Results 51 to 60 of about 6,104,936 (275)
Force field-inspired molecular representation learning for property prediction
Journal of Cheminformatics, 2023 Molecular representation learning is a crucial task to accelerate drug discovery and materials design. Graph neural networks (GNNs) have emerged as a promising approach to tackle this task.
Gao-Peng Ren +3 more
doaj +1 more source
Multiparameter Persistent Homology for Molecular Property Prediction
CoRR, 2023 In this study, we present a novel molecular fingerprint generation method based on multiparameter persistent homology. This approach reveals the latent structures and relationships within molecular geometry, and detects topological features that exhibit persistence across multiple scales along multiple parameters, such as atomic mass, partial charge ...
Andac Demir, Bulent Kiziltan
openaire +3 more sources
Hierarchical Molecular Graph Self-Supervised Learning for property prediction
Communications Chemistry, 2023 Graph Neural Networks are employed to encode molecular graph representations, but structural information and chemical functions are largely missing. Here, the authors develop hierarchical molecular graph self-supervised learning as a framework to learn ...
Xuan Zang, Xianbing Zhao, Buzhou Tang
doaj +1 more source
Unraveling Key Elements Underlying Molecular Property Prediction: A Systematic Study [PDF]
, 2023 Artificial intelligence (AI) has been widely applied in drug discovery with a major task as molecular property prediction. Despite booming techniques in molecular representation learning, key elements underlying molecular property prediction remain ...
Deng, Jianyuan +5 more
core +1 more source
Molecular Property Prediction Based on a Multichannel Substructure Graph
IEEE Access, 2020 Molecular property prediction is important to drug design. With the development of artificial intelligence, deep learning methods are effective for extracting molecular features. In this paper, we propose a multichannel substructure-graph gated recurrent
Shuang Wang +5 more
doaj +1 more source
BERTology of Molecular Property Prediction
CoRRChemical language models (CLMs) have emerged as promising competitors to popular classical machine learning models for molecular property prediction (MPP) tasks. However, an increasing number of studies have reported inconsistent and contradictory results for the performance of CLMs across various MPP benchmark tasks.
Mohammad Mostafanejad +2 more
openaire +3 more sources
Molecular property prediction by semantic-invariant contrastive learning
Bioinformatics, 2023 Abstract Motivation Contrastive learning has been widely used as pretext tasks for self-supervised pre-trained molecular representation learning models in AI-aided drug design and discovery. However, existing methods that generate molecular views by noise-adding operations for contrastive learning may
Ziqiao Zhang +3 more
openaire +4 more sources
Taking into account stereoisomerism in the prediction of molecular properties [PDF]
2016 23rd International Conference on Pattern Recognition (ICPR), 2016 The prediction of molecule's properties through Quantitative Structure Activity (resp. Property) Relationships are two active research fields named QSAR and QSPR. Within these frameworks Graph kernels allow to combine a natural encoding of a molecule by a graph with classical statistical tools such as SVM or kernel ridge regression.
Grenier, Pierre-Anthony +2 more
openaire +3 more sources
Transferring a Molecular Foundation Model for Polymer Property Predictions
Journal of Chemical Information and Modeling, 2023 Transformer-based large language models have remarkable potential to accelerate design optimization for applications such as drug development and materials discovery. Self-supervised pretraining of transformer models requires large-scale datasets, which are often sparsely populated in topical areas such as polymer science.
Pei Zhang +5 more
openaire +4 more sources
QSARtuna: an automated QSAR modelling platform for molecular property prediction in drug design [PDF]
Machine-learning (ML) and Deep-Learning (DL) approaches to predict the molecular properties of small molecules are increasingly deployed within the design-make-test-analyse (DMTA) drug design cycle to predict molecular properties of interest.
Lewis, Mervin +3 more
core +1 more source