Search Results for author:
Found 7 papers, 1 papers with code
Enhancing Model Learning and Interpretation Using Multiple Molecular Graph Representations for Compound Property and Activity Prediction
The results indicate that combining atom graph representation with reduced molecular graph representation can yield promising model performance.
Faster Lead Optimization Mapper Algorithm for Large-Scale Relative Free Energy Perturbation
In this study, we aimed to reduce the computational cost of Lomap to enable the construction of FEP graphs for hundreds of compounds.
Compound virtual screening by learning-to-rank with gradient boosting decision tree and enrichment-based cumulative gain
Furthermore, although the ranking metric called Normalized Discounted Cumulative Gain (NDCG) is widely used in information retrieval, it only determines whether the predictions are better than those of other models.
MEGADOCK-GUI: a GUI-based complete cross-docking tool for exploring protein-protein interactions
However, a friendly interface for users who are not sufficiently familiar with the command line interface has not been developed so far.
MEGADOCK-Web-Mito: human mitochondrial protein-protein interaction prediction database
Mitochondrial diseases are largely caused by dysfunction in mitochondrial proteins.
Molecular activity prediction using graph convolutional deep neural network considering distance on a molecular graph
Second, different weight matrices were used depending on the distance on the graph in the convolution layers of the pair features.
Link Mining for Kernel-based Compound-Protein Interaction Predictions Using a Chemogenomics Approach
The pairwise kernel method (PKM) is a state-of-the-art CGBVS method and shows high accuracy for prediction of new compounds.
