|
Sony AIらのチームが2026年9月3日に査読前論文を公開し、時系列知識グラフと大規模言語モデルを統合して未記録の科学的関係を予測するシステム「Hakken」を発表しました。 「Hakken」は過去の論文から知識グラフを構築し、老化関連で150万件の仮説を生成。検証でTP53とBAMBI、RAF1とTNFの新相互作用が2件確認されたということです。 このニュースを生成AIに深掘りさせましたので、ご参照ください。なお、生成AIによる調査・分析結果は、公開された情報だけに基づくものであり、必ずしも実情を示したものではなく、誤った情報を含む可能性があることにご留意のうえ、ご参照ください。 Sony AIのHakkenが老化関連の未知遺伝子関係を発見 https://x.com/i/trending/2097223841047105797 Hakken, a Scientific Discovery Prediction System Developed by Sony AI A team including researchers from Sony AI released a preprint on September 3, 2026, introducing “Hakken,” a system that integrates temporal knowledge graphs with large language models to predict previously undocumented scientific relationships. Hakken constructs knowledge graphs from previously published research papers and generated 1.5 million hypotheses related to aging. According to the report, validation confirmed two novel interactions: one between TP53 and BAMBI, and another between RAF1 and TNF. I asked generative AI to investigate this news in depth and invite you to review its findings. Please note, however, that the AI-generated research and analysis are based solely on publicly available information, may not necessarily reflect the actual situation, and may contain inaccuracies. Please keep these limitations in mind when reviewing the findings. Your browser does not support viewing this document. Click here to download the document. Your browser does not support viewing this document. Click here to download the document. Your browser does not support viewing this document. Click here to download the document. Your browser does not support viewing this document. Click here to download the document. Your browser does not support viewing this document. Click here to download the document. Your browser does not support viewing this document. Click here to download the document.
0 Comments
Leave a Reply. |
著者萬秀憲 アーカイブ
April 2026
カテゴリー |
RSS Feed