Cargando…
Molecular property prediction by contrastive learning with attention-guided positive sample selection
MOTIVATION: Predicting molecular properties is one of the fundamental problems in drug design and discovery. In recent years, self-supervised learning (SSL) has shown its promising performance in image recognition, natural language processing, and single-cell data analysis. Contrastive learning (CL)...
Autores principales: | Wang, Jinxian, Guan, Jihong, Zhou, Shuigeng |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10188298/ https://www.ncbi.nlm.nih.gov/pubmed/37079731 http://dx.doi.org/10.1093/bioinformatics/btad258 |
Ejemplares similares
-
Molecular property prediction by semantic-invariant contrastive learning
por: Zhang, Ziqiao, et al.
Publicado: (2023) -
FraGAT: a fragment-oriented multi-scale graph attention model for molecular property prediction
por: Zhang, Ziqiao, et al.
Publicado: (2021) -
A comparison study on feature selection of DNA structural properties for promoter prediction
por: Gan, Yanglan, et al.
Publicado: (2012) -
Selecting high-quality negative samples for effectively predicting protein-RNA interactions
por: Cheng, Zhanzhan, et al.
Publicado: (2017) -
Improving compound–protein interaction prediction by building up highly credible negative samples
por: Liu, Hui, et al.
Publicado: (2015)