Scholarlink

<p>Large language models (LLMs) have recently been adopted to assist in the interpretation of human genomic variants. However, general-purpose LLMs can produce incorrect outputs (commonly termed ‘hallucinations’), particularly on specialized queries, raising concerns about their reliability for variant interpretation. Here, to mitigate this risk, we developed ChatTogoVar, a retrieval-augmented generation system that queries TogoVar, a variant database that integrates information, such as allele frequency and clinical significance, and incorporates the retrieved results into prompts. We constructed a benchmark of 150 questions sampled from a predefined pool of 1500 template–variant combinations (50 templates × 30 variants). For large-scale assessment, we used the full 1500-question pool for automated LLM-based scoring. ChatTogoVar achieved the highest score for 135/150 questions, outperforming both a general-purpose LLM and an existing specialized system. Furthermore, automatic evaluation of all 1500 questions by an LLM confirmed the same trend. These results suggest that integrating a reliable variant database with an LLM can improve the accuracy of variant interpretation and that ChatTogoVar may serve as a practical tool to support genomic medicine and personalized healthcare.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

ChatTogoVar: a TogoVar-based retrieval-augmented generation system for precise genomic variant interpretation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月9日

查看全文
  • Nobutaka Mitsuhashi,
  • Toyofumi Fujiwara,
  • Atsuko Yamaguchi

摘要

Large language models (LLMs) have recently been adopted to assist in the interpretation of human genomic variants. However, general-purpose LLMs can produce incorrect outputs (commonly termed ‘hallucinations’), particularly on specialized queries, raising concerns about their reliability for variant interpretation. Here, to mitigate this risk, we developed ChatTogoVar, a retrieval-augmented generation system that queries TogoVar, a variant database that integrates information, such as allele frequency and clinical significance, and incorporates the retrieved results into prompts. We constructed a benchmark of 150 questions sampled from a predefined pool of 1500 template–variant combinations (50 templates × 30 variants). For large-scale assessment, we used the full 1500-question pool for automated LLM-based scoring. ChatTogoVar achieved the highest score for 135/150 questions, outperforming both a general-purpose LLM and an existing specialized system. Furthermore, automatic evaluation of all 1500 questions by an LLM confirmed the same trend. These results suggest that integrating a reliable variant database with an LLM can improve the accuracy of variant interpretation and that ChatTogoVar may serve as a practical tool to support genomic medicine and personalized healthcare.