Instructions to use paolomanlapaz/rispice-1000bp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use paolomanlapaz/rispice-1000bp with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("models/base/bpe5") model = PeftModel.from_pretrained(base_model, "paolomanlapaz/rispice-1000bp") - Notebooks
- Google Colab
- Kaggle
RiSPICE LoRA Adapter (1000 bp)
This repository provides the 1000 bp LoRA adapter for RiSPICE (Rice SNP Prioritization Integrating Chromatin Effects), fine-tuned on top of DNABERT-2-117M for multi-label prediction of rice chromatin features from DNA sequences.
Model Summary
- Method: RiSPICE (Rice SNP Prioritization Integrating Chromatin Effects)
- Base Model:
paolomanlapaz/rispice-base - Adapter Type: PEFT / LoRA
- Sequence Length: 1000 bp
- Task: Multi-label Chromatin Feature Prediction (
num_labels=12)
Feature Order
The model outputs logits/probabilities corresponding to the following 12 chromatin features in exact order (Index 0 to 11):
| Index | Feature |
|---|---|
0 |
ATAC-Seq |
1 |
H3K4ac |
2 |
H3K4me2 |
3 |
H3K4me3 |
4 |
H3K9ac |
5 |
H3K9me1 |
6 |
H3K23ac |
7 |
H3K27ac |
8 |
H3K27me3 |
9 |
H3K36me3 |
10 |
H4K12ac |
11 |
H4K16ac |
Usage & Pipeline Code
For dataset preprocessing, model loading, and batch inference scripts, please refer to our GitHub repository:
๐ bioinfodlsu/rispice
- Downloads last month
- 21
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for paolomanlapaz/rispice-1000bp
Base model
zhihan1996/DNABERT-2-117M