TorchDrug

A open-source machine learning platform for drug discovery developed at Mila-Quebec AI Institute

[TorchDrug @DrugTorch]

🚀 New version with the latest PyTorch support! Now you can run TorchDrug on your Apple M1/M2 chips. Thanks our awesome contributors to make this happen.
https://t.co/g8rRqcOyZx

[Michael Galkin @michael_galkin]

🎄It's 2023! In a new post, we provide an overview of Graph ML and its subfields (and hypothesize for '23), eg Generative Models, Physics, PDEs, Theory, KGs, Algorithmic Reasoning, and more!
With @ren_hongyu @zhu_zhaocheng @chrsmrrs and @jo_brandstetter

https://t.co/VDYo8vgUHh

[TorchDrug @DrugTorch]

TorchProtein unifies the representations of protein sequences and structures within a compact data structure. It provides a concise framework with off-the-shelf modules, including popular protein datasets, advanced protein sequence and structure models, and various protein tasks.

[TorchDrug @DrugTorch]

Tired of gluing up different solutions from various sources by hand? In the v0.2.0 major release, TorchDrug comes with a new family member TorchProtein, and has seamlessly adapted itself from small molecule research to macro one (the protein)!
👉https://t.co/PDanrCIHoj

[TorchDrug @DrugTorch]

TorchDrug 0.1.3 is released! This time we have W&B, the most popular tool for experiment tracking, integrated in TorchDrug. This version also introduces index reference to support fancy reference attributes. https://t.co/KkHqtrQjQv

[TorchDrug @DrugTorch]

Let us know what more features you expect for our W&B logger😀

[TorchDrug @DrugTorch]

TorchDrug now supports logging through Weights & Biases platform! With just one line of code, you can log all your training progress and evaluation results to W&B and track them in your browser. Thanks @wandb for this awesome integration.

https://t.co/LIcoHy9XMD

[TorchDrug @DrugTorch]

TorchDrug will be at #CDW21!

Join us to get hands-on experience using our platform, TorchDrug, to build machine learning models for drug discovery! We can't wait to see you there!

[Connected Data @Connected_Data]

Welcoming @zhu_zhaocheng to #CDW21

Lead developer & maintainer @DrugTorch #opensource #machinelearning platform for drug discovery developed at @Mila_Quebec #AI Institute

#Masterclass: TorchDrug: A powerful & flexible #ML platform for drug discovery

https://t.co/6Gr4nyFEvQ

[TorchDrug @DrugTorch]

We'd love to share our slides for the tutorial at IVADO @IVADO_Qc . If you're also interested in drug discovery, let us know your needs for better Torchdrug development. Join us now! Slide link👉:https://t.co/EPTOOtRmtR

[TorchDrug @DrugTorch]

Thanks the PyTorch community for recognition! TorchDrug is now a part of the PyTorch ecosystem.

[PyTorch @PyTorch]

Drug research and development is an arduous and expensive process. Using PyTorch, TorchDrug expedites the time and reduces the cost of developing drugs.
Read more below: https://t.co/tJTzFD6MDg

[TorchDrug @DrugTorch]

New release 0.1.2! Many updates include interactive Colab tutorials, new data structures and functions for edge pattern matching and batching of irregular structures, new datasets and many bug fixes. Checkout our release highlights👉: https://t.co/7bbCpe2mA8

[Mila - Institut québécois d'IA @Mila_Quebec]

Jian Tang (@tangjianpku) of Mila and @HEC_Montreal and his team launch #TorchDrug: an open-source ML platform aimed at making AI #drugdiscovery software and librairies freely available to the research community.

https://t.co/Ed0nR9xIkk