Combining Docking Pose Rank and Structure with Deep Learning Improves Protein-Ligand Binding Mode Prediction over a Baseline Docking Approach

@article{Morrone2020CombiningDP,
  title={Combining Docking Pose Rank and Structure with Deep Learning Improves Protein-Ligand Binding Mode Prediction over a Baseline Docking Approach},
  author={Joseph A Morrone and J. Weber and T. Huynh and Heng Luo and W. Cornell},
  journal={Journal of chemical information and modeling},
  year={2020}
}
  • Joseph A Morrone, J. Weber, +2 authors W. Cornell
  • Published 2020
  • Computer Science, Chemistry, Biology, Physics, Mathematics, Medicine
  • Journal of chemical information and modeling
We present a simple, modular graph-based convolutional neural network that takes structural information from protein-ligand complexes as input to generate models for activity and binding mode prediction. Complex structures are generated by a standard docking procedure and fed into a dual-graph architecture that includes separate sub-networks for the ligand bonded topology and the ligand-protein contact map. Recent work has indicated that dataset bias drives many past promising results derived… Expand
Recent Applications of Deep Learning Methods on Evolution- and Contact-Based Protein Structure Prediction
  • Donghyuk Suh, Jai Woo Lee, Sun Choi, Yoonji Lee
  • International Journal of Molecular Sciences
  • 2021
Improvement of Prediction Performance With Conjoint Molecular Fingerprint in Deep Learning
Assigning Confidence to Molecular Property Prediction
Beware of the generic machine learning-based scoring functions in structure-based virtual screening
...
1
2
...

References

SHOWING 1-10 OF 58 REFERENCES
Boosting Docking-Based Virtual Screening with Deep Learning
Machine learning optimization of cross docking accuracy
  • E. Bjerrum
  • Computer Science, Medicine
  • Comput. Biol. Chem.
  • 2016
Protein-Ligand Scoring with Convolutional Neural Networks
PotentialNet for Molecular Property Prediction
...
1
2
3
4
5
...