From 784c47ed1652e5211c8c84c421fa2d21be9702c0 Mon Sep 17 00:00:00 2001 From: Donovan Parks Date: Fri, 10 Apr 2026 09:42:29 +1000 Subject: [PATCH] feat: added Organicella extenuata and_Pinguicoccus supinus as using table 4 in the ground truth script --- gtranslate/training/ground_truth_by_taxonomy.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/gtranslate/training/ground_truth_by_taxonomy.py b/gtranslate/training/ground_truth_by_taxonomy.py index 6f6d278..e211eb2 100755 --- a/gtranslate/training/ground_truth_by_taxonomy.py +++ b/gtranslate/training/ground_truth_by_taxonomy.py @@ -59,7 +59,9 @@ def __init__(self): # Ground truth from NCBI classifications self.NCBI_TT4 = set(['s__Candidatus Hodgkinia cicadicola', 's__Candidatus Nasuia deltocephalinicola', 's__Candidatus Stammera capleta']) + self.NCBI_TT4.update(set(['s__Candidatus Organicella extenuata', 's__Candidatus Pinguicoccus supinus'])) self.NCBI_TT4.update(set(['s__Hodgkinia cicadicola', 's__Nasuia deltocephalinicola', 's__Stammera capleta'])) + self.NCBI_TT4.update(set(['s__Organicella extenuata', 's__Pinguicoccus supinus'])) # These species clusters have an unclear ground truth, see https://doi.org/10.1093/gbe/evad164 self.GTDB_UNRESOLVED = set(['s__Providencia_A siddallii', 's__Providencia_A siddallii_A'])