The Naïve Bayes Classifier ++ for Metagenomic Taxonomic Classification-Query Evaluation

Haozhe Neil Duan; Gavin Hearne; Robi Polikar; Gail L Rosen

doi:10.1093/bioinformatics/btae743

Back

The Naïve Bayes Classifier ++ for Metagenomic Taxonomic Classification-Query Evaluation

Journal article

Open access

Peer reviewed

The Naïve Bayes Classifier ++ for Metagenomic Taxonomic Classification-Query Evaluation

Haozhe Neil Duan, Gavin Hearne, Robi Polikar and Gail L Rosen

Bioinformatics (Oxford, England), v 41(1), btae743

19 Dec 2024

DOI: https://doi.org/10.1093/bioinformatics/btae743

PMID: 39700412

Featured in Collection : UN Sustainable Development Goals @ Drexel

Files and links (1)

url

https://doi.org/10.1093/bioinformatics/btae743View

Published, Version of Record (VoR)Open Access (License Unspecified), Open

Abstract

taxonomic classification

metagenomics

Machine Learning

This study examines the query performance of the NBC ++ (Incremental Naive Bayes Classifier) program for variations in canonicality, k-mer size, databases, and input sample data size. We demonstrate that both NBC ++ and Kraken2 are influenced by database depth, with macro measures improving as depth increases. However, fully capturing the diversity of life, especially viruses, remains a challenge. NBC ++ can competitively profile the superkingdom content of metagenomic samples using a small training database. NBC ++ spends less time training and can use a fraction of the memory than Kraken2 but at the cost of long querying time. Major NBC ++ enhancements include accommodating canonical k-mer storage (leading to significant storage savings) and adaptable and optimized memory allocation that accelerates query analysis and enables the software to be run on nearly any system. Additionally, the output now includes log-likelihood values for each training genome, providing users with valuable confidence information. Source code and Dockerfile are available at http://github.com/EESI/Naive_Bayes. Supplementary data are available at Bioinformatics online, and databases are available at Zenodo records #11657719 and #11643985.

Metrics

10 Record Views

5 citations in Web of Science

1 citations in Scopus

Details

Title: The Naïve Bayes Classifier ++ for Metagenomic Taxonomic Classification-Query Evaluation
Creators: Haozhe Neil Duan - Drexel University
Gavin Hearne - Drexel University
Robi Polikar - Rowan University
Gail L Rosen (Corresponding Author) - Drexel University
Publication Details: Bioinformatics (Oxford, England), v 41(1), btae743
Publisher: Oxford University Press
Number of pages: 6
Grant note: National Science Foundation (NSF): 1936791, 1936782, 2107108
This work was supported in part by funds from the National Science Foundation (NSF) [1936791, 1936782, and 2107108].
Resource Type: Journal article
Language: English
Academic Unit: Electrical and Computer Engineering
Web of Science ID: WOS:001395453900001
Scopus ID: 2-s2.0-85215371549
Other Identifier: 991022005651404721

UN Sustainable Development Goals (SDGs)

This publication has contributed to the advancement of the following goals:

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types: Domestic collaboration
Web of Science research areas: Biochemical Research Methods; Biotechnology & Applied Microbiology; Computer Science, Interdisciplinary Applications; Mathematical & Computational Biology; Statistics & Probability