Article
Biochemical Research Methods
Jianmin Wang, Yanyi Chu, Jiashun Mao, Hyeon-Nae Jeon, Haiyan Jin, Amir Zeb, Yuil Jang, Kwang-Hwi Cho, Tao Song, Kyoung Tai No
Summary: This study constructs a dataset for protein-protein interaction (PPI) targeted drug-likeness and proposes a deep molecular generative framework to generate novel drug-like molecules based on the features of seed compounds. The results show that the generated molecules have better PPI-targeted drug-likeness and drug-likeness, and the model performs comparably to other state-of-the-art molecule generation models.
BRIEFINGS IN BIOINFORMATICS
(2022)
Review
Biochemistry & Molecular Biology
Varnavas D. Mouchlis, Antreas Afantitis, Angela Serra, Michele Fratello, Anastasios G. Papadiamantis, Vassilis Aidinis, Iseult Lynch, Dario Greco, Georgia Melagraki
Summary: De novo drug design is a process of generating novel molecular structures using computational methods, with traditional approaches including structure-based and ligand-based design. Artificial intelligence and machine learning have a positive impact in this field.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2021)
Article
Chemistry, Multidisciplinary
Carlo Abate, Sergio Decherchi, Andrea Cavalli
Summary: Drug design is resource and time-consuming. Generative deep learning techniques, using biochemical data and computing power, are paving the way for new tools and methods in drug discovery. Graph neural networks (GNNs) are learning models that can natively process graphs, and their use in drug design is growing exponentially. These GNNs, coupled with conditioning techniques, hold promise for routine application in drug discovery.
WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL MOLECULAR SCIENCE
(2023)
Article
Biochemical Research Methods
Fengqing Lu, Mufei Li, Xiaoping Min, Chunyan Li, Xiangxiang Zeng
Summary: This study introduces a computational framework called DLGN for generating bioactive molecules towards two specific targets. DLGN utilizes adversarial training and reinforcement learning to explore chemical spaces and encourage the generation of molecules that belong to the intersection of two bioactive compound distributions. The proposed model shows promise in generating novel compounds with high similarity to multiple bioactive datasets.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Biochemistry & Molecular Biology
Ssemuyiga Charles, Rajani Kanta Mahapatra
Summary: This study used generative modeling techniques to create potential PfPMX inhibitors and evaluated them through screening, simulation, and assessment. The results showed that these inhibitors have good activity and acceptable drug properties, making them promising antimalarials.
JOURNAL OF BIOMOLECULAR STRUCTURE & DYNAMICS
(2023)
Article
Chemistry, Medicinal
Young Jae Lee, Hyungu Kahng, Seoung Bum Kim
Summary: This study introduces a method based on generative adversarial networks and reinforcement learning for de novo molecular design in the chemical industry, which has successfully generated molecules with more practical chemical properties.
MOLECULAR INFORMATICS
(2021)
Article
Automation & Control Systems
Wonsuk Kim, Soojeong Kim, Minhyeok Lee, Junhee Seok
Summary: Efficiently designing structures with desired properties is a challenging task in engineering and scientific applications. Traditional methods involve experts designing structures and performing simulations to evaluate their properties. Inverse design framework allows for directly constructing structures with desired properties. This paper introduces a model based on a controllable generative adversarial network (ControlGAN) for generating nanophotonic devices with user-defined properties, which outperforms other GAN-based models in producing structures with maximum transmittance at specific wavelengths. The proposed inverse design model can accelerate device designs in the field of nanophotonics and other nanostructures.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Biochemistry & Molecular Biology
Tzu-Tang Lin, Li-Yen Yang, Chung-Yen Lin, Ching-Tien Wang, Chia-Wen Lai, Chi-Fong Ko, Yang-Hsin Shih, Shu-Hwa Chen
Summary: Due to the increase in clinical antibiotic resistance cases recent years, novel antimicrobial peptides (AMPs) may serve as ideal next-generation antibiotics. This study used a Wasserstein generative adversarial network with gradient penalty (WGAN-GP) trained on known AMPs to generate new AMP candidates. The quality of the generated AMPs was evaluated in silico and eight peptides, named GAN-pep 1-8, were selected, synthesized, and tested for antibacterial activity. Seven of the synthesized peptides demonstrated antibacterial effects, with GAN-pep 3 and GAN-pep 8 exhibiting broad-spectrum activity against antibiotic-resistant bacteria strains. GAN-pep 3, the most promising candidate, displayed low minimum inhibitory concentrations (MICs) against all tested bacteria.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Huidong Tang, Chen Li, Shuai Jiang, Huachong Yu, Sayaka Kamei, Yoshihiro Yamanishi, Yasuhiko Morimoto
Summary: This paper introduces an enhanced actor-critic RL agent-driven Generative Adversarial Network (EarlGAN) for de novo drug design. EarlGAN performs autoregressive predictions at the atomic level and employs moment rewards, global-level discrimination rewards, and information entropy maximization to generate diverse molecule samples.
