Rethinking tokenizer and decoder in masked graph modeling for molecules
Masked graph modeling excels in the self-supervised representation learning of molecular
graphs. Scrutinizing previous studies, we can reveal a common scheme consisting of three …
graphs. Scrutinizing previous studies, we can reveal a common scheme consisting of three …
Molecular fragmentation as a crucial step in the AI-based drug development pathway
S Jinsong, J Qifeng, C Xing, Y Hao… - Communications Chemistry, 2024 - nature.com
The AI-based small molecule drug discovery has become a significant trend at the
intersection of computer science and life sciences. In the pursuit of novel compounds …
intersection of computer science and life sciences. In the pursuit of novel compounds …
HimGNN: a novel hierarchical molecular graph representation learning framework for property prediction
Accurate prediction of molecular properties is an important topic in drug discovery. Recent
works have developed various representation schemes for molecular structures to capture …
works have developed various representation schemes for molecular structures to capture …
Impact of Domain Knowledge and Multi-Modality on Intelligent Molecular Property Prediction: A Systematic Survey
The precise prediction of molecular properties is essential for advancements in drug
development, particularly in virtual screening and compound optimization. The recent …
development, particularly in virtual screening and compound optimization. The recent …
FG-BERT: a generalized and self-supervised functional group-based molecular representation learning framework for properties prediction
Artificial intelligence-based molecular property prediction plays a key role in molecular
design such as bioactive molecules and functional materials. In this study, we propose a self …
design such as bioactive molecules and functional materials. In this study, we propose a self …
Knowledge-augmented Graph Machine Learning for Drug Discovery: From Precision to Interpretability
Conventional Artificial Intelligence models are heavily limited in handling complex
biomedical structures (such as 2D or 3D protein and molecule structures) and providing …
biomedical structures (such as 2D or 3D protein and molecule structures) and providing …
Enhancing property and activity prediction and interpretation using multiple molecular graph representations with MMGX
A Kengkanna, M Ohue - Communications Chemistry, 2024 - nature.com
Abstract Graph Neural Networks (GNNs) excel in compound property and activity prediction,
but the choice of molecular graph representations significantly influences model learning …
but the choice of molecular graph representations significantly influences model learning …
Molecular gas-phase conformational ensembles
S Das, KM Merz Jr - Journal of Chemical Information and …, 2024 - ACS Publications
Accurately determining the global minima of a molecular structure is important in diverse
scientific fields, including drug design, materials science, and chemical synthesis …
scientific fields, including drug design, materials science, and chemical synthesis …
Enhancing molecular representations via graph transformation layers
GP Ren, KJ Wu, Y He - Journal of Chemical Information and …, 2023 - ACS Publications
Molecular representation learning is an essential component of many molecule-oriented
tasks, such as molecular property prediction and molecule generation. In recent years …
tasks, such as molecular property prediction and molecule generation. In recent years …
Application of self-supervised approaches to the classification of X-ray diffraction spectra during phase transitions
Y Sun, S Brockhauser, P Hegedűs, C Plückthun… - Scientific Reports, 2023 - nature.com
Spectroscopy and X-ray diffraction techniques encode ample information on investigated
samples. The ability of rapidly and accurately extracting these enhances the means to steer …
samples. The ability of rapidly and accurately extracting these enhances the means to steer …