Update README.md

README.md

@@ -4,9 +4,9 @@ license: cc-by-nc-nd-4.0
 
 ![Overview of PeptiVerse](peptiverse-cover.png)
 
-# PeptiVerse 🧬🌌
+# PeptiVerse: A Unified Platform for Therapeutic Peptide Property Prediction 🧬🌌
 
-A collection of machine learning predictors for canonical and non-canonical peptide property prediction using sequence and SMILES representations. 🧬 PeptiVerse 🌌 enables evaluation of key biophysical and therapeutic properties of peptides for property-optimized generation.
+This is the repository for [PeptiVerse: A Unified Platform for Therapeutic Peptide Property Prediction](https://www.biorxiv.org/content/10.64898/2025.12.31.697180), a collection of machine learning predictors for canonical and non-canonical peptide property prediction using sequence and SMILES representations. 🧬 PeptiVerse 🌌 enables evaluation of key biophysical and therapeutic properties of peptides for property-optimized generation.
 
 ## Table of Contents
 
@@ -26,7 +26,7 @@ A collection of machine learning predictors for canonical and non-canonical pept
 - [Troubleshooting](#troubleshooting-)
 - [Citation](#citation-)
 
-## Quick start 🌟
+## Quick Start
 
 ```bash
 # Clone repository
@@ -38,13 +38,13 @@ pip install -r requirements.txt
 # Run inference
 python inference.py
 ```
-## Installation 🌟
-### Minimal Setup 🚀
+## Installation
+### Minimal Setup
 - Easy start-up environment (using transformers, xgboost models)
 ```bash
 pip install -r requirements.txt
 ```
-### Full Setup 🚀
+### Full Setup
 - Additional access to trained SVM and ElastNet models requires installation of `RAPIDS cuML`, with instructions available from their official [github page](https://github.com/rapidsai/cuml) (**CUDA-capable GPU required**).
 - Optional: pre-compiled Singularity/Apptainer environment (7.52G) is available at [Google drive](https://drive.google.com/file/d/1RJQ9HK0_gsPOhRo5H5ZmH_MYcpJqQD7e/view?usp=sharing) with everything you need (still need CUDA/GPU to load cuML models).
     ```
@@ -54,7 +54,7 @@ pip install -r requirements.txt
     # run inference (see below)
     apptainer exec peptiverse.sif python inference.py
     ```
-## Repository structure 🌟
+## Repository Structure
 This repo contains important large files for [PeptiVerse](https://huggingface.co/spaces/ChatterjeeLab/PeptiVerse), an interactive app for peptide property prediction. [Paper link.](https://www.biorxiv.org/content/10.64898/2025.12.31.697180v1)
 
 ```
@@ -75,7 +75,7 @@ PeptiVerse/
 └── requirements.txt           # Python dependencies
 ```
 
-## Training Data Collection 🌟
+## Training Data Collection
 
 <table>
   <caption><strong>Data distribution.</strong> Classification tasks report counts for class 0/1; regression tasks report total sample size (N).</caption>
@@ -158,7 +158,7 @@ PeptiVerse/
 </table>
 
 
-## Best Model List 🌟
+## Best Model List
 
 ### Full model set (cuML-enabled)
 | Property                    | Best Model (Sequence) | Best Model (SMILES) | Task Type   | Threshold (Sequence) | Threshold (SMILES) |
@@ -190,7 +190,7 @@ PeptiVerse/
 >Note: Models marked as SVM or ENET are replaced with XGB as these models are not currently supported in the deployment environment without cuML setups. *xgb_wt_log* indicated log-scaled transformation of time during training.
 
 
-## Usage 🌟
+## Usage
 
 ### Local Application Hosting
 - Host the [PeptiVerse UI](https://huggingface.co/spaces/ChatterjeeLab/PeptiVerse) locally with your own resources. 
@@ -263,7 +263,7 @@ print("Downloaded to:", local_dir)
             length: `int` (=L);
     
 
-### Quick inference by property per model
+### Quick Inference By Property Per Model
 ```python
 from inference import PeptiVersePredictor
 
@@ -352,7 +352,7 @@ print(out)
 
 ```
 
-## Interpretation 🌟 
+## Interpretation
 
 You can also find the same description in the paper or in the PeptiVerse app `Documentation` tab.
 
@@ -414,7 +414,7 @@ Predicts peptide-protein binding affinity. Requires both peptide and target prot
     - A difference of 1 unit in score corresponds to an approximately tenfold change in binding affinity.<br>
 
 
-## Model Architecture 🌟
+## Model Architecture
 
 - **Sequence Embeddings:** [ESM-2 650M model](https://huggingface.co/facebook/esm2_t33_650M_UR50D) / [PeptideCLM model](https://huggingface.co/aaronfeller/PeptideCLM-23M-all). Foundational embeddings are frozen.
 - **XGBoost Model:** Gradient boosting on pooled embedding features for efficient, high-performance prediction.
@@ -423,7 +423,7 @@ Predicts peptide-protein binding affinity. Requires both peptide and target prot
 - **SVR Model:** Support Vector Regression applied to pooled embeddings, providing a kernel-based, nonparametric regression baseline that is robust on smaller or noisy datasets.
 - **Others:** SVM and Elastic Nets were trained with [RAPIDS cuML](https://github.com/rapidsai/cuml), which requires a CUDA environment and is therefore not supported in the web app. Model checkpoints remain available in the Hugging Face repository.
 
-## Troubleshooting 🌟
+## Troubleshooting
 
 ### LFS Download Issues
 
@@ -438,7 +438,7 @@ huggingface-cli download ChatterjeeLab/PeptiVerse \
 ### TODOs
 Bug loading transformer half-life model now, will fix soon.
 
-## Citation 🌟
+## Citation
 
 If you find this repository helpful for your publications, please consider citing our paper: