# ConST

**Repository Path**: sculab/ConST

## Basic Information

- **Project Name**: ConST
- **Description**: Conservation and Structure-based Trait analysis
- **Primary Language**: Python
- **License**: MulanPSL-2.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-05-29
- **Last Updated**: 2025-06-10

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# ConST  
An AI-assisted workflow for analyzing the evolutionary characteristics of functional genes using genome skimming data. ConST integrates Evo2-based sequence conservativeness scoring and AlphaFold3-based molecular docking to support structure-informed evolutionary inference.

## ConST: Conservation & Structure-based Trait analysis
![输入图片说明](flowchart.jpg)
---

## Installation

Please refer to the installation guide:

scripts/install_instructions.txt

It explains how to set up the required environments for Evo2 and AutoDock Vina.

---

## Configuration

All user parameters are managed via config files stored in the scripts/ directory.

- Sequence_Conservativeness_Analysis.txt  
  → Controls Evo2 input/output paths, CUDA device, and model name.

- Molecular_Docking.txt  
  → Defines docking software paths, working directories, box center/size, and number of threads.

---

## Pipeline Usage

### 1. Sequence Conservativeness Analysis

Prepare a FASTA file containing functional gene sequences.

Run the analysis using:

python scripts/Sequence_Conservativeness_Analysis.py --config scripts/Sequence_Conservativeness_Analysis.txt

The output CSV file will contain conservation scores for each gene.

---

### 2. Molecular Docking

Prepare:

- Receptor protein files (.cif) in: example/receptors/
- Ligand molecule files (.sdf) in: example/ligands/

Run the docking pipeline using:

python scripts/Molecular_Docking.py --config scripts/Molecular_Docking.txt

The output directory will contain docking results and a summary .csv file of ligand-receptor affinities.

---

## Example Data

A minimal test dataset is provided in the example/ directory, including:

- receptors/example_receptor.cif  
- ligands/example_ligand.sdf

Refer to:

example/README_example.md

for step-by-step instructions to validate your installation.

---

## Output Summary

Module                          | Output File
-------------------------------|-------------------------------
Sequence Conservativeness       | evo2_scores.csv
Molecular Docking               | docking_results/ligand_receptor_affinity.csv

---


## Contact

For questions, suggestions, or bug reports, please contact:  
hhe@stu.scu.edu.cn