feat(phylo): add --iqtree-min-freq to filter rare nucleotide states

Introduces --iqtree-min-freq (default 0.001) to treat low-frequency nucleotide states as missing data during IQ-TREE alignment generation when --free-loss is active. This triggers a recoding pass that folds rare states into the missing symbol, followed by non-informative site removal and alphabet recomputation to maintain output consistency. The change also adds Sankoff model configuration files and updates related tests and documentation.
This commit is contained in:
Eric Coissac
2026-08-17 11:06:03 +02:00
parent c8f2b16b4c
commit 128db64564
10 changed files with 756 additions and 7 deletions
+167
View File
@@ -0,0 +1,167 @@
ratio_ceiling: 0.5
cardinality_transitions:
- from: 0
to: 0
count: 13019012
probability: 0.8682962128540935
- from: 0
to: 1
count: 1945560
probability: 0.12975810913150784
- from: 0
to: 2
count: 26381
probability: 0.0017594670310852958
- from: 0
to: 3
count: 2792
probability: 0.000186210983313375
- from: 0
to: 4
count: 0
probability: 0.0
- from: 1
to: 0
count: 1945560
probability: 0.9666005228573729
- from: 1
to: 1
count: 66078
probability: 0.03282912341401421
- from: 1
to: 2
count: 1123
probability: 0.0005579331334776772
- from: 1
to: 3
count: 25
probability: 0.000012420595135300028
- from: 1
to: 4
count: 0
probability: 0.0
- from: 2
to: 0
count: 26381
probability: 0.9567346050627402
- from: 2
to: 1
count: 1123
probability: 0.04072677159643142
- from: 2
to: 2
count: 51
probability: 0.0018495684340320592
- from: 2
to: 3
count: 19
probability: 0.0006890549067962574
- from: 2
to: 4
count: 0
probability: 0.0
- from: 3
to: 0
count: 2792
probability: 0.9841381741275996
- from: 3
to: 1
count: 25
probability: 0.008812125484666901
- from: 3
to: 2
count: 19
probability: 0.0066972153683468455
- from: 3
to: 3
count: 1
probability: 0.00035248501938667606
- from: 3
to: 4
count: 0
probability: 0.0
- from: 4
to: 0
count: 0
probability: 0.0
- from: 4
to: 1
count: 0
probability: 0.0
- from: 4
to: 2
count: 0
probability: 0.0
- from: 4
to: 3
count: 0
probability: 0.0
- from: 4
to: 4
count: 0
probability: 0.0
composition_transitions:
- from: 'A'
to: 'A'
count: 0
probability: 0.0
- from: 'A'
to: 'C'
count: 0
probability: 0.0
- from: 'A'
to: 'G'
count: 0
probability: 0.0
- from: 'A'
to: 'T'
count: 0
probability: 0.0
- from: 'C'
to: 'A'
count: 0
probability: 0.0
- from: 'C'
to: 'C'
count: 10771
probability: 0.9619540948468339
- from: 'C'
to: 'G'
count: 163
probability: 0.014557470751094042
- from: 'C'
to: 'T'
count: 263
probability: 0.023488434402071982
- from: 'G'
to: 'A'
count: 0
probability: 0.0
- from: 'G'
to: 'C'
count: 163
probability: 0.006662851536952256
- from: 'G'
to: 'G'
count: 24073
probability: 0.9840173315892741
- from: 'G'
to: 'T'
count: 228
probability: 0.009319816873773708
- from: 'T'
to: 'A'
count: 0
probability: 0.0
- from: 'T'
to: 'C'
count: 263
probability: 0.008464484567603231
- from: 'T'
to: 'G'
count: 228
probability: 0.007338032248720672
- from: 'T'
to: 'T'
count: 30580
probability: 0.9841974831836761