Add Colab badge + demo link
Browse files
README.md
CHANGED
|
@@ -1,3 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# SF-Cluster (workshop OSS release)
|
| 2 |
|
| 3 |
Frustration-guided MSA subset builders for AlphaFold2 multi-conformer
|
|
|
|
| 1 |
+
[](https://colab.research.google.com/github/ChatterjeeLab/SF-Cluster/blob/main/examples/SF_Cluster_Demo.ipynb)
|
| 2 |
+
|
| 3 |
+
> **Or run from Hugging Face:** open <https://colab.research.google.com/> → *File* → *Open notebook* → *URL* tab → paste
|
| 4 |
+
> `https://huggingface.co/ChatterjeeLab/SF-Cluster/resolve/main/examples/SF_Cluster_Demo.ipynb`
|
| 5 |
+
|
| 6 |
+
## Demo
|
| 7 |
+
|
| 8 |
+
A self-contained, CPU-only Colab notebook is provided at
|
| 9 |
+
[`examples/SF_Cluster_Demo.ipynb`](examples/SF_Cluster_Demo.ipynb). It installs the
|
| 10 |
+
package, downloads a small KaiB demo bundle (filtered MSA + FrustrAI-Seq FI matrix,
|
| 11 |
+
~200 KB), builds 12 mosaic and 12 gradient subsets, visualises the contrast-score
|
| 12 |
+
distribution and per-subset means, and writes A3M files ready for AF2. Expected
|
| 13 |
+
end-to-end runtime on a free Colab CPU instance: **~2 minutes**.
|
| 14 |
+
|
| 15 |
# SF-Cluster (workshop OSS release)
|
| 16 |
|
| 17 |
Frustration-guided MSA subset builders for AlphaFold2 multi-conformer
|