add name-tree command and fix --free-loss cost matrix

Introduce the obikmer name-tree subcommand to map numeric leaf labels in phylogenetic tree exports back to taxon names using a reference FASTA file. Correct the --free-loss flag behavior by removing cardinality transition costs from pairwise cost calculations, ensuring sibling gains and losses are priced identically to whole-family events. Update documentation, configuration parameters, and add reference phylogenetic data files.
This commit is contained in:
Eric Coissac
2026-08-16 13:11:06 +02:00
parent 8615da59a8
commit eee71430a4
14 changed files with 1444 additions and 82 deletions
+74 -74
View File
@@ -2,166 +2,166 @@ ratio_ceiling: 0.5
cardinality_transitions:
- from: 0
to: 0
count: 37622567
probability: 0.7765461217831444
count: 54999793
probability: 0.7934021725308564
- from: 0
to: 1
count: 6977400
probability: 0.14401656617768033
count: 8873859
probability: 0.12801028195383377
- from: 0
to: 2
count: 3744558
probability: 0.0772893033240408
count: 5305545
probability: 0.07653539585976665
- from: 0
to: 3
count: 91083
probability: 0.0018799926759482985
count: 126109
probability: 0.001819191475424167
- from: 0
to: 4
count: 12985
probability: 0.0002680160391861122
count: 16149
probability: 0.00023295818011898336
- from: 1
to: 0
count: 6977400
probability: 0.820630384894398
count: 8873859
probability: 0.8510749571674425
- from: 1
to: 1
count: 1018042
probability: 0.1197346000370715
count: 1041044
probability: 0.09984455215137214
- from: 1
to: 2
count: 502624
probability: 0.05911493200578466
count: 507272
probability: 0.048651493749477304
- from: 1
to: 3
count: 4197
probability: 0.000493620220340211
count: 4248
probability: 0.00040741760918753563
- from: 1
to: 4
count: 225
probability: 0.000026462842405658202
probability: 0.00002157932252052625
- from: 2
to: 0
count: 3744558
probability: 0.8804244781723005
count: 5305545
probability: 0.9117891245815953
- from: 2
to: 1
count: 502624
probability: 0.11817749195415704
count: 507272
probability: 0.08717767784549091
- from: 2
to: 2
count: 5162
probability: 0.0012136949558066439
count: 5227
probability: 0.0008982907041949506
- from: 2
to: 3
count: 688
probability: 0.0001617632951559417
count: 689
probability: 0.00011840870388182915
- from: 2
to: 4
count: 96
probability: 0.00002257162257989884
probability: 0.000016498164836945715
- from: 3
to: 0
count: 91083
probability: 0.9478728718311618
count: 126109
probability: 0.9614164824273843
- from: 3
to: 1
count: 4197
probability: 0.04367689297756317
count: 4248
probability: 0.03238545399100404
- from: 3
to: 2
count: 688
probability: 0.007159805186696083
count: 689
probability: 0.005252725470763132
- from: 3
to: 3
count: 98
probability: 0.0010198559713607792
probability: 0.0007471220553480217
- from: 3
to: 4
count: 26
probability: 0.00027057403321816594
probability: 0.00019821605550049553
- from: 4
to: 0
count: 12985
probability: 0.972950696838004
count: 16149
probability: 0.9781344639612356
- from: 4
to: 1
count: 225
probability: 0.01685898396523303
probability: 0.013628104179285281
- from: 4
to: 2
count: 96
probability: 0.0071931664918327585
probability: 0.00581465778316172
- from: 4
to: 3
count: 26
probability: 0.0019481492582047056
probability: 0.0015748031496062992
- from: 4
to: 4
count: 14
probability: 0.0010490034467256107
probability: 0.0008479709267110841
composition_transitions:
- from: 'A'
to: 'A'
count: 157182
probability: 0.46648741052031767
count: 161774
probability: 0.4701762136303263
- from: 'A'
to: 'C'
count: 27305
probability: 0.08103624298111281
count: 27788
probability: 0.0807624007835592
- from: 'A'
to: 'G'
count: 128548
probability: 0.38150693875612857
count: 130019
probability: 0.3778842157577942
- from: 'A'
to: 'T'
count: 23913
probability: 0.07096940774244097
count: 24490
probability: 0.07117716982832031
- from: 'C'
to: 'A'
count: 27305
probability: 0.07823849488677553
count: 27788
probability: 0.0780165140757087
- from: 'C'
to: 'C'
count: 179118
probability: 0.5132365034656459
count: 184047
probability: 0.5167232390273484
- from: 'C'
to: 'G'
count: 19392
probability: 0.055564947549692406
count: 19622
probability: 0.05508996830263265
- from: 'C'
to: 'T'
count: 123182
probability: 0.3529600540978862
count: 124724
probability: 0.3501702785943102
- from: 'G'
to: 'A'
count: 128548
probability: 0.3637269077214298
count: 130019
probability: 0.3610094570655886
- from: 'G'
to: 'C'
count: 19392
probability: 0.05486971555009776
count: 19622
probability: 0.05448224926003876
- from: 'G'
to: 'G'
count: 179245
probability: 0.5071742039901647
count: 183951
probability: 0.5107565097152884
- from: 'G'
to: 'T'
count: 26234
probability: 0.07422917273830779
count: 26562
probability: 0.07375178395908417
- from: 'T'
to: 'A'
count: 23913
probability: 0.07307212790143376
count: 24490
probability: 0.07335783586895636
- from: 'T'
to: 'C'
count: 123182
probability: 0.3764132839524281
count: 124724
probability: 0.37360076443118473
- from: 'T'
to: 'G'
count: 26234
probability: 0.08016452153080807
count: 26562
probability: 0.07956434611479049
- from: 'T'
to: 'T'
count: 153923
probability: 0.4703500666153301
count: 158067
probability: 0.4734770535850684