Auditing Retrieval-Augmented LLM Hypotheses for Longitudinal Cell Painting Morphology

• URL: http://arxiv.org/abs/2607.19415v1
• Date: Fri, 17 Jul 2026 17:11:11 GMT
• Title: Auditing Retrieval-Augmented LLM Hypotheses for Longitudinal Cell Painting Morphology
• Abstract summary: We present an evaluation-first, retrieval-augmented interpretation framework for longitudinal Cell Painting morphology.<n>Week-matched treated-control morphology deltas are combined with retrieved perturbation neighbors, pathway context, and literature evidence through stable evidence identifiers.<n>The framework produces auditable, falsifiable biological hypotheses, including an adaptive phenotype involving metabolic reprogramming and proteostatic stress at lower dose rates.
• Score: 18.947145132707025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-content morphological profiling (Cell Painting) yields sensitive, high-dimensional signatures of cellular state, but translating longitudinal morphology trajectories into interpretable biology remains difficult, especially for weak, chronic perturbations such as low-dose-rate ionizing radiation. Large language models (LLMs) can synthesize heterogeneous evidence into biological narratives, yet their scientific use requires quantitative auditing. We present an evaluation-first, retrieval-augmented interpretation framework for longitudinal Cell Painting morphology, applied to a 9-week RPE-1 time course across five dose rates (0.003--6.0 mGy/hr). Week-matched treated-control morphology deltas are combined with retrieved perturbation neighbors, pathway context, and literature evidence through stable evidence identifiers, enabling an LLM to generate structured, evidence-linked hypotheses that are hierarchically summarized while preserving provenance. We introduce two quantitative auditing tests: V1 citation validity, which verifies that cited evidence identifiers exist in the prompt, and V2 proxy-based morphology compatibility, which evaluates consistency between predicted biological processes and the most altered morphology features. In our experiments, V1 detected no invalid evidence references, while V2 showed meaningful morphology compatibility that increased with perturbation strength and was positively associated with an independent morphology drift summary. The framework produces auditable, falsifiable biological hypotheses, including an adaptive phenotype involving metabolic reprogramming and proteostatic stress at lower dose rates (0.003--0.3 mGy/hr). Current limitations include proxy-based evaluation and the lack of ground-truth mechanism labels.

Related papers

• Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning [103.788281428856]
  We introduce SciReasoner, a scientific foundation model for native structural reasoning across proteins, small molecules and inorganic crystals.<n>SciReasoner discretizes coordinates, topologies and periodic connectivities into a unified structure-aware vocabulary.<n>Across 86 benchmarks, SciReasoner achieves state-of-the-art performance on 67 tasks.
  arXiv  Detail & Related papers  (2026-07-08T17:59:59Z)
• Position: Genomic Model Research Must Move Beyond Anecdotal Evaluation of Interpretability Methods [8.920725431658777]
  We argue for a validation framework analogous to clinical trials.<n>Just as trials require rigorous design and adverse-event reporting, genomic interpretability must move beyond cherry-picked plausibility.
  arXiv  Detail & Related papers  (2026-05-29T12:20:12Z)
• When Brains Disagree: Biological Ambiguity Underlies the Challenge of Amyloid PET Synthesis from Structural MRI [2.3047461366838755]
  MRI captures neurodegeneration, while PET measures amyloid pathology.<n>As a result, similar MRI patterns may correspond to different amyloid states, creating ambiguous one-to-many mappings.<n>We show that ambiguity in the data distribution, rather than architectural capacity, constrains performance.
  arXiv  Detail & Related papers  (2026-05-12T09:47:44Z)
• AROMA: Augmented Reasoning Over a Multimodal Architecture for Virtual Cell Genetic Perturbation Modeling [10.19071074895934]
  We propose AROMA, an Augmented Reasoning Over a Multimodal Architecture for virtual cell genetic perturbation modeling.<n>AROMA integrates textual evidence, graph-topology information, and protein sequence features to model perturbation-target dependencies.<n>It is trained with a two-stage optimization strategy to yield predictions that are both accurate and interpretable.
  arXiv  Detail & Related papers  (2026-04-22T07:10:45Z)
• Empowering Chemical Structures with Biological Insights for Scalable Phenotypic Virtual Screening [13.925550352212412]
  This study presents DECODE, a framework that bridges the gap by empowering chemical representations with intrinsic biological semantics.<n>Our evaluations demonstrate that DECODE retrieves functionally similar drugs in zero-shot settings with over 20% relative improvement over chemical baselines in mechanism-of-action prediction.
  arXiv  Detail & Related papers  (2026-03-16T09:13:08Z)
• EvoMorph: Counterfactual Explanations for Continuous Time-Series Extrinsic Regression Applied to Photoplethysmography [4.11690617621503]
  Time-series regression models increasingly leverage photoplethysmography signals to estimate clinically relevant outcomes.<n>For clinical reasoning and trust, single point estimates alone are insufficient.<n>We introduce EvoMorph, a framework for generating physiologically plausible and diverse CFE for TSER applications.
  arXiv  Detail & Related papers  (2026-01-15T12:58:59Z)
• Learning Cell-Aware Hierarchical Multi-Modal Representations for Robust Molecular Modeling [74.25438319700929]
  We propose CHMR (Cell-aware Hierarchical Multi-modal Representations), a robust framework that models local-global dependencies between molecules and cellular responses.<n> evaluated on nine public benchmarks spanning 728 tasks, CHMR outperforms state-of-the-art baselines.<n>Results demonstrate the advantage of hierarchy-aware, multimodal learning for reliable and biologically grounded molecular representations.
  arXiv  Detail & Related papers  (2025-11-26T07:15:00Z)
• TRIDENT: A Trimodal Cascade Generative Framework for Drug and RNA-Conditioned Cellular Morphology Synthesis [56.9460577864211]
  TRIDENT is a cascade generative framework that synthesizes realistic cellular morphology by conditioning on both the perturbation and the corresponding gene expression profile.<n> TRIDENT significantly outperforms state-of-the-art approaches, achieving up to 7-fold improvement with strong generalization to unseen compounds.
  arXiv  Detail & Related papers  (2025-11-23T04:43:27Z)
• Unlasting: Unpaired Single-Cell Multi-Perturbation Estimation by Dual Conditional Diffusion Implicit Bridges [68.98973318553983]
  We propose a framework based on Dual Diffusion Implicit Bridges (DDIB) to learn the mapping between different data distributions.<n>We integrate gene regulatory network (GRN) information to propagate perturbation signals in a biologically meaningful way.<n>We also incorporate a masking mechanism to predict silent genes, improving the quality of generated profiles.
  arXiv  Detail & Related papers  (2025-06-26T09:05:38Z)
• Causal Representation Learning from Multimodal Biomedical Observations [57.00712157758845]
  We develop flexible identification conditions for multimodal data and principled methods to facilitate the understanding of biomedical datasets.<n>Key theoretical contribution is the structural sparsity of causal connections between modalities.<n>Results on a real-world human phenotype dataset are consistent with established biomedical research.
  arXiv  Detail & Related papers  (2024-11-10T16:40:27Z)
• Correct block-design experiments mitigate temporal correlation bias in EEG classification [68.85562949901077]
  We show that the main claim in [1] is drastically overstated and their other analyses are seriously flawed by wrong methodological choices. We investigate the influence of EEG temporal correlation on classification accuracy by testing the same models in two additional experimental settings.
  arXiv  Detail & Related papers  (2020-11-25T22:25:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.