Passion4ever/SiamProm
Passion4ever/SiamProm has 30 GitHub stars and 3 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-15 20:33 UTC. Last push 2026-09-29.
Measured star growth
- in 24h
- 0
- in 7 days
- Collecting history
- in 15 days
- Collecting history
- in 1 month
- Collecting history
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
About
Cyanobacterial promoter identification with Siamese network-based contrastive learning
Machine LearningREADME.md
Original🧬 SiamProm
Cyanobacterial promoter identification with Siamese network-based contrastive learning

Novel non-promoter generation · Siamese contrastive learning
Usage
Google Colab
Predict promoters from pasted or uploaded 81 bp sequences on a free Colab GPU, no installation needed.
Local
Environment
conda env create -f env_SiamProm.yaml
conda activate SiamProm
Inference
python predict.py --checkpoint weights/siamprom_phantom.pth --fasta seqs.fasta --output results.csv
Arguments
| Argument | Description | Default |
|---|---|---|
--checkpoint |
Model checkpoint path | — |
--fasta |
Input FASTA file (81bp sequences) | — |
--output |
Output CSV path | — |
--device |
cpu or GPU index |
0 |
--batch-size |
Batch size | 256 |
--threshold |
Classification threshold | 0.5 |
The output CSV contains columns: name, sequence, prediction, confidence.
Train from scratch
python train.py sampling=phantom
Options
Optional values for the parameter sampling are phantom(default), random, cds, and partial.
For more detailed instructions on parameter management and configuration usage, please refer to the Hydra documentation.
Citation
@article{yang2024recognition,
title = {Recognition of cyanobacteria promoters via Siamese network-based contrastive learning under novel non-promoter generation},
author = {Yang, Guang and Li, Jianing and Hu, Jinlu and Shi, Jian-Yu},
journal = {Briefings in Bioinformatics},
volume = {25},
number = {3},
pages = {bbae193},
year = {2024},
doi = {10.1093/bib/bbae193},
}