| | --- |
| | library_name: pytorch |
| | framework: pytorch |
| | tags: |
| | - pytorch |
| | - pytorch-lightning |
| | - bioinformatics |
| | - rna-binding-proteins |
| | - explainability |
| | - alternative-splicing |
| | - deep-learning |
| | license: mit |
| | --- |
| | |
| | # DeepRBP Predictor (pretrained) |
| |
|
| | This repository provides a **pretrained DeepRBP predictor model**, a deep learning framework designed to infer **RNA-binding protein (RBP)–transcript and RBP–gene regulatory relationships** from expression data. |
| |
|
| | DeepRBP was introduced in the following preprint: |
| |
|
| | > **DeepRBP: A deep neural network for inferring splicing regulation** |
| | > https://doi.org/10.1101/2024.04.11.589004 |
| |
|
| | The model is intended to be used **directly for inference and explainability**, without retraining. |
| |
|
| | --- |
| |
|
| | ## Model overview |
| |
|
| | DeepRBP is composed of two conceptual stages: |
| |
|
| | 1. **Prediction stage** |
| | A neural network predicts transcript abundances from: |
| | - RBP expression |
| | - Gene expression |
| |
|
| | 2. **Explainability stage** |
| | Feature attribution methods (e.g. DeepLIFT) are applied on the trained predictor to compute: |
| | - Transcript × RBP (TxRBP) scores |
| | - Gene × RBP (GxRBP) scores |
| |
|
| | This repository contains **only the pretrained predictor and its required preprocessing artifacts**. |
| |
|
| | --- |
| |
|
| | ## Files in this repository |
| |
|
| | ⚠️ **All files are required for correct inference and explainability.** |
| |
|
| | | File | Description | |
| | |-----|-------------| |
| | | `model.ckpt` | PyTorch Lightning checkpoint of the pretrained DeepRBP predictor | |
| | | `scaler.joblib` | Fitted input scaler used during model training | |
| | | `sigma.npy` | Scaling parameter required to reconstruct transcript abundance values | |
| |
|
| | The scaler and sigma are **part of the trained model state** and must be used together with the checkpoint. |
| |
|
| | --- |
| |
|
| | ## Intended use |
| |
|
| | This pretrained model is intended for: |
| |
|
| | - Computing transcript abundance predictions |
| | - Running explainability analyses (e.g. DeepLIFT-based attribution) |
| | - Identifying candidate RBP–transcript and RBP–gene regulatory relationships |
| | - Downstream biological interpretation and hypothesis generation |
| |
|
| | Typical applications include: |
| | - Cancer transcriptomics (e.g. TCGA) |
| | - Perturbation studies (e.g. RBP knockdowns) |
| | - Comparative regulatory analyses across conditions |
| |
|
| | --- |
| |
|
| | ## Usage |
| |
|
| | This repository **does not provide a standalone inference script**. |
| |
|
| | Please refer to the **main DeepRBP code repository** for: |
| | - Data preprocessing |
| | - Model loading |
| | - Running prediction and explainability pipelines |
| |
|
| | 👉 **Main repository:** |
| | https://github.com/ML4BM-Lab/DeepRBP |
| |
|
| | The main repository contains: |
| | - End-to-end examples |
| | - Command-line interfaces |
| | - Explainability workflows |
| | - Validation pipelines |
| |
|
| | --- |
| |
|
| | ## Reproducibility notes |
| |
|
| | - The model was trained on public datasets (TCGA, GTEx and related resources). |
| | - The provided scaler and sigma ensure: |
| | - Consistent input normalization |
| | - Comparable predictions and explainability scores across users |
| | - Using a different scaler or recomputing normalization **will break comparability**. |
| |
|
| | --- |
| |
|
| | ## Limitations |
| |
|
| | - The model was trained on bulk RNA-seq data and may not generalize to: |
| | - Single-cell RNA-seq |
| | - Extremely low-coverage datasets |
| | - Predictions represent **associations**, not direct causal regulation. |
| | - Experimental validation is required before biological conclusions. |
| |
|
| | --- |
| |
|
| | ## License |
| |
|
| | This model is released under the **MIT License**. |
| |
|
| | You are free to use, modify and redistribute it, provided that the license and copyright notice are preserved. |
| |
|
| | --- |
| |
|
| | ## Citation |
| |
|
| | If you use DeepRBP in your work, please cite: |
| |
|
| | DeepRBP: A deep neural network for inferring splicing regulation |
| | bioRxiv (2024) |
| | https://doi.org/10.1101/2024.04.11.589004 |
| |
|
