← Back to archive day

Mamba-SSM with LLM Reasoning for Biomarker Discovery: Causal Feature Refinement via Chain-of-Thought Gene Evaluation

Pushpa Kumar Balan, Aijing Feng

38

Recommendation Score

breakthrough🔴 AdvancedReasoning & AgentsLLM ReasoningMethodUseful for both

Research context

Primary field

Reasoning & Agents

Reasoning, planning, tool use, and agentic workflows.

Topics

LLM Reasoning

Paper type

Method

Best for

Useful for both

arXiv categories

cs.AI

Why It Matters

Mamba-SSM + LLM CoT filters confounding genes via causal reasoning, boosting biomarker specificity—enabling reliable, interpretable genomic discovery without manual curation, directly impacting precision medicine pipelines.

Abstract

Gradient saliency from deep sequence models surfaces candidate biomarkers efficiently, but the resulting gene lists are contaminated by tissue-composition confounders that degrade downstream classifiers. We study whether LLM chain-of-thought (CoT) reasoning can faithfully filter these confounders, and whether reasoning quality drives downstream performance. We train a Mamba SSM on TCGA-BRCA RNA-seq and extract the top-50 genes by gradient saliency; DeepSeek-R1 evaluates every candidate with structured CoT to produce a final 17-gene set. The raw 50-gene saliency set (no LLM) performs worse than a 5,000-gene variance baseline (AUC 0.832 vs. 0.903), while the LLM-filtered set surpasses it (AUC 0.927), using 294x fewer features. A faithfulness audit (COSMIC CGC, OncoKB, PAM50) reveals only 6 of 17 selected genes (35.3%) are validated BRCA biomarkers, yet 10 of 16 known BRCA genes in the input were missed - including FOXA1. This gap between downstream performance and reasoning faithfulness suggests selective faithfulness: targeted confounder removal is sufficient for performance gains even without comprehensive recall.

Published April 15, 2026
© 2026 A2A.pub — AI to Action. From papers to practice, daily.
Summaries are AI-assistedPrivacyTerms