Autonomous mechanistic discovery of colorectal cancer vulnerabilities via multi-scale AI swarms

• URL: http://arxiv.org/abs/2607.16262v1
• Date: Sun, 28 Jun 2026 18:39:51 GMT
• Title: Autonomous mechanistic discovery of colorectal cancer vulnerabilities via multi-scale AI swarms
• Abstract summary: Octopus is a neuro-symbolic architecture that unites zero-leakage, local LLM swarms with strict algorithmic physics engines.<n>System autonomously generated therapeutic hypotheses against in vitro dependency data.<n>It traced dynamic causal cascades using mechanistic interpretability.
• Score: 8.752003883104182
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The acceleration of automated scientific discovery has been fundamentally bottlenecked by the epistemic gap between the semantic reasoning of large language models (LLMs) and the deterministic physics of mammalian biology. While recent multi-agent frameworks have achieved autonomous hypothesis generation and in vitro experimental analysis, they lack the mathematically grounded, causal constraints required for multi-scale clinical translation. Furthermore, while algorithmic clinical digital twins successfully forecast biological states, they rely on black-box latent spaces, sacrificing mechanistic interpretability for predictive accuracy. Here, we introduce the Multi-Scale Autonomous Discovery Engine (Octopus), a neuro-symbolic architecture that unites zero-leakage, local LLM swarms with strict algorithmic physics engines. Rather than stopping at isolated cellular assays, the system autonomously generated therapeutic hypotheses against in vitro CRISPR dependency data (CCLE), traced dynamic causal cascades using mechanistic interpretability (XGBoost SHAP vectors), and orthogonally translated the emergent vulnerabilities in silico to predict in vivo mammalian tumor trajectory (PDX) and human overall survival (Marisa). In a fully unsupervised sweep of colorectal cancer transcriptomes, the pipeline autonomously identified Insulin-like Growth Factor 2 (IGF2) as a strictly bounded vulnerability to 5-Fluorouracil resistance. The discovery maintained significance after rigorous Benjamini-Hochberg false discovery rate correction (q=0.0292, Log-Rank p=0.0007 ) and successfully predicted significant in vivo tumor volume shrinkage in an independent mouse cohort (Mann-Whitney p=0.0373). By bridging the chasm between multi-agent reasoning and mathematically bounded clinical survival, this framework establishes a verifiable, zero-leakage paradigm for automated, end-to-end biomedical discovery.

