mirror of
https://github.com/metabarcoding/obitools4.git
synced 2026-11-09 17:24:41 +00:00
Eric Coissac
3087c70daa
This commit introduces core functionality for oligonucleotide family tagging, constrained k-mer generation, and clique finding. It also includes updates to the Go language version and refactors the logic for k-mer dissimilarity metrics.
42 lines
867 B
Go
42 lines
867 B
Go
package obiseq
|
|
|
|
var _iupac = [26]byte{
|
|
// a b c d e f
|
|
1, 14, 2, 13, 0, 0,
|
|
// g h i j k l
|
|
4, 11, 0, 0, 12, 0,
|
|
// m n o p q r
|
|
3, 15, 0, 0, 0, 5,
|
|
// s t u v w x
|
|
6, 8, 8, 13, 9, 0,
|
|
// y z
|
|
10, 0,
|
|
}
|
|
|
|
func SameIUPACNuc(a, b byte) bool {
|
|
if (a >= 'A') && (a <= 'Z') {
|
|
a |= 32
|
|
}
|
|
if (b >= 'A') && (b <= 'Z') {
|
|
b |= 32
|
|
}
|
|
|
|
if (a >= 'a') && (a <= 'z') && (b >= 'a') && (b <= 'z') {
|
|
return (_iupac[a-'a'] & _iupac[b-'a']) > 0
|
|
}
|
|
return a == b
|
|
}
|
|
|
|
// IUPACNucMask returns the set of nucleotides denoted by the IUPAC code b
|
|
// (case insensitive, U is read as T) as a 4 bits mask: bit 0 is A, bit 1 is C,
|
|
// bit 2 is G and bit 3 is T. It returns 0 if b is not an IUPAC nucleotide code.
|
|
func IUPACNucMask(b byte) byte {
|
|
if (b >= 'A') && (b <= 'Z') {
|
|
b |= 32
|
|
}
|
|
if (b < 'a') || (b > 'z') {
|
|
return 0
|
|
}
|
|
return _iupac[b-'a']
|
|
}
|