Automated Genomic Interpretation via Concept Bottleneck Models for Medical Robotics

2025-10-01

AI Summary

This study addresses the challenge of automating and rendering interpretable the translation from DNA sequences to clinical decisions for intelligent diagnosis and intervention in medical robotics. We propose a novel framework integrating Chaos Game Representation (CGR) with Concept Bottleneck Models (CBMs), embedding explicit, biologically grounded concepts into an interpretable latent layer. To ensure traceability and clinical credibility, we introduce concept fidelity supervision, prior-consistency alignment, and uncertainty calibration via KL-divergence matching. Furthermore, we design a cost-aware recommendation strategy and a multi-task supervised learning mechanism to enhance clinical utility. Evaluated on HIV subtype classification, our model significantly reduces misclassification rates and retesting costs, achieving optimal trade-offs among accuracy, calibration, and practical deployability. The framework establishes a trustworthy, production-ready AI paradigm for genomics-driven precision medicine.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: Learning & Optimization for ROB
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We propose an automated genomic interpretation module that transforms raw DNA sequences into actionable, interpretable decisions suitable for integration into medical automation and robotic systems. Our framework combines Chaos Game Representation (CGR) with a Concept Bottleneck Model (CBM), enforcing predictions to flow through biologically meaningful concepts such as GC content, CpG density, and k mer motifs. To enhance reliability, we incorporate concept fidelity supervision, prior consistency alignment, KL distribution matching, and uncertainty calibration. Beyond accurate classification of HIV subtypes across both in-house and LANL datasets, our module delivers interpretable evidence that can be directly validated against biological priors. A cost aware recommendation layer further translates predictive outputs into decision policies that balance accuracy, calibration, and clinical utility, reducing unnecessary retests and improving efficiency. Extensive experiments demonstrate that the proposed system achieves state of the art classification performance, superior concept prediction fidelity, and more favorable cost benefit trade-offs compared to existing baselines. By bridging the gap between interpretable genomic modeling and automated decision-making, this work establishes a reliable foundation for robotic and clinical automation in genomic medicine.

Problem

• Automating genomic interpretation from raw DNA sequences for medical robotics
• Providing interpretable genomic decisions through biologically meaningful concepts
• Balancing classification accuracy with clinical utility and cost efficiency

Innovation

• Uses Chaos Game Representation for DNA sequence encoding
• Implements Concept Bottleneck Model with biological concepts
• Incorporates cost-aware recommendation layer for clinical decisions