Correlated RNN Framework to Quickly Generate Molecules with Desired Properties for Energetic Materials in the Low Data Regime

起爆 化学 循环神经网络 计算机科学 爆炸物 化学空间 集合(抽象数据类型) 人工智能 深度学习 数据集 人工神经网络 化学 药物发现 生物化学 有机化学 程序设计语言
作者
Chuan Li,Chenghui Wang,Ming Sun,Yan Zeng,Yuan Yuan,Qiaolin Gou,Guangchuan Wang,Yanzhi Guo,Xuemei Pu
出处
期刊:Journal of Chemical Information and Modeling [American Chemical Society]
卷期号:62 (20): 4873-4887 被引量:16
标识
DOI:10.1021/acs.jcim.2c00997
摘要

Motivated by the challenging of deep learning on the low data regime and the urgent demand for intelligent design on highly energetic materials, we explore a correlated deep learning framework, which consists of three recurrent neural networks (RNNs) correlated by the transfer learning strategy, to efficiently generate new energetic molecules with a high detonation velocity in the case of very limited data available. To avoid the dependence on the external big data set, data augmentation by fragment shuffling of 303 energetic compounds is utilized to produce 500,000 molecules to pretrain RNN, through which the model can learn sufficient structure knowledge. Then the pretrained RNN is fine-tuned by focusing on the 303 energetic compounds to generate 7153 molecules similar to the energetic compounds. In order to more reliably screen the molecules with a high detonation velocity, the SMILE enumeration augmentation coupled with the pretrained knowledge is utilized to build an RNN-based prediction model, through which R2 is boosted from 0.4446 to 0.9572. The comparable performance with the transfer learning strategy based on an existing big database (ChEMBL) to produce the energetic molecules and drug-like ones further supports the effectiveness and generality of our strategy in the low data regime. High-precision quantum mechanics calculations further confirm that 35 new molecules present a higher detonation velocity and lower synthetic accessibility than the classic explosive RDX, along with good thermal stability. In particular, three new molecules are comparable to caged CL-20 in the detonation velocity. All the source codes and the data set are freely available at https://github.com/wangchenghuidream/RNNMGM.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
哈喽完成签到,获得积分10
刚刚
唐唐完成签到 ,获得积分10
1秒前
皓月星辰完成签到,获得积分10
2秒前
鹿叽叽完成签到,获得积分10
2秒前
佳佳应助JIE采纳,获得10
3秒前
xiangzq完成签到,获得积分10
5秒前
胖宏完成签到 ,获得积分10
6秒前
拼搏尔风完成签到,获得积分10
6秒前
顾闭月完成签到,获得积分10
7秒前
biofresh完成签到,获得积分10
9秒前
牛姐完成签到,获得积分10
9秒前
lyan完成签到,获得积分10
10秒前
呆萌滑板完成签到 ,获得积分10
11秒前
lym完成签到,获得积分10
11秒前
Behappy完成签到 ,获得积分10
12秒前
12秒前
iiiau完成签到,获得积分10
12秒前
科奇应助科研通管家采纳,获得10
13秒前
充电宝应助科研通管家采纳,获得10
13秒前
ztt27999完成签到,获得积分10
13秒前
xmqaq完成签到,获得积分10
14秒前
14秒前
15秒前
momo完成签到 ,获得积分10
15秒前
无限翅膀完成签到,获得积分10
15秒前
yecheng完成签到,获得积分10
15秒前
文献一搜就出完成签到,获得积分10
16秒前
高高的丹雪完成签到 ,获得积分10
16秒前
请叫我风吹麦浪应助啊哈采纳,获得10
16秒前
Lenacici完成签到,获得积分10
16秒前
贱小贱完成签到,获得积分10
16秒前
kitty完成签到 ,获得积分10
16秒前
123完成签到,获得积分10
17秒前
菜菜求带完成签到 ,获得积分10
17秒前
时光完成签到,获得积分10
18秒前
内向怀曼完成签到,获得积分10
18秒前
nater4ver完成签到,获得积分10
18秒前
Mia完成签到,获得积分10
19秒前
LIN2QI完成签到,获得积分10
19秒前
慕山完成签到 ,获得积分10
20秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3968593
求助须知:如何正确求助?哪些是违规求助? 3513416
关于积分的说明 11167791
捐赠科研通 3248853
什么是DOI,文献DOI怎么找? 1794507
邀请新用户注册赠送积分活动 875170
科研通“疑难数据库(出版商)”最低求助积分说明 804671