MOFMeld: a structure–language fusion framework for MOF property prediction in carbon capture
MOFMeld: MOFの物性予測のための構造・言語融合フレームワーク（炭素回収向け） (AI 翻訳)
Huajie You, Shengde Zhang, Liang Du, Chuxuan Zeng, Teng Zhou, Xiaowen Chu
🤖 gxceed AI 要約
日本語
MOFMeldは、文献データとMOF特化大規模言語モデル（MOFLLaMA）および結晶構造エンベディングを統合し、炭素回収向けMOFの効率的スクリーニングを実現。6種類の物性予測で、少ない学習データながら高い精度を示し、UMAP解析により構造–物性関係の可解釈性も向上。
English
MOFMeld integrates a literature-grounded MOF-specialized LLM (MOFLLaMA) with crystal-aware embeddings for efficient screening of MOFs in carbon capture. It achieves competitive accuracy on six property targets with less data than GNN baselines, and offers interpretable structure-property relationships via UMAP.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本のGX政策ではCCUSの早期実用化が重視されており、MOFMeldのようなAI駆動の材料スクリーニングは新規吸着材探索を加速し、導入コスト低減に貢献する可能性がある。
In the global GX context
As CCUS scales globally, AI-driven screening frameworks like MOFMeld can dramatically accelerate sorbent discovery and property prediction, reducing time and cost for both research and industrial deployment.
👥 読者別の含意
🔬研究者:This paper presents a novel structure–language fusion method for MOF property prediction, relevant for those working on machine learning for materials discovery in carbon capture.
📄 Abstract（原文）
Efficient carbon capture requires sorbents that combine high CO2 affinity, stability, and low regeneration energy. While metal–organic frameworks (MOFs) are promising candidates, their efficient screening remains a significant challenge: performance is governed by crystal topology, yet relevant data is scattered across the literature, and conventional experimental or computational methods are time-intensive and data-limited. To address this, we introduce MOFMeld, a structure–language fusion framework that integrates a literature-grounded, MOF-specialized large language model (MOFLLaMA) with crystal-aware structural embeddings via a lightweight bridge module. MOFLLaMA is adapted from LLaMA-3.1-8B-Instruct by supervised fine-tuning on ~20,000 MOF question-answer pairs distilled from ~1500 publications and, at inference, is grounded by a MOF knowledge graph to support factual, traceable reasoning. Structural information is encoded from CIF files and aligned to the language space, enabling structure-conditioned question answering and property prediction. Evaluated across six key targets—pore-limiting diameter, largest cavity diameter, surface area, void fraction, and CO2 uptake at 2.5 and 0.01 bar—MOFMeld achieves competitive or superior accuracy to a strong graph neural network (GNN) baseline despite substantially less training data. UMAP analyses reveal coherent organization of structure–property relationships within the learned embeddings, enhancing model interpretability. An automated literature pipeline further enables continual knowledge updates. Collectively, MOFMeld offers a scalable and transparent pathway toward literature-aware, structure-informed MOF screening for carbon capture applications.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.1038/s44387-026-00106-1first seen 2026-05-17 06:32:06 · last seen 2026-05-20 05:13:28
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。