The discovery of new chemical entities is a crucial part of drug discovery, which requires the lead compounds to have desired properties to be pharmaceutically active. De novo drug design aims to generate and optimize novel ligands for macromolecular targets from scratch. The development of graph-based deep generative neural networks has provided a new method. In this review, we gave a brief introduction to graph representation and graph-based generative models for de novo drug design, summarized them as four architectures, and concluded each's characteristics. We also discussed generative models for scaffold- and fragment-based design and graph-based generative models' future directions.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.ddtec.2020.11.004 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A clinical knowledge graph-based framework to prioritize candidate genes for facilitating diagnosis of Mendelian diseases and rare genetic conditions.
BMC Bioinformatics
March 2025
Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN, 55905, USA.
Background: Diagnosing Mendelian and rare genetic conditions requires identifying phenotype-associated genetic findings and prioritizing likely disease-causing genes. This task is labor-intensive for molecular and clinical geneticists, who must review extensive literature and databases to link patient phenotypes with causal genotypes. The challenge is further complicated by the large number of genetic variants detected through next-generation sequencing, which impacts both diagnosis timelines and patient care strategies.
View Article and Find Full Text PDFGCN-Based Framework for Materials Screening and Phase Identification.
Materials (Basel)
February 2025
Faculty of Humanities and Social Sciences, Macao Polytechnic University, Macao, China.
This study proposes a novel framework using graph convolutional networks to analyze and interpret X-ray diffraction patterns, addressing challenges in phase identification for multi-phase materials. By representing X-ray diffraction patterns as graphs, the framework captures both local and global relationships between diffraction peaks, enabling accurate phase identification even in the presence of overlapping peaks and noisy data. The framework outperforms traditional machine learning models, achieving a precision of 0.
View Article and Find Full Text PDFTandem LTR-retrotransposon structures are common and highly polymorphic in plant genomes.
Mob DNA
March 2025
Centre for Research in Agricultural Genomics, CRAG (CSIC- IRTA-UAB-UB), Campus UAB, Cerdanyola del Vallès, Barcelona, Spain.
Background: LTR-retrotransposons (LTR-RT) are a major component of plant genomes and important drivers of genome evolution. Most LTR-RT copies in plant genomes are defective elements found as truncated copies, nested insertions or as part of more complex structures. The recent availability of highly contiguous plant genome assemblies based on long-read sequences now allows to perform detailed characterization of these complex structures and to evaluate their importance for plant genome evolution.
View Article and Find Full Text PDFAn Integrated Fuzzy Neural Network and Topological Data Analysis for Molecular Graph Representation Learning and Property Forecasting.
Mol Inform
March 2025
Faculty of Information Technology, HUTECH University, Ho Chi Minh City, Vietnam.
Within a recent decade, graph neural network (GNN) has emerged as a powerful neural architecture for various graph-structured data modelling and task-driven representation learning problems. Recent studies have highlighted the remarkable capabilities of GNNs in handling complex graph representation learning tasks, achieving state-of-the-art results in node/graph classification, regression, and generation. However, most traditional GNN-based architectures like GCN and GraphSAGE still faced several challenges related to the capability of preserving the multi-scaled topological structures.
View Article and Find Full Text PDFMyocardial perfusion imaging SPECT left ventricle segmentation with graphs.
EJNMMI Phys
March 2025
Nuclear Medicine, Semmelweis University, Üllői street 78b, Budapest, Pest, 1083, Hungary.
Purpose: Various specialized and general collimators are used for myocardial perfusion imaging (MPI) with single-photon emission computed tomography (SPECT) to assess different types of coronary artery disease (CAD). Alongside the wide variability in imaging characteristics, the apriori "learnt" information of left ventricular (LV) shape can affect the final diagnosis of the imaging protocol. This study evaluates the effect of prior information incorporation into the segmentation process, compared to deep learning (DL) approaches, as well as the differences of 4 collimation techniques on 5 different datasets.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!