGroupInfo
	// contains filtered or unexported fields
}

func RawBamOpen 

func RawBamOpen(fn string) (fp *RawBamFile, err error)

func (*RawBamFile) Close 

func (rb *RawBamFile) Close()

func (*RawBamFile) FindAllStringTags 

func (rb *RawBamFile) FindAllStringTags(b []byte, tagname string) []string

func (*RawBamFile) NextReadBin 

func (rb *RawBamFile) NextReadBin() (ret []byte, vfile_pos_rstart int64, err error)

func (*RawBamFile) Read 

func (rb *RawBamFile) Read(data []byte) (rlen int, err error)

func (*RawBamFile) ReadBinBasicInfo 

func (rb *RawBamFile) ReadBinBasicInfo(b []byte) (readname string, flag int32, chro string, pos, cigar_opts, read_len int32, extra_data []byte)

type ReadGroupInfo 

type ReadGroupInfo struct {
	GroupName string
}

type SAMAppendix 

type SAMAppendix struct {
	TagName  string
	TagType  byte
	TagValue string
}

func SAMRecordParser 

func SAMRecordParser(fli []string) (read_name string, flags int, chro string, pos, mapq int, cigar, mate_chro string, mate_pos, tlen int, seq, qual string, extra_columns []SAMAppendix, err error)

type SamBamReader 

type SamBamReader interface {
	SAMRecordEx() (read_name string, flags int, chro string, pos, mapq int, cigar, mate_chro string, mate_pos, tlen int, seq, qual string, extra_columns []SAMAppendix, err error)
	SAMRecord() (read_name string, flags int, chro string, pos, mapq int, cigar, mate_chro string, mate_pos, tlen int, seq, qual string, err error)
	GetChromosomeInfo(chro_name string) *ChromosomeInfo
}

type SamBuffered 

type SamBuffered struct {
	// contains filtered or unexported fields
}

func CreateBufferedSam 

func CreateBufferedSam(qs *Qfile) *SamBuffered

func (*SamBuffered) GetNextPair 

func (sb *SamBuffered) GetNextPair()

func (*SamBuffered) HasThisName 

func (sb *SamBuffered) HasThisName(rname string) (hasThis bool, chr1, chr2 string, flag1, flag2, pos1, pos2 int, cigar1, cigar2 string, ex1, ex2 []SAMAppendix, isEOF bool)

type ScoringParams 

type ScoringParams struct {
	MatchScore       int
	MismatchPenalty  int
	GapCreatePenalty int // Cost to open a new gap
	GapExtPenalty    int // Cost to extend an existing gap
}

type SmithParams 

type SmithParams struct {
	MatchScore       int
	MismatchPenalty  int
	GapOpenPenalty   int
	GapExtendPenalty int
}

SmithParams holds the penalties and scores. Note: ALL positive values

type SmithResult 

type SmithResult struct {
	CIGAR    string
	RefStart int // 0-based index start in Reference
	RefEnd   int // 0-based index end in Reference (exclusive)
	Score    int
	QuerySeq string
	RefSeq   string
}

SmithResult holds the output of the algorithm.

func SmithWatermanSemiGlobal 

func SmithWatermanSemiGlobal(query, ref string, params SmithParams) SmithResult

SmithWatermanSemiGlobal performs alignment where the entire query must be mapped, but it can map to any substring of the reference.

type SortedFeatureReadMatching 

type SortedFeatureReadMatching []FeatureReadMatching

func (SortedFeatureReadMatching) Len 

func (mas SortedFeatureReadMatching) Len() int

func (SortedFeatureReadMatching) Less 

func (mas SortedFeatureReadMatching) Less(i, j int) bool

func (SortedFeatureReadMatching) Swap 

func (mas SortedFeatureReadMatching) Swap(i, j int)

type SortedTable 

type SortedTable struct {
	SortedEntries []int
}

func CreateSortedTable 

func CreateSortedTable() *SortedTable

func (*SortedTable) Append 

func (me *SortedTable) Append(pos int)

func (*SortedTable) LessOrEqual 

func (me *SortedTable) LessOrEqual(pos int) int

func (*SortedTable) PrintEntries 

func (me *SortedTable) PrintEntries()

func (*SortedTable) Range 

func (me *SortedTable) Range(pos_start, pos_stop int) []int

func (*SortedTable) Sort 

func (me *SortedTable) Sort()

type SortingFeature 

type SortingFeature []*GeneFeature

func (SortingFeature) Len 

func (s SortingFeature) Len() int

func (SortingFeature) Less 

func (s SortingFeature) Less(i, j int) bool

func (SortingFeature) Swap 

func (s SortingFeature) Swap(i, j int)

type Transcript 

type Transcript struct {
	GeneID, TranscriptID string
	Exons                []Exon
}

func LoadTranscripts 

func LoadTranscripts(GTF_fname string, gtf_gene_id, gtf_transcript_id string) (txns []Transcript, err error)

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.