在分子生成模型中识别并消除序列伪影，实现化学性质的精准控制。
Molecules Meet Language: Confound-Aware Representation Learning and Chemical Property Steering in Transformer-VAE Latent Spaces
- 用线性探针分析自回归Transformer-VAE的潜在空间，定位可调控方向。
- 在去除序列干扰后，成功实现6种化学性质的稳定单调调控。
- 揭示部分性质适合全局方向控制，部分需局部梯度调节，适合药物设计者参考。
分子生成模型常假设潜在空间具有有意义的几何结构，但看似可预测的性质可能源于序列层面的捷径，而非化学组织。本文在SELFIES数据上训练无监督自回归Transformer-VAE，冻结模型后，使用线性探针拟合RDKit描述符，并将探针权重作为候选全局调控方向。为区分化学信号与SELFIES伪影，提出基于残差化、共现方向对齐分析及解码分子遍历的混淆感知评估方法。因为SELFIES长度、分支标记、环标记和标记熵在潜在空间中被强烈编码。在此混淆感知评估下，发现对cLogP、FractionCSP3、HeavyAtomCount、TPSA、BertzCT和HBA存在稳健的单调调控。非线性探针进一步表明，某些性质可由稳定全局方向描述，而另一些则更适合局部潜变量梯度。结果表明，即使在纠缠的分子潜在空间中，经解码分子验证并控制表示级混杂因素后，仍可实现化学上有意义的调控。
原文摘要 · Abstract (English)
Molecular generative models often assume meaningful latent geometry, but apparent property predictability can reflect sequence-level shortcuts rather than chemical organization. We study this issue in an unsupervised autoregressive Transformer-VAE trained on SELFIES. After training, we freeze the model, fit linear probes to RDKit descriptors, and use the probe weights as candidate global steering directions. To separate chemical signal from SELFIES artifacts, we introduce a confound-aware evaluation based on residualization, confound-direction alignment analysis, and decoded-molecule traversal. This is necessary because SELFIES length, branch tokens, ring tokens, and token entropy are strongly encoded in the latent space. Under this confound-aware evaluation, we find robust monotonic steering for cLogP, FractionCSP3, HeavyAtomCount, TPSA, BertzCT, and HBA. Nonlinear probes further show that some properties admit stable global directions, while others are better described by local latent gradients. Overall, our results show that chemically meaningful steering can emerge in entangled molecular latent spaces, but only when validated through decoded molecules and controlled for representation-level confounds.
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。