Skip to content

Commit ebf308d

Browse files
committed
docs: Add citation, web-service URL, fix parameter typo
1 parent d632891 commit ebf308d

File tree

1 file changed

+51
-26
lines changed

1 file changed

+51
-26
lines changed

README.md

+51-26
Original file line numberDiff line numberDiff line change
@@ -1,12 +1,32 @@
11
# ProtSpace
22

3-
ProtSpace is a visualization tool for exploring protein embeddings or similarity matrix along their 3D protein structures. It allows users to interactively visualize high-dimensional protein language model data in 2D or 3D space, color-code proteins based on various features, and view protein structures when available.
3+
ProtSpace is a visualization tool for exploring **protein embeddings** or **similarity matrix** along their 3D protein structures. It allows users to interactively visualize high-dimensional protein language model data in 2D or 3D space, color-code proteins based on various features, and view protein structures when available.
4+
5+
## Web Interface
6+
Try ProtSpace directly in your browser without installation:
7+
https://protspace.rostlab.org/
8+
9+
## Quick Start with Google Colab
10+
11+
Try ProtSpace instantly using our Google Colab notebooks:
12+
13+
**Note**: Some Google Colab functionalities may not work properly in Safari browsers. For the best experience, we recommend using Chrome or Firefox.
14+
15+
1. **Explore Pre-computed Visualizations**:
16+
[![Open Explorer In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/tsenoner/protspace/blob/main/examples/notebook/Explore_ProtSpace.ipynb)
17+
18+
2. **Generate Protein Embeddings**:
19+
[![Open Embeddings In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/tsenoner/protspace/blob/main/examples/notebook/ClickThrough_GenerateEmbeddings.ipynb)
20+
21+
3. **Full Pipeline Demo**:
22+
[![Open Pipeline In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/tsenoner/protspace/blob/main/examples/notebook/Run_ProtSpace.ipynb)
423

524
## Table of Contents
625

726
- [ProtSpace](#protspace)
8-
- [Table of Contents](#table-of-contents)
27+
- [Web Interface](#web-interface)
928
- [Quick Start with Google Colab](#quick-start-with-google-colab)
29+
- [Table of Contents](#table-of-contents)
1030
- [Example Outputs](#example-outputs)
1131
- [2D Scatter Plot (SVG)](#2d-scatter-plot-svg)
1232
- [3D Interactive Plot](#3d-interactive-plot)
@@ -23,21 +43,7 @@ ProtSpace is a visualization tool for exploring protein embeddings or similarity
2343
- [File Formats](#file-formats)
2444
- [Input](#input)
2545
- [Output](#output)
26-
27-
## Quick Start with Google Colab
28-
29-
Try ProtSpace instantly using our Google Colab notebooks:
30-
31-
**Note**: Some Google Colab functionalities may not work properly in Safari browsers. For the best experience, we recommend using Chrome or Firefox.
32-
33-
1. **Explore Pre-computed Visualizations**:
34-
[![Open Explorer In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/tsenoner/protspace/blob/main/examples/notebook/Explore_ProtSpace.ipynb)
35-
36-
2. **Generate Protein Embeddings**:
37-
[![Open Embeddings In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/tsenoner/protspace/blob/main/examples/notebook/ClickThrough_GenerateEmbeddings.ipynb)
38-
39-
3. **Full Pipeline Demo**:
40-
[![Open Pipeline In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/tsenoner/protspace/blob/main/examples/notebook/Run_ProtSpace.ipynb)
46+
- [Citation](#citation)
4147

4248
## Example Outputs
4349

@@ -66,7 +72,7 @@ protspace-json -i embeddings.h5 -m features.csv -o output.json --methods pca3 um
6672
### Running protspace
6773

6874
```bash
69-
protspace output.json [--pdb_zip pdb_files.zip] [--port 8050]
75+
protspace --json output.json [--pdb_zip pdb_files.zip] [--port 8050]
7076
```
7177

7278
Access the interface at `http://localhost:8050`
@@ -82,7 +88,7 @@ Access the interface at `http://localhost:8050`
8288
- Feature-based coloring and marker styling
8389
- Protein structure visualization (with PDB files)
8490
- Search and highlight functionality
85-
- High-quality plot exports
91+
- High-quality plot exports (SVG for 2D, interactive HTML for 3D)
8692
- Responsive web interface
8793

8894
## Data Preparation
@@ -98,6 +104,7 @@ The `protspace-json` command supports:
98104

99105
### Optional Arguments
100106

107+
- `--delimiter`: Specify delimiter for metadata file (default: comma)
101108
- `--custom_names`: Custom projection names (e.g., pca2=PCA_2D)
102109
- `--verbose`: Increase output verbosity
103110

@@ -115,6 +122,7 @@ The `protspace-json` command supports:
115122
- MDS:
116123
- `--n_init`: Number of initializations (default: 4)
117124
- `--max_iter`: Maximum iterations (default: 300)
125+
- `--eps`: Convergence tolerance (default: 1e-3)
118126

119127
## Custom Feature Styling
120128

@@ -142,20 +150,37 @@ Available shapes: circle, circle-open, cross, diamond, diamond-open, square, squ
142150
### Input
143151

144152
1. **Embeddings/Similarity**
145-
- HDF5 (.h5) for embeddings
146-
- CSV for similarity matrix
153+
- HDF5 (.h5) for embeddings
154+
- CSV for similarity matrix
147155

148156
2. **Metadata**
149-
- CSV with mandatory 'identifier' column matching IDs in embeddings/similarity data
150-
- Additional columns for features
157+
- CSV with mandatory 'identifier' column matching IDs in embeddings/similarity data
158+
- Additional columns for features
151159

152160
3. **Structures**
153-
- ZIP containing PDB/CIF files
154-
- Filenames match identifiers (dots replaced with underscores)
161+
- ZIP containing PDB/CIF files
162+
- Filenames match identifiers (dots replaced with underscores)
155163

156164
### Output
157165

158166
- JSON containing:
159167
- Protein features
160168
- Projection coordinates
161-
- Visualization state (colors, shapes)
169+
- Visualization state (colors, shapes)
170+
171+
## Citation
172+
173+
If you use ProtSpace in your research, please cite:
174+
175+
```bibtex
176+
@article{SENONER2025168940,
177+
title = {ProtSpace: A Tool for Visualizing Protein Space},
178+
journal = {Journal of Molecular Biology},
179+
pages = {168940},
180+
year = {2025},
181+
issn = {0022-2836},
182+
doi = {https://doi.org/10.1016/j.jmb.2025.168940},
183+
url = {https://www.sciencedirect.com/science/article/pii/S0022283625000063},
184+
author = {Tobias Senoner and Tobias Olenyi and Michael Heinzinger and Anton Spannagl and George Bouras and Burkhard Rost and Ivan Koludarov}
185+
}
186+
```

0 commit comments

Comments
 (0)