David McDonald's repositories
aizynthfinder
A tool for retrosynthetic planning
breaking_cycles_in_noisy_hierarchies
breaking cycles in noisy hierarchies
elephas
Distributed Deep learning with Keras & Spark
EXP2SL
EXP2SL: a Machine Learning Framework for Cell-Line Specific Synthetic Lethality Prediction
gcn
Implementation of Graph Convolutional Networks in TensorFlow
graph2gauss
Gaussian node embeddings. Implementation of "Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking".
graphvite
GraphVite: A General and High-performance Graph Embedding System
hgcn
Hyperbolic Graph Convolutional Networks in PyTorch.
HNEMA
Improving Therapeutic Synergy Score Predictions with Adverse Effects using Multi-task Heterogeneous Network Embedding
HOB
Machine learning model for predicting Human Oral Bioavailability
HyperA
Started as a Team Project for CS690D at UMass Amherst, now turning into pytorch implementation of hyperbolic neural networks using Poincare Ball model. [Final report](https://github.com/dhruvdcoder/HyperA/tree/master/report)
hyperbolic_nn
Source code for the paper "Hyperbolic Neural Networks", https://arxiv.org/abs/1805.09112
hyperbolics
Hyperbolic Embeddings
KG4SL
Synthetic lethality (SL) is a promising gold mine for the discovery of anti-cancer drug targets. KG4SL is the first graph neural network (GNN)-based model that uses knowledge graph for SL prediction.
LigTMap
LigTMap currently supports prediction for 17 protein target classes that include 6000+ protein targets.
LINE
LINE: Large-scale information network embedding
mim
Exploratory code for preparation of ArangoDB graph database
Natural-product-function
scripts for predicting natural product activity from biosynthetic gene cluster sequences
Off-target-P-ML
This repository contains the necessary scripts to derive off-target models through (1) A neural network framework based on Keras and Tensorflow (2)An autmomated machine learning framework based on AutoGluon
OpenANE
OpenANE: the first Open source framework specialized in Attributed Network Embedding (ANE)
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 provide an ensemble of pre-trained models which can readily be used for quickly generating rank-ordered predictions of compound affinity relative to a given target. DISCLAIMER: Compounds predicted by PharML.Bind should not be used without consulting a doctor or pharmacist - all results should be considered unverified and used only as a starting point for further investigation. Use at your own risk!
poincare-embeddings
PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"
PyRMD
AI-powered Virtual Screening