LA-MARRVEL: A Knowledge-Grounded, Language-Aware LLM Framework for Clinically Robust Rare Disease Gene Prioritization

2025/11/04 by Yao, Lin, Lee, Jaeyeon, Jeong, Hyun-Hwan +1
Biochemistry, Genetics and Molecular Biology · #Artificial Intelligence (cs.AI) #Bioinformatics and Genomic Networks #Biomedical Text Mining and Ontologies #FOS: Biological sciences #FOS: Computer and information sciences #Genomics (q-bio.GN) #Genomics and Rare Diseases

paper · doi:10.48550/arxiv.2511.02263

openalex publication_date 2025/11/04 · openalex created_date 2025/11/06 · openalex updated_date 2026/07/28

Abstract

Rare disease diagnosis requires matching variant-bearing genes to complex patient phenotypes across large and heterogeneous evidence sources. This process remains time-intensive in current clinical interpretation pipelines. To overcome these limitations, We present LA-MARRVEL, a knowledge-grounded, language-aware LLM framework and designed for clinical robustness and practical deployment. LA-MARRVEL delivers a 12-15 percentage-point absolute improvement in Recall@1 over established gene prioritization approaches, showing that architectural design can drive substantial accuracy gains. We found that the central contributor is structured, phenotype-rich prompt construction that explicitly encodes patient and disease phenotypes, preserving clinically meaningful context more effectively than disease labels alone. Across three real-world cohorts, LA-MARRVEL consistently improves gene-ranking performance, including in challenging cases where the causal gene was initially ranked lower by first-stage prioritization. For each candidate gene, the system delivers clinically relevant, ACMG-aligned reasoning that integrates phenotype concordance, inheritance patterns, and variant-level evidence into auditable explanations, enabling streamlined clinical review. These findings suggest that knowledge-grounded LLM layer can enhance existing rare-disease gene prioritization workflows without altering established diagnostic pipelines.

Citations

• An Agentic System for Rare Disease Diagnosis with Traceable Reasoning
• ConSol: Sequential Probability Ratio Testing to Find Consistent LLM Reasoning Paths Efficiently
• Survey and Improvement Strategies for Gene Prioritization with Large Language Models
• Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• PRAG: Paninian Retrieval-Augmented Generation for Safety-Critical Medical Question Answering

Related

• Survey and Improvement Strategies for Gene Prioritization with Large Language Models
• Assessing the Utility of Large Language Models for Phenotype-Driven Gene Prioritization in Rare Genetic Disorder Diagnosis
• Integrating Chain-of-Thought and Retrieval Augmented Generation Enhances Rare Disease Diagnosis from Clinical Notes
• A Systematic Review on the Generative AI Applications in Human Medical Genomics
• Decoding Rarity: Large Language Models in the Diagnosis of Rare Diseases