https://github.com/krishnaura45/rna-3d-folding

🧪Predicting 🧬RNA 3D Structures 🚀ML
https://github.com/krishnaura45/rna-3d-folding

alphafold3 bioinformatics casp16 kaggle-competition ml protein-folding research-project rna-3d-structure rna-sequencing stanford-machine-learning vfold

Last synced: 4 months ago
JSON representation

🧪Predicting 🧬RNA 3D Structures 🚀ML

• Host: GitHub
• URL: https://github.com/krishnaura45/rna-3d-folding
• Owner: krishnaura45
• License: mit
• Created: 2025-04-26T10:20:46.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2025-06-06T14:54:50.000Z (4 months ago)
• Last Synced: 2025-06-13T00:41:36.853Z (4 months ago)
• Topics: alphafold3, bioinformatics, casp16, kaggle-competition, ml, protein-folding, research-project, rna-3d-structure, rna-sequencing, stanford-machine-learning, vfold
• Language: Jupyter Notebook
• Homepage:
• Size: 28.3 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# rna-3d-folding

Sequence-to-Structure Prediction for RNA Molecules

![Python](https://img.shields.io/badge/Python-3776AB?style=for-the-badge&logo=python&logoColor=white)

![Kaggle](https://img.shields.io/badge/Kaggle-20BEFF?style=for-the-badge&logo=kaggle&logoColor=white)

[![Template Modeling Score Optimized](https://img.shields.io/badge/Metric-TM%20Score-yellowgreen?style=for-the-badge)](https://www.kaggle.com/code/metric/ribonanza-tm-score)

![Solo](https://img.shields.io/badge/Participation%3A%20Solo-orange?style=for-the-badge)

### Project Duration: Apr 25, 2025 - May 29, 2025

---

## 🌟 Introduction

RNA is vital to life’s most essential processes, but despite its significance, predicting its 3D structure is still difficult. Deep learning breakthroughs like AlphaFold have transformed protein structure prediction, but progress with RNA has been much slower due to limited data and evaluation methods. 

This project is part of a research challenge which was hosted on Kaggle. The objective is to develop machine learning models to predict an RNA molecule’s 3D structure from its sequence. The goal is to improve our understanding of biological processes and drive new advancements in medicine and biotechnology. In short, we have to predict five 3D structures for each RNA sequence. **Template Modeling (TM-Score)** is the custom metric which is being utilized to evaluate submissions.

---

## 🔗 References

- 📁 Kaggle Competition: Stanford RNA 3D Folding


- 📂 Other sources:

  - Protein Data Bank Database

  - CASP-16 2024 Competition

  

---

## 🛠️ Tech Stack

- Language: Python 🐍

- Libraries:

  - `pandas`, `numpy` for data handling

  - `biopython`, `torch`, `matplotlib`

- Tools:

  - Jupyter Notebook / Kaggle Notebooks for experimentation

  - Helper functions for template modeling optimization

 

---