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 2 years ago
Alternatives and similar repositories for MolKGNN
Users that are interested in MolKGNN are comparing it to the libraries listed below
Sorting:
- Graph neural networks for molecular machine learning. Implemented and compatible with TensorFlow and Keras.☆61Updated 3 months ago
- Recursion's molecular foundation model☆64Updated 6 months ago
- 🔥 PyTorch implementation of GNINA scoring function for molecular docking☆71Updated 9 months ago
- Atom-in-SMILES tokenizer for SMILES strings.☆42Updated last year
- Official implementation for ActFound (Nature Machine Intelligence): A bioactivity foundation model using pairwise meta-learning☆45Updated last year
- Molecule Optimization via Fragment-based Generative Models☆42Updated 2 years ago
- A simple molecule fragmentation method.☆40Updated 2 years ago
- Kinase–drug binding prediction with calibrated uncertainty quantification☆23Updated last year
- Chemical representation learning paper in Digital Discovery☆63Updated last year
- ☆40Updated 5 years ago
- Few-shot machine learning for low-data drug discovery.☆19Updated 3 years ago
- Multi-Scale Representation Learning on Proteins (NeurIPS 2021)☆49Updated 2 years ago
- ☆94Updated 2 years ago
- ☆29Updated 2 years ago
- MiniMol is a 10M-parameters molecular fingerprinting model pre-trained on >3300 biological and quantum tasks☆31Updated 6 months ago
- ☆17Updated 3 years ago
- pre-training BERT with molecular data☆50Updated 4 years ago
- Interpretable AI pipeline improving binding predictions for novel protein targets and ligands☆31Updated last year
- SELFormer: Molecular Representation Learning via SELFIES Language Models☆104Updated last year
- An E(3) Equivariant Variational Autoencoder for Molecular Linker Design☆49Updated 3 years ago
- Official implementation of "Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Design"☆67Updated last year
- ☆21Updated 3 years ago
- Fragment-based Molecular Expansion☆25Updated last year
- Integrated physics-based and ligand-based modeling.☆66Updated last month
- Utilities for working with SMILES based encodings of molecules for deep learning (PyTorch oriented)☆83Updated last year
- pythonic interface to virtual screening software☆91Updated 3 months ago
- ☆32Updated 2 years ago
- Supporting code for the paper "Bidirectional Molecule Generation with Recurrent Neural Networks" (J. Chem. Inf. 2020, 60, 3).☆53Updated 5 years ago
- ☆76Updated 3 years ago
- Fast and accurate molecular docking with an AI pose scoring function☆42Updated last year