Skip to content

Commit

Permalink
Update README.md (#132)
Browse files Browse the repository at this point in the history
  • Loading branch information
ZiyaoLi authored Nov 30, 2023
1 parent 595c0c3 commit 019732d
Showing 1 changed file with 13 additions and 8 deletions.
21 changes: 13 additions & 8 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,19 @@

[[UF-Symmetry bioRxiv](https://www.biorxiv.org/content/10.1101/2022.08.30.505833)]


---

## NEWEST in Uni-Fold

[2023-09-21] Quick try of Uni-Fold at [Bohrium Apps](https://app.bohrium.dp.tech/uni-fold/)! Check [here](https://github.com/dptech-corp/Uni-Fold/issues/131) for details.

[2022-11-15] We released the full dataset used to train Uni-Fold.

[2022-09-06] We released the code of Uni-Fold Symmetry (UF-Symmetry), a fast solution to fold large symmetric protein complexes. The details of UF-Symmetry can be found in [bioRxiv: Uni-Fold Symmetry: Harnessing Symmetry in Folding Large Protein Complexes](https://doi.org/10.1101/2022.08.30.505833). The code of UF-Symmetry is concentrated in the folder [`unifold/symmetry`](./unifold/symmetry/).

---

We proudly present Uni-Fold as a thoroughly open-source platform for developing protein models beyond [AlphaFold](https://github.com/deepmind/alphafold/). Uni-Fold introduces the following features:

- Reimplemented AlphaFold and AlphaFold-Multimer models in PyTorch framework. **This is currently the first (if any else) open-source repository that supports training AlphaFold-Multimer.**
Expand Down Expand Up @@ -44,14 +57,6 @@ Figure 3. Uni-Fold is to our knowledge the fastest implemetation of AlphaFold.

The name Uni-Fold is inherited from our previous repository, [Uni-Fold-JAX](https://github.com/dptech-corp/Uni-Fold-jax). First released on Dec 8 2021, Uni-Fold-JAX was the first open-source project (with training scripts) that successfully reproduced the from-scratch training of AlphaFold. Until recently, Uni-Fold-JAX is still the only project that supports training of the original AlphaFold implementation in JAX framework. Due to efficiency and collaboration considerations, we moved from JAX to PyTorch on Jan 2022, based on which we further developed the multimer models.

---

## NEWEST in Uni-Fold

[2022-11-15] We released the full dataset used to train Uni-Fold.

[2022-09-06] We released the code of Uni-Fold Symmetry (UF-Symmetry), a fast solution to fold large symmetric protein complexes. The details of UF-Symmetry can be found in [bioRxiv: Uni-Fold Symmetry: Harnessing Symmetry in Folding Large Protein Complexes](https://doi.org/10.1101/2022.08.30.505833). The code of UF-Symmetry is concentrated in the folder [`unifold/symmetry`](./unifold/symmetry/).

![case](./img/uf-symmetry-effect.gif)
<center>
<small>
Expand Down

0 comments on commit 019732d

Please sign in to comment.