Comparison between Ribosomal Assembly and Machine Learning Tools for Microbial Identification of Organisms with Different Characteristics

Aug 3, 2026

Genome assembly tools reconstruct genomic sequences from raw sequencing reads, enabling identification of organisms present in metagenomic samples. Recent machine learning methods have expanded bioinformatics workflows, and this study evaluates their use for organism identification. Several metagenomic assembly tools (PhyloFlash, MEGAHIT, MetaSPAdes, Kraken2, Mothur, UniCycler, PathRacer) are compared with deep learning classifiers (DNABERT, DeLUCS) using two synthetic mock community datasets. Results test whether ensembling assembly and machine learning improves performance versus using individual tools, and assess effectiveness by organism repetitiveness, genome size, and GC content.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages27

Reading Time1 h 8 min

AccessFree to download

Abstract

Background and problem scope

Methodology and tool comparisons

Ensembling evaluation

Key findings by organism characteristics

San Jose State University SJSU ScholarWorks | Faculty Research, Scholarly, and Creative Activity | | --- | | 7-25-2024
Comparison between Ribosomal Assembly and Machine Learning Tools for Microbial Identification of Organisms with Different Characteristics
Stephanie Chau
San Jose State University
Carlos Rojas
San Jose State University, [carlos.rojas@sjsu.edu](carlos.rojas@sjsu.edu)
Jorjeta G. Jetcheva
San Jose State University, [jorjeta.jetcheva@sjsu.edu](jorjeta.jetcheva@sjsu.edu)
Mary Markart
San Jose State University
Sudha Vijayakumar
San Jose State University
See next page for additional authors
Follow this and additional works at: [https://scholarworks.sjsu.edu/faculty_rsca](https://scholarworks.sjsu.edu/faculty_rsca) | Recommended Citation Stephanie Chau, Carlos Rojas, Jorjeta G. Jetcheva, Mary Markart, Sudha Vijayakumar, Sophia Yuan, Vincent Stowbunenko, Amanda N. Shelton, and William B. Andreopoulos. "Comparison between Ribosomal Assembly and Machine Learning Tools for Microbial Identification of Organisms with Different Characteristics" Current Bioinformatics (2024): 595-619 . [https://doi.org/10.2174/](https://doi.org/10.2174/) 0115748936299440240709070105 This Article is brought to you for free and open access by SJSU ScholarWorks. It has been accepted for inclusion in Faculty Research, Scholarly, and Creative Activity by an authorized administrator of SJSU ScholarWorks. For more information, please contact [scholarworks@sjsu.edu](scholarworks@sjsu.edu). Authors Stephanie Chau, Carlos Rojas, Jorjeta G. Jetcheva, Mary Markart, Sudha Vijayakumar, Sophia Yuan, Vincent Stowbunenko, Amanda N. Shelton, and William B. Andreopoulos This article is available at SJSU ScholarWorks: [https://scholarworks.sjsu.edu/faculty_rsca/6233](https://scholarworks.sjsu.edu/faculty_rsca/6233) Send Orders for Reprints [to reprints@benthamscience.net](to reprints@benthamscience.net) Current Bioinformatics, xxxx, xx, x-x 1 RESEARCH ARTICLE Comparison between Ribosomal Assembly and Machine Learning Tools for Microbial Identification of Organisms with Different Characteristics Stephanie Chau 1,\#, Carlos Rojas 1,\#, Jorjeta G. Jetcheva 1,\#, Mary Markart 1, Sudha Vijayakumar 1, Sophia Yuan 1, Vincent Stowbunenko2, Amanda N. Shelton3 and William B. Andreopoulos2,\#,* 1Department of Computer Engineering, San José State University, San José, CA, USA; 2Department of Computer Science, San José State University, San José, CA, USA; 3Department of Plant Biology, Carnegie Institution for Science, Stanford, CA, USA A R T I C L E H I S T O R Y Received: February 12, 2024 Revised: April 25, 2024 Accepted: May 03, 2024 DOI: 10. 2174/0115748936299440240709070105 Abstract: Background: Genome assembly tools are used to reconstruct genomic sequences from raw sequencing data, which are then used for identifying the organisms present in a metagenomic sample. Methodology: More recently, machine learning approaches have been applied to a variety of bioinformatics problems, and in this paper, we explore their use for organism identification. We start by evaluating several commonly used metagenomic assembly tools, including PhyloFlash, MEGAHIT, MetaSPAdes, Kraken2, Mothur, UniCycler, and PathRacer, and compare them against state-of-theart deep learning-based machine learning classification approaches represented by DNABERT and DeLUCS, in the context of two synthetic mock community datasets. Result: Our analysis focuses on determining whether ensembling metagenome assembly tools with machine learning tools have the potential to improve identification performance relative to using the tools individually. Conclusion: We find that this is indeed the case, and analyze the level of effectiveness of potential tool ensembling for organisms with different characteristics (based on factors such as repetitiveness, genome size, and GC content) . Keywords: PhyloFlash, MEGAHIT, metaSPAdes,

FAQs

What is the main goal of this study on metagenomic analysis?

The study aims to compare ribosomal/metagenomic assembly tools with machine learning tools for identifying organisms in metagenomic samples, and to test whether combining them improves identification accuracy.

Which tools and approaches are evaluated in the comparison?

The work evaluates multiple metagenomic assembly tools (including PhyloFlash, MEGAHIT, MetaSPAdes, Kraken2, Mothur, UniCycler, PathRacer) and compares them with deep learning classification methods represented by DNABERT and DeLUCS.

How does the study assess performance improvements across organism types?

It analyzes whether ensembling metagenome assembly with machine learning improves identification relative to using tools individually, and evaluates effectiveness based on organism characteristics such as repetitiveness, genome size, and GC content.

Aug 3, 2026

Upload by Genevieve