A microbial-trained transformer, adapted to plants via label-free masked language modeling on Pfam-domain sequences, improves known plant BGC recovery to 67.6% at 100% coverage.
Chavali, Ricardo Nilo-Poyanco, Thomas Bernard, Daniel Kahn, and Seung Y
1 Pith paper cite this work, alongside 383 external citations. Polarity classification is still indexing.
1
Pith paper citing it
383
external citations · OpenAlex
fields
q-bio.GN 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PlantBGC: Transformer for Plant BGC Discovery via Label-Free Domain Adaptation and Weak Supervision
A microbial-trained transformer, adapted to plants via label-free masked language modeling on Pfam-domain sequences, improves known plant BGC recovery to 67.6% at 100% coverage.