LanceKnight / MolKGNNLinks
MolKGNN is a deep learning model for predicting biological activity or molecular properties. It features in 1. SE(3)-invariance 2. conformation-invariance 3. interpretability. MolKGNN uses a novel molecular convolution to leverage the similarity of molecular neighborhood and kernels. It shows superior results in realistic drug discovery dataset…
☆13Updated last year
Alternatives and similar repositories for MolKGNN
Users that are interested in MolKGNN are comparing it to the libraries listed below
Sorting:
- ProCare: A Point Cloud Registration Approach to Align Protein Cavities☆30Updated 2 years ago
- Python API for Pharmer☆12Updated 6 years ago
- Pocket-Oriented Elaboration of Molecules: application to CDK8 inhibition☆14Updated 2 years ago
- Source code accompanying the 'MF-PCBA: Multi-fidelity high-throughput screening benchmarks for drug discovery and machine learning' paper☆27Updated last week
- COMA: Efficient Structure-constrained Molecular Generation using Contractive and Margin losses☆18Updated last year
- Transformer-based molecular generative model for antiviral drug design☆16Updated 8 months ago
- Autoregressive fragment-based diffusion for target-aware ligand design☆29Updated last year
- ☆17Updated 2 years ago
- ☆18Updated 3 years ago
- ☆16Updated 3 years ago
- The BigBind protein-ligand binding dataset (and BayesBind benchmark)☆19Updated 8 months ago
- ☆26Updated 2 years ago
- A versatile workflow for the generation of receptor-based pharmacophore models for virtual screening☆29Updated 2 months ago
- Knowledge-Guided Diffusion Model for 3D Ligand-Pharmacophore Mapping☆35Updated last month
- ☆12Updated 3 years ago
- ☆36Updated last year
- ☆26Updated last year
- ☆19Updated 7 months ago
- ☆28Updated last year
- Scaffold decoration and fragment linking with chemical language models and RL☆26Updated 4 months ago
- ACGCN: Graph Convolutional Networks for Activity Cliff Prediction Between Matched Molecular Pairs (Park et al., 2022)☆19Updated 2 years ago
- ☆23Updated last year
- Benchmarking compound activity prediction for real-world drug discovery applications☆14Updated last year
- ☆20Updated 2 years ago
- ☆37Updated 4 years ago
- Data and code required to reach the main conclusions of the fastsmcg paper☆10Updated last year
- ☆26Updated last year
- ☆11Updated 10 months ago
- ☆21Updated last year
- ☆25Updated 11 months ago