CASCADE：基于 MCP 的智能体调控网络框架，用 TCGA 患者数据验证基因扰动下游预测

View PDF HTML (experimental)

Abstract:CASCADE is an agentic framework that predicts downstream transcriptional effects of gene perturbation from precomputed ARACNe regulatory networks, exposed via MCP. Prior work validates such tools by checking whether predicted genes are known cancer genes (membership); we instead test whether the predicted direction of change matches reality, using focal-gene copy-number amplification as a dosage-based proxy for the inverse of knockdown against real TCGA patient tumor data. For MYC, CASCADE's predicted knockdown targets show strong concordance with real amplified-vs-non-amplified tumor expression across three cancer types (BRCA: 90.0%, COAD: 72.0%, STAD: 85.7%; all p<=0.0013), well above permutation baselines, surviving a PAM50 subtype control and replicating in an independent cohort (METABRIC, 87.2%). Compared against curated MSigDB gene-set baselines via Fisher's exact test, CASCADE's accuracy is not shown to exceed existing public knowledge of MYC- or E2F-driven biology, though its gene-specific direction-calling clearly outperforms a naive uniform guess. Extending to fifteen additional genes, validation proves gene-specific rather than universal: proliferation-machinery regulators mostly replicate, while lineage-identity transcription factors and one cyclin-D paralog (CCND2) consistently fail, a pattern we discuss as a hedged, post-hoc hypothesis. We separately benchmark whether an LLM-based agent correctly grounds natural-language requests into CASCADE's real MCP tool calls. Across 35 queries, a documented local model reaches 71.4% exact match (85.7% for a larger model); schema and gene-alias failures are resolved by scale or server-side correction, but both models confidently default to the wrong perturbation type on ambiguous queries, a failure a targeted fix could not resolve because its trigger condition never occurs.

Comments:	26 pages, 2 figures. v3: corrected the this http URL reference; updated the RegNetAgents comparison to its v3; replaced OncoKB with IntOGen; updated data, licensing and code availability (software v1.5.0). Results unchanged
Subjects:	Artificial Intelligence (cs.AI)
Cite as:	arXiv:2608.05359 [cs.AI]
	(or arXiv:2608.05359v3 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2608.05359 arXiv-issued DOI via DataCite

Submission history

From: Jose Bird PhD [view email]
[v1] Wed, 5 Aug 2026 19:30:44 UTC (67 KB)
[v2] Mon, 14 Sep 2026 20:54:59 UTC (67 KB)
[v3] Fri, 9 Oct 2026 13:38:23 UTC (68 KB)