论文标题
部分可观测时空混沌系统的无模型预测
Molecular Fingerprints for Robust and Efficient ML-Driven Molecular Generation
论文作者
论文摘要
我们提出了一种新型的基于分子指纹的分子特性自身指码，用于在现实世界中的分子上生成分子。我们定义了更合适的，与药物相关的基线指标和测试，重点是产生多样化，类似药物的新型小分子和支架。当我们将这些分子生成指标应用于新型模型时，我们观察到化学合成可及性的显着改善（$δ\ bar {sas} $ = -0.83）和与现有的基于目前的基于ART的Smiles Smiles结构相比，高达5.9倍的计算效率。
We propose a novel molecular fingerprint-based variational autoencoder applied for molecular generation on real-world drug molecules. We define more suitable and pharma-relevant baseline metrics and tests, focusing on the generation of diverse, drug-like, novel small molecules and scaffolds. When we apply these molecular generation metrics to our novel model, we observe a substantial improvement in chemical synthetic accessibility ($Δ\bar{SAS}$ = -0.83) and in computational efficiency up to 5.9x in comparison to an existing state-of-the-art SMILES-based architecture.
