DynamicDTA combines a drug molecular graph, a protein sequence encoder, and four per-protein dynamic descriptors with cross-attention and tensor fusion to predict binding affinity, outperforming seven baselines in most settings but with questionable train-test separation.
Nature 616(7958):673–685
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
DynamicDTA: Drug-Target Binding Affinity Prediction Using Dynamic Descriptors and Graph Representation
DynamicDTA combines a drug molecular graph, a protein sequence encoder, and four per-protein dynamic descriptors with cross-attention and tensor fusion to predict binding affinity, outperforming seven baselines in most settings but with questionable train-test separation.