use public links in README

README.md

@@ -1,7 +1,6 @@
 <p align="center">
-  <img src="docs/assets/banner.png" alt="novae_banner" width="100%"/>
+  <img src="https://raw.githubusercontent.com/MICS-Lab/novae/main/docs/assets/banner.png" alt="novae_banner" width="100%"/>
 </p>
-<!-- TODO: when it becomes public: https://raw.githubusercontent.com/MICS-Lab/novae/main/docs/assets/banner.png -->
 
 <div align="center">
 
@@ -20,14 +19,16 @@
   💫 Graph-based foundation model for spatial transcriptomics data
 </b></i></p>
 
+Novae is a deep learning model for spatial domain assignments of spatial transcriptomics data (at both single-cell or spot resolution). It works across multiple gene panels, tissues, and technologies. Novae offers several additional features, including: (i) native batch-effect correction, (ii) analysis of spatially variable genes and pathways, and (iii) architecture analysis of tissue slides.
+
 ## Documentation
 
 Check [Novae's documentation](https://mics-lab.github.io/novae/) to get started. It contains installation explanations, API details, and tutorials.
 
 ## Overview
 
 <p align="center">
-  <img src="docs/assets/Figure1.png" alt="novae_overview" width="100%"/>
+  <img src="https://raw.githubusercontent.com/MICS-Lab/novae/main/docs/assets/Figure1.png" alt="novae_overview" width="100%"/>
 </p>
 
 > **(a)** Novae was trained on a large dataset, and is shared on [Hugging Face Hub](https://huggingface.co/collections/MICS-Lab/novae-669cdf1754729d168a69f6bd). **(b)** Illustration of the main tasks and properties of Novae. **(c)** Illustration of the method behing Novae (self-supervision on graphs, adapted from [SwAV](https://arxiv.org/abs/2006.09882)).

docs/index.md

@@ -2,4 +2,25 @@
   <img src="./assets/logo_white.png" alt="novae_logo" width="300px"/>
 </p>
 
-TODO
+<p align="center"><b><i>
+  💫 Graph-based foundation model for spatial transcriptomics data
+</b></i></p>
+
+Novae is a deep learning model for spatial domain assignments of spatial transcriptomics data (at both single-cell or spot resolution). It works across multiple gene panels, tissues, and technologies. Novae offers several additional features, including: (i) native batch-effect correction, (ii) analysis of spatially variable genes and pathways, and (iii) architecture analysis of tissue slides.
+
+## Overview
+
+<p align="center">
+  <img src="https://raw.githubusercontent.com/MICS-Lab/novae/main/docs/assets/Figure1.png" alt="novae_overview" width="100%"/>
+</p>
+
+> **(a)** Novae was trained on a large dataset, and is shared on [Hugging Face Hub](https://huggingface.co/collections/MICS-Lab/novae-669cdf1754729d168a69f6bd). **(b)** Illustration of the main tasks and properties of Novae. **(c)** Illustration of the method behing Novae (self-supervision on graphs, adapted from [SwAV](https://arxiv.org/abs/2006.09882)).
+
+
+## Why using Novae
+
+- It is already pretrained on a large dataset (pan human/mouse tissues, brain, ...). Therefore, you can compute spatial domains in a zero-shot manner (i.e., without fine-tuning).
+- It has been developed to find consistent domain across many slides. This also work if you have different technologies (e.g., MERSCOPE/Xenium) and multiple gene panels.
+- You can natively correct batch effect, without using external tools.
+- After inference, the spatial domain assignment is super fast, allowing to try multiple resolutions easily.
+- It supports many downstream tasks, all included inside one framework.

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "novae"
-version = "0.0.2"
+version = "0.0.5"
 description = "Graph-based foundation model for spatial transcriptomics data"
 documentation = "https://mics-lab.github.io/novae/"
 homepage = "https://mics-lab.github.io/novae/"