Tag
This paper proposes using signed, fusion-aware Integrated Gradients for attributing predictions in feature-tokenized transformers like BiomeGPT, overcoming limitations of CLS attention weights and revealing disease-supporting versus protective microbial signals.
A study from Southeast University found that GLP-1 drugs like Ozempic reverse depression-like behavior in mice by promoting growth of Lactobacillus delbrueckii, which produces endocannabinoids that reduce stress effects.
This paper evaluates the robustness of tabular foundation models to biologically inspired distribution shifts in microbiome data, finding that protecting discriminative features is insufficient and zero-imputation is the most harmful perturbation.
This paper introduces PolyILR, a canonical orthonormal decomposition of the Aitchison tangent space that aligns with any tree topology, providing stable and interpretable features for compositional data such as microbiome and single-cell profiles.