arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1603.00856stat.MLcs.LG
收藏

分子图卷积:超越指纹

Molecular Graph Convolutions: Moving Beyond Fingerprints

Stanford University(斯坦福大学);Google Inc.(谷歌公司)

Steven Kearnes, Kevin McCloskey, Marc Berndl, Vijay Pande, Patrick Riley

摘要:

编码结构信息的分子“指纹”是药物发现应用中化学信息学和机器学习的主力。然而,指纹表示必须强调分子结构的特定方面,而忽略其他方面,而不是允许模型做出数据驱动的决策。我们描述了分子“图卷积”,一个机器学习架构学习无向图,特别是小分子。图卷积使用分子图的简单编码-原子,键,距离等。这允许模型更好地利用图结构中的信息。虽然图卷积并不优于所有基于指纹的方法,但它们(以及其他基于图的方法)代表了基于配体的虚拟筛选的新范式,具有令人兴奋的未来改进机会。

英文摘要:

Molecular "fingerprints" encoding structural information are the workhorse of cheminformatics and machine learning in drug discovery applications. However, fingerprint representations necessarily emphasize particular aspects of the molecular structure while ignoring others, rather than allowing the model to make data-driven decisions. We describe molecular "graph convolutions", a machine learning architecture for learning from undirected graphs, specifically small molecules. Graph convolutions use a simple encoding of the molecular graph---atoms, bonds, distances, etc.---which allows the model to take greater advantage of information in the graph structure. Although graph convolutions do not outperform all fingerprint-based methods, they (along with other graph-based methods) represent a new paradigm in ligand-based virtual screening with exciting opportunities for future improvement.

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。

↑