Skip to content

Deep learning models for predicting protein functions from proteomic data, including techniques to handle data imbalance. Developed as part of a master’s thesis in Image and Information Engineering at Ferhat Abbas University.

Notifications You must be signed in to change notification settings

almascer/Protein-Function-Prediction-using-deep-learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 

Repository files navigation

look at the changes i made and tell me if i should change anything : # 🧬 Protein Function Prediction using Deep Learning

This project explores multiple deep learning architectures and parameter configurations to predict protein functions from proteomic data, in addition to implementing multiple ways to handle highly imbalanced data.
It was developed as part of my master’s thesis in Image and Information Engineering at Ferhat Abbas University.

📘 Overview

The main goal of this work is to evaluate how different deep learning models and hyperparameter choices affect the accuracy of protein function prediction.
The models were trained and tested on proteomic datasets, proteins sequences to be precise, using various preprocessing, feature extraction and data balancing techniques.


⚙️ Features

  • Data preprocessing and normalization of proteins sequences
  • Implementation of different neural network architectures
  • Comparison of results under various hyperparameter settings
  • Visualization of performance metrics and loss curves
  • Blancing the data to get better predictions

🏗️ Project Structure

About

Deep learning models for predicting protein functions from proteomic data, including techniques to handle data imbalance. Developed as part of a master’s thesis in Image and Information Engineering at Ferhat Abbas University.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published