-
公开(公告)号：US12027240B2
公开(公告)日：2024-07-02
申请号：US17522702
申请日：2021-11-09
发明人： Yaodong Yang , Hongyao Tang , Guangyong Chen , Shengyu Zhang , Changyu Hsieh , Jianye Hao
摘要： Embodiments of this application relate to a retrosynthesis processing method and apparatus, an electronic device, and a computer-readable storage medium. A retrosynthesis processing method is performed by a computer device. The method includes determining molecular representation information of a target molecule. The method includes inputting the molecular representation information into a target neural network. The method includes performing, via the target neural network, retrosynthesis processing on the target molecule based on the molecular representation information of the target molecule, to obtain a respective retrosynthesis reaction of the target molecule for each step of the retrosynthesis processing. The target neural network is obtained by training a predetermined neural network according to a sample cost dictionary that is generated by concurrently performing retrosynthesis reaction training on each of a plurality of sample molecules, and the respective retrosynthesis reaction is performed according to a preset retrosynthesis reaction architecture.
-
公开(公告)号：US20220068442A1
公开(公告)日：2022-03-03
申请号：US17522702
申请日：2021-11-09
发明人： Yaodong YANG , Hongyao Tang , Guangyong Chen , Shengyu Zhang , Changyu Hsieh , Jianye Hao
摘要： Embodiments of this application relate to a retrosynthesis processing method and apparatus, an electronic device, and a computer-readable storage medium. A retrosynthesis processing method is performed by a computer device. The method includes determining molecular representation information of a target molecule. The method includes inputting the molecular representation information into a target neural network. The method includes performing, via the target neural network, retrosynthesis processing on the target molecule based on the molecular representation information of the target molecule, to obtain a respective retrosynthesis reaction of the target molecule for each step of the retrosynthesis processing. The target neural network is obtained by training a predetermined neural network according to a sample cost dictionary that is generated by concurrently performing retrosynthesis reaction training on each of a plurality of sample molecules, and the respective retrosynthesis reaction is performed according to a preset retrosynthesis reaction architecture.
-
搜索结果
2 条记录 (耗时 0.017 秒)
