Downloads · 30 days
39
35% of all-time downloads
zhangtaolab/PlantHelixSeek-promoter_strength
PlantHelixSeek-promoter_strength is a text classification model from zhangtaolab. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
Fine-tuned checkpoint of PlantHelixSeek (470M parameters) for regression of core-promoter strength.
Downloads · 30 days
39
35% of all-time downloads
All-time downloads
112
Public
Parameters
471M
1.9 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.9 GB · 100%
From the Hugging Face model README
Fine-tuned checkpoint of PlantHelixSeek (470M parameters) for regression of core-promoter strength.
The checkpoint uses the released train.csv, dev.csv and test.csv splits of plant-multi-species-promoter-strength (58,179 / 6,825 / 7,154 sequences). The source of the dataset is described on its dataset card.
| Setting | Value |
|---|---|
| Base model | PlantHelixSeek-470M |
| Epochs | 3 |
| Learning rate | 2e-5 |
| Per-device batch size | 6 |
| Gradient accumulation | 2 |
| Effective batch size | 12 |
| Warm-up ratio | 0.1 |
| Weight decay | 0.01 |
| Scheduler | linear |
| Optimizer | AdamW (fused) |
| Precision | bf16 |
| Gradient clipping | 1.0 |
| Seed | 42 |
| Hardware | one NVIDIA GPU |
| Training loss | 0.800 |
| Training time | 0.4 h |
Metrics on the held-out dev.csv split (the split used for checkpoint selection).
| Metric | Value |
|---|---|
| spearmanr | 0.881 |
| r2 | 0.778 |
| mae | 0.600 |
| mse | 0.609 |
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model = AutoModelForSequenceClassification.from_pretrained(
"zhangtaolab/PlantHelixSeek-promoter_strength", trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(
"zhangtaolab/PlantHelixSeek-promoter_strength", trust_remote_code=True
)
Always pass trust_remote_code=True; the HelixSeek architecture is registered through the Hugging Face auto_map mechanism.
Wu Y, He Y, Chen L, Liu Y, Wang T, Zhao H, Zhang Y, Zhang T. PlantHelixSeek learns transferable genome representations that capture conserved genome grammar for functional interpretation across plant species. Molecular Plant, 2026. Manuscript MOLECULAR-PLANT-D-26-00999 (DOI to be assigned).
Dataset source: Mendoza-Revilla et al., Communications Biology 2024; Jores et al., Nature Plants 2021, doi:10.1038/s41477-021-00932-y.
CC-BY-NC 4.0 (research use; contact the authors for commercial licensing).