PATTERN RECOGNITION LETTERS
(2023)
Article
Chemistry, Multidisciplinary
Yuxia Tang, Jiulou Zhang, Doudou He, Wenfang Miao, Wei Liu, Yang Li, Guangming Lu, Feiyun Wu, Shouju Wang
Summary: The study introduces a Generative Adversarial Network for Distribution Analysis (GANDA) to describe and generate intratumoral quantum dots distribution, offering a new approach to investigate NPs distribution and guide nanomedicine optimization.
JOURNAL OF CONTROLLED RELEASE
(2021)
Article
Engineering, Electrical & Electronic
Mu-Yen Chen, Wei Wei, Han-Chieh Chao, Yi-Fen Li
Summary: Robotic musicianship research focuses on enabling robots to analyze, reason, and generate music autonomously, aiming to achieve inspiring and meaningful musical interactions between humans and artificially creative robots. This research introduces a new model of automatic music generation using least squares and generative adversarial networks (GANs). By applying sequence generation adversarial network (SeqGAN) techniques, the research addresses the challenges in generating classical piano melodies. The proposed method, called Least Squares SeqGAN (LS-SeqGAN), effectively creates melody units on different chords and generates a set of music pieces with high quality and creativity, offering a robust infrastructure for human-robotic interaction.
IEEE SENSORS JOURNAL
(2022)
Article
Biochemistry & Molecular Biology
Kostas Papadopoulos, Kathryn A. Giblin, Jon Paul Janet, Atanas Patronov, Ola Engkvist
Summary: The deep generative model trained with reinforcement learning using 3D shape and pharmacophore similarity scoring component has been shown to efficiently discover new leads in molecular design without relying on other information. Comparison with 2D QSAR models indicates that the 3D similarity based model produces more diverse outputs and allows for scaffold hopping and generation of novel series. Combining the two scoring components for training the generative model leads to more efficient exploration of desirable chemical space.
BIOORGANIC & MEDICINAL CHEMISTRY
(2021)
Article
Computer Science, Artificial Intelligence
Mohamed Ali Souibgui, Yousri Kessentini
Summary: This paper proposes an effective end-to-end framework, called document enhancement generative adversarial networks (DE-GAN), for restoring severely degraded document images using conditional GANs (cGANs). The results show that DE-GAN can generate high-quality enhanced versions of degraded documents in tasks such as document clean up, binarization, deblurring, and watermark removal. It also outperforms state-of-the-art methods on widely used datasets, demonstrating its ability to restore degraded document images to ideal condition.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Information Systems
Aurele Tohokantche Aurele Tohokantche, Wenming Cao, Xudong Mao, Si Wu, Hau-San Wong, Qing Li
Summary: This paper proposes a parametric and robust AB loss function to improve the performance of generative adversarial networks (GAN) on different datasets and alleviate the issue of mode collapse. Experimental results demonstrate that this approach can enhance the quality of synthetic images.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Laurenz Berger, Max Haberbusch, Francesco Moscato
Summary: Generating synthetic ECG signals using GANs is a promising tool for data augmentation of imbalanced datasets and improves classification performance. However, evaluating the quality of generated signals remains challenging, and future work should focus on establishing quality evaluation metrics.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2023)