VAMP-Net combines permutation-invariant set attention and quality-aware CNN to predict MTB drug resistance with >95% accuracy and AUC ~0.97 while recovering known resistance genes and identifying novel loci via feature attribution.
Interpreting attention mechanisms in genomic transformer models: A framework for biological insights.bioRxiv, pages 2025–06
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
VAMP-Net: An Interpretable Multi-Path Network of Genomic Permutation-Invariant Set Attention and Quality-Aware 1D-CNN for MTB Drug Resistance
VAMP-Net combines permutation-invariant set attention and quality-aware CNN to predict MTB drug resistance with >95% accuracy and AUC ~0.97 while recovering known resistance genes and identifying novel loci via feature attribution.