BEGAN: Boltzmann-Reweighted Data Augmentation for Enhanced GAN-Based Molecule Design in Insect Pheromone Receptors
文献类型: 外文期刊
作者: Dai, Jialei;Zhang, Yutong;Shi, Chen;Liu, Yang;Xiu, Peng;Wang, Yong
作者机构:
关键词: 无
期刊名称: JOURNAL OF PHYSICAL CHEMISTRY B
ISSN: 1520-6106
年卷期: 2025 年
页码:
收录情况: SCIE(2024版) ; ; EI(2024版)
摘要: Identifying small molecules that bind strongly to target proteins in rational molecular design is crucial. Machine learning techniques, such as generative adversarial networks (GAN), are now essential tools for generating such molecules. In this study, we present an enhanced method for molecule generation using objective-reinforced GANs. Specifically, we introduce BEGAN (Boltzmann-enhanced GAN), a novel approach that adjusts molecule occurrence frequencies during training based on the Boltzmann distribution exp(-Delta U/tau), where Delta U represents the estimated binding free energy derived from docking algorithms and tau is a temperature-related scaling hyperparameter. This Boltzmann reweighting process shifts the generation process toward molecules with higher binding affinities, allowing the GAN to explore molecular spaces with superior binding properties. The reweighting process can also be refined through multiple iterations without altering the overall distribution shape. To validate our approach, we apply it to the design of sex pheromone analogs targeting Spodoptera frugiperda pheromone receptor SfruOR16, illustrating that the Boltzmann reweighting significantly increases the likelihood of generating promising sex pheromone analogs with improved binding affinities to SfruOR16, further supported by atomistic molecular dynamics simulations. Furthermore, we conduct a comprehensive investigation into parameter dependencies and propose a reasonable range for the hyperparameter tau. Our method offers a promising approach for optimizing molecular generation for enhanced protein binding, potentially increasing the efficiency of molecular discovery pipelines.
分类号:
- 相关文献
作者其他论文 更多>>
-
Lactic Acid Bacteria as the Green and Safe Food Preservatives: Their Mechanisms, Applications and Prospects
作者:Zhang, Yuwei;Li, Lianrui;Pang, Xiaoyang;Zhang, Shuwen;Liu, Yang;Wang, Yunna;Xie, Ning;Li, Xu
关键词:lactic acid bacteria (LAB);food preservatives;antimicrobial mechanism;food control;prospects
-
Rapid introgression of the clubroot resistance gene CRa into cabbage skeleton inbred lines through marker assisted selection
作者:Zhang, Na;Zhu, Mingzhao;Qiu, Yuting;Fang, Zhiyuan;Zhuang, Mu;Zhang, Yangyong;Lv, Honghao;Ji, Jialei;Hou, Xilin;Yang, Limei;Wang, Yong
关键词:Clubroot;Breeding;Backcross;Marker assisted selection
-
Synergistic effect of pectin and the flavanols mixture on in vitro starch digestion and the corresponding mechanism
作者:Qin, Yajuan;Zhang, Yutong;Chen, Xiaoai;Xu, Fei;Zhu, Kexue;Wang, Ping;Zhang, Yanjun
关键词:Rutin;Quercetin;Kaempferol;alpha-Glucosidase;Pectin;In vitro starch digestion
-
Virtual screening, molecular dynamics simulations, and in vitro analysis of Sophora flavescens-derived aloperine against Haemonchus contortus
作者:Li, Anben;Ma, Yan;Li, Wenxi;Zhai, Bintao;Fu, Nana;Li, Jun;Zhou, Qianyu;Liu, Yang
关键词:Haemonchus contortus;virtual screening;aloperine;IVM;HC-Pgp
-
Pectin enhances the inhibition of α-amylase via the mixture of rutin and quercetin
作者:Qin, Yajuan;Chen, Xiaoai;Xu, Fei;Zhu, Kexue;Wang, Ping;Zhang, Yutong;Zhang, Yanjun
关键词:Rutin-quercetin mixture;Pectin;alpha-Amylase
-
Transcriptome and Metabolome Analyses Offer New Insights into Bolting Time Regulation in Broccoli
作者:Kuang, Linqian;Zhang, Yue;Zhang, Nan;Zhang, Yangyong;Lv, Honghao;Wang, Yong;Zhuang, Mu;Yang, Limei;Huang, Ke;Li, Zhansheng;Ji, Jialei
关键词:broccoli;bolting time;transcriptome;metabolome;floral pathway;sugar signal;hormone signaling
-
The DNA N6-adenine methylation target gene GhMAF1 promotes fiber initiation at the base of Gossypium ovules
作者:Pei, Yanfei;Liu, Yongming;Peng, Jun;Pei, Yayue;Zhang, Tianen;Miao, Pengfei;Liu, Yuanyuan;Liu, Yang;Liu, Ji;Yang, Zuoren;Li, Fuguang;Wang, Zhi
关键词:6mA methylation;cotton;fiber initiation;GhMAF1;spatial differentiation