Related papers

• An immune world model for multiscale forecasting and therapeutic hypothesis generation [76.0289504908521]
  We used a governed evolutionary AI Scientist to construct the Immune World Model.<n>The Immune World Model is an action-conditioned model that learns how interventions move immune states across cellular, tissue, and individual levels.<n>It provides a framework for multiscale immune simulation that connects AI Scientist-driven model construction, intervention forecasting, and the generation of prospectively testable therapeutic hypotheses.
  arXiv  Detail & Related papers  (2026-09-13T18:06:18Z)
• Explainable AI for Cancer Drug Response Prediction: Beyond Univariate Feature Attributions [4.432106960947219]
  We present ILLUME+, a scalable post-hoc explainability framework that moves beyond single-gene assessments to capture multiple forms of explanation.<n>ILLUME+ produces more stable gene importance scores than existing baselines, recovers established drug-gene associations and mechanisms of action, and enables AI-assisted hypothesis generation to uncover novel interaction-driven molecular signals in cancer biology.
  arXiv  Detail & Related papers  (2026-07-01T13:34:04Z)
• Predicting Immune Biomarkers with MultiModal Mixture-of-Expert Pathology Foundation Models Empowers Precision Oncology [47.79180201495836]
  MixTIME is a multimodal foundation model that integrates pathology foundation models trained across distinct modalities.<n>It predicts multiplex immunofluorescence (mIF) protein expression from hematoxylin and eosin whole-slide images.<n>MixTIME achieves state-of-the-art performance across 17 protein markers as measured by correlation metrics.
  arXiv  Detail & Related papers  (2026-06-16T16:22:42Z)
• Genotype-Conditioned Molecular Generation via Evidence-Grounded Multi-Objective Latent Perturbation in Diffusion Models [28.58133087329719]
  Generative models conditioned on cancer genotypes offer a promising avenue for personalized drug discovery.<n>We present a latent-space optimization approach for a pretrained genotype-to-drug diffusion model.<n>We show consistent and noticeable improvements over competing baselines in sensitivity, drug-likeness, synthesizability, and chemical validity.
  arXiv  Detail & Related papers  (2026-05-31T21:43:11Z)
• Predicting Neuromodulation Outcome for Parkinson's Disease with Generative Virtual Brain Model [95.41752463487008]
  Parkinson's disease affects over ten million people worldwide.<n>Inter-individual variability limits empirical treatment selection, increasing non-negligible surgical risk and cost.<n>We bridge this gap with a pretraining-finetuning framework to predict outcomes directly from resting-state fMRI.
  arXiv  Detail & Related papers  (2026-03-31T02:36:10Z)
• Brain-WM: Brain Glioblastoma World Model [56.45393372490125]
  We present Brain-WM, a pioneering GBM world model that unifies next-step treatment prediction and future MRI generation.<n>Brain-WM encodes latent dynamics into a shared latent space for joint autoregressive treatment prediction and flow-based future MRI generation.<n>Ultimately, Brain-WM offers a robust clinical sandbox for optimizing patient healthcare.
  arXiv  Detail & Related papers  (2026-03-08T09:54:08Z)
• Contextual Invertible World Models: A Neuro-Symbolic Agentic Framework for Colorectal Cancer Drug Response [4.796382757669091]
  Precision oncology is currently limited by the small-N, large-P paradox.<n>We present a Neuro-Symbolic Agentic Framework that bridges this gap.<n>Our framework provides a transparent, biologically grounded path towards explainable AI in cancer research.
  arXiv  Detail & Related papers  (2026-03-01T16:15:58Z)
• Biologically Disentangled Multi-Omic Modeling Reveals Mechanistic Insights into Pan-Cancer Immunotherapy Resistance [0.9787436863401008]
  We introduce the Biologically Disentangled Variational Autoencoder (BDVAE), a deep generative model that integrates transcriptomic and genomic data.<n>Applying to a pan-cancer cohort of 366 patients, BDVAE accurately predicts treatment response.<n>It uncovers critical resistance mechanisms, including immune suppression, metabolic shifts, and neuronal signaling.
  arXiv  Detail & Related papers  (2025-08-26T03:33:56Z)
• Organ-Agents: Virtual Human Physiology Simulator via LLMs [66.40796430669158]
  Organ-Agents is a multi-agent framework that simulates human physiology via LLM-driven agents.<n>We curated data from 7,134 sepsis patients and 7,895 controls, generating high-resolution trajectories across 9 systems and 125 variables.<n>Organ-Agents achieved high simulation accuracy on 4,509 held-out patients, with per-system MSEs 0.16 and robustness across SOFA-based severity strata.
  arXiv  Detail & Related papers  (2025-08-20T01:58:45Z)
• Towards an AI co-scientist [48.11351101913404]
  We introduce an AI co-scientist, a multi-agent system built on Gemini 2.0.<n>The AI co-scientist is intended to help uncover new, original knowledge and to formulate demonstrably novel research hypotheses.<n>The system's design incorporates a generate, debate, and evolve approach to hypothesis generation, inspired by the scientific method.
  arXiv  Detail & Related papers  (2025-02-26T06:17:13Z)
• Sensitivity analysis of biological washout and depth selection for a machine learning based dose verification framework in proton therapy [19.718172235291647]
  Dose verification based on proton-induced positron emitters is a promising quality assurance tool. To move a step closer towards practical application, the sensitivity analysis of two factors needs to be performed: biological washout and depth selection. Our proposed AI framework shows good immunity to the perturbation associated with two factors.
  arXiv  Detail & Related papers  (2022-12-21T20:43:35Z)

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.