htalibart

mmap.ninja

Memory mapped numpy arrays of varying shapes

awesome-small-molecule-ml

A curated list of resources for machine learning for small-molecule drug discovery

RGCVAE

RGCVAE: Relational Graph Conditioned Variational Autoencoder for Molecule Design

cupy

NumPy & SciPy for GPU

OptiMol

Optimization of binding affinities in chemical space for drug discovery

awesome-python-chemistry

A curated list of Python packages related to chemistry

EDmodel

preliminary repository for EDmodel

MolVAE

Molecule Generation and Translation Framework. This is a joint PyTorch implementation of three papers in VAE-based molecule generation and translation including JTVAE, V-JTNN-GAN, HierVAE and HierVGNN

cddd

Implementation of the Paper "Learning Continuous and Data-Driven Molecular Descriptors by Translating Equivalent Chemical Representations" by Robin Winter, Floriane Montanari, Frank Noe and Djork-Arne Clevert.

DeepPurpose

A Deep Learning Toolkit for DTI, Drug Property, PPI, DDI, Protein Function Prediction (Bioinformatics)

Unipressed

Comprehensive Python client for the Uniprot REST API

proteinshake

Protein structure datasets for machine learning.

pytorch-template

PyTorch deep learning projects made easy.

alphafold-multistate

pymol-open-source

Open-source foundation of the user-sponsored PyMOL molecular visualization system.

pyhmmer

Cython bindings and Python interface to HMMER3.

molgpt

transformer-vae

A library for making Transformer Variational Autoencoders. (Extends the Huggingface/transformers library.)

ConfVAE-ICML21

An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming (ICML'21)

HEBO

Bayesian optimisation & Reinforcement Learning library developped by Huawei Noah's Ark Lab

Re-balanced-VAE

Code for our paper Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation.

Metric_MHG-VAE

molvecgen

Molecular vectorization and batch generation

ChemSpacE

latent-space-EBM-prior

autoencoder

Contains the AE architectures for 10.1002/minf.201700123

HighContentScreening

DrugEx

Deep learning toolkit for Drug Design with Pareto-based Multi-Objective optimization in Polypharmacology

AMPL

The ATOM Modeling PipeLine (AMPL) is an open-source, modular, extensible software pipeline for building and sharing models to advance in silico drug discovery.

molecule-generation

Implementation of MoLeR: a generative model of molecular graphs which supports scaffold-constrained generation