Related Experiment Video
Updated: Jan 2, 2026
08:20
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
Published on: October 27, 2023
2.4K
Automated identification of Myxobacterial genera using Convolutional Neural Network
Hedieh Sajedi1, Fatemeh Mohammadipanah2, Ali Pashaei3
1Department of Computer Science, School of Mathematics, Statistics and Computer Science, College of Science, University of Tehran, 14155-6455, Tehran, Iran. hhsajedi@ut.ac.ir.
Scientific Reports
|December 5, 2019
Summary
This study introduces a machine learning model for identifying Myxococcales genera using fruiting body images. The Convolutional Neural Network (CNN) approach accurately classifies genera and suborders, simplifying bacterial identification.
Area of Science:
- Microbiology
- Bioinformatics
- Machine Learning
Background:
- Myxococcales bacteria are identified by fruiting bodies, but classification relies on subjective stereomicroscopic observation.
- Accurate taxonomic identification traditionally requires 16SrRNA gene sequencing, a complex and time-consuming process.
Purpose of the Study:
- To develop an automated method for classifying Myxococcales genera using image pattern analysis.
- To reduce reliance on expert-driven morphological identification and genetic sequencing.
Main Methods:
- Image pattern analysis of fruiting body structures.
- Development of a database for Myxococcales fruiting bodies.
- Implementation of a Convolutional Neural Network (CNN) model, with parts replaced by other classifiers, for genus recognition.
Main Results:
- The proposed machine learning model achieved 77.24% accuracy in recognizing Myxococcales genera.
- The model demonstrated 88.92% accuracy in recognizing Myxococcales suborders.
- Identification was possible directly from stereomicroscopic images without gene sequencing or extensive sample preparation.
Conclusions:
- The developed model offers a reliable and efficient alternative for Myxococcales genus identification.
- This approach simplifies bacterial taxonomy and has significant implications for microbial ecology and diagnostics.
