Related Experiment Video
Updated: Oct 5, 2025
05:25
Author Spotlight: Quantifying Rough Eye Phenotypes in Drosophila Models of Amyotrophic Lateral Sclerosis with Frontotemporal Dementia
Published on: October 4, 2024
1.1K
Gender Identification and Classification of Drosophila melanogaster Flies Using Machine Learning Techniques.
Channabasava Chola1,2, J V Bibal Benifa1, D S Guru2
1Department of Computer Science and Engineering, Indian Institute of Information Technology, Kottayam, India.
Computational and Mathematical Methods in Medicine
|January 24, 2022
Summary
This study introduces an automated system for classifying male and female Drosophila melanogaster using machine learning on microscopic images. The K-nearest neighbor (KNN) classifier achieved 90% accuracy, outperforming SVM.
Area of Science:
- Genetics and Genomics
- Bioinformatics
- Computational Biology
Background:
- Drosophila melanogaster is a key genetic model organism with significant homology to human genes and proteins.
- Research in Drosophila aids in understanding gene function and human-related diseases.
- Automated methods are needed for efficient analysis of biological data, including fly phenotyping.
Purpose of the Study:
- To develop and evaluate an automated system for classifying the gender of Drosophila melanogaster from microscopic images.
- To compare the performance of different machine learning classifiers for this classification task.
Main Methods:
- An automated system was designed to process ventral view microscopic images of Drosophila.
- Image preprocessing involved converting images to grayscale and extracting texture features.
- Machine learning classifiers, including Support Vector Machines (SVM), Naive Bayes (NB), and K-nearest neighbor (KNN), were employed.
Main Results:
- The K-nearest neighbor (KNN) classifier achieved the highest accuracy of 90% in gender classification.
- The KNN classifier demonstrated superior performance compared to the Support Vector Machines (SVM) classifier.
- The proposed system effectively classifies Drosophila gender using image texture features.
Conclusions:
- Automated gender classification of Drosophila melanogaster is feasible using machine learning and image analysis.
- The KNN algorithm shows high potential for accurate and efficient sex determination in Drosophila.
- This system can serve as a valuable tool in Drosophila research, streamlining phenotyping and genetic studies.
