meilerlab / 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…
☆20Updated last year
Alternatives and similar repositories for MolKGNN
Users that are interested in MolKGNN are comparing it to the libraries listed below
Sorting:
- Reagent prediction with Molecular Transformer. Improvement of data for reaction product prediction in a self-supervised fashion.☆24Updated 7 months ago
- Drug-Target Interactive Prediction Model using ChemBERTa and ProtBert☆14Updated 7 months ago
- Atom-in-SMILES tokenizer for SMILES strings.☆36Updated 10 months ago
- MiniMol is a 10M-parameters molecular fingerprinting model pre-trained on >3300 biological and quantum tasks☆19Updated last week
- ☆15Updated 2 years ago
- Fragment-based Molecular Expansion☆20Updated last year
- ☆12Updated last year
- ☆26Updated last year
- A simple molecule fragmentation method.☆36Updated last year
- Implementation of the Confidence Bootstrapping procedure for protein-ligand docking.☆26Updated last year
- Code for "HiGNN: A Hierarchical Informative Graph Neural Network for Molecular Property Prediction Equipped with Feature-Wise Attention"☆50Updated 2 years ago
- Recursion's molecular foundation model☆50Updated this week
- Kinase–drug binding prediction with calibrated uncertainty quantification☆23Updated last year
- Official implementation for ActFound (Nature Machine Intelligence): A bioactivity foundation model using pairwise meta-learning☆42Updated 7 months ago
- maxsmi: a guide to SMILES augmentation. Find the optimal SMILES augmentation for accurate molecular prediction.☆31Updated last year
- Few-shot machine learning for low-data drug discovery.☆19Updated 2 years ago
- Multi-Scale Representation Learning on Proteins (NeurIPS 2021)☆46Updated last year
- DeepDelta is a pairwise deep learning approach based on Chemprop that processes two molecules simultaneously and learns to predict proper…☆47Updated last year
- ☆24Updated 2 years ago
- ☆28Updated 2 years ago
- COMA: Efficient Structure-constrained Molecular Generation using Contractive and Margin losses☆18Updated last year
- Diffusion-based molecule conformer generation☆41Updated last year
- ☆20Updated 2 years ago
- ☆31Updated 11 months ago
- ☆22Updated 9 months ago
- ProCare: A Point Cloud Registration Approach to Align Protein Cavities☆29Updated 2 years ago
- source code for deppHop☆36Updated 2 years ago
- Official implementation of "Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Design"☆64Updated 6 months ago
- ☆33Updated 6 months ago
- ☆41Updated last year