会议论文详细信息
Similarity-based learning on structures
An adaptive model for learning molecular endpoints
计算机科学;物理学
Ian Walsh1 ; Alessandro Vullo1 ; Gianluca Pollastri1
PID  :  80216
学科分类:计算机科学(综合)
来源: CEUR
PDF
【 摘 要 】

Accurately predicting the endpoints of chemical compounds is a important step towards drug design and molecular screening in particular. Here we develop a recursive architecture that is capable of mapping Undirected Graphs into individual labels, and apply it to the prediction of a number of dif ferent properties of small molecules. The results we obtain are generally stateof theart. The final model is completely general and may be applied not only to prediction of molecular properties, but to a vast range of problems in which the input is a graph and the output is either a single property or (with small modifications) a set of properties of the nodes.

【 预 览 】
附件列表
Files Size Format View
An adaptive model for learning molecular endpoints 624KB PDF download
  文献评价指标  
  下载次数:4次 浏览次数:9次