On the Frustration to Predict Binding Affinities from Protein-Ligand Structures with Deep Neural Networks.
By M. Volkov, Joseph-André Turk, Nicolas Drizard, N. Martin, Brice Hoffmann, Y. Gaston-Mathé, Didier Rognan. 2022
156 citations recorded by the source corpus.
Accurate prediction of binding affinities from protein-ligand atomic coordinates remains a major challenge in early stages of drug discovery. Using modular message passing graph neural networks describing both the ligand and the protein in their free and bound states, we unambiguously evidence that an explicit description of protein-ligand noncovalent interactions does not provide any advantage with respect to ligand or protein descriptors. Simple models, inferring binding affinities of test samples from that of the closest ligands or proteins in the training set, already exhibit good performances, suggesting that memorization largely dominates true learning in the deep neural networks. The current study suggests considering only noncovalent interactions while omitting their protein and ligand atomic environments. Removing all hidden biases probably requires much denser protein-ligand training matrices and a coordinated effort of the drug design community to solve the necessary protein-ligand structures.
Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Theory and Mathematics
- Tommi S. Jaakkola
- Regina Barzilay
- Bowen Jing
- Gabriele Corso
- Hannes Stärk
- Anastasiia V. Sadybekov
- Vsevolod Katritch
- Wengong Jin
In Materials Chemistry
- Tommi S. Jaakkola
- Regina Barzilay
- Anastasiia V. Sadybekov
- Gabriele Corso
- Bowen Jing
- Hannes Stärk
- Vsevolod Katritch
- Wengong Jin
In Molecular Biology
- Tommi S. Jaakkola
- Regina Barzilay
- Hannes Stärk
- Bowen Jing
- Gabriele Corso
- Anastasiia V. Sadybekov
- Vsevolod Katritch
- Shuya Nakata
Citations in the corpus
- DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking (2022, methodology): “This is motivated by the further adoption of the same split [4] and the critical assessment of PDBBind splits by [14] who favor temporal splits over artificial splits based on molecular scaffolds or protein sequence/structure similarity.”
- Computational approaches streamlining drug discovery (2023, background): “87.”