📘 design_of_promoter_logic

This repository provides an AI tool to propose transcription factor binding site (TFBS) recombination with a promoter sequence to alter its original logic.

---

🚀 Getting Started

Follow the steps below to set up your environment and run the code.

1. Clone the repository

git clone https://github.com/CDS-UWB/design_of_promoter_logic.git
cd design_of_promoter_logic

2. Create and activate a virtual environment

We recommend using conda:

conda create -n myenv python=3.10.14
conda activate myenv

3. Install dependencies

pip install -r requirements.txt

4. Run the notebook

Open the notebook with:

jupyter notebook propose_recombination.ipynb

---

🧬 Required Inputs

Before running the notebook, set the following variables in the appropriate cell:

• SEQUENCE_PROMOTER: Promoter DNA sequence
  Note: If the sequence is longer than 400bp, it will be truncated to the last 400bp.

• SEQUENCE_QUERY: TFBS sequence (length 8–64bp)

• NAME_PROMOTER: Name or ID of the promoter

• NAME_QUERY: Name or ID of the TFBS

---

📎 Example

SEQUENCE_PROMOTER = "ACTG..."  # full DNA sequence
SEQUENCE_QUERY = "TGCATGCA"
NAME_PROMOTER = "P_example"
NAME_QUERY = "TFBS_example"

---

📂 Project Structure

.
├── propose_recombination.ipynb
├── requirements.txt
├── README.md
├── src
│   ├── constants.py
│   ├── data.py
│   ├── model.py
│   └── proposal.py
└── data
    ├── models
    │   ├── determiner
    │   │   ├── model_determiner_1-10.h5
    │   │   └── metadata.tsv
    │   └── place_back
    │   │   ├── model_place_back_1-4.h5
    │       └── metadata.tsv
    └── vocabulary
        └── vocab.json

---

📝 License

This project is licensed under the GNU General Public License v3.0.
See the LICENSE file for details.

---

🤝 Contributions

Feel free to open issues or pull requests if you have suggestions or improvements.

---

🌐 Online Tool

You can also try the tool directly online at:
👉 Promoter Logic Webserver

---

🙏 Acknowledgments

This work was supported by ELIXIR CZ Research Infrastructure (ID LM2023055, MEYS CR). Computational resources were provided by the e-INFRA CZ project (ID:90254), supported by the Ministry of Education, Youth and Sports of the Czech Republic.

We acknowledge the resources and know-how of XENO Cells Innovations s.r.o., and thank Filip Jani (server framework), Jiri Fatka (consultations on online deployment), and Lucie Houdová (support and guidance).