The Flow has not summarised this story yet — read it at arXiv Machine Learning.
arXiv:2607. 17671v1 Announce Type: new Abstract: Large-scale single-cell perturbation atlases make it possible to ask an inverse question: given an observed transcriptional response, which annotated targets and compounds in a fixed library are most consistent with that response?
arXiv:2610.15117v1 Announce Type: cross Abstract: To evaluate whether a compact bidirectional state-space autoencoder improves joint classification of species, cell type, and disease state from singl...
arXiv:2606. 09558v1 Announce Type: cross Abstract: Motivation: Transformer-based models are increasingly applied to large-scale single-cell transcriptomics, showing strong performance through self-supervised learning on millions of cells.
scDEFT is a deep learning framework that treats a drug as a conditioning operator on single‑cell representations, enabling prediction of drug‑induced state changes and responder status. The model learns drug‑conditioned cell latents via feature‑wise linear modulation, aggregates them over transcriptional neighborhoods, and ranks latent dimensions to identify genes distinguishing responders from non‑responders. Applied to a harmonized inflammatory bowel disease atlas of 1.16 million cells, scDEFT achieves 45% of the baseline‑to‑reproducibility ceiling in state‑change prediction and stratifies responders before treatment with an AUROC of 0.70, outperforming standard predictors.
The study evaluates the robustness of deep learning models for DNA regulatory sequence prediction under biologically and technically induced distribution shifts. Using a mechanistic simulation benchmark and a massively parallel reporter assay dataset, the authors show that while models perform well under mild GC content changes, they exhibit higher error, miscalibration, and coverage collapse when faced with motif rewiring, noise, and batch effects. Incorporating biological priors and uncertainty-aware selective prediction improves robustness, though protection against strong assay noise remains limited.
Accurate prediction of patient-specific therapeutic response from pre-treatment transcriptomes is hindered by the scarcity of matched clinical response labels and post-treatment molecular profiles. Preclinical transfer-learning models can simulate drug-induced expression changes but are often hard to interpret and unstable, whereas knowledge-graph methods provide mechanistic context yet remain static and fail to capture drug-induced transcriptomic perturbation dynamics.