Uni-Mol: A Universal 3D Molecular Representation Learning Framework
By Gengmo Zhou, Zhifeng Gao, Qiankun Ding, Hang Zheng, Hongteng Xu, Zhewei Wei, Linfeng Zhang, Guolin Ke. 2023
625 citations recorded by the source corpus.
Subfields: Representation & Self-Supervised Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Representation & Self-Supervised Learning
- Pushmeet Kohli
- Bin Cui
- Yue Zhao
- Ming-Hsuan Yang
- Alexander Pritzel
- Fajie Yuan
- Guolin Ke
- Demis Hassabis
Citations in the corpus
- Galactica: A Large Language Model for Science (2022, background): “The scaling is slower than tasks like QA, and the base model lags a specialist model with explicit 3D information and 10 times more molecules (Zhou et al., 2022).”
- Accurate structure prediction of biomolecular interactions with AlphaFold 3 (2024, methodology): “For example, Uni-Mol specifies the pocket as any residue within 6 Å of the heavy atoms in the ligand of interest 26 .”
- Generalized Biomolecular Modeling and Design with RoseTTAFold All-Atom (2023, methodology): “To enable blind testing of RFAA prediction performance, we enrolled an RFAA server in the blind Continuous Automated Model EvaluatiOn (CAMEO) ligand-docking evaluation, which carries out predictions on all struc- turessubmittedtothePDBeachweekwitheachenrolledserverandevaluatestheirperfor-mance( 16…”
- SaProt: Protein Language Modeling with Structure-aware Vocabulary (2024, methodology): “This approach was applied by Uni-Mol, ESMFold (Lin et al., 2022) and Evoformer.”
- Do Deep Learning Models Really Outperform Traditional Approaches in Molecular Docking? (2023, methodology): “Recently, deep learning has been widely used in drug design applications, such as molecular property prediction [5, 6, 7, 8] and protein structure predition [9].”
- Diffusion Models: A Comprehensive Survey of Methods and Applications (2022, background): “On one hand, recent works propose to pre-train GNN/transformer [169, 337] specifically for molecules/proteins with biomedical or physical insights [160, 324], and achieve remarkable results.”