benanbardak

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

gpt2-dialogue-generation-pytorch

The PyTorch implementation of fine-tuning the GPT-2(Generative Pre-trained Transformer 2) for dialogue generation.

Twitter-API-v2-sample-code

Sample code for the Twitter API v2 endpoints

twitter-python-ads-sdk

A Twitter supported and maintained Ads API SDK for Python.

GraphINVENT

Graph neural networks for molecular design.

ProLIF

Interaction Fingerprints for protein-ligand complexes and more

tf_geometric

Efficient and Friendly Graph Neural Network Library for TensorFlow 1.x and 2.x

Data-Science--Cheat-Sheet

Cheat Sheets

stellargraph

StellarGraph - Machine Learning on Graphs

Data-Science-Notes

数据科学的笔记以及资料搜集

protein-vae

Variational autoencoder for protein sequences - add metal binding sites and generate sequences for novel topologies

gcWGAN

Guided Conditional Wasserstein GAN for De Novo Protein Design

spektral

Graph Neural Networks with Keras and Tensorflow 2.

Apollo1060

Data and models (with prediction scripts) used in publications related to Apollo1060 platform

graph-neural-networks-for-drug-discovery

Text-Generation-using-Bidirectional-LSTM-and-Doc2Vec-models

Text Generation using Bidirectional LSTM and Doc2Vec models

reinvent-randomized

Recurrent Neural Network using randomized SMILES strings to generate molecules

ReLeaSE

Deep Reinforcement Learning for de-novo Drug Design

DataScienceCourse

This holds iPython notebooks and lecture slides for the Intro to Data Science Master's course I teach at NYU.

ARAE_SMILES

CH485---Artificial-Intelligence-and-Chemistry

CH485 - Artificial Intelligence and Chemistry

frame-predict-VAE-LSTM

Predicting image frames using autoencoder and LSTM

rdkit

The official sources for the RDKit library

molenc

MolEnc: a molecular encoder using rdkit and OCaml.

map4

The MinHashed Atom Pair fingerprint of radius 2

qhoptim

Implementations of quasi-hyperbolic optimization algorithms.

keras-adamw

Keras/TF implementation of AdamW, SGDW, NadamW, Warm Restarts, and Learning Rate multipliers

diffGrad

diffGrad: An Optimization Method for Convolutional Neural Networks

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.

dgl

Python package built to ease deep learning on graph, on top of existing DL frameworks.