CellCanon is an agentic cellular world model that integrates single‑cell expression prediction, evidence‑grounded explanation, and observation‑driven updating. Its predictive core reuses condition‑level biological evidence to generate gene‑specific readouts, while a shared world state links predictions, measurements, and source‑linked claims to support explanation and revision. On 339 held‑out SciPlex3 conditions across three cell lines, CellCanon outperforms baselines in differential‑expression AUPRC, Macro‑F1, and direction Macro‑F1, and its explanation module correctly answers all answerable questions with supporting proofs.
arXiv:2606. 01042v1 Announce Type: cross Abstract: Perturbation experiments are central to understanding cellular mechanisms, but remain costly and sparse, motivating prediction of gene expression responses for unobserved conditions.
The paper introduces CELLAUDIT, a method for auditing whether inputs claimed to influence predictive models actually do so. By testing if an input can enter the computation, whether predictions depend on it, and if that dependence improves observed responses, the authors evaluate agent-generated predictors on a morphology‑transcriptomics benchmark (BBBC047). Their findings show that many models claim compound contributions that are not supported by the data, and that falsification‑guided revisions can recover genuine input effects while improving performance.
arXiv:2606. 30695v1 Announce Type: cross Abstract: Single-cell drug perturbation models should predict not only transcriptional response magnitude, but also whether a treatment alters the proliferative state of a cell.
The paper introduces CellForge, a team of autonomous agents that can autonomously generate, train, and validate predictive models for single‑cell perturbation data across transcriptomic, epigenomic, and proteomic contexts. By surveying literature, parsing data, and engaging in critic‑mediated discussions among specialized agents, CellForge produces end‑to‑end model architectures and code without human specification, achieving performance competitive with state‑of‑the‑art hand‑crafted methods. Human evaluators found CellForge’s research plans to be more scientifically sound and innovative than those produced by single large language models or deep‑research systems.
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.
arXiv:2608. 05359v1 Announce Type: new Abstract: CASCADE is an agentic framework that predicts downstream transcriptional effects of gene perturbation from precomputed ARACNe regulatory networks, exposed via MCP.
The paper introduces PhenoAIR, a reliability‑aware multi‑agent framework for predicting mechanisms of action (MOA) from Cell Painting morphological profiles. It treats retrieved neighbors as uncertain evidence, calibrating their reliability based on source, phenotype stability, and mechanism confusion, and refines predictions through controller‑guided evidence evaluation. PhenoAIR is benchmarked on JUMP Cell Painting data and outperforms both representation‑matching and LLM‑based baselines across controlled, realistic, and open‑world settings.
arXiv:2603. 02274v3 Announce Type: replace-cross Abstract: Precision oncology is currently limited by the small-N, large-P paradox, where high-dimensional genomic data is abundant but pharmacological response samples are sparse.
arXiv:2607. 18777v1 Announce Type: new Abstract: Evaluating machine learning in scientific domains requires separating correct predictions from correct reasons under realistic distribution shifts.
arXiv:2601. 12805v4 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown growing promise in biomedical research, particularly for knowledge-driven interpretation tasks.
arXiv:2606. 03435v1 Announce Type: new Abstract: Cell Painting combines multiplexed fluorescent staining, high-content imaging, and quantitative analysis to generate high-dimensional phenotypic readouts to support diverse downstream tasks such as mechanism-of-action (MoA) inference, toxicity prediction, and construction of drug-disease atlases.
The study evaluates whether biological reasoning models actually use their biological inputs by testing six models on DNA, protein, and single‑cell tasks. By perturbing one biological input while keeping others fixed, the authors find that many models (e.g., Evo2, ESM3, BioReason, BioReason‑Pro) rely primarily on textual information, with minimal impact from the biological representations. In contrast, models like ChatNT, Prot2Text‑V2, CellWhisperer, and Cell2Sentence‑Scale show greater dependence on their biological inputs, yet overall accuracy gains do not consistently reflect increased biological input contribution.