用SHA-256嵌入增强分子生成，低数据下高效发现高能炸药。
SHA-256 Infused Embedding-Driven Generative Modeling of High-Energy Molecules in Low-Data Regimes
- 将SHA-256固定嵌入与可训练表示结合，重构分子表征空间。
- 生成分子有效率67.5%，新颖性37.5%，多样性Tanimoto系数0.214。
- 无需预训练即发现37种预测爆速超9 km/s的新超爆物，适合材料发现研究者。
高能材料（HEMs）在推进与国防领域至关重要，但其发现受限于实验数据匮乏和测试设施稀缺。本文提出一种新方法，结合LSTM网络进行分子生成与注意力图神经网络（GNN）进行性质预测。通过引入固定SHA-256嵌入与部分可训练表示的融合策略，重构分子输入空间的表征基础，而非依赖传统正则化手段。该框架无需预训练，生成分子有效性达67.5%，新颖性37.5%；生成库与训练集平均Tanimoto系数为0.214，表明具备良好化学空间多样性。共识别出37种预测爆速超过9 km/s的新超爆物质。
原文摘要 · Abstract (English)
High-energy materials (HEMs) are critical for propulsion and defense domains, yet their discovery remains constrained by experimental data and restricted access to testing facilities. This work presents a novel approach toward high-energy molecules by combining Long Short-Term Memory (LSTM) networks for molecular generation and Attentive Graph Neural Networks (GNN) for property predictions. We propose a transformative embedding space construction strategy that integrates fixed SHA-256 embeddings with partially trainable representations. Unlike conventional regularization techniques, this changes the representational basis itself, reshaping the molecular input space before learning begins. Without recourse to pretraining, the generator achieves 67.5% validity and 37.5% novelty. The generated library exhibits a mean Tanimoto coefficient of 0.214 relative to training set signifying the ability of framework to generate a diverse chemical space. We identified 37 new super explosives higher than 9 km/s predicted detonation velocity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。