jbalma / pharml
PharML is a framework for predicting compound affinity for protein structures. It utilizes a novel Molecular-Highway Graph Neural Network (MH-GNN) architecture based on state-of-the-art techniques in deep learning. This repository contains the visualization, preprocessing, training, and inference code written in Python and C. In addition, we pro…
☆13Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for pharml
- ☆12Updated 9 years ago
- Graph Inference on MoLEcular Topology☆26Updated last year
- Implementation of "Semi-supervised learning of hierarchical representations of molecules using neural message passing" (arXiv:1711.10168)☆14Updated 6 years ago
- Data and analysis scripts for understanding molecular entropies, including conformer flexibility☆11Updated 3 years ago
- Python framework for multi-parameter optimization and evaluation of protein folding models☆16Updated 3 years ago
- PointNet for Deep Rank: protein-protein interaction scoring using neural networks☆9Updated 4 years ago
- Tutorial notebooks for SciFM24☆11Updated 7 months ago
- ☆11Updated 5 years ago
- MaxEnt code for fitting simulation outcomes/statistical models to observations☆16Updated 2 years ago
- Modeling and Bayesian analysis of fluorescence and absorbance assays.☆18Updated 3 years ago
- An experimental package for deep learning for molecular docking☆20Updated 4 years ago
- Explain a SMARTS using SmartsView (K. Schomburg and M. Rarey)☆12Updated 3 years ago
- Bayesian Active Learning for Optimization and Uncertainty Quantification with Applications to Protein Docking☆13Updated 3 years ago
- Python Bioinformatics Toolkit for CATH (Protein Classification Database @ UCL)☆14Updated last month
- Tools and routines to calculate distances between synthesis routes and to cluster them.☆20Updated 2 months ago
- Virtual screening and cheminformatics utilities☆14Updated 8 years ago
- A high-quality hand-curated logD7.4 dataset of 1,130 compounds☆17Updated 6 years ago
- OCEAN - Optimized Cross rEActivity estimatioN☆11Updated 4 years ago
- An efficient method for the conversion from internal to Cartesian coordinates that utilizes the platform-agnostic JAX Python library.☆15Updated 5 months ago
- JAXChem is a JAX-based deep learning library for complex and versatile chemical modeling☆79Updated 4 years ago
- Matrix factorization and deep learning for molecular property prediction☆12Updated 5 years ago
- Normal Mode Analysis for Macromolecules☆15Updated 7 years ago
- Python package for virtual screening of generated molecules using autodock-vina and tensorflow☆14Updated 3 years ago
- An experimental repo for experimenting with PyTorch models☆35Updated last year
- Reinforcement learning environments for drug discovery☆16Updated 2 months ago
- JupyterLab extension for py3Dmol☆19Updated 2 years ago
- ☆10Updated last year
- ☆11Updated 2 months ago
- GNN enabled surrogate modeling for chemical docking☆13Updated 2 years ago
- ☆15Updated 5 years ago
- Universal Transforming Geometric Network for protein structure prediction.☆8Updated 4 years ago