# TorchDrug equivalence in Julia?

**URL:** <https://discourse.julialang.org/t/torchdrug-equivalence-in-julia/78910>\
**Category:** Machine Learning\
**Created:** [April 2, 2022, 2:52pm UTC](https://discourse.julialang.org/t/torchdrug-equivalence-in-julia/78910 "2022-04-02T14:52:35Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![DoktorMike](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/doktormike/32/2736_2.png) [@DoktorMike](https://discourse.julialang.org/u/DoktorMike)\
**Post date:** [April 2, 2022, 2:52pm UTC](https://discourse.julialang.org/t/torchdrug-equivalence-in-julia/78910/1 "2022-04-02T14:52:35Z")

</div>

I ran into TorchDrug a few months ago and it looks really useful. Is anyone in this community doing drug discovery using Julia? My question is mainly due to thinking about how useful/hard it would be to create a community around this topic in Julia. Any pointers would be greatly appreciated. I suspect that GraphNeuralNetworks.jl and by extension Flux will be the foundation for such a community / software.

---

<div class="post-metadata">

**Author:** ![nilshg](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/nilshg/32/2283_2.png) [@nilshg](https://discourse.julialang.org/u/nilshg)\
**Post date:** [April 2, 2022, 3:37pm UTC](https://discourse.julialang.org/t/torchdrug-equivalence-in-julia/78910/2 "2022-04-02T15:37:08Z")

</div>

Well

[https://juliacomputing.com/products/pumas/](https://juliacomputing.com/products/pumas/)

Is afaik the most successful product of Julia computing thus far, and given that it claims to cover the entire development pipeline it’s probably fair to say that yes, there are people doing this in Julia.

---

<div class="post-metadata">

**Author:** ![ChrisRackauckas](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/chrisrackauckas/32/77_2.png) [@ChrisRackauckas](https://discourse.julialang.org/u/ChrisRackauckas)\
**Post date:** [April 2, 2022, 4:00pm UTC](https://discourse.julialang.org/t/torchdrug-equivalence-in-julia/78910/3 "2022-04-02T16:00:21Z")

</div>

Pumas doesn’t do drug discovery, it does drug development. Those are different parts of the process with different tools.

For similar drug discovery stuff there’s Chemellia:

[https://github.com/Chemellia](https://github.com/Chemellia)

And that’s where you’ll find all of the stuff like atomic graph nets and graph transformers.

[https://github.com/Chemellia/AtomicGraphNets.jl](https://github.com/Chemellia/AtomicGraphNets.jl)

[https://github.com/Chemellia/GraphTransformer.jl](https://github.com/Chemellia/GraphTransformer.jl)

These build on the GeometricFlux.jl tool for graph neural networks.

[https://github.com/FluxML/GeometricFlux.jl](https://github.com/FluxML/GeometricFlux.jl)

---

<div class="post-metadata">

**Author:** ![DoktorMike](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/doktormike/32/2736_2.png) [@DoktorMike](https://discourse.julialang.org/u/DoktorMike)\
**Post date:** [April 2, 2022, 7:24pm UTC](https://discourse.julialang.org/t/torchdrug-equivalence-in-julia/78910/4 "2022-04-02T19:24:52Z")

</div>

Great, thanks for the repos and links. I’ll dive in and learn more about them. 🙏🏻