mirror of
https://github.com/metabarcoding/obitools4.git
synced 2026-11-10 01:24:41 +00:00
Add error handling for ambiguous bases in k-mer encoding
This commit introduces error handling for ambiguous DNA bases (N, R, Y, W, S, K, M, B, D, H, V) in k-mer encoding. It adds new functions IterNormalizedKmersWithErrors and EncodeNormalizedKmersWithErrors that track and encode the number of ambiguous bases in each k-mer using error markers in the top 2 bits. The commit also updates the version string to reflect the latest changes.
This commit is contained in:
1 parent
28162ac36f
commit
60f27c1dc8
3 files changed
+290
-1
No files matched your search
@@ -5,6 +5,10 @@ import (
|
||||
"git.metabarcoding.org/obitools/obitools4/obitools4/pkg/obiutils"
|
||||
)
|
||||
|
||||
// __single_base_code__ encodes DNA bases to 2-bit values.
|
||||
// Standard bases: A=0, C=1, G=2, T/U=3
|
||||
// Ambiguous bases (N, R, Y, W, S, K, M, B, D, H, V): 0xFF (255) to signal error
|
||||
|
||||
var __single_base_code__ = []byte{0,
|
||||
// A, B, C, D,
|
||||
0, 0, 1, 0,
|
||||
|
||||
Reference in new issue
Block a user