graph neural networkgraph attention networksprotein structureProteins are engines involved in almost all functions of life. They have specific spatial structures formed by twisting and folding of one or more polypeptide chains composed of amino acids. Protein sites are protein structure microenvironments ...
This study reports an in silico antibody maturation pipeline based on a pretrainable geometric graph neural network, GearBind, and the successful application of the pipeline on two distinct antibodies, CR3022 and anti-5T4 UdAb. Substantial in silico experiments were done to evaluate model performanc...
To this end, we propose a structure-aware interactive graph neural network (SIGN) which consists of two components: polar-inspired graph attention layers (PGAL) and pairwise interactive pooling (PiPool). Specifically, PGAL iteratively performs the node-edge aggregation process to update embeddings ...
Besides, the interpretability of the graph-based DTA models highly relies on the graph attention mechanism, which can not reveal the global relationship between each atom of a molecule. In this study, we proposed a deep multiscale graph neural network based on chemical intuition for DTA ...
Due to their capacity to handle graph structure data, GNN have recently garnered a great deal of attention, and several graph data types, such as social networks and drug-protein graphs, have become popular. This paper focuses on one of the variations of GNN that apply convolution over a ...
One of the models that may be most suitable for the DTA prediction task is the graph neural network (GNN). The GNN can directly process graph data that can preserve structural information, and this approach has already made research progress. GraphDTA [17] introduces GNN into the DTA predictio...
Our neural networks consist of cross-attention, 1D convolutional neural network block, self-attention, and fully connected layers. One of the ensembles achieves the highest R-value of 0.914 with the lowest RMSE of 0.957 on the benchmark test set CASF2016 compared to all the state-of-the-art...
Joint attention mechanism Graph convolution neural network (GCNN) with separate attention mechanism (Update: Apr. 22, 2021)data_DeepRelations: A newly curated dataset for explainabe prediction of compound-protein affinities, containing 4446 pairs between 3672 compounds and 1287 proteins, labeled with ...
《Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers》(CVPR 2022) GitHub: github.com/rulixiang/afa [fig5]《Exploring Dual-task Correlation for Pose Guided Person Image Generation》(CVPR 2022) GitHub: github.com/PangzeCheung/Dual-task-Pose-...
BACPI: a bi-directional attention neural network for compound-protein interaction and binding affinity prediction Requirements numpy==1.19.1 pandas==1.0.5 rdkit==2009.Q1-1 scikit_learn==1.0.2 scipy==1.5.0 torch==1.6.0 Example usage