Pre-training with fractional denoising to enhance molecular property prediction

Y Ni, S Feng, X Hong, Y Sun, WY Ma, ZM Ma… - Nature Machine …, 2024 - nature.com
Deep learning methods have been considered promising for accelerating molecular
screening in drug discovery and material design. Due to the limited availability of labelled …

Navigating chemical-linguistic sharing space with heterogeneous molecular encoding

L Lv, H Li, Y Wang, Z Yan, Z Chen, Z Lin… - arxiv preprint arxiv …, 2024 - arxiv.org
Chemical language models (CLMs) are prominent for their effectiveness in exploring
chemical space and enabling molecular engineering. However, while exploring chemical …

Pretraining graph transformer for molecular representation with fusion of multimodal information

R Chen, C Li, L Wang, M Liu, S Chen, J Yang, X Zeng - Information Fusion, 2025 - Elsevier
Molecular representation learning (MRL) is essential in certain applications including drug
discovery and life science. Despite advancements in multiview and multimodal learning in …

Self-Supervised Molecular Representation Learning With Topology and Geometry

X Zang, J Zhang, B Tang - IEEE Journal of Biomedical and …, 2024 - ieeexplore.ieee.org
Molecular representation learning is of great importance for drug molecular analysis. The
development in molecular representation learning has demonstrated great promise through …

MolTRES: Improving Chemical Language Representation Learning for Molecular Property Prediction

JH Park, Y Kim, M Lee, H Park, SK Lee - arxiv preprint arxiv:2408.01426, 2024 - arxiv.org
Chemical representation learning has gained increasing interest due to the limited
availability of supervised data in fields such as drug and materials design. This interest …

MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild

X Fang, J Wang, X Cai, S Chen, S Yang, L Yao… - arxiv preprint arxiv …, 2024 - arxiv.org
In recent decades, chemistry publications and patents have increased rapidly. A significant
portion of key information is embedded in molecular structure figures, complicating large …

HiMolformer: Integrating graph and sequence representations for predicting liver microsome stability with SMILES

S Yun, G Nam, J Koo - Computational Biology and Chemistry, 2024 - Elsevier
In the initial stages of drug discovery or pre-clinical studies, understanding the metabolic
stability of new molecules is crucial. Recently, research on pre-trained deep learning for …

Atomas: Hierarchical Alignment on Molecule-Text for Unified Molecule Understanding and Generation

Y Zhang, G Ye, C Yuan, B Han, LK Huang… - arxiv preprint arxiv …, 2024 - arxiv.org
Molecule-and-text cross-modal representation learning has emerged as a promising
direction for enhancing the quality of molecular representation, thereby improving …

Equivariant Pretrained Transformer for Unified Geometric Learning on Multi-Domain 3D Molecules

R Jiao, X Kong, Z Yu, W Huang, Y Liu - arxiv preprint arxiv:2402.12714, 2024 - arxiv.org
Pretraining on a large number of unlabeled 3D molecules has showcased superiority in
various scientific applications. However, prior efforts typically focus on pretraining models on …

MoleculeCLA: Rethinking Molecular Benchmark via Computational Ligand-Target Binding Analysis

S Feng, J Zheng, Y Jia, Y Huang, F Zhou… - arxiv preprint arxiv …, 2024 - arxiv.org
Molecular representation learning is pivotal for various molecular property prediction tasks
related to drug discovery. Robust and accurate benchmarks are essential for refining and …