用神经网络自动编码无向分子图
Autoencoding Undirected Molecular Graphs With Neural Networks
摘要：
用于验证分子结构的离散结构规则通常限于满足八隅体规则或类似的简单确定性几何学。我们提出了一个模型，灵感来自自然语言处理的语言建模，具有从无向分子图集合中学习的能力，能够拟合集合中存在的任何底层结构规则。我们介绍了一个适应流行的Transformer模型，它可以学习原子和键之间的关系。据我们所知，Transformer自适应是第一个被训练来解决恢复部分观察到的分子的无监督任务的模型。在这项工作中，我们评估如何不同程度的信息影响性能w.r.t.拟合QM9数据集，其符合八隅体规则，以及拟合ZINC数据集，其包含需要模型学习更复杂的结构规则的超价分子和离子。更具体地说，我们测试了一个完整的离散图与键序信息，一个完整的离散图，只有连接，一袋的邻居，一袋的原子，和计数为基础的unigram统计。这些结果提供了令人鼓舞的证据，即神经网络，即使只有连通性可用，也可以学习特定于数据集的任意分子结构规则，因为Transformer自适应超过了ZINC数据集上的强八位规则基线。
英文摘要：
Discrete structure rules for validating molecular structures are usually limited to fulfillment of the octet rule or similar simple deterministic heuristics. We propose a model, inspired by language modeling from natural language processing, with the ability to learn from a collection of undirected molecular graphs, enabling fitting of any underlying structure rule present in the collection. We introduce an adaption to the popular Transformer model, which can learn relationships between atoms and bonds. To our knowledge, the Transformer adaption is the first model that is trained to solve the unsupervised task of recovering partially observed molecules. In this work, we assess how different degrees of information impact performance w.r.t. to fitting the QM9 dataset, which conforms to the octet rule, and to fitting the ZINC dataset, which contains hypervalent molecules and ions requiring the model to learn a more complex structure rule. More specifically, we test a full discrete graph with bond order information, a full discrete graph with only connectivity, a bag-of-neighbors, a bag-of-atoms, and a count-based unigram statistics. These results provide encouraging evidence that neural networks, even when only connectivity is available, can learn arbitrary molecular structure rules specific to a dataset, as the Transformer adaption surpasses a strong octet rule baseline on the ZINC dataset.